* [PATCH net-next 01/10] net: Add sk_lookup struct and helper
2017-08-01 3:13 [PATCH net-next 00/10] net: l3mdev: Support for sockets bound to enslaved device David Ahern
@ 2017-08-01 3:13 ` David Ahern
2017-08-01 3:13 ` [PATCH net-next 02/10] net: ipv4: Convert udp socket lookups to new struct David Ahern
` (10 subsequent siblings)
11 siblings, 0 replies; 15+ messages in thread
From: David Ahern @ 2017-08-01 3:13 UTC (permalink / raw)
To: netdev; +Cc: David Ahern
Consolidate the socket lookup args into a struct.
Add helper that compares sk_bound_dev_if for a socket to the lookup
parameters.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/sock.h | 38 ++++++++++++++++++++++++++++++++++++++
1 file changed, 38 insertions(+)
diff --git a/include/net/sock.h b/include/net/sock.h
index 7c0632c7e870..a2db5fd30192 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -491,6 +491,44 @@ enum sk_pacing {
#define rcu_dereference_sk_user_data(sk) rcu_dereference(__sk_user_data((sk)))
#define rcu_assign_sk_user_data(sk, ptr) rcu_assign_pointer(__sk_user_data((sk)), ptr)
+/* used for socket lookups */
+struct sk_lookup {
+ union {
+ const struct in6_addr *ipv6;
+ __be32 ipv4;
+ } saddr;
+ union {
+ const struct in6_addr *ipv6;
+ __be32 ipv4;
+ } daddr;
+
+ __be16 sport;
+ __be16 dport;
+ unsigned short hnum;
+
+ int dif;
+ bool exact_dif;
+};
+
+/* Compare sk_bound_dev_if to socket lookup dif
+ * Returns:
+ * -1 exact dif required and not met
+ * 0 sk_bound_dev_if is either not set or does not match
+ * 1 sk_bound_dev_if is set and matches dif
+ */
+static inline int sk_lookup_device_cmp(const struct sock *sk,
+ const struct sk_lookup *params)
+{
+ /* exact_dif true == l3mdev case */
+ if (params->exact_dif && sk->sk_bound_dev_if != params->dif)
+ return -1;
+
+ if (sk->sk_bound_dev_if && sk->sk_bound_dev_if == params->dif)
+ return 1;
+
+ return 0;
+}
+
/*
* SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK
* or not whether his port will be reused by someone else. SK_FORCE_REUSE
--
2.1.4
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PATCH net-next 02/10] net: ipv4: Convert udp socket lookups to new struct
2017-08-01 3:13 [PATCH net-next 00/10] net: l3mdev: Support for sockets bound to enslaved device David Ahern
2017-08-01 3:13 ` [PATCH net-next 01/10] net: Add sk_lookup struct and helper David Ahern
@ 2017-08-01 3:13 ` David Ahern
2017-08-01 3:13 ` [PATCH net-next 03/10] net: ipv4: Convert inet " David Ahern
` (9 subsequent siblings)
11 siblings, 0 replies; 15+ messages in thread
From: David Ahern @ 2017-08-01 3:13 UTC (permalink / raw)
To: netdev; +Cc: David Ahern
Convert udp4_lib_lookup and __udp4_lib_lookup to use the new sk_lookup
struct.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/udp.h | 6 +-
net/ipv4/netfilter/nf_socket_ipv4.c | 11 ++-
net/ipv4/udp.c | 170 +++++++++++++++++++-----------------
net/ipv4/udp_diag.c | 51 +++++++----
net/netfilter/xt_TPROXY.c | 11 ++-
5 files changed, 144 insertions(+), 105 deletions(-)
diff --git a/include/net/udp.h b/include/net/udp.h
index 972ce4baab6b..5e0ff095dc6d 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -283,10 +283,8 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname,
int udp_lib_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, unsigned int optlen,
int (*push_pending_frames)(struct sock *));
-struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
- __be32 daddr, __be16 dport, int dif);
-struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
- __be32 daddr, __be16 dport, int dif,
+struct sock *udp4_lib_lookup(struct net *net, struct sk_lookup *params);
+struct sock *__udp4_lib_lookup(struct net *net, struct sk_lookup *params,
struct udp_table *tbl, struct sk_buff *skb);
struct sock *udp4_lib_lookup_skb(struct sk_buff *skb,
__be16 sport, __be16 dport);
diff --git a/net/ipv4/netfilter/nf_socket_ipv4.c b/net/ipv4/netfilter/nf_socket_ipv4.c
index e9293bdebba0..121767b36763 100644
--- a/net/ipv4/netfilter/nf_socket_ipv4.c
+++ b/net/ipv4/netfilter/nf_socket_ipv4.c
@@ -81,14 +81,21 @@ nf_socket_get_sock_v4(struct net *net, struct sk_buff *skb, const int doff,
const __be16 sport, const __be16 dport,
const struct net_device *in)
{
+ struct sk_lookup params = {
+ .saddr.ipv4 = saddr,
+ .daddr.ipv4 = daddr,
+ .sport = sport,
+ .dport = dport,
+ .dif = in->ifindex,
+ };
+
switch (protocol) {
case IPPROTO_TCP:
return inet_lookup(net, &tcp_hashinfo, skb, doff,
saddr, sport, daddr, dport,
in->ifindex);
case IPPROTO_UDP:
- return udp4_lib_lookup(net, saddr, sport, daddr, dport,
- in->ifindex);
+ return udp4_lib_lookup(net, ¶ms);
}
return NULL;
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b057653ceca9..132a8f070d16 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -379,15 +379,13 @@ int udp_v4_get_port(struct sock *sk, unsigned short snum)
}
static int compute_score(struct sock *sk, struct net *net,
- __be32 saddr, __be16 sport,
- __be32 daddr, unsigned short hnum, int dif,
- bool exact_dif)
+ const struct sk_lookup *params)
{
- int score;
struct inet_sock *inet;
+ int score, rc;
if (!net_eq(sock_net(sk), net) ||
- udp_sk(sk)->udp_port_hash != hnum ||
+ udp_sk(sk)->udp_port_hash != params->hnum ||
ipv6_only_sock(sk))
return -1;
@@ -395,28 +393,28 @@ static int compute_score(struct sock *sk, struct net *net,
inet = inet_sk(sk);
if (inet->inet_rcv_saddr) {
- if (inet->inet_rcv_saddr != daddr)
+ if (inet->inet_rcv_saddr != params->daddr.ipv4)
return -1;
score += 4;
}
if (inet->inet_daddr) {
- if (inet->inet_daddr != saddr)
+ if (inet->inet_daddr != params->saddr.ipv4)
return -1;
score += 4;
}
if (inet->inet_dport) {
- if (inet->inet_dport != sport)
+ if (inet->inet_dport != params->sport)
return -1;
score += 4;
}
- if (sk->sk_bound_dev_if || exact_dif) {
- if (sk->sk_bound_dev_if != dif)
- return -1;
+ rc = sk_lookup_device_cmp(sk, params);
+ if (rc < 0)
+ return -1;
+ if (rc > 0)
score += 4;
- }
if (sk->sk_incoming_cpu == raw_smp_processor_id())
score++;
return score;
@@ -436,10 +434,9 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
/* called with rcu_read_lock() */
static struct sock *udp4_lib_lookup2(struct net *net,
- __be32 saddr, __be16 sport,
- __be32 daddr, unsigned int hnum, int dif, bool exact_dif,
- struct udp_hslot *hslot2,
- struct sk_buff *skb)
+ const struct sk_lookup *params,
+ struct udp_hslot *hslot2,
+ struct sk_buff *skb)
{
struct sock *sk, *result;
int score, badness, matches = 0, reuseport = 0;
@@ -448,13 +445,14 @@ static struct sock *udp4_lib_lookup2(struct net *net,
result = NULL;
badness = 0;
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
- score = compute_score(sk, net, saddr, sport,
- daddr, hnum, dif, exact_dif);
+ score = compute_score(sk, net, params);
if (score > badness) {
reuseport = sk->sk_reuseport;
if (reuseport) {
- hash = udp_ehashfn(net, daddr, hnum,
- saddr, sport);
+ hash = udp_ehashfn(net, params->daddr.ipv4,
+ params->hnum,
+ params->saddr.ipv4,
+ params->sport);
result = reuseport_select_sock(sk, hash, skb,
sizeof(struct udphdr));
if (result)
@@ -476,28 +474,27 @@ static struct sock *udp4_lib_lookup2(struct net *net,
/* UDP is nearly always wildcards out the wazoo, it makes no sense to try
* harder than this. -DaveM
*/
-struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
- __be16 sport, __be32 daddr, __be16 dport,
- int dif, struct udp_table *udptable, struct sk_buff *skb)
+struct sock *__udp4_lib_lookup(struct net *net, struct sk_lookup *params,
+ struct udp_table *udptable, struct sk_buff *skb)
{
struct sock *sk, *result;
- unsigned short hnum = ntohs(dport);
+ unsigned short hnum = ntohs(params->dport);
unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
- bool exact_dif = udp_lib_exact_dif_match(net, skb);
int score, badness, matches = 0, reuseport = 0;
u32 hash = 0;
+ params->hnum = hnum;
+ params->exact_dif = udp_lib_exact_dif_match(net, skb);
+
if (hslot->count > 10) {
- hash2 = udp4_portaddr_hash(net, daddr, hnum);
+ hash2 = udp4_portaddr_hash(net, params->daddr.ipv4, hnum);
slot2 = hash2 & udptable->mask;
hslot2 = &udptable->hash2[slot2];
if (hslot->count < hslot2->count)
goto begin;
- result = udp4_lib_lookup2(net, saddr, sport,
- daddr, hnum, dif,
- exact_dif, hslot2, skb);
+ result = udp4_lib_lookup2(net, params, hslot2, skb);
if (!result) {
unsigned int old_slot2 = slot2;
hash2 = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
@@ -510,9 +507,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
if (hslot->count < hslot2->count)
goto begin;
- result = udp4_lib_lookup2(net, saddr, sport,
- daddr, hnum, dif,
- exact_dif, hslot2, skb);
+ result = udp4_lib_lookup2(net, params, hslot2, skb);
}
return result;
}
@@ -520,13 +515,14 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
result = NULL;
badness = 0;
sk_for_each_rcu(sk, &hslot->head) {
- score = compute_score(sk, net, saddr, sport,
- daddr, hnum, dif, exact_dif);
+ score = compute_score(sk, net, params);
if (score > badness) {
reuseport = sk->sk_reuseport;
if (reuseport) {
- hash = udp_ehashfn(net, daddr, hnum,
- saddr, sport);
+ hash = udp_ehashfn(net, params->daddr.ipv4,
+ params->hnum,
+ params->saddr.ipv4,
+ params->sport);
result = reuseport_select_sock(sk, hash, skb,
sizeof(struct udphdr));
if (result)
@@ -551,10 +547,16 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
struct udp_table *udptable)
{
const struct iphdr *iph = ip_hdr(skb);
+ struct net *net = dev_net(skb->dev);
+ struct sk_lookup params = {
+ .saddr.ipv4 = iph->saddr,
+ .daddr.ipv4 = iph->daddr,
+ .sport = sport,
+ .dport = dport,
+ .dif = inet_iif(skb),
+ };
- return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
- iph->daddr, dport, inet_iif(skb),
- udptable, skb);
+ return __udp4_lib_lookup(net, ¶ms, udptable, skb);
}
struct sock *udp4_lib_lookup_skb(struct sk_buff *skb,
@@ -570,13 +572,11 @@ EXPORT_SYMBOL_GPL(udp4_lib_lookup_skb);
#if IS_ENABLED(CONFIG_NETFILTER_XT_MATCH_SOCKET) || \
IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TPROXY) || \
IS_ENABLED(CONFIG_NF_SOCKET_IPV4)
-struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
- __be32 daddr, __be16 dport, int dif)
+struct sock *udp4_lib_lookup(struct net *net, struct sk_lookup *params)
{
struct sock *sk;
- sk = __udp4_lib_lookup(net, saddr, sport, daddr, dport,
- dif, &udp_table, NULL);
+ sk = __udp4_lib_lookup(net, params, &udp_table, NULL);
if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
return sk;
@@ -585,21 +585,21 @@ EXPORT_SYMBOL_GPL(udp4_lib_lookup);
#endif
static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
- __be16 loc_port, __be32 loc_addr,
- __be16 rmt_port, __be32 rmt_addr,
- int dif, unsigned short hnum)
+ const struct sk_lookup *params)
{
struct inet_sock *inet = inet_sk(sk);
+ __be32 loc_addr = params->daddr.ipv4;
+ __be32 rmt_addr = params->saddr.ipv4;
if (!net_eq(sock_net(sk), net) ||
- udp_sk(sk)->udp_port_hash != hnum ||
+ udp_sk(sk)->udp_port_hash != params->hnum ||
(inet->inet_daddr && inet->inet_daddr != rmt_addr) ||
- (inet->inet_dport != rmt_port && inet->inet_dport) ||
+ (inet->inet_dport != params->sport && inet->inet_dport) ||
(inet->inet_rcv_saddr && inet->inet_rcv_saddr != loc_addr) ||
ipv6_only_sock(sk) ||
- (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
+ (sk->sk_bound_dev_if && sk->sk_bound_dev_if != params->dif))
return false;
- if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, dif))
+ if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, params->dif))
return false;
return true;
}
@@ -626,10 +626,15 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
int harderr;
int err;
struct net *net = dev_net(skb->dev);
-
- sk = __udp4_lib_lookup(net, iph->daddr, uh->dest,
- iph->saddr, uh->source, skb->dev->ifindex, udptable,
- NULL);
+ struct sk_lookup params = {
+ .saddr.ipv4 = iph->daddr,
+ .daddr.ipv4 = iph->saddr,
+ .sport = uh->dest,
+ .dport = uh->source,
+ .dif = skb->dev->ifindex,
+ };
+
+ sk = __udp4_lib_lookup(net, ¶ms, udptable, NULL);
if (!sk) {
__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
return; /* No socket for error */
@@ -1956,9 +1961,16 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
struct udp_hslot *hslot = udp_hashslot(udptable, net, hnum);
unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10);
unsigned int offset = offsetof(typeof(*sk), sk_node);
- int dif = skb->dev->ifindex;
struct hlist_node *node;
struct sk_buff *nskb;
+ struct sk_lookup params = {
+ .saddr.ipv4 = saddr,
+ .daddr.ipv4 = daddr,
+ .sport = uh->source,
+ .dport = uh->dest,
+ .hnum = hnum,
+ .dif = skb->dev->ifindex,
+ };
if (use_hash2) {
hash2_any = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum) &
@@ -1970,8 +1982,7 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
}
sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) {
- if (!__udp_is_mcast_sock(net, sk, uh->dest, daddr,
- uh->source, saddr, dif, hnum))
+ if (!__udp_is_mcast_sock(net, sk, ¶ms))
continue;
if (!first) {
@@ -2159,13 +2170,10 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
* If more than one socket found returns NULL
*/
static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
- __be16 loc_port, __be32 loc_addr,
- __be16 rmt_port, __be32 rmt_addr,
- int dif)
+ const struct sk_lookup *params)
{
struct sock *sk, *result;
- unsigned short hnum = ntohs(loc_port);
- unsigned int slot = udp_hashfn(net, hnum, udp_table.mask);
+ unsigned int slot = udp_hashfn(net, params->hnum, udp_table.mask);
struct udp_hslot *hslot = &udp_table.hash[slot];
/* Do not bother scanning a too big list */
@@ -2174,8 +2182,7 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
result = NULL;
sk_for_each_rcu(sk, &hslot->head) {
- if (__udp_is_mcast_sock(net, sk, loc_port, loc_addr,
- rmt_port, rmt_addr, dif, hnum)) {
+ if (__udp_is_mcast_sock(net, sk, params)) {
if (result)
return NULL;
result = sk;
@@ -2190,21 +2197,20 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
* if the first socket is an exact match and if not move on.
*/
static struct sock *__udp4_lib_demux_lookup(struct net *net,
- __be16 loc_port, __be32 loc_addr,
- __be16 rmt_port, __be32 rmt_addr,
- int dif)
+ const struct sk_lookup *params)
{
- unsigned short hnum = ntohs(loc_port);
- unsigned int hash2 = udp4_portaddr_hash(net, loc_addr, hnum);
+ unsigned int hash2 = udp4_portaddr_hash(net, params->daddr.ipv4,
+ params->hnum);
unsigned int slot2 = hash2 & udp_table.mask;
struct udp_hslot *hslot2 = &udp_table.hash2[slot2];
- INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr);
- const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum);
+ INET_ADDR_COOKIE(acookie, params->saddr.ipv4, params->daddr.ipv4);
+ const __portpair ports = INET_COMBINED_PORTS(params->sport,
+ params->hnum);
struct sock *sk;
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
- if (INET_MATCH(sk, net, acookie, rmt_addr,
- loc_addr, ports, dif))
+ if (INET_MATCH(sk, net, acookie, params->saddr.ipv4,
+ params->daddr.ipv4, ports, params->dif))
return sk;
/* Only check first socket in chain */
break;
@@ -2215,11 +2221,13 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
void udp_v4_early_demux(struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
+ struct sk_lookup params = {
+ .dif = skb->dev->ifindex,
+ };
const struct iphdr *iph;
const struct udphdr *uh;
struct sock *sk = NULL;
struct dst_entry *dst;
- int dif = skb->dev->ifindex;
int ours;
/* validate the packet */
@@ -2228,6 +2236,11 @@ void udp_v4_early_demux(struct sk_buff *skb)
iph = ip_hdr(skb);
uh = udp_hdr(skb);
+ params.saddr.ipv4 = iph->saddr;
+ params.daddr.ipv4 = iph->daddr;
+ params.sport = uh->source;
+ params.dport = uh->dest;
+ params.hnum = ntohs(uh->dest);
if (skb->pkt_type == PACKET_BROADCAST ||
skb->pkt_type == PACKET_MULTICAST) {
@@ -2244,12 +2257,9 @@ void udp_v4_early_demux(struct sk_buff *skb)
return;
}
- sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
- uh->source, iph->saddr, dif);
- } else if (skb->pkt_type == PACKET_HOST) {
- sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr,
- uh->source, iph->saddr, dif);
- }
+ sk = __udp4_lib_mcast_demux_lookup(net, ¶ms);
+ } else if (skb->pkt_type == PACKET_HOST)
+ sk = __udp4_lib_demux_lookup(net, ¶ms);
if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt))
return;
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 4515836d2a3a..5e0640877536 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -41,11 +41,17 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
struct net *net = sock_net(in_skb->sk);
rcu_read_lock();
- if (req->sdiag_family == AF_INET)
- sk = __udp4_lib_lookup(net,
- req->id.idiag_src[0], req->id.idiag_sport,
- req->id.idiag_dst[0], req->id.idiag_dport,
- req->id.idiag_if, tbl, NULL);
+ if (req->sdiag_family == AF_INET) {
+ struct sk_lookup params = {
+ .saddr.ipv4 = req->id.idiag_src[0],
+ .daddr.ipv4 = req->id.idiag_dst[0],
+ .sport = req->id.idiag_sport,
+ .dport = req->id.idiag_dport,
+ .dif = req->id.idiag_if,
+ };
+
+ sk = __udp4_lib_lookup(net, ¶ms, tbl, NULL);
+ }
#if IS_ENABLED(CONFIG_IPV6)
else if (req->sdiag_family == AF_INET6)
sk = __udp6_lib_lookup(net,
@@ -178,27 +184,38 @@ static int __udp_diag_destroy(struct sk_buff *in_skb,
rcu_read_lock();
- if (req->sdiag_family == AF_INET)
- sk = __udp4_lib_lookup(net,
- req->id.idiag_dst[0], req->id.idiag_dport,
- req->id.idiag_src[0], req->id.idiag_sport,
- req->id.idiag_if, tbl, NULL);
+ if (req->sdiag_family == AF_INET) {
+ struct sk_lookup params = {
+ .saddr.ipv4 = req->id.idiag_dst[0],
+ .daddr.ipv4 = req->id.idiag_src[0],
+ .sport = req->id.idiag_dport,
+ .dport = req->id.idiag_sport,
+ .dif = req->id.idiag_if,
+ };
+
+ sk = __udp4_lib_lookup(net, ¶ms, tbl, NULL);
+ }
#if IS_ENABLED(CONFIG_IPV6)
else if (req->sdiag_family == AF_INET6) {
if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) &&
- ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src))
- sk = __udp4_lib_lookup(net,
- req->id.idiag_dst[3], req->id.idiag_dport,
- req->id.idiag_src[3], req->id.idiag_sport,
- req->id.idiag_if, tbl, NULL);
-
- else
+ ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) {
+ struct sk_lookup params = {
+ .saddr.ipv4 = req->id.idiag_dst[3],
+ .daddr.ipv4 = req->id.idiag_src[3],
+ .sport = req->id.idiag_dport,
+ .dport = req->id.idiag_sport,
+ .dif = req->id.idiag_if,
+ };
+
+ sk = __udp4_lib_lookup(net, ¶ms, tbl, NULL);
+ } else {
sk = __udp6_lib_lookup(net,
(struct in6_addr *)req->id.idiag_dst,
req->id.idiag_dport,
(struct in6_addr *)req->id.idiag_src,
req->id.idiag_sport,
req->id.idiag_if, tbl, NULL);
+ }
}
#endif
else {
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index d767e35fff6b..972a0e40c59a 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -112,6 +112,14 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
const struct net_device *in,
const enum nf_tproxy_lookup_t lookup_type)
{
+ struct sk_lookup params = {
+ .saddr.ipv4 = saddr,
+ .daddr.ipv4 = daddr,
+ .sport = sport,
+ .dport = dport,
+ .dif = in->ifindex,
+ };
+
struct sock *sk;
struct tcphdr *tcph;
@@ -145,8 +153,7 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
}
break;
case IPPROTO_UDP:
- sk = udp4_lib_lookup(net, saddr, sport, daddr, dport,
- in->ifindex);
+ sk = udp4_lib_lookup(net, ¶ms);
if (sk) {
int connected = (sk->sk_state == TCP_ESTABLISHED);
int wildcard = (inet_sk(sk)->inet_rcv_saddr == 0);
--
2.1.4
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PATCH net-next 03/10] net: ipv4: Convert inet socket lookups to new struct
2017-08-01 3:13 [PATCH net-next 00/10] net: l3mdev: Support for sockets bound to enslaved device David Ahern
2017-08-01 3:13 ` [PATCH net-next 01/10] net: Add sk_lookup struct and helper David Ahern
2017-08-01 3:13 ` [PATCH net-next 02/10] net: ipv4: Convert udp socket lookups to new struct David Ahern
@ 2017-08-01 3:13 ` David Ahern
2017-08-01 3:13 ` [PATCH net-next 04/10] net: ipv4: Convert raw sockets to sk_lookup David Ahern
` (8 subsequent siblings)
11 siblings, 0 replies; 15+ messages in thread
From: David Ahern @ 2017-08-01 3:13 UTC (permalink / raw)
To: netdev; +Cc: David Ahern
Convert the various inet_lookup functions to use the new sk_lookup
struct.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/inet_hashtables.h | 57 ++++++++++++++--------------------
net/dccp/ipv4.c | 19 +++++++++---
net/ipv4/inet_diag.c | 33 ++++++++++++++------
net/ipv4/inet_hashtables.c | 48 +++++++++++++++-------------
net/ipv4/netfilter/nf_socket_ipv4.c | 5 ++-
net/ipv4/tcp_ipv4.c | 62 +++++++++++++++++++++++++++----------
net/ipv4/udp_diag.c | 3 ++
net/netfilter/xt_TPROXY.c | 10 +++---
8 files changed, 142 insertions(+), 95 deletions(-)
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 5026b1f08bb8..c5f4dc3c06e4 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -218,19 +218,16 @@ void inet_unhash(struct sock *sk);
struct sock *__inet_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
- const __be32 saddr, const __be16 sport,
- const __be32 daddr,
- const unsigned short hnum,
- const int dif);
+ struct sk_lookup *params);
static inline struct sock *inet_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
- __be32 saddr, __be16 sport,
- __be32 daddr, __be16 dport, int dif)
+ struct sk_lookup *params)
{
- return __inet_lookup_listener(net, hashinfo, skb, doff, saddr, sport,
- daddr, ntohs(dport), dif);
+ params->hnum = ntohs(params->dport);
+
+ return __inet_lookup_listener(net, hashinfo, skb, doff, params);
}
/* Socket demux engine toys. */
@@ -286,53 +283,44 @@ static inline struct sock *inet_lookup_listener(struct net *net,
*/
struct sock *__inet_lookup_established(struct net *net,
struct inet_hashinfo *hashinfo,
- const __be32 saddr, const __be16 sport,
- const __be32 daddr, const u16 hnum,
- const int dif);
+ const struct sk_lookup *params);
static inline struct sock *
inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo,
- const __be32 saddr, const __be16 sport,
- const __be32 daddr, const __be16 dport,
- const int dif)
+ struct sk_lookup *params)
{
- return __inet_lookup_established(net, hashinfo, saddr, sport, daddr,
- ntohs(dport), dif);
+ params->hnum = ntohs(params->dport);
+
+ return __inet_lookup_established(net, hashinfo, params);
}
static inline struct sock *__inet_lookup(struct net *net,
struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
- const __be32 saddr, const __be16 sport,
- const __be32 daddr, const __be16 dport,
- const int dif,
+ struct sk_lookup *params,
bool *refcounted)
{
- u16 hnum = ntohs(dport);
struct sock *sk;
- sk = __inet_lookup_established(net, hashinfo, saddr, sport,
- daddr, hnum, dif);
+ params->hnum = ntohs(params->dport);
+
+ sk = __inet_lookup_established(net, hashinfo, params);
*refcounted = true;
if (sk)
return sk;
*refcounted = false;
- return __inet_lookup_listener(net, hashinfo, skb, doff, saddr,
- sport, daddr, hnum, dif);
+ return __inet_lookup_listener(net, hashinfo, skb, doff, params);
}
static inline struct sock *inet_lookup(struct net *net,
struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
- const __be32 saddr, const __be16 sport,
- const __be32 daddr, const __be16 dport,
- const int dif)
+ struct sk_lookup *params)
{
struct sock *sk;
bool refcounted;
- sk = __inet_lookup(net, hashinfo, skb, doff, saddr, sport, daddr,
- dport, dif, &refcounted);
+ sk = __inet_lookup(net, hashinfo, skb, doff, params, &refcounted);
if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
@@ -342,21 +330,22 @@ static inline struct sock *inet_lookup(struct net *net,
static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
struct sk_buff *skb,
int doff,
- const __be16 sport,
- const __be16 dport,
+ struct sk_lookup *params,
bool *refcounted)
{
struct sock *sk = skb_steal_sock(skb);
const struct iphdr *iph = ip_hdr(skb);
+ params->dif = inet_iif(skb);
+ params->saddr.ipv4 = iph->saddr;
+ params->daddr.ipv4 = iph->daddr;
+
*refcounted = true;
if (sk)
return sk;
return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb,
- doff, iph->saddr, sport,
- iph->daddr, dport, inet_iif(skb),
- refcounted);
+ doff, params, refcounted);
}
u32 inet6_ehashfn(const struct net *net,
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index f85d901f4e3f..f98a65fa5f5e 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -244,6 +244,11 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
__u64 seq;
int err;
struct net *net = dev_net(skb->dev);
+ struct sk_lookup params = {
+ .saddr.ipv4 = iph->daddr,
+ .daddr.ipv4 = iph->saddr,
+ .dif = inet_iif(skb),
+ };
/* Only need dccph_dport & dccph_sport which are the first
* 4 bytes in dccp header.
@@ -253,10 +258,11 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
dh = (struct dccp_hdr *)(skb->data + offset);
- sk = __inet_lookup_established(net, &dccp_hashinfo,
- iph->daddr, dh->dccph_dport,
- iph->saddr, ntohs(dh->dccph_sport),
- inet_iif(skb));
+ params.sport = dh->dccph_dport;
+ params.dport = dh->dccph_sport;
+ params.hnum = ntohs(dh->dccph_sport);
+
+ sk = inet_lookup_established(net, &dccp_hashinfo, ¶ms);
if (!sk) {
__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
return;
@@ -763,6 +769,7 @@ EXPORT_SYMBOL_GPL(dccp_invalid_packet);
/* this is called when real data arrives */
static int dccp_v4_rcv(struct sk_buff *skb)
{
+ struct sk_lookup params = {};
const struct dccp_hdr *dh;
const struct iphdr *iph;
bool refcounted;
@@ -801,9 +808,11 @@ static int dccp_v4_rcv(struct sk_buff *skb)
DCCP_SKB_CB(skb)->dccpd_ack_seq);
}
+ params.sport = dh->dccph_sport;
+ params.dport = dh->dccph_dport;
lookup:
sk = __inet_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh),
- dh->dccph_sport, dh->dccph_dport, &refcounted);
+ ¶ms, &refcounted);
if (!sk) {
dccp_pr_debug("failed to look up flow ID in table and "
"get corresponding socket\n");
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 3828b3a805cd..6c3bc4e408d0 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -396,18 +396,33 @@ struct sock *inet_diag_find_one_icsk(struct net *net,
struct sock *sk;
rcu_read_lock();
- if (req->sdiag_family == AF_INET)
- sk = inet_lookup(net, hashinfo, NULL, 0, req->id.idiag_dst[0],
- req->id.idiag_dport, req->id.idiag_src[0],
- req->id.idiag_sport, req->id.idiag_if);
+ if (req->sdiag_family == AF_INET) {
+ struct sk_lookup params = {
+ .saddr.ipv4 = req->id.idiag_dst[0],
+ .daddr.ipv4 = req->id.idiag_src[0],
+ .sport = req->id.idiag_dport,
+ .dport = req->id.idiag_sport,
+ .hnum = ntohs(req->id.idiag_sport),
+ .dif = req->id.idiag_if,
+ };
+
+ sk = inet_lookup(net, hashinfo, NULL, 0, ¶ms);
+ }
#if IS_ENABLED(CONFIG_IPV6)
else if (req->sdiag_family == AF_INET6) {
if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) &&
- ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src))
- sk = inet_lookup(net, hashinfo, NULL, 0, req->id.idiag_dst[3],
- req->id.idiag_dport, req->id.idiag_src[3],
- req->id.idiag_sport, req->id.idiag_if);
- else
+ ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) {
+ struct sk_lookup params = {
+ .saddr.ipv4 = req->id.idiag_dst[3],
+ .daddr.ipv4 = req->id.idiag_src[3],
+ .sport = req->id.idiag_dport,
+ .dport = req->id.idiag_sport,
+ .hnum = ntohs(req->id.idiag_sport),
+ .dif = req->id.idiag_if,
+ };
+
+ sk = inet_lookup(net, hashinfo, NULL, 0, ¶ms);
+ } else
sk = inet6_lookup(net, hashinfo, NULL, 0,
(struct in6_addr *)req->id.idiag_dst,
req->id.idiag_dport,
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 2e3389d614d1..5fe9300795b8 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -169,26 +169,28 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
EXPORT_SYMBOL_GPL(__inet_inherit_port);
static inline int compute_score(struct sock *sk, struct net *net,
- const unsigned short hnum, const __be32 daddr,
- const int dif, bool exact_dif)
+ const struct sk_lookup *params)
{
int score = -1;
struct inet_sock *inet = inet_sk(sk);
- if (net_eq(sock_net(sk), net) && inet->inet_num == hnum &&
- !ipv6_only_sock(sk)) {
+ if (net_eq(sock_net(sk), net) &&
+ inet->inet_num == params->hnum &&
+ !ipv6_only_sock(sk)) {
__be32 rcv_saddr = inet->inet_rcv_saddr;
+ int rc;
+
score = sk->sk_family == PF_INET ? 2 : 1;
if (rcv_saddr) {
- if (rcv_saddr != daddr)
+ if (rcv_saddr != params->daddr.ipv4)
return -1;
score += 4;
}
- if (sk->sk_bound_dev_if || exact_dif) {
- if (sk->sk_bound_dev_if != dif)
- return -1;
+ rc = sk_lookup_device_cmp(sk, params);
+ if (rc < 0)
+ return -1;
+ if (rc > 0)
score += 4;
- }
if (sk->sk_incoming_cpu == raw_smp_processor_id())
score++;
}
@@ -206,24 +208,25 @@ static inline int compute_score(struct sock *sk, struct net *net,
struct sock *__inet_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
- const __be32 saddr, __be16 sport,
- const __be32 daddr, const unsigned short hnum,
- const int dif)
+ struct sk_lookup *params)
{
- unsigned int hash = inet_lhashfn(net, hnum);
+ unsigned int hash = inet_lhashfn(net, params->hnum);
struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
int score, hiscore = 0, matches = 0, reuseport = 0;
- bool exact_dif = inet_exact_dif_match(net, skb);
struct sock *sk, *result = NULL;
u32 phash = 0;
+ params->exact_dif = inet_exact_dif_match(net, skb);
+
sk_for_each_rcu(sk, &ilb->head) {
- score = compute_score(sk, net, hnum, daddr, dif, exact_dif);
+ score = compute_score(sk, net, params);
if (score > hiscore) {
reuseport = sk->sk_reuseport;
if (reuseport) {
- phash = inet_ehashfn(net, daddr, hnum,
- saddr, sport);
+ phash = inet_ehashfn(net, params->daddr.ipv4,
+ params->hnum,
+ params->saddr.ipv4,
+ params->sport);
result = reuseport_select_sock(sk, phash,
skb, doff);
if (result)
@@ -265,11 +268,14 @@ void sock_edemux(struct sk_buff *skb)
EXPORT_SYMBOL(sock_edemux);
struct sock *__inet_lookup_established(struct net *net,
- struct inet_hashinfo *hashinfo,
- const __be32 saddr, const __be16 sport,
- const __be32 daddr, const u16 hnum,
- const int dif)
+ struct inet_hashinfo *hashinfo,
+ const struct sk_lookup *params)
{
+ __be32 saddr = params->saddr.ipv4;
+ __be32 daddr = params->daddr.ipv4;
+ __be16 sport = params->sport;
+ u16 hnum = params->hnum;
+ int dif = params->dif;
INET_ADDR_COOKIE(acookie, saddr, daddr);
const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
struct sock *sk;
diff --git a/net/ipv4/netfilter/nf_socket_ipv4.c b/net/ipv4/netfilter/nf_socket_ipv4.c
index 121767b36763..b0f9954712f9 100644
--- a/net/ipv4/netfilter/nf_socket_ipv4.c
+++ b/net/ipv4/netfilter/nf_socket_ipv4.c
@@ -86,14 +86,13 @@ nf_socket_get_sock_v4(struct net *net, struct sk_buff *skb, const int doff,
.daddr.ipv4 = daddr,
.sport = sport,
.dport = dport,
+ .hnum = ntohs(dport),
.dif = in->ifindex,
};
switch (protocol) {
case IPPROTO_TCP:
- return inet_lookup(net, &tcp_hashinfo, skb, doff,
- saddr, sport, daddr, dport,
- in->ifindex);
+ return inet_lookup(net, &tcp_hashinfo, skb, doff, ¶ms);
case IPPROTO_UDP:
return udp4_lib_lookup(net, ¶ms);
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3a19ea28339f..a83d1d437abc 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -382,10 +382,16 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
u32 delta_us;
int err;
struct net *net = dev_net(icmp_skb->dev);
-
- sk = __inet_lookup_established(net, &tcp_hashinfo, iph->daddr,
- th->dest, iph->saddr, ntohs(th->source),
- inet_iif(icmp_skb));
+ struct sk_lookup params = {
+ .saddr.ipv4 = iph->daddr,
+ .daddr.ipv4 = iph->saddr,
+ .sport = th->dest,
+ .dport = th->source,
+ .hnum = ntohs(th->source),
+ .dif = inet_iif(icmp_skb),
+ };
+
+ sk = inet_lookup_established(net, &tcp_hashinfo, ¶ms);
if (!sk) {
__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
return;
@@ -651,6 +657,15 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)
&ip_hdr(skb)->saddr, AF_INET);
} else if (hash_location) {
+ struct sk_lookup params = {
+ .saddr.ipv4 = ip_hdr(skb)->saddr,
+ .daddr.ipv4 = ip_hdr(skb)->daddr,
+ .sport = th->source,
+ .dport = th->source,
+ .hnum = ntohs(th->source),
+ .dif = inet_iif(skb),
+ };
+
/*
* active side is lost. Try to find listening socket through
* source port, and then find md5 key through listening socket.
@@ -658,10 +673,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
* Incoming packet is checked with md5 hash with finding key,
* no RST generated if md5 hash doesn't match.
*/
- sk1 = __inet_lookup_listener(net, &tcp_hashinfo, NULL, 0,
- ip_hdr(skb)->saddr,
- th->source, ip_hdr(skb)->daddr,
- ntohs(th->source), inet_iif(skb));
+ sk1 = inet_lookup_listener(net, &tcp_hashinfo, NULL, 0,
+ ¶ms);
/* don't send rst if it can't find key */
if (!sk1)
goto out;
@@ -1509,6 +1522,9 @@ void tcp_v4_early_demux(struct sk_buff *skb)
const struct iphdr *iph;
const struct tcphdr *th;
struct sock *sk;
+ struct sk_lookup params = {
+ .dif = skb->skb_iif,
+ };
if (skb->pkt_type != PACKET_HOST)
return;
@@ -1522,10 +1538,13 @@ void tcp_v4_early_demux(struct sk_buff *skb)
if (th->doff < sizeof(struct tcphdr) / 4)
return;
- sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo,
- iph->saddr, th->source,
- iph->daddr, ntohs(th->dest),
- skb->skb_iif);
+ params.saddr.ipv4 = iph->saddr;
+ params.daddr.ipv4 = iph->daddr;
+ params.sport = th->source;
+ params.dport = th->dest;
+ params.hnum = ntohs(th->dest),
+
+ sk = inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo, ¶ms);
if (sk) {
skb->sk = sk;
skb->destructor = sock_edemux;
@@ -1645,6 +1664,7 @@ EXPORT_SYMBOL(tcp_filter);
int tcp_v4_rcv(struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
+ struct sk_lookup params = { };
const struct iphdr *iph;
const struct tcphdr *th;
bool refcounted;
@@ -1693,9 +1713,11 @@ int tcp_v4_rcv(struct sk_buff *skb)
TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
TCP_SKB_CB(skb)->sacked = 0;
+ params.sport = th->source;
+ params.dport = th->dest;
lookup:
- sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source,
- th->dest, &refcounted);
+ sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), ¶ms,
+ &refcounted);
if (!sk)
goto no_tcp_socket;
@@ -1819,12 +1841,18 @@ int tcp_v4_rcv(struct sk_buff *skb)
}
switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) {
case TCP_TW_SYN: {
+ struct sk_lookup params = {
+ .saddr.ipv4 = iph->saddr,
+ .daddr.ipv4 = iph->daddr,
+ .sport = th->source,
+ .dport = th->dest,
+ .hnum = ntohs(th->dest),
+ .dif = inet_iif(skb),
+ };
struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev),
&tcp_hashinfo, skb,
__tcp_hdrlen(th),
- iph->saddr, th->source,
- iph->daddr, th->dest,
- inet_iif(skb));
+ ¶ms);
if (sk2) {
inet_twsk_deschedule_put(inet_twsk(sk));
sk = sk2;
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 5e0640877536..d7f6af42ebcc 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -47,6 +47,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
.daddr.ipv4 = req->id.idiag_dst[0],
.sport = req->id.idiag_sport,
.dport = req->id.idiag_dport,
+ .hnum = ntohs(req->id.idiag_dport),
.dif = req->id.idiag_if,
};
@@ -190,6 +191,7 @@ static int __udp_diag_destroy(struct sk_buff *in_skb,
.daddr.ipv4 = req->id.idiag_src[0],
.sport = req->id.idiag_dport,
.dport = req->id.idiag_sport,
+ .hnum = ntohs(req->id.idiag_sport),
.dif = req->id.idiag_if,
};
@@ -204,6 +206,7 @@ static int __udp_diag_destroy(struct sk_buff *in_skb,
.daddr.ipv4 = req->id.idiag_src[3],
.sport = req->id.idiag_dport,
.dport = req->id.idiag_sport,
+ .hnum = ntohs(req->id.idiag_sport),
.dif = req->id.idiag_if,
};
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 972a0e40c59a..5cce7eb7dea2 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -117,6 +117,7 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
.daddr.ipv4 = daddr,
.sport = sport,
.dport = dport,
+ .hnum = ntohs(dport),
.dif = in->ifindex,
};
@@ -129,11 +130,9 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
case NFT_LOOKUP_LISTENER:
tcph = hp;
sk = inet_lookup_listener(net, &tcp_hashinfo, skb,
- ip_hdrlen(skb) +
+ ip_hdrlen(skb) +
__tcp_hdrlen(tcph),
- saddr, sport,
- daddr, dport,
- in->ifindex);
+ ¶ms);
if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
@@ -145,8 +144,7 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
break;
case NFT_LOOKUP_ESTABLISHED:
sk = inet_lookup_established(net, &tcp_hashinfo,
- saddr, sport, daddr, dport,
- in->ifindex);
+ ¶ms);
break;
default:
BUG();
--
2.1.4
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PATCH net-next 04/10] net: ipv4: Convert raw sockets to sk_lookup
2017-08-01 3:13 [PATCH net-next 00/10] net: l3mdev: Support for sockets bound to enslaved device David Ahern
` (2 preceding siblings ...)
2017-08-01 3:13 ` [PATCH net-next 03/10] net: ipv4: Convert inet " David Ahern
@ 2017-08-01 3:13 ` David Ahern
2017-08-01 3:13 ` [PATCH net-next 05/10] net: ipv6: Convert udp socket lookups to new struct David Ahern
` (7 subsequent siblings)
11 siblings, 0 replies; 15+ messages in thread
From: David Ahern @ 2017-08-01 3:13 UTC (permalink / raw)
To: netdev; +Cc: David Ahern
Convert __raw_v4_lookup to use the new sk_lookup struct
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/raw.h | 3 +--
net/ipv4/raw.c | 72 ++++++++++++++++++++++++++++++++++-------------------
net/ipv4/raw_diag.c | 15 +++++++----
3 files changed, 58 insertions(+), 32 deletions(-)
diff --git a/include/net/raw.h b/include/net/raw.h
index 57c33dd22ec4..8d0f0e5d013b 100644
--- a/include/net/raw.h
+++ b/include/net/raw.h
@@ -25,8 +25,7 @@ extern struct proto raw_prot;
extern struct raw_hashinfo raw_v4_hashinfo;
struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
- unsigned short num, __be32 raddr,
- __be32 laddr, int dif);
+ const struct sk_lookup *params);
int raw_abort(struct sock *sk, int err);
void raw_icmp_error(struct sk_buff *, int, u32);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index b0bb5d0a30bd..4da5d87a61a5 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -122,15 +122,23 @@ void raw_unhash_sk(struct sock *sk)
EXPORT_SYMBOL_GPL(raw_unhash_sk);
struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
- unsigned short num, __be32 raddr, __be32 laddr, int dif)
+ const struct sk_lookup *params)
{
+ __be32 raddr = params->saddr.ipv4;
+ __be32 laddr = params->daddr.ipv4;
+
sk_for_each_from(sk) {
struct inet_sock *inet = inet_sk(sk);
+ bool dev_match;
+
+ dev_match = (!sk->sk_bound_dev_if ||
+ sk->sk_bound_dev_if == params->dif);
- if (net_eq(sock_net(sk), net) && inet->inet_num == num &&
- !(inet->inet_daddr && inet->inet_daddr != raddr) &&
+ if (net_eq(sock_net(sk), net) &&
+ inet->inet_num == params->hnum &&
+ !(inet->inet_daddr && inet->inet_daddr != raddr) &&
!(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) &&
- !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
+ dev_match)
goto found; /* gotcha */
}
sk = NULL;
@@ -169,23 +177,20 @@ static int icmp_filter(const struct sock *sk, const struct sk_buff *skb)
* RFC 1122: SHOULD pass TOS value up to the transport layer.
* -> It does. And not only TOS, but all IP header.
*/
-static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
+static int __raw_v4_input(struct sk_buff *skb, const struct iphdr *iph,
+ struct hlist_head *head)
{
- struct sock *sk;
- struct hlist_head *head;
+ struct net *net = dev_net(skb->dev);
+ const struct sk_lookup params = {
+ .saddr.ipv4 = iph->saddr,
+ .daddr.ipv4 = iph->daddr,
+ .hnum = iph->protocol,
+ .dif = skb->dev->ifindex,
+ };
int delivered = 0;
- struct net *net;
-
- read_lock(&raw_v4_hashinfo.lock);
- head = &raw_v4_hashinfo.ht[hash];
- if (hlist_empty(head))
- goto out;
-
- net = dev_net(skb->dev);
- sk = __raw_v4_lookup(net, __sk_head(head), iph->protocol,
- iph->saddr, iph->daddr,
- skb->dev->ifindex);
+ struct sock *sk;
+ sk = __raw_v4_lookup(net, __sk_head(head), ¶ms);
while (sk) {
delivered = 1;
if ((iph->protocol != IPPROTO_ICMP || !icmp_filter(sk, skb)) &&
@@ -197,11 +202,22 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
if (clone)
raw_rcv(sk, clone);
}
- sk = __raw_v4_lookup(net, sk_next(sk), iph->protocol,
- iph->saddr, iph->daddr,
- skb->dev->ifindex);
+ sk = __raw_v4_lookup(net, sk_next(sk), ¶ms);
}
-out:
+
+ return delivered;
+}
+
+static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
+{
+ struct hlist_head *head;
+ int delivered = 0;
+
+ read_lock(&raw_v4_hashinfo.lock);
+ head = &raw_v4_hashinfo.ht[hash];
+ if (!hlist_empty(head))
+ delivered = __raw_v4_input(skb, iph, head);
+
read_unlock(&raw_v4_hashinfo.lock);
return delivered;
}
@@ -297,12 +313,18 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info)
read_lock(&raw_v4_hashinfo.lock);
raw_sk = sk_head(&raw_v4_hashinfo.ht[hash]);
if (raw_sk) {
+ struct sk_lookup params = {
+ .hnum = protocol,
+ .dif = skb->dev->ifindex,
+ };
+
iph = (const struct iphdr *)skb->data;
net = dev_net(skb->dev);
- while ((raw_sk = __raw_v4_lookup(net, raw_sk, protocol,
- iph->daddr, iph->saddr,
- skb->dev->ifindex)) != NULL) {
+ params.saddr.ipv4 = iph->daddr;
+ params.daddr.ipv4 = iph->saddr;
+ while ((raw_sk = __raw_v4_lookup(net, raw_sk,
+ ¶ms)) != NULL) {
raw_err(raw_sk, skb, info);
raw_sk = sk_next(raw_sk);
iph = (const struct iphdr *)skb->data;
diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c
index e1a51ca68d23..a708de070cc6 100644
--- a/net/ipv4/raw_diag.c
+++ b/net/ipv4/raw_diag.c
@@ -42,11 +42,16 @@ static struct sock *raw_lookup(struct net *net, struct sock *from,
struct inet_diag_req_raw *r = (void *)req;
struct sock *sk = NULL;
- if (r->sdiag_family == AF_INET)
- sk = __raw_v4_lookup(net, from, r->sdiag_raw_protocol,
- r->id.idiag_dst[0],
- r->id.idiag_src[0],
- r->id.idiag_if);
+ if (r->sdiag_family == AF_INET) {
+ const struct sk_lookup params = {
+ .saddr.ipv4 = r->id.idiag_dst[0],
+ .daddr.ipv4 = r->id.idiag_src[0],
+ .hnum = r->sdiag_raw_protocol,
+ .dif = r->id.idiag_if,
+ };
+
+ sk = __raw_v4_lookup(net, from, ¶ms);
+ }
#if IS_ENABLED(CONFIG_IPV6)
else
sk = __raw_v6_lookup(net, from, r->sdiag_raw_protocol,
--
2.1.4
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PATCH net-next 05/10] net: ipv6: Convert udp socket lookups to new struct
2017-08-01 3:13 [PATCH net-next 00/10] net: l3mdev: Support for sockets bound to enslaved device David Ahern
` (3 preceding siblings ...)
2017-08-01 3:13 ` [PATCH net-next 04/10] net: ipv4: Convert raw sockets to sk_lookup David Ahern
@ 2017-08-01 3:13 ` David Ahern
2017-08-01 3:13 ` [PATCH net-next 06/10] net: ipv6: Convert inet " David Ahern
` (6 subsequent siblings)
11 siblings, 0 replies; 15+ messages in thread
From: David Ahern @ 2017-08-01 3:13 UTC (permalink / raw)
To: netdev; +Cc: David Ahern
Convert udp6_lib_lookup and __udp6_lib_lookup to use the new sk_lookup
struct.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/udp.h | 12 +--
net/ipv4/udp_diag.c | 33 ++++---
net/ipv6/netfilter/nf_socket_ipv6.c | 11 ++-
net/ipv6/udp.c | 177 +++++++++++++++++++-----------------
net/netfilter/xt_TPROXY.c | 10 +-
5 files changed, 135 insertions(+), 108 deletions(-)
diff --git a/include/net/udp.h b/include/net/udp.h
index 5e0ff095dc6d..c5a75e9422c6 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -288,15 +288,9 @@ struct sock *__udp4_lib_lookup(struct net *net, struct sk_lookup *params,
struct udp_table *tbl, struct sk_buff *skb);
struct sock *udp4_lib_lookup_skb(struct sk_buff *skb,
__be16 sport, __be16 dport);
-struct sock *udp6_lib_lookup(struct net *net,
- const struct in6_addr *saddr, __be16 sport,
- const struct in6_addr *daddr, __be16 dport,
- int dif);
-struct sock *__udp6_lib_lookup(struct net *net,
- const struct in6_addr *saddr, __be16 sport,
- const struct in6_addr *daddr, __be16 dport,
- int dif, struct udp_table *tbl,
- struct sk_buff *skb);
+struct sock *udp6_lib_lookup(struct net *net, struct sk_lookup *params);
+struct sock *__udp6_lib_lookup(struct net *net, struct sk_lookup *params,
+ struct udp_table *tbl, struct sk_buff *skb);
struct sock *udp6_lib_lookup_skb(struct sk_buff *skb,
__be16 sport, __be16 dport);
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index d7f6af42ebcc..10738c10c5ae 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -54,13 +54,17 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
sk = __udp4_lib_lookup(net, ¶ms, tbl, NULL);
}
#if IS_ENABLED(CONFIG_IPV6)
- else if (req->sdiag_family == AF_INET6)
- sk = __udp6_lib_lookup(net,
- (struct in6_addr *)req->id.idiag_src,
- req->id.idiag_sport,
- (struct in6_addr *)req->id.idiag_dst,
- req->id.idiag_dport,
- req->id.idiag_if, tbl, NULL);
+ else if (req->sdiag_family == AF_INET6) {
+ struct sk_lookup params = {
+ .saddr.ipv6 = (struct in6_addr *)req->id.idiag_src,
+ .daddr.ipv6 = (struct in6_addr *)req->id.idiag_dst,
+ .sport = req->id.idiag_sport,
+ .dport = req->id.idiag_dport,
+ .dif = req->id.idiag_if,
+ };
+
+ sk = __udp6_lib_lookup(net, ¶ms, tbl, NULL);
+ }
#endif
if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
@@ -212,12 +216,15 @@ static int __udp_diag_destroy(struct sk_buff *in_skb,
sk = __udp4_lib_lookup(net, ¶ms, tbl, NULL);
} else {
- sk = __udp6_lib_lookup(net,
- (struct in6_addr *)req->id.idiag_dst,
- req->id.idiag_dport,
- (struct in6_addr *)req->id.idiag_src,
- req->id.idiag_sport,
- req->id.idiag_if, tbl, NULL);
+ struct sk_lookup params = {
+ .saddr.ipv6 = (struct in6_addr *)req->id.idiag_dst,
+ .daddr.ipv6 = (struct in6_addr *)req->id.idiag_src,
+ .sport = req->id.idiag_dport,
+ .dport = req->id.idiag_sport,
+ .dif = req->id.idiag_if,
+ };
+
+ sk = __udp6_lib_lookup(net, ¶ms, tbl, NULL);
}
}
#endif
diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c
index ebb2bf84232a..c1c193103063 100644
--- a/net/ipv6/netfilter/nf_socket_ipv6.c
+++ b/net/ipv6/netfilter/nf_socket_ipv6.c
@@ -86,14 +86,21 @@ nf_socket_get_sock_v6(struct net *net, struct sk_buff *skb, int doff,
const __be16 sport, const __be16 dport,
const struct net_device *in)
{
+ struct sk_lookup params = {
+ .saddr.ipv6 = saddr,
+ .daddr.ipv6 = daddr,
+ .sport = sport,
+ .dport = dport,
+ .dif = in->ifindex,
+ };
+
switch (protocol) {
case IPPROTO_TCP:
return inet6_lookup(net, &tcp_hashinfo, skb, doff,
saddr, sport, daddr, dport,
in->ifindex);
case IPPROTO_UDP:
- return udp6_lib_lookup(net, saddr, sport, daddr, dport,
- in->ifindex);
+ return udp6_lib_lookup(net, ¶ms);
}
return NULL;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 5f8b8d766c63..00b362a8bd91 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -67,13 +67,14 @@ static bool udp6_lib_exact_dif_match(struct net *net, struct sk_buff *skb)
}
static u32 udp6_ehashfn(const struct net *net,
- const struct in6_addr *laddr,
- const u16 lport,
- const struct in6_addr *faddr,
- const __be16 fport)
+ const struct sk_lookup *params)
{
+ const struct in6_addr *laddr = params->daddr.ipv6;
+ const struct in6_addr *faddr = params->saddr.ipv6;
static u32 udp6_ehash_secret __read_mostly;
static u32 udp_ipv6_hash_secret __read_mostly;
+ const __be16 fport = params->sport;
+ const u16 lport = params->hnum;
u32 lhash, fhash;
@@ -127,15 +128,13 @@ static void udp_v6_rehash(struct sock *sk)
}
static int compute_score(struct sock *sk, struct net *net,
- const struct in6_addr *saddr, __be16 sport,
- const struct in6_addr *daddr, unsigned short hnum,
- int dif, bool exact_dif)
+ const struct sk_lookup *params)
{
- int score;
struct inet_sock *inet;
+ int score, rc;
if (!net_eq(sock_net(sk), net) ||
- udp_sk(sk)->udp_port_hash != hnum ||
+ udp_sk(sk)->udp_port_hash != params->hnum ||
sk->sk_family != PF_INET6)
return -1;
@@ -143,28 +142,28 @@ static int compute_score(struct sock *sk, struct net *net,
inet = inet_sk(sk);
if (inet->inet_dport) {
- if (inet->inet_dport != sport)
+ if (inet->inet_dport != params->sport)
return -1;
score++;
}
if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
- if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
+ if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, params->daddr.ipv6))
return -1;
score++;
}
if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
- if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
+ if (!ipv6_addr_equal(&sk->sk_v6_daddr, params->saddr.ipv6))
return -1;
score++;
}
- if (sk->sk_bound_dev_if || exact_dif) {
- if (sk->sk_bound_dev_if != dif)
- return -1;
+ rc = sk_lookup_device_cmp(sk, params);
+ if (rc < 0)
+ return -1;
+ if (rc > 0)
score++;
- }
if (sk->sk_incoming_cpu == raw_smp_processor_id())
score++;
@@ -174,10 +173,9 @@ static int compute_score(struct sock *sk, struct net *net,
/* called with rcu_read_lock() */
static struct sock *udp6_lib_lookup2(struct net *net,
- const struct in6_addr *saddr, __be16 sport,
- const struct in6_addr *daddr, unsigned int hnum, int dif,
- bool exact_dif, struct udp_hslot *hslot2,
- struct sk_buff *skb)
+ const struct sk_lookup *params,
+ struct udp_hslot *hslot2,
+ struct sk_buff *skb)
{
struct sock *sk, *result;
int score, badness, matches = 0, reuseport = 0;
@@ -186,13 +184,11 @@ static struct sock *udp6_lib_lookup2(struct net *net,
result = NULL;
badness = -1;
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
- score = compute_score(sk, net, saddr, sport,
- daddr, hnum, dif, exact_dif);
+ score = compute_score(sk, net, params);
if (score > badness) {
reuseport = sk->sk_reuseport;
if (reuseport) {
- hash = udp6_ehashfn(net, daddr, hnum,
- saddr, sport);
+ hash = udp6_ehashfn(net, params);
result = reuseport_select_sock(sk, hash, skb,
sizeof(struct udphdr));
@@ -213,30 +209,27 @@ static struct sock *udp6_lib_lookup2(struct net *net,
}
/* rcu_read_lock() must be held */
-struct sock *__udp6_lib_lookup(struct net *net,
- const struct in6_addr *saddr, __be16 sport,
- const struct in6_addr *daddr, __be16 dport,
- int dif, struct udp_table *udptable,
- struct sk_buff *skb)
+struct sock *__udp6_lib_lookup(struct net *net, struct sk_lookup *params,
+ struct udp_table *udptable, struct sk_buff *skb)
{
struct sock *sk, *result;
- unsigned short hnum = ntohs(dport);
+ unsigned short hnum = ntohs(params->dport);
unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
- bool exact_dif = udp6_lib_exact_dif_match(net, skb);
int score, badness, matches = 0, reuseport = 0;
u32 hash = 0;
+ params->hnum = hnum;
+ params->exact_dif = udp6_lib_exact_dif_match(net, skb);
+
if (hslot->count > 10) {
- hash2 = udp6_portaddr_hash(net, daddr, hnum);
+ hash2 = udp6_portaddr_hash(net, params->daddr.ipv6, hnum);
slot2 = hash2 & udptable->mask;
hslot2 = &udptable->hash2[slot2];
if (hslot->count < hslot2->count)
goto begin;
- result = udp6_lib_lookup2(net, saddr, sport,
- daddr, hnum, dif, exact_dif,
- hslot2, skb);
+ result = udp6_lib_lookup2(net, params, hslot2, skb);
if (!result) {
unsigned int old_slot2 = slot2;
hash2 = udp6_portaddr_hash(net, &in6addr_any, hnum);
@@ -249,10 +242,7 @@ struct sock *__udp6_lib_lookup(struct net *net,
if (hslot->count < hslot2->count)
goto begin;
- result = udp6_lib_lookup2(net, saddr, sport,
- daddr, hnum, dif,
- exact_dif, hslot2,
- skb);
+ result = udp6_lib_lookup2(net, params, hslot2, skb);
}
return result;
}
@@ -260,13 +250,11 @@ struct sock *__udp6_lib_lookup(struct net *net,
result = NULL;
badness = -1;
sk_for_each_rcu(sk, &hslot->head) {
- score = compute_score(sk, net, saddr, sport, daddr, hnum, dif,
- exact_dif);
+ score = compute_score(sk, net, params);
if (score > badness) {
reuseport = sk->sk_reuseport;
if (reuseport) {
- hash = udp6_ehashfn(net, daddr, hnum,
- saddr, sport);
+ hash = udp6_ehashfn(net, params);
result = reuseport_select_sock(sk, hash, skb,
sizeof(struct udphdr));
if (result)
@@ -292,23 +280,34 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
struct sock *sk;
+ struct sk_lookup params = {
+ .saddr.ipv6 = &iph->saddr,
+ .daddr.ipv6 = &iph->daddr,
+ .sport = sport,
+ .dport = dport,
+ .dif = inet6_iif(skb),
+ };
sk = skb_steal_sock(skb);
if (unlikely(sk))
return sk;
- return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
- &iph->daddr, dport, inet6_iif(skb),
- udptable, skb);
+
+ return __udp6_lib_lookup(dev_net(skb->dev), ¶ms, udptable, skb);
}
struct sock *udp6_lib_lookup_skb(struct sk_buff *skb,
__be16 sport, __be16 dport)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
-
- return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
- &iph->daddr, dport, inet6_iif(skb),
- &udp_table, skb);
+ struct sk_lookup params = {
+ .saddr.ipv6 = &iph->saddr,
+ .daddr.ipv6 = &iph->daddr,
+ .sport = sport,
+ .dport = dport,
+ .dif = inet6_iif(skb),
+ };
+
+ return __udp6_lib_lookup(dev_net(skb->dev), ¶ms, &udp_table, skb);
}
EXPORT_SYMBOL_GPL(udp6_lib_lookup_skb);
@@ -318,13 +317,11 @@ EXPORT_SYMBOL_GPL(udp6_lib_lookup_skb);
#if IS_ENABLED(CONFIG_NETFILTER_XT_MATCH_SOCKET) || \
IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TPROXY) || \
IS_ENABLED(CONFIG_NF_SOCKET_IPV6)
-struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport,
- const struct in6_addr *daddr, __be16 dport, int dif)
+struct sock *udp6_lib_lookup(struct net *net, struct sk_lookup *params)
{
struct sock *sk;
- sk = __udp6_lib_lookup(net, saddr, sport, daddr, dport,
- dif, &udp_table, NULL);
+ sk = __udp6_lib_lookup(net, params, &udp_table, NULL);
if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
return sk;
@@ -487,16 +484,20 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
{
struct ipv6_pinfo *np;
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
- const struct in6_addr *saddr = &hdr->saddr;
- const struct in6_addr *daddr = &hdr->daddr;
struct udphdr *uh = (struct udphdr *)(skb->data+offset);
+ struct sk_lookup params = {
+ .saddr.ipv6 = &hdr->daddr,
+ .daddr.ipv6 = &hdr->saddr,
+ .sport = uh->dest,
+ .dport = uh->source,
+ .dif = inet6_iif(skb),
+ };
struct sock *sk;
int harderr;
int err;
struct net *net = dev_net(skb->dev);
- sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source,
- inet6_iif(skb), udptable, skb);
+ sk = __udp6_lib_lookup(net, ¶ms, udptable, skb);
if (!sk) {
__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
@@ -658,21 +659,21 @@ static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
}
static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
- __be16 loc_port, const struct in6_addr *loc_addr,
- __be16 rmt_port, const struct in6_addr *rmt_addr,
- int dif, unsigned short hnum)
+ struct sk_lookup *params)
{
+ const struct in6_addr *loc_addr = params->daddr.ipv6;
+ const struct in6_addr *rmt_addr = params->saddr.ipv6;
struct inet_sock *inet = inet_sk(sk);
if (!net_eq(sock_net(sk), net))
return false;
- if (udp_sk(sk)->udp_port_hash != hnum ||
+ if (udp_sk(sk)->udp_port_hash != params->hnum ||
sk->sk_family != PF_INET6 ||
- (inet->inet_dport && inet->inet_dport != rmt_port) ||
+ (inet->inet_dport && inet->inet_dport != params->sport) ||
(!ipv6_addr_any(&sk->sk_v6_daddr) &&
!ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) ||
- (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) ||
+ (sk->sk_bound_dev_if && sk->sk_bound_dev_if != params->dif) ||
(!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)))
return false;
@@ -705,9 +706,16 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
struct udp_hslot *hslot = udp_hashslot(udptable, net, hnum);
unsigned int offset = offsetof(typeof(*sk), sk_node);
unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10);
- int dif = inet6_iif(skb);
struct hlist_node *node;
struct sk_buff *nskb;
+ struct sk_lookup params = {
+ .saddr.ipv6 = saddr,
+ .daddr.ipv6 = daddr,
+ .sport = uh->source,
+ .dport = uh->dest,
+ .hnum = hnum,
+ .dif = inet6_iif(skb),
+ };
if (use_hash2) {
hash2_any = udp6_portaddr_hash(net, &in6addr_any, hnum) &
@@ -719,8 +727,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
}
sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) {
- if (!__udp_v6_is_mcast_sock(net, sk, uh->dest, daddr,
- uh->source, saddr, dif, hnum))
+ if (!__udp_v6_is_mcast_sock(net, sk, ¶ms))
continue;
/* If zero checksum and no_check is not on for
* the socket then skip it.
@@ -873,21 +880,22 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
static struct sock *__udp6_lib_demux_lookup(struct net *net,
- __be16 loc_port, const struct in6_addr *loc_addr,
- __be16 rmt_port, const struct in6_addr *rmt_addr,
- int dif)
+ const struct sk_lookup *params)
{
- unsigned short hnum = ntohs(loc_port);
- unsigned int hash2 = udp6_portaddr_hash(net, loc_addr, hnum);
+ unsigned short hnum = params->hnum;
+ unsigned int hash2 = udp6_portaddr_hash(net, params->daddr.ipv6, hnum);
unsigned int slot2 = hash2 & udp_table.mask;
struct udp_hslot *hslot2 = &udp_table.hash2[slot2];
- const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum);
+ const __portpair ports = INET_COMBINED_PORTS(params->sport, hnum);
struct sock *sk;
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
if (sk->sk_state == TCP_ESTABLISHED &&
- INET6_MATCH(sk, net, rmt_addr, loc_addr, ports, dif))
+ INET6_MATCH(sk, net, params->saddr.ipv6,
+ params->daddr.ipv6, ports,
+ params->dif))
return sk;
+
/* Only check first socket in chain */
break;
}
@@ -900,7 +908,14 @@ static void udp_v6_early_demux(struct sk_buff *skb)
const struct udphdr *uh;
struct sock *sk;
struct dst_entry *dst;
- int dif = skb->dev->ifindex;
+ struct sk_lookup params = {
+ .saddr.ipv6 = &ipv6_hdr(skb)->saddr,
+ .daddr.ipv6 = &ipv6_hdr(skb)->daddr,
+ .dif = skb->dev->ifindex,
+ };
+
+ if (skb->pkt_type != PACKET_HOST)
+ return;
if (!pskb_may_pull(skb, skb_transport_offset(skb) +
sizeof(struct udphdr)))
@@ -908,13 +923,11 @@ static void udp_v6_early_demux(struct sk_buff *skb)
uh = udp_hdr(skb);
- if (skb->pkt_type == PACKET_HOST)
- sk = __udp6_lib_demux_lookup(net, uh->dest,
- &ipv6_hdr(skb)->daddr,
- uh->source, &ipv6_hdr(skb)->saddr,
- dif);
- else
- return;
+ params.dport = uh->dest;
+ params.hnum = ntohs(uh->dest);
+ params.sport = uh->source;
+
+ sk = __udp6_lib_demux_lookup(net, ¶ms);
if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt))
return;
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 5cce7eb7dea2..56bb40544035 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -188,6 +188,13 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
const struct net_device *in,
const enum nf_tproxy_lookup_t lookup_type)
{
+ struct sk_lookup params = {
+ .saddr.ipv6 = saddr,
+ .daddr.ipv6 = daddr,
+ .sport = sport,
+ .dport = dport,
+ .dif = in->ifindex,
+ };
struct sock *sk;
struct tcphdr *tcph;
@@ -220,8 +227,7 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
}
break;
case IPPROTO_UDP:
- sk = udp6_lib_lookup(net, saddr, sport, daddr, dport,
- in->ifindex);
+ sk = udp6_lib_lookup(net, ¶ms);
if (sk) {
int connected = (sk->sk_state == TCP_ESTABLISHED);
int wildcard = ipv6_addr_any(&sk->sk_v6_rcv_saddr);
--
2.1.4
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PATCH net-next 06/10] net: ipv6: Convert inet socket lookups to new struct
2017-08-01 3:13 [PATCH net-next 00/10] net: l3mdev: Support for sockets bound to enslaved device David Ahern
` (4 preceding siblings ...)
2017-08-01 3:13 ` [PATCH net-next 05/10] net: ipv6: Convert udp socket lookups to new struct David Ahern
@ 2017-08-01 3:13 ` David Ahern
2017-08-01 3:13 ` [PATCH net-next 07/10] net: ipv6: Convert raw sockets to sk_lookup David Ahern
` (5 subsequent siblings)
11 siblings, 0 replies; 15+ messages in thread
From: David Ahern @ 2017-08-01 3:13 UTC (permalink / raw)
To: netdev; +Cc: David Ahern
Convert the various inet6_lookup functions to use the new sk_lookup
struct.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/inet6_hashtables.h | 39 +++++++-------------
net/dccp/ipv6.c | 22 ++++++++----
net/ipv4/inet_diag.c | 19 ++++++----
net/ipv4/udp_diag.c | 2 ++
net/ipv6/inet6_hashtables.c | 72 +++++++++++++++++++------------------
net/ipv6/netfilter/nf_socket_ipv6.c | 5 ++-
net/ipv6/tcp_ipv6.c | 60 +++++++++++++++++++++----------
net/netfilter/xt_TPROXY.c | 8 ++---
8 files changed, 125 insertions(+), 102 deletions(-)
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index b87becacd9d3..15db41272ff2 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -46,63 +46,50 @@ static inline unsigned int __inet6_ehashfn(const u32 lhash,
*/
struct sock *__inet6_lookup_established(struct net *net,
struct inet_hashinfo *hashinfo,
- const struct in6_addr *saddr,
- const __be16 sport,
- const struct in6_addr *daddr,
- const u16 hnum, const int dif);
+ const struct sk_lookup *params);
struct sock *inet6_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
- const struct in6_addr *saddr,
- const __be16 sport,
- const struct in6_addr *daddr,
- const unsigned short hnum, const int dif);
+ struct sk_lookup *params);
static inline struct sock *__inet6_lookup(struct net *net,
struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
- const struct in6_addr *saddr,
- const __be16 sport,
- const struct in6_addr *daddr,
- const u16 hnum,
- const int dif,
+ struct sk_lookup *params,
bool *refcounted)
{
- struct sock *sk = __inet6_lookup_established(net, hashinfo, saddr,
- sport, daddr, hnum, dif);
+ struct sock *sk = __inet6_lookup_established(net, hashinfo, params);
+
*refcounted = true;
if (sk)
return sk;
*refcounted = false;
- return inet6_lookup_listener(net, hashinfo, skb, doff, saddr, sport,
- daddr, hnum, dif);
+ return inet6_lookup_listener(net, hashinfo, skb, doff, params);
}
static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
- const __be16 sport,
- const __be16 dport,
- int iif,
+ struct sk_lookup *params,
bool *refcounted)
{
struct sock *sk = skb_steal_sock(skb);
+ params->saddr.ipv6 = &ipv6_hdr(skb)->saddr,
+ params->daddr.ipv6 = &ipv6_hdr(skb)->daddr,
+ params->hnum = ntohs(params->dport),
+
*refcounted = true;
if (sk)
return sk;
return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb,
- doff, &ipv6_hdr(skb)->saddr, sport,
- &ipv6_hdr(skb)->daddr, ntohs(dport),
- iif, refcounted);
+ doff, params, refcounted);
}
struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
- const struct in6_addr *saddr, const __be16 sport,
- const struct in6_addr *daddr, const __be16 dport,
- const int dif);
+ struct sk_lookup *params);
int inet6_hash(struct sock *sk);
#endif /* IS_ENABLED(CONFIG_IPV6) */
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index c376af5bfdfb..e92f10a832dd 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -70,6 +70,11 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
+ struct sk_lookup params = {
+ .saddr.ipv6 = &hdr->daddr,
+ .daddr.ipv6 = &hdr->saddr,
+ .dif = inet6_iif(skb),
+ };
const struct dccp_hdr *dh;
struct dccp_sock *dp;
struct ipv6_pinfo *np;
@@ -86,11 +91,10 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8);
dh = (struct dccp_hdr *)(skb->data + offset);
- sk = __inet6_lookup_established(net, &dccp_hashinfo,
- &hdr->daddr, dh->dccph_dport,
- &hdr->saddr, ntohs(dh->dccph_sport),
- inet6_iif(skb));
-
+ params.sport = dh->dccph_dport;
+ params.dport = dh->dccph_sport;
+ params.hnum = ntohs(dh->dccph_sport);
+ sk = __inet6_lookup_established(net, &dccp_hashinfo, ¶ms);
if (!sk) {
__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
@@ -656,6 +660,9 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
static int dccp_v6_rcv(struct sk_buff *skb)
{
+ struct sk_lookup params = {
+ .dif = inet6_iif(skb),
+ };
const struct dccp_hdr *dh;
bool refcounted;
struct sock *sk;
@@ -683,10 +690,11 @@ static int dccp_v6_rcv(struct sk_buff *skb)
else
DCCP_SKB_CB(skb)->dccpd_ack_seq = dccp_hdr_ack_seq(skb);
+ params.sport = dh->dccph_sport;
+ params.dport = dh->dccph_dport;
lookup:
sk = __inet6_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh),
- dh->dccph_sport, dh->dccph_dport,
- inet6_iif(skb), &refcounted);
+ ¶ms, &refcounted);
if (!sk) {
dccp_pr_debug("failed to look up flow ID in table and "
"get corresponding socket\n");
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 6c3bc4e408d0..c1ec0d3cc4b9 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -422,13 +422,18 @@ struct sock *inet_diag_find_one_icsk(struct net *net,
};
sk = inet_lookup(net, hashinfo, NULL, 0, ¶ms);
- } else
- sk = inet6_lookup(net, hashinfo, NULL, 0,
- (struct in6_addr *)req->id.idiag_dst,
- req->id.idiag_dport,
- (struct in6_addr *)req->id.idiag_src,
- req->id.idiag_sport,
- req->id.idiag_if);
+ } else {
+ struct sk_lookup params = {
+ .saddr.ipv6 = (struct in6_addr *)req->id.idiag_dst,
+ .daddr.ipv6 = (struct in6_addr *)req->id.idiag_src,
+ .sport = req->id.idiag_dport,
+ .dport = req->id.idiag_sport,
+ .hnum = ntohs(req->id.idiag_sport),
+ .dif = req->id.idiag_if,
+ };
+
+ sk = inet6_lookup(net, hashinfo, NULL, 0, ¶ms);
+ }
}
#endif
else {
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 10738c10c5ae..bd358f9dde1f 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -60,6 +60,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
.daddr.ipv6 = (struct in6_addr *)req->id.idiag_dst,
.sport = req->id.idiag_sport,
.dport = req->id.idiag_dport,
+ .hnum = ntohs(req->id.idiag_dport),
.dif = req->id.idiag_if,
};
@@ -221,6 +222,7 @@ static int __udp_diag_destroy(struct sk_buff *in_skb,
.daddr.ipv6 = (struct in6_addr *)req->id.idiag_src,
.sport = req->id.idiag_dport,
.dport = req->id.idiag_sport,
+ .hnum = ntohs(req->id.idiag_sport),
.dif = req->id.idiag_if,
};
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index b13b8f93079d..878c03094f2e 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -52,33 +52,35 @@ u32 inet6_ehashfn(const struct net *net,
*/
struct sock *__inet6_lookup_established(struct net *net,
struct inet_hashinfo *hashinfo,
- const struct in6_addr *saddr,
- const __be16 sport,
- const struct in6_addr *daddr,
- const u16 hnum,
- const int dif)
+ const struct sk_lookup *params)
{
+ const __portpair ports = INET_COMBINED_PORTS(params->sport,
+ params->hnum);
+ const struct in6_addr *saddr = params->saddr.ipv6;
+ const struct in6_addr *daddr = params->daddr.ipv6;
struct sock *sk;
const struct hlist_nulls_node *node;
- const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
+
/* Optimize here for direct hit, only listening connections can
* have wildcards anyways.
*/
- unsigned int hash = inet6_ehashfn(net, daddr, hnum, saddr, sport);
+ unsigned int hash = inet6_ehashfn(net, daddr, params->hnum,
+ saddr, params->sport);
unsigned int slot = hash & hashinfo->ehash_mask;
struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
-
begin:
sk_nulls_for_each_rcu(sk, node, &head->chain) {
if (sk->sk_hash != hash)
continue;
- if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif))
+ if (!INET6_MATCH(sk, net, saddr, daddr, ports,
+ params->dif))
continue;
if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
goto out;
- if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports, dif))) {
+ if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports,
+ params->dif))) {
sock_gen_put(sk);
goto begin;
}
@@ -94,26 +96,27 @@ struct sock *__inet6_lookup_established(struct net *net,
EXPORT_SYMBOL(__inet6_lookup_established);
static inline int compute_score(struct sock *sk, struct net *net,
- const unsigned short hnum,
- const struct in6_addr *daddr,
- const int dif, bool exact_dif)
+ const struct sk_lookup *params)
{
int score = -1;
- if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum &&
+ if (net_eq(sock_net(sk), net) &&
+ inet_sk(sk)->inet_num == params->hnum &&
sk->sk_family == PF_INET6) {
+ int rc;
score = 1;
if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
- if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
+ if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr,
+ params->daddr.ipv6))
return -1;
score++;
}
- if (sk->sk_bound_dev_if || exact_dif) {
- if (sk->sk_bound_dev_if != dif)
- return -1;
+ rc = sk_lookup_device_cmp(sk, params);
+ if (rc < 0)
+ return -1;
+ if (rc > 0)
score++;
- }
if (sk->sk_incoming_cpu == raw_smp_processor_id())
score++;
}
@@ -122,26 +125,27 @@ static inline int compute_score(struct sock *sk, struct net *net,
/* called with rcu_read_lock() */
struct sock *inet6_lookup_listener(struct net *net,
- struct inet_hashinfo *hashinfo,
- struct sk_buff *skb, int doff,
- const struct in6_addr *saddr,
- const __be16 sport, const struct in6_addr *daddr,
- const unsigned short hnum, const int dif)
+ struct inet_hashinfo *hashinfo,
+ struct sk_buff *skb, int doff,
+ struct sk_lookup *params)
{
- unsigned int hash = inet_lhashfn(net, hnum);
+ unsigned int hash = inet_lhashfn(net, params->hnum);
struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
int score, hiscore = 0, matches = 0, reuseport = 0;
- bool exact_dif = inet6_exact_dif_match(net, skb);
struct sock *sk, *result = NULL;
u32 phash = 0;
+ params->exact_dif = inet6_exact_dif_match(net, skb);
+
sk_for_each(sk, &ilb->head) {
- score = compute_score(sk, net, hnum, daddr, dif, exact_dif);
+ score = compute_score(sk, net, params);
if (score > hiscore) {
reuseport = sk->sk_reuseport;
if (reuseport) {
- phash = inet6_ehashfn(net, daddr, hnum,
- saddr, sport);
+ phash = inet6_ehashfn(net, params->daddr.ipv6,
+ params->hnum,
+ params->saddr.ipv6,
+ params->sport);
result = reuseport_select_sock(sk, phash,
skb, doff);
if (result)
@@ -163,15 +167,12 @@ EXPORT_SYMBOL_GPL(inet6_lookup_listener);
struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
- const struct in6_addr *saddr, const __be16 sport,
- const struct in6_addr *daddr, const __be16 dport,
- const int dif)
+ struct sk_lookup *params)
{
struct sock *sk;
bool refcounted;
- sk = __inet6_lookup(net, hashinfo, skb, doff, saddr, sport, daddr,
- ntohs(dport), dif, &refcounted);
+ sk = __inet6_lookup(net, hashinfo, skb, doff, params, &refcounted);
if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
return sk;
@@ -203,7 +204,8 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
if (sk2->sk_hash != hash)
continue;
- if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, dif))) {
+ if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports,
+ dif))) {
if (sk2->sk_state == TCP_TIME_WAIT) {
tw = inet_twsk(sk2);
if (twsk_unique(sk, sk2, twp))
diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c
index c1c193103063..1d815e0933b7 100644
--- a/net/ipv6/netfilter/nf_socket_ipv6.c
+++ b/net/ipv6/netfilter/nf_socket_ipv6.c
@@ -91,14 +91,13 @@ nf_socket_get_sock_v6(struct net *net, struct sk_buff *skb, int doff,
.daddr.ipv6 = daddr,
.sport = sport,
.dport = dport,
+ .hnum = ntohs(dport),
.dif = in->ifindex,
};
switch (protocol) {
case IPPROTO_TCP:
- return inet6_lookup(net, &tcp_hashinfo, skb, doff,
- saddr, sport, daddr, dport,
- in->ifindex);
+ return inet6_lookup(net, &tcp_hashinfo, skb, doff, ¶ms);
case IPPROTO_UDP:
return udp6_lib_lookup(net, ¶ms);
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 2968a33cca7d..19fee98e1ae0 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -45,6 +45,7 @@
#include <linux/random.h>
#include <net/tcp.h>
+#include <net/inet_hashtables.h>
#include <net/ndisc.h>
#include <net/inet6_hashtables.h>
#include <net/inet6_connection_sock.h>
@@ -338,6 +339,13 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
{
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
const struct tcphdr *th = (struct tcphdr *)(skb->data+offset);
+ struct sk_lookup params = {
+ .saddr.ipv6 = &hdr->daddr,
+ .daddr.ipv6 = &hdr->saddr,
+ .sport = th->dest,
+ .hnum = ntohs(th->source),
+ .dif = skb->dev->ifindex,
+ };
struct net *net = dev_net(skb->dev);
struct request_sock *fastopen;
struct ipv6_pinfo *np;
@@ -347,11 +355,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
bool fatal;
int err;
- sk = __inet6_lookup_established(net, &tcp_hashinfo,
- &hdr->daddr, th->dest,
- &hdr->saddr, ntohs(th->source),
- skb->dev->ifindex);
-
+ sk = __inet6_lookup_established(net, &tcp_hashinfo, ¶ms);
if (!sk) {
__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
@@ -907,6 +911,14 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
if (sk && sk_fullsock(sk)) {
key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr);
} else if (hash_location) {
+ struct sk_lookup params = {
+ .saddr.ipv6 = &ipv6h->saddr,
+ .daddr.ipv6 = &ipv6h->daddr,
+ .sport = th->source,
+ .hnum = ntohs(th->source),
+ .dif = tcp_v6_iif(skb),
+ };
+
/*
* active side is lost. Try to find listening socket through
* source port, and then find md5 key through listening socket.
@@ -915,10 +927,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
* no RST generated if md5 hash doesn't match.
*/
sk1 = inet6_lookup_listener(dev_net(skb_dst(skb)->dev),
- &tcp_hashinfo, NULL, 0,
- &ipv6h->saddr,
- th->source, &ipv6h->daddr,
- ntohs(th->source), tcp_v6_iif(skb));
+ &tcp_hashinfo, NULL, 0, ¶ms);
if (!sk1)
goto out;
@@ -1403,6 +1412,9 @@ static int tcp_v6_rcv(struct sk_buff *skb)
struct sock *sk;
int ret;
struct net *net = dev_net(skb->dev);
+ struct sk_lookup params = {
+ .dif = inet6_iif(skb),
+ };
if (skb->pkt_type != PACKET_HOST)
goto discard_it;
@@ -1428,10 +1440,11 @@ static int tcp_v6_rcv(struct sk_buff *skb)
th = (const struct tcphdr *)skb->data;
hdr = ipv6_hdr(skb);
+ params.sport = th->source;
+ params.dport = th->dest;
lookup:
sk = __inet6_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th),
- th->source, th->dest, inet6_iif(skb),
- &refcounted);
+ ¶ms, &refcounted);
if (!sk)
goto no_tcp_socket;
@@ -1558,13 +1571,17 @@ static int tcp_v6_rcv(struct sk_buff *skb)
switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) {
case TCP_TW_SYN:
{
+ struct sk_lookup params = {
+ .saddr.ipv6 = &ipv6_hdr(skb)->saddr,
+ .daddr.ipv6 = &ipv6_hdr(skb)->daddr,
+ .sport = th->source,
+ .hnum = ntohs(th->dest),
+ .dif = tcp_v6_iif(skb),
+ };
struct sock *sk2;
sk2 = inet6_lookup_listener(dev_net(skb->dev), &tcp_hashinfo,
- skb, __tcp_hdrlen(th),
- &ipv6_hdr(skb)->saddr, th->source,
- &ipv6_hdr(skb)->daddr,
- ntohs(th->dest), tcp_v6_iif(skb));
+ skb, __tcp_hdrlen(th), ¶ms);
if (sk2) {
struct inet_timewait_sock *tw = inet_twsk(sk);
inet_twsk_deschedule_put(tw);
@@ -1591,6 +1608,10 @@ static int tcp_v6_rcv(struct sk_buff *skb)
static void tcp_v6_early_demux(struct sk_buff *skb)
{
+ /* Note : We use inet6_iif() here, not tcp_v6_iif() */
+ struct sk_lookup params = {
+ .dif = inet6_iif(skb),
+ };
const struct ipv6hdr *hdr;
const struct tcphdr *th;
struct sock *sk;
@@ -1607,11 +1628,12 @@ static void tcp_v6_early_demux(struct sk_buff *skb)
if (th->doff < sizeof(struct tcphdr) / 4)
return;
- /* Note : We use inet6_iif() here, not tcp_v6_iif() */
+ params.saddr.ipv6 = &hdr->saddr,
+ params.daddr.ipv6 = &hdr->daddr,
+ params.sport = th->source,
+ params.hnum = ntohs(th->dest),
sk = __inet6_lookup_established(dev_net(skb->dev), &tcp_hashinfo,
- &hdr->saddr, th->source,
- &hdr->daddr, ntohs(th->dest),
- inet6_iif(skb));
+ ¶ms);
if (sk) {
skb->sk = sk;
skb->destructor = sock_edemux;
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 56bb40544035..3ee75189d1c3 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -193,6 +193,7 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
.daddr.ipv6 = daddr,
.sport = sport,
.dport = dport,
+ .hnum = ntohs(dport),
.dif = in->ifindex,
};
struct sock *sk;
@@ -205,9 +206,7 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
tcph = hp;
sk = inet6_lookup_listener(net, &tcp_hashinfo, skb,
thoff + __tcp_hdrlen(tcph),
- saddr, sport,
- daddr, ntohs(dport),
- in->ifindex);
+ ¶ms);
if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
@@ -219,8 +218,7 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
break;
case NFT_LOOKUP_ESTABLISHED:
sk = __inet6_lookup_established(net, &tcp_hashinfo,
- saddr, sport, daddr, ntohs(dport),
- in->ifindex);
+ ¶ms);
break;
default:
BUG();
--
2.1.4
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PATCH net-next 07/10] net: ipv6: Convert raw sockets to sk_lookup
2017-08-01 3:13 [PATCH net-next 00/10] net: l3mdev: Support for sockets bound to enslaved device David Ahern
` (5 preceding siblings ...)
2017-08-01 3:13 ` [PATCH net-next 06/10] net: ipv6: Convert inet " David Ahern
@ 2017-08-01 3:13 ` David Ahern
2017-08-01 3:13 ` [PATCH net-next 08/10] net: Add sdif " David Ahern
` (4 subsequent siblings)
11 siblings, 0 replies; 15+ messages in thread
From: David Ahern @ 2017-08-01 3:13 UTC (permalink / raw)
To: netdev; +Cc: David Ahern
Convert __raw_v6_lookup to use the new sk_lookup struct
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/rawv6.h | 3 +--
net/ipv4/raw_diag.c | 15 ++++++++++-----
net/ipv6/raw.c | 41 +++++++++++++++++++++++------------------
3 files changed, 34 insertions(+), 25 deletions(-)
diff --git a/include/net/rawv6.h b/include/net/rawv6.h
index cbe4e9de1894..406268324d26 100644
--- a/include/net/rawv6.h
+++ b/include/net/rawv6.h
@@ -5,8 +5,7 @@
extern struct raw_hashinfo raw_v6_hashinfo;
struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
- unsigned short num, const struct in6_addr *loc_addr,
- const struct in6_addr *rmt_addr, int dif);
+ const struct sk_lookup *params);
int raw_abort(struct sock *sk, int err);
diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c
index a708de070cc6..e081c03fd408 100644
--- a/net/ipv4/raw_diag.c
+++ b/net/ipv4/raw_diag.c
@@ -53,11 +53,16 @@ static struct sock *raw_lookup(struct net *net, struct sock *from,
sk = __raw_v4_lookup(net, from, ¶ms);
}
#if IS_ENABLED(CONFIG_IPV6)
- else
- sk = __raw_v6_lookup(net, from, r->sdiag_raw_protocol,
- (const struct in6_addr *)r->id.idiag_src,
- (const struct in6_addr *)r->id.idiag_dst,
- r->id.idiag_if);
+ else {
+ struct sk_lookup params = {
+ .saddr.ipv6 = (const struct in6_addr *)r->id.idiag_dst,
+ .daddr.ipv6 = (const struct in6_addr *)r->id.idiag_src,
+ .hnum = r->sdiag_raw_protocol,
+ .dif = r->id.idiag_if,
+ };
+
+ sk = __raw_v6_lookup(net, from, ¶ms);
+ }
#endif
return sk;
}
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 60be012fe708..51e651f18ffb 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -71,14 +71,14 @@ struct raw_hashinfo raw_v6_hashinfo = {
EXPORT_SYMBOL_GPL(raw_v6_hashinfo);
struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
- unsigned short num, const struct in6_addr *loc_addr,
- const struct in6_addr *rmt_addr, int dif)
+ const struct sk_lookup *params)
{
+ const struct in6_addr *loc_addr = params->daddr.ipv6;
+ const struct in6_addr *rmt_addr = params->saddr.ipv6;
bool is_multicast = ipv6_addr_is_multicast(loc_addr);
sk_for_each_from(sk)
- if (inet_sk(sk)->inet_num == num) {
-
+ if (inet_sk(sk)->inet_num == params->hnum) {
if (!net_eq(sock_net(sk), net))
continue;
@@ -86,7 +86,8 @@ struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
!ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr))
continue;
- if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)
+ if (sk->sk_bound_dev_if &&
+ sk->sk_bound_dev_if != params->dif)
continue;
if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
@@ -159,15 +160,17 @@ EXPORT_SYMBOL(rawv6_mh_filter_unregister);
*/
static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
{
- const struct in6_addr *saddr;
- const struct in6_addr *daddr;
+ struct sk_lookup params = {
+ .saddr.ipv6 = &ipv6_hdr(skb)->saddr,
+ .daddr.ipv6 = &ipv6_hdr(skb)->daddr,
+ .hnum = nexthdr,
+ .dif = inet6_iif(skb),
+ };
struct sock *sk;
bool delivered = false;
__u8 hash;
struct net *net;
- saddr = &ipv6_hdr(skb)->saddr;
- daddr = saddr + 1;
hash = nexthdr & (RAW_HTABLE_SIZE - 1);
@@ -178,7 +181,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
goto out;
net = dev_net(skb->dev);
- sk = __raw_v6_lookup(net, sk, nexthdr, daddr, saddr, inet6_iif(skb));
+ sk = __raw_v6_lookup(net, sk, ¶ms);
while (sk) {
int filtered;
@@ -221,8 +224,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
rawv6_rcv(sk, clone);
}
}
- sk = __raw_v6_lookup(net, sk_next(sk), nexthdr, daddr, saddr,
- inet6_iif(skb));
+ sk = __raw_v6_lookup(net, sk_next(sk), ¶ms);
}
out:
read_unlock(&raw_v6_hashinfo.lock);
@@ -362,23 +364,26 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr,
u8 type, u8 code, int inner_offset, __be32 info)
{
struct sock *sk;
- int hash;
- const struct in6_addr *saddr, *daddr;
struct net *net;
+ int hash;
hash = nexthdr & (RAW_HTABLE_SIZE - 1);
read_lock(&raw_v6_hashinfo.lock);
sk = sk_head(&raw_v6_hashinfo.ht[hash]);
if (sk) {
+ struct sk_lookup params = {
+ .hnum = nexthdr,
+ .dif = inet6_iif(skb),
+ };
/* Note: ipv6_hdr(skb) != skb->data */
const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data;
- saddr = &ip6h->saddr;
- daddr = &ip6h->daddr;
+
+ params.daddr.ipv6 = &ip6h->saddr;
+ params.saddr.ipv6 = &ip6h->daddr;
net = dev_net(skb->dev);
- while ((sk = __raw_v6_lookup(net, sk, nexthdr, saddr, daddr,
- inet6_iif(skb)))) {
+ while ((sk = __raw_v6_lookup(net, sk, ¶ms))) {
rawv6_err(sk, skb, NULL, type, code,
inner_offset, info);
sk = sk_next(sk);
--
2.1.4
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PATCH net-next 08/10] net: Add sdif to sk_lookup
2017-08-01 3:13 [PATCH net-next 00/10] net: l3mdev: Support for sockets bound to enslaved device David Ahern
` (6 preceding siblings ...)
2017-08-01 3:13 ` [PATCH net-next 07/10] net: ipv6: Convert raw sockets to sk_lookup David Ahern
@ 2017-08-01 3:13 ` David Ahern
2017-08-01 3:13 ` [PATCH net-next 09/10] net: ipv4: Support for sockets bound to enslaved device David Ahern
` (3 subsequent siblings)
11 siblings, 0 replies; 15+ messages in thread
From: David Ahern @ 2017-08-01 3:13 UTC (permalink / raw)
To: netdev; +Cc: David Ahern
Add a second device index, sdif, to the socket lookup struct. sdif
will be the device index for devices enslaved to an l3mdev. It allows
the lookups to consider the enslaved device as well as the L3 master
device when searching for a socket.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/sock.h | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/include/net/sock.h b/include/net/sock.h
index a2db5fd30192..c5d93a4bcd0a 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -507,23 +507,27 @@ struct sk_lookup {
unsigned short hnum;
int dif;
+ int sdif;
bool exact_dif;
};
-/* Compare sk_bound_dev_if to socket lookup dif
+/* Compare sk_bound_dev_if to socket lookup dif and sdif
* Returns:
* -1 exact dif required and not met
* 0 sk_bound_dev_if is either not set or does not match
- * 1 sk_bound_dev_if is set and matches dif
+ * 1 sk_bound_dev_if is set and matches dif or sdif
*/
static inline int sk_lookup_device_cmp(const struct sock *sk,
const struct sk_lookup *params)
{
+ bool dev_match = (sk->sk_bound_dev_if == params->dif ||
+ sk->sk_bound_dev_if == params->sdif);
+
/* exact_dif true == l3mdev case */
- if (params->exact_dif && sk->sk_bound_dev_if != params->dif)
+ if (params->exact_dif && !dev_match)
return -1;
- if (sk->sk_bound_dev_if && sk->sk_bound_dev_if == params->dif)
+ if (sk->sk_bound_dev_if && dev_match)
return 1;
return 0;
--
2.1.4
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PATCH net-next 09/10] net: ipv4: Support for sockets bound to enslaved device
2017-08-01 3:13 [PATCH net-next 00/10] net: l3mdev: Support for sockets bound to enslaved device David Ahern
` (7 preceding siblings ...)
2017-08-01 3:13 ` [PATCH net-next 08/10] net: Add sdif " David Ahern
@ 2017-08-01 3:13 ` David Ahern
2017-08-01 3:13 ` [PATCH net-next 10/10] net: ipv6: " David Ahern
` (2 subsequent siblings)
11 siblings, 0 replies; 15+ messages in thread
From: David Ahern @ 2017-08-01 3:13 UTC (permalink / raw)
To: netdev; +Cc: David Ahern
Add support for sockets bound to a network interface enslaved to an
L3 Master device (e.g, VRF). Currently for VRF, skb->dev points to the
VRF device meaning socket lookups only consider this device index. The
real ingress device index is saved to IPCB(skb)->iif and the VRF driver
marks the skb with IPSKB_L3SLAVE to know that the real ingress device
is an enslaved one without having to lookup the iif.
Use those flags to add the enslaved device index to the socket lookup
and allow sk->sk_bound_dev_if to match either dif (VRF device) or sdif
(enslaved device).
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/linux/igmp.h | 3 ++-
include/net/inet_hashtables.h | 10 ++++++----
include/net/ip.h | 10 ++++++++++
include/net/tcp.h | 10 ++++++++++
net/ipv4/igmp.c | 6 ++++--
net/ipv4/inet_hashtables.c | 11 +++++++----
net/ipv4/raw.c | 7 +++++--
net/ipv4/tcp_ipv4.c | 6 ++++--
net/ipv4/udp.c | 11 ++++++++---
9 files changed, 56 insertions(+), 18 deletions(-)
diff --git a/include/linux/igmp.h b/include/linux/igmp.h
index 97caf1821de8..f8231854b5d6 100644
--- a/include/linux/igmp.h
+++ b/include/linux/igmp.h
@@ -118,7 +118,8 @@ extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf,
struct ip_msfilter __user *optval, int __user *optlen);
extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf,
struct group_filter __user *optval, int __user *optlen);
-extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, int dif);
+extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt,
+ int dif, int sdif);
extern void ip_mc_init_dev(struct in_device *);
extern void ip_mc_destroy_dev(struct in_device *);
extern void ip_mc_up(struct in_device *);
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index c5f4dc3c06e4..2de3d4bc00ba 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -259,22 +259,24 @@ static inline struct sock *inet_lookup_listener(struct net *net,
(((__force __u64)(__be32)(__daddr)) << 32) | \
((__force __u64)(__be32)(__saddr)))
#endif /* __BIG_ENDIAN */
-#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif) \
+#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \
(((__sk)->sk_portpair == (__ports)) && \
((__sk)->sk_addrpair == (__cookie)) && \
(!(__sk)->sk_bound_dev_if || \
- ((__sk)->sk_bound_dev_if == (__dif))) && \
+ ((__sk)->sk_bound_dev_if == (__dif)) || \
+ ((__sk)->sk_bound_dev_if == (__sdif))) && \
net_eq(sock_net(__sk), (__net)))
#else /* 32-bit arch */
#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
const int __name __deprecated __attribute__((unused))
-#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif) \
+#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \
(((__sk)->sk_portpair == (__ports)) && \
((__sk)->sk_daddr == (__saddr)) && \
((__sk)->sk_rcv_saddr == (__daddr)) && \
(!(__sk)->sk_bound_dev_if || \
- ((__sk)->sk_bound_dev_if == (__dif))) && \
+ ((__sk)->sk_bound_dev_if == (__dif)) || \
+ ((__sk)->sk_bound_dev_if == (__sdif))) && \
net_eq(sock_net(__sk), (__net)))
#endif /* 64-bit arch */
diff --git a/include/net/ip.h b/include/net/ip.h
index 821cedcc8e73..e10da8814dba 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -78,6 +78,16 @@ struct ipcm_cookie {
#define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))
#define PKTINFO_SKB_CB(skb) ((struct in_pktinfo *)((skb)->cb))
+/* return enslaved device index if relevant */
+static inline int ip_sdif(struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+ if (skb && ipv4_l3mdev_skb(IPCB(skb)->flags))
+ return IPCB(skb)->iif;
+#endif
+ return 0;
+}
+
struct ip_ra_chain {
struct ip_ra_chain __rcu *next;
struct sock *sk;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 12d68335acd4..19827dd05dcc 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -861,6 +861,16 @@ static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb)
return false;
}
+/* TCP_SKB_CB reference means this can not be used from early demux */
+static inline int tcp_v4_sdif(struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+ if (skb && ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags))
+ return TCP_SKB_CB(skb)->header.h4.iif;
+#endif
+ return 0;
+}
+
/* Due to TSO, an SKB can be composed of multiple actual
* packets. To keep these tracked properly, we use this.
*/
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 28f14afd0dd3..5bc8570c2ec3 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2549,7 +2549,8 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf,
/*
* check if a multicast source filter allows delivery for a given <src,dst,intf>
*/
-int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif)
+int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr,
+ int dif, int sdif)
{
struct inet_sock *inet = inet_sk(sk);
struct ip_mc_socklist *pmc;
@@ -2564,7 +2565,8 @@ int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif)
rcu_read_lock();
for_each_pmc_rcu(inet, pmc) {
if (pmc->multi.imr_multiaddr.s_addr == loc_addr &&
- pmc->multi.imr_ifindex == dif)
+ (pmc->multi.imr_ifindex == dif ||
+ (sdif && pmc->multi.imr_ifindex == sdif)))
break;
}
ret = inet->mc_all;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 5fe9300795b8..12c387264a65 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -275,6 +275,7 @@ struct sock *__inet_lookup_established(struct net *net,
__be32 daddr = params->daddr.ipv4;
__be16 sport = params->sport;
u16 hnum = params->hnum;
+ int sdif = params->sdif;
int dif = params->dif;
INET_ADDR_COOKIE(acookie, saddr, daddr);
const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
@@ -292,11 +293,12 @@ struct sock *__inet_lookup_established(struct net *net,
if (sk->sk_hash != hash)
continue;
if (likely(INET_MATCH(sk, net, acookie,
- saddr, daddr, ports, dif))) {
+ saddr, daddr, ports, dif, sdif))) {
if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
goto out;
if (unlikely(!INET_MATCH(sk, net, acookie,
- saddr, daddr, ports, dif))) {
+ saddr, daddr, ports,
+ dif, sdif))) {
sock_gen_put(sk);
goto begin;
}
@@ -327,9 +329,10 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
__be32 daddr = inet->inet_rcv_saddr;
__be32 saddr = inet->inet_daddr;
int dif = sk->sk_bound_dev_if;
+ struct net *net = sock_net(sk);
+ int sdif = l3mdev_master_ifindex_by_index(net, dif);
INET_ADDR_COOKIE(acookie, saddr, daddr);
const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
- struct net *net = sock_net(sk);
unsigned int hash = inet_ehashfn(net, daddr, lport,
saddr, inet->inet_dport);
struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
@@ -345,7 +348,7 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
continue;
if (likely(INET_MATCH(sk2, net, acookie,
- saddr, daddr, ports, dif))) {
+ saddr, daddr, ports, dif, sdif))) {
if (sk2->sk_state == TCP_TIME_WAIT) {
tw = inet_twsk(sk2);
if (twsk_unique(sk, sk2, twp))
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 4da5d87a61a5..a94f8f115b6e 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -132,7 +132,8 @@ struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
bool dev_match;
dev_match = (!sk->sk_bound_dev_if ||
- sk->sk_bound_dev_if == params->dif);
+ sk->sk_bound_dev_if == params->dif ||
+ sk->sk_bound_dev_if == params->sdif);
if (net_eq(sock_net(sk), net) &&
inet->inet_num == params->hnum &&
@@ -186,6 +187,7 @@ static int __raw_v4_input(struct sk_buff *skb, const struct iphdr *iph,
.daddr.ipv4 = iph->daddr,
.hnum = iph->protocol,
.dif = skb->dev->ifindex,
+ .sdif = ip_sdif(skb),
};
int delivered = 0;
struct sock *sk;
@@ -195,7 +197,7 @@ static int __raw_v4_input(struct sk_buff *skb, const struct iphdr *iph,
delivered = 1;
if ((iph->protocol != IPPROTO_ICMP || !icmp_filter(sk, skb)) &&
ip_mc_sf_allow(sk, iph->daddr, iph->saddr,
- skb->dev->ifindex)) {
+ skb->dev->ifindex, params.sdif)) {
struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC);
/* Not releasing hash table! */
@@ -316,6 +318,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info)
struct sk_lookup params = {
.hnum = protocol,
.dif = skb->dev->ifindex,
+ .sdif = ip_sdif(skb),
};
iph = (const struct iphdr *)skb->data;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a83d1d437abc..415722007a24 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1664,7 +1664,9 @@ EXPORT_SYMBOL(tcp_filter);
int tcp_v4_rcv(struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
- struct sk_lookup params = { };
+ struct sk_lookup params = {
+ .sdif = ip_sdif(skb),
+ };
const struct iphdr *iph;
const struct tcphdr *th;
bool refcounted;
@@ -1846,8 +1848,8 @@ int tcp_v4_rcv(struct sk_buff *skb)
.daddr.ipv4 = iph->daddr,
.sport = th->source,
.dport = th->dest,
- .hnum = ntohs(th->dest),
.dif = inet_iif(skb),
+ .sdif = tcp_v4_sdif(skb),
};
struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev),
&tcp_hashinfo, skb,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 132a8f070d16..5c9fffed9c4a 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -485,6 +485,7 @@ struct sock *__udp4_lib_lookup(struct net *net, struct sk_lookup *params,
u32 hash = 0;
params->hnum = hnum;
+ params->sdif = ip_sdif(skb);
params->exact_dif = udp_lib_exact_dif_match(net, skb);
if (hslot->count > 10) {
@@ -597,9 +598,10 @@ static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
(inet->inet_dport != params->sport && inet->inet_dport) ||
(inet->inet_rcv_saddr && inet->inet_rcv_saddr != loc_addr) ||
ipv6_only_sock(sk) ||
- (sk->sk_bound_dev_if && sk->sk_bound_dev_if != params->dif))
+ (sk->sk_bound_dev_if && sk->sk_bound_dev_if != params->dif &&
+ sk->sk_bound_dev_if != params->sdif))
return false;
- if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, params->dif))
+ if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, params->dif, params->sdif))
return false;
return true;
}
@@ -1970,6 +1972,7 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
.dport = uh->dest,
.hnum = hnum,
.dif = skb->dev->ifindex,
+ .sdif = ip_sdif(skb),
};
if (use_hash2) {
@@ -2210,7 +2213,8 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
if (INET_MATCH(sk, net, acookie, params->saddr.ipv4,
- params->daddr.ipv4, ports, params->dif))
+ params->daddr.ipv4, ports, params->dif,
+ params->sdif))
return sk;
/* Only check first socket in chain */
break;
@@ -2223,6 +2227,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
struct net *net = dev_net(skb->dev);
struct sk_lookup params = {
.dif = skb->dev->ifindex,
+ .sdif = ip_sdif(skb),
};
const struct iphdr *iph;
const struct udphdr *uh;
--
2.1.4
^ permalink raw reply related [flat|nested] 15+ messages in thread* [PATCH net-next 10/10] net: ipv6: Support for sockets bound to enslaved device
2017-08-01 3:13 [PATCH net-next 00/10] net: l3mdev: Support for sockets bound to enslaved device David Ahern
` (8 preceding siblings ...)
2017-08-01 3:13 ` [PATCH net-next 09/10] net: ipv4: Support for sockets bound to enslaved device David Ahern
@ 2017-08-01 3:13 ` David Ahern
2017-08-01 14:15 ` [PATCH net-next 00/10] net: l3mdev: " David Laight
2017-08-02 0:41 ` David Miller
11 siblings, 0 replies; 15+ messages in thread
From: David Ahern @ 2017-08-01 3:13 UTC (permalink / raw)
To: netdev; +Cc: David Ahern
Add support for sockets bound to a network interface enslaved to an
L3 Master device (e.g, VRF). Currently for VRF, skb->dev points to the
VRF device meaning socket lookups only consider this device index. The
real ingress device index is saved to IP6CB(skb)->iif and the VRF driver
marks the skb with IP6SKB_L3SLAVE to know that the real ingress device
is an enslaved one without having to lookup the iif.
Use those flags to add the enslaved device index to the socket lookup
and allow sk->sk_bound_dev_if to match either dif (VRF device) or sdif
(enslaved device).
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/linux/ipv6.h | 8 ++++++++
include/net/inet6_hashtables.h | 5 +++--
include/net/tcp.h | 7 +++++++
net/ipv6/inet6_hashtables.c | 9 +++++----
net/ipv6/raw.c | 5 ++++-
net/ipv6/tcp_ipv6.c | 3 +++
net/ipv6/udp.c | 8 ++++++--
7 files changed, 36 insertions(+), 9 deletions(-)
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index e1b442996f81..094357907b45 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -153,6 +153,14 @@ static inline int inet6_iif(const struct sk_buff *skb)
}
/* can not be used in TCP layer after tcp_v6_fill_cb */
+static inline int inet6_sdif(const struct sk_buff *skb)
+{
+ bool l3_slave = ipv6_l3mdev_skb(IP6CB(skb)->flags);
+
+ return l3_slave ? IP6CB(skb)->iif : 0;
+}
+
+/* can not be used in TCP layer after tcp_v6_fill_cb */
static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb)
{
#if defined(CONFIG_NET_L3_MASTER_DEV)
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 15db41272ff2..0fc5a2fe4ad3 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -94,13 +94,14 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
int inet6_hash(struct sock *sk);
#endif /* IS_ENABLED(CONFIG_IPV6) */
-#define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif) \
+#define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif, __sdif) \
(((__sk)->sk_portpair == (__ports)) && \
((__sk)->sk_family == AF_INET6) && \
ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr)) && \
ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr)) && \
(!(__sk)->sk_bound_dev_if || \
- ((__sk)->sk_bound_dev_if == (__dif))) && \
+ ((__sk)->sk_bound_dev_if == (__dif)) || \
+ ((__sk)->sk_bound_dev_if == (__sdif))) && \
net_eq(sock_net(__sk), (__net)))
#endif /* _INET6_HASHTABLES_H */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 19827dd05dcc..8a081cff33f8 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -848,6 +848,13 @@ static inline int tcp_v6_iif(const struct sk_buff *skb)
return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif;
}
+
+static inline int tcp_v6_sdif(const struct sk_buff *skb)
+{
+ bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);
+
+ return l3_slave ? TCP_SKB_CB(skb)->header.h6.iif : 0;
+}
#endif
/* TCP_SKB_CB reference means this can not be used from early demux */
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 878c03094f2e..06120efb2036 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -74,13 +74,13 @@ struct sock *__inet6_lookup_established(struct net *net,
if (sk->sk_hash != hash)
continue;
if (!INET6_MATCH(sk, net, saddr, daddr, ports,
- params->dif))
+ params->dif, params->sdif))
continue;
if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
goto out;
if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports,
- params->dif))) {
+ params->dif, params->sdif))) {
sock_gen_put(sk);
goto begin;
}
@@ -188,8 +188,9 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr;
const struct in6_addr *saddr = &sk->sk_v6_daddr;
const int dif = sk->sk_bound_dev_if;
- const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
struct net *net = sock_net(sk);
+ const int sdif = l3mdev_master_ifindex_by_index(net, dif);
+ const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr,
inet->inet_dport);
struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
@@ -205,7 +206,7 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
continue;
if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports,
- dif))) {
+ dif, sdif))) {
if (sk2->sk_state == TCP_TIME_WAIT) {
tw = inet_twsk(sk2);
if (twsk_unique(sk, sk2, twp))
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 51e651f18ffb..bab365214d17 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -87,7 +87,8 @@ struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
continue;
if (sk->sk_bound_dev_if &&
- sk->sk_bound_dev_if != params->dif)
+ sk->sk_bound_dev_if != params->dif &&
+ sk->sk_bound_dev_if != params->sdif)
continue;
if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
@@ -165,6 +166,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
.daddr.ipv6 = &ipv6_hdr(skb)->daddr,
.hnum = nexthdr,
.dif = inet6_iif(skb),
+ .sdif = inet6_sdif(skb),
};
struct sock *sk;
bool delivered = false;
@@ -375,6 +377,7 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr,
struct sk_lookup params = {
.hnum = nexthdr,
.dif = inet6_iif(skb),
+ .sdif = inet6_sdif(skb),
};
/* Note: ipv6_hdr(skb) != skb->data */
const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 19fee98e1ae0..67bd95cec4ec 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -917,6 +917,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
.sport = th->source,
.hnum = ntohs(th->source),
.dif = tcp_v6_iif(skb),
+ .sdif = tcp_v6_sdif(skb),
};
/*
@@ -1414,6 +1415,7 @@ static int tcp_v6_rcv(struct sk_buff *skb)
struct net *net = dev_net(skb->dev);
struct sk_lookup params = {
.dif = inet6_iif(skb),
+ .sdif = inet6_sdif(skb),
};
if (skb->pkt_type != PACKET_HOST)
@@ -1577,6 +1579,7 @@ static int tcp_v6_rcv(struct sk_buff *skb)
.sport = th->source,
.hnum = ntohs(th->dest),
.dif = tcp_v6_iif(skb),
+ .sdif = tcp_v6_sdif(skb),
};
struct sock *sk2;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 00b362a8bd91..8cf7c5cbd02a 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -220,6 +220,7 @@ struct sock *__udp6_lib_lookup(struct net *net, struct sk_lookup *params,
u32 hash = 0;
params->hnum = hnum;
+ params->sdif = inet6_sdif(skb);
params->exact_dif = udp6_lib_exact_dif_match(net, skb);
if (hslot->count > 10) {
@@ -673,7 +674,8 @@ static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
(inet->inet_dport && inet->inet_dport != params->sport) ||
(!ipv6_addr_any(&sk->sk_v6_daddr) &&
!ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) ||
- (sk->sk_bound_dev_if && sk->sk_bound_dev_if != params->dif) ||
+ (sk->sk_bound_dev_if && sk->sk_bound_dev_if != params->dif &&
+ sk->sk_bound_dev_if != params->sdif) ||
(!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)))
return false;
@@ -715,6 +717,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
.dport = uh->dest,
.hnum = hnum,
.dif = inet6_iif(skb),
+ .sdif = inet6_sdif(skb),
};
if (use_hash2) {
@@ -893,7 +896,7 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net,
if (sk->sk_state == TCP_ESTABLISHED &&
INET6_MATCH(sk, net, params->saddr.ipv6,
params->daddr.ipv6, ports,
- params->dif))
+ params->dif, params->sdif))
return sk;
/* Only check first socket in chain */
@@ -912,6 +915,7 @@ static void udp_v6_early_demux(struct sk_buff *skb)
.saddr.ipv6 = &ipv6_hdr(skb)->saddr,
.daddr.ipv6 = &ipv6_hdr(skb)->daddr,
.dif = skb->dev->ifindex,
+ .sdif = inet6_sdif(skb),
};
if (skb->pkt_type != PACKET_HOST)
--
2.1.4
^ permalink raw reply related [flat|nested] 15+ messages in thread* RE: [PATCH net-next 00/10] net: l3mdev: Support for sockets bound to enslaved device
2017-08-01 3:13 [PATCH net-next 00/10] net: l3mdev: Support for sockets bound to enslaved device David Ahern
` (9 preceding siblings ...)
2017-08-01 3:13 ` [PATCH net-next 10/10] net: ipv6: " David Ahern
@ 2017-08-01 14:15 ` David Laight
2017-08-01 14:45 ` David Ahern
2017-08-02 0:41 ` David Miller
11 siblings, 1 reply; 15+ messages in thread
From: David Laight @ 2017-08-01 14:15 UTC (permalink / raw)
To: 'David Ahern', netdev@vger.kernel.org
From: David Ahern
> Sent: 01 August 2017 04:13
...
> Existing code for socket lookups already pass in 6+ arguments. Rather
> than add another for the enslaved device index, the existing lookups
> are converted to use a new sk_lookup struct. From there, the enslaved
> device index becomes another element of the struct.
>
> Patch 1 introduces sk_lookup struct and helper.
I guess that socket lookup happens quite often!
Passing the lookup parameters in a structure might have a
measurable negative effect on performance - especially if the
structure isn't passed through to other functions.
Have you made any performance mearurements?
David
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [PATCH net-next 00/10] net: l3mdev: Support for sockets bound to enslaved device
2017-08-01 14:15 ` [PATCH net-next 00/10] net: l3mdev: " David Laight
@ 2017-08-01 14:45 ` David Ahern
0 siblings, 0 replies; 15+ messages in thread
From: David Ahern @ 2017-08-01 14:45 UTC (permalink / raw)
To: David Laight, netdev@vger.kernel.org
On 8/1/17 8:15 AM, David Laight wrote:
> From: David Ahern
>> Sent: 01 August 2017 04:13
> ...
>> Existing code for socket lookups already pass in 6+ arguments. Rather
>> than add another for the enslaved device index, the existing lookups
>> are converted to use a new sk_lookup struct. From there, the enslaved
>> device index becomes another element of the struct.
>>
>> Patch 1 introduces sk_lookup struct and helper.
>
> I guess that socket lookup happens quite often!
> Passing the lookup parameters in a structure might have a
> measurable negative effect on performance - especially if the
> structure isn't passed through to other functions.
>
> Have you made any performance mearurements?
Before patches:
IPv4
Test TCP_RR 23769.42 23862.59 23867.69 sum
71499.70 avg 23833
Test TCP_CRR 8649.29 8650.94 8661.24 sum
25961.47 avg 8653
Test UDP_RR 26935.38 26813.30 26747.88 sum
80496.56 avg 26832
IPv6
Test TCP_RR 24708.10 24629.43 24593.75 sum
73931.28 avg 24643
Test TCP_CRR 8432.82 8489.26 8474.82 sum
25396.90 avg 8465
Test UDP_RR 23607.57 23722.37 23713.80 sum
71043.74 avg 23681
#################################################################
After patches:
IPv4
Test TCP_RR 24204.41 23993.05 24129.18 sum
72326.64 avg 24108
Test TCP_CRR 8690.31 8630.12 8620.88 sum
25941.31 avg 8647
Test UDP_RR 26653.26 26725.76 26587.70 sum
79966.72 avg 26655
IPv6
Test TCP_RR 24807.54 24698.30 24849.84 sum
74355.68 avg 24785
Test TCP_CRR 8573.22 8640.02 8624.09 sum
25837.33 avg 8612
Test UDP_RR 23800.14 23747.01 23814.94 sum
71362.09 avg 23787
The middle columns are the results of each 30-second run and then the
average of the 3 is on the end.
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: [PATCH net-next 00/10] net: l3mdev: Support for sockets bound to enslaved device
2017-08-01 3:13 [PATCH net-next 00/10] net: l3mdev: Support for sockets bound to enslaved device David Ahern
` (10 preceding siblings ...)
2017-08-01 14:15 ` [PATCH net-next 00/10] net: l3mdev: " David Laight
@ 2017-08-02 0:41 ` David Miller
2017-08-04 20:17 ` David Ahern
11 siblings, 1 reply; 15+ messages in thread
From: David Miller @ 2017-08-02 0:41 UTC (permalink / raw)
To: dsahern; +Cc: netdev
From: David Ahern <dsahern@gmail.com>
Date: Mon, 31 Jul 2017 20:13:16 -0700
> Existing code for socket lookups already pass in 6+ arguments. Rather
> than add another for the enslaved device index, the existing lookups
> are converted to use a new sk_lookup struct. From there, the enslaved
> device index becomes another element of the struct.
Sorry, not gonna happen :-)
I know it's difficult, but maybe we should think about why we're
passing so much crap into each lookup.
And perhaps, why it can't (for example) be constituted in the lookup
function itself given sufficient (relevant) context.
I think passing a big struct into the lookups, by reference, is a big
step backwards.
For one thing, if you pass it by pointer then the compiler can't
potentially pass parts in registers even if it could. However
if you pass it by value, that's actually a possibility.
But I'd like to avoid this on-stack blob altogether if possible.
Thanks.
^ permalink raw reply [flat|nested] 15+ messages in thread* Re: [PATCH net-next 00/10] net: l3mdev: Support for sockets bound to enslaved device
2017-08-02 0:41 ` David Miller
@ 2017-08-04 20:17 ` David Ahern
0 siblings, 0 replies; 15+ messages in thread
From: David Ahern @ 2017-08-04 20:17 UTC (permalink / raw)
To: David Miller; +Cc: netdev
On 8/1/17 6:41 PM, David Miller wrote:
> From: David Ahern <dsahern@gmail.com>
> Date: Mon, 31 Jul 2017 20:13:16 -0700
>
>> Existing code for socket lookups already pass in 6+ arguments. Rather
>> than add another for the enslaved device index, the existing lookups
>> are converted to use a new sk_lookup struct. From there, the enslaved
>> device index becomes another element of the struct.
>
> Sorry, not gonna happen :-)
>
> I know it's difficult, but maybe we should think about why we're
> passing so much crap into each lookup.\
The 'crap' is essential data to find a socket -- the hash table (common
lookup functions for multiple backends), destination address, dest port,
source address, source port and device index make 6 parameters to be
matched. The socket data is what I consolidated into 1 struct.
Ultimately that data has to make its way from high level wrappers to
compute_score and INET{6}_MATCH at the very bottom.
>
> And perhaps, why it can't (for example) be constituted in the lookup
> function itself given sufficient (relevant) context.
There are several contexts for lookups -- ingress packets (ipv4 and v6,
tcp, udp, updlite, dccp), error paths for those protocols, netfilter and
socket diagnostic API. The 5 socket parameters do not have a consistent
storage across those contexts.
Further there are several layers of wrappers to what are the real lookup
functions, each wrapper abstracting some piece of data. The call
heirarchy for inet lookups for example:
tcp_v4_early_demux
__inet_lookup_established
tcp_v4_rcv / dccp_v4_rcv
__inet_lookup_skb
__inet_lookup
__inet_lookup_listener
__inet_lookup_established
tcp_v4_rcv - TCP_TW_SYN
inet_lookup_listener
__inet_lookup_listener
nf_tproxy_get_sock_v4
inet_lookup_listener
__inet_lookup_listener
inet_lookup_established
__inet_lookup_established
inet_diag_find_one_icsk / nf_socket_get_sock_v4
inet_lookup
__inet_lookup
__inet_lookup_listener
__inet_lookup_established
tcp_v4_send_reset - MD5 path
__inet_lookup_listener
tcp_v4_err / dccp_v4_err
__inet_lookup_established
>
> I think passing a big struct into the lookups, by reference, is a big
> step backwards.
>
> For one thing, if you pass it by pointer then the compiler can't
> potentially pass parts in registers even if it could. However
> if you pass it by value, that's actually a possibility.
>
> But I'd like to avoid this on-stack blob altogether if possible.
Just sent a v2 that just adds sdif to the existing functions.
^ permalink raw reply [flat|nested] 15+ messages in thread