summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/inet_hashtables.c60
-rw-r--r--net/ipv4/tcp_ipv4.c4
-rw-r--r--net/ipv4/udp.c97
3 files changed, 131 insertions, 30 deletions
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 2bbaaf0c7176..4eb4cd8d20dd 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -246,6 +246,21 @@ static inline int compute_score(struct sock *sk, struct net *net,
return score;
}
+static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk,
+ struct sk_buff *skb, int doff,
+ __be32 saddr, __be16 sport,
+ __be32 daddr, unsigned short hnum)
+{
+ struct sock *reuse_sk = NULL;
+ u32 phash;
+
+ if (sk->sk_reuseport) {
+ phash = inet_ehashfn(net, daddr, hnum, saddr, sport);
+ reuse_sk = reuseport_select_sock(sk, phash, skb, doff);
+ }
+ return reuse_sk;
+}
+
/*
* Here are some nice properties to exploit here. The BSD API
* does not allow a listening sock to specify the remote port nor the
@@ -265,21 +280,17 @@ static struct sock *inet_lhash2_lookup(struct net *net,
struct inet_connection_sock *icsk;
struct sock *sk, *result = NULL;
int score, hiscore = 0;
- u32 phash = 0;
inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) {
sk = (struct sock *)icsk;
score = compute_score(sk, net, hnum, daddr,
dif, sdif, exact_dif);
if (score > hiscore) {
- if (sk->sk_reuseport) {
- phash = inet_ehashfn(net, daddr, hnum,
- saddr, sport);
- result = reuseport_select_sock(sk, phash,
- skb, doff);
- if (result)
- return result;
- }
+ result = lookup_reuseport(net, sk, skb, doff,
+ saddr, sport, daddr, hnum);
+ if (result)
+ return result;
+
result = sk;
hiscore = score;
}
@@ -288,6 +299,29 @@ static struct sock *inet_lhash2_lookup(struct net *net,
return result;
}
+static inline struct sock *inet_lookup_run_bpf(struct net *net,
+ struct inet_hashinfo *hashinfo,
+ struct sk_buff *skb, int doff,
+ __be32 saddr, __be16 sport,
+ __be32 daddr, u16 hnum)
+{
+ struct sock *sk, *reuse_sk;
+ bool no_reuseport;
+
+ if (hashinfo != &tcp_hashinfo)
+ return NULL; /* only TCP is supported */
+
+ no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP,
+ saddr, sport, daddr, hnum, &sk);
+ if (no_reuseport || IS_ERR_OR_NULL(sk))
+ return sk;
+
+ reuse_sk = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum);
+ if (reuse_sk)
+ sk = reuse_sk;
+ return sk;
+}
+
struct sock *__inet_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo,
struct sk_buff *skb, int doff,
@@ -299,6 +333,14 @@ struct sock *__inet_lookup_listener(struct net *net,
struct sock *result = NULL;
unsigned int hash2;
+ /* Lookup redirect from BPF */
+ if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
+ result = inet_lookup_run_bpf(net, hashinfo, skb, doff,
+ saddr, sport, daddr, hnum);
+ if (result)
+ goto done;
+ }
+
hash2 = ipv4_portaddr_hash(net, daddr, hnum);
ilb2 = inet_lhash2_bucket(hashinfo, hash2);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index cd81b6e04efb..daa39d33702b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -76,6 +76,7 @@
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/inetdevice.h>
+#include <linux/btf_ids.h>
#include <crypto/hash.h>
#include <linux/scatterlist.h>
@@ -2946,7 +2947,7 @@ static void bpf_iter_fini_tcp(void *priv_data)
bpf_iter_fini_seq_net(priv_data);
}
-static const struct bpf_iter_reg tcp_reg_info = {
+static struct bpf_iter_reg tcp_reg_info = {
.target = "tcp",
.seq_ops = &bpf_iter_tcp_seq_ops,
.init_seq_private = bpf_iter_init_tcp,
@@ -2961,6 +2962,7 @@ static const struct bpf_iter_reg tcp_reg_info = {
static void __init bpf_iter_register(void)
{
+ tcp_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON];
if (bpf_iter_reg_target(&tcp_reg_info))
pr_warn("Warning: could not register bpf iterator tcp\n");
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index d4be4471c424..bb95cddcb040 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -106,6 +106,7 @@
#include <net/xfrm.h>
#include <trace/events/udp.h>
#include <linux/static_key.h>
+#include <linux/btf_ids.h>
#include <trace/events/skb.h>
#include <net/busy_poll.h>
#include "udp_impl.h"
@@ -408,6 +409,25 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
udp_ehash_secret + net_hash_mix(net));
}
+static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk,
+ struct sk_buff *skb,
+ __be32 saddr, __be16 sport,
+ __be32 daddr, unsigned short hnum)
+{
+ struct sock *reuse_sk = NULL;
+ u32 hash;
+
+ if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) {
+ hash = udp_ehashfn(net, daddr, hnum, saddr, sport);
+ reuse_sk = reuseport_select_sock(sk, hash, skb,
+ sizeof(struct udphdr));
+ /* Fall back to scoring if group has connections */
+ if (reuseport_has_conns(sk, false))
+ return NULL;
+ }
+ return reuse_sk;
+}
+
/* called with rcu_read_lock() */
static struct sock *udp4_lib_lookup2(struct net *net,
__be32 saddr, __be16 sport,
@@ -418,7 +438,6 @@ static struct sock *udp4_lib_lookup2(struct net *net,
{
struct sock *sk, *result;
int score, badness;
- u32 hash = 0;
result = NULL;
badness = 0;
@@ -426,15 +445,11 @@ static struct sock *udp4_lib_lookup2(struct net *net,
score = compute_score(sk, net, saddr, sport,
daddr, hnum, dif, sdif);
if (score > badness) {
- if (sk->sk_reuseport &&
- sk->sk_state != TCP_ESTABLISHED) {
- hash = udp_ehashfn(net, daddr, hnum,
- saddr, sport);
- result = reuseport_select_sock(sk, hash, skb,
- sizeof(struct udphdr));
- if (result && !reuseport_has_conns(sk, false))
- return result;
- }
+ result = lookup_reuseport(net, sk, skb,
+ saddr, sport, daddr, hnum);
+ if (result)
+ return result;
+
badness = score;
result = sk;
}
@@ -442,6 +457,29 @@ static struct sock *udp4_lib_lookup2(struct net *net,
return result;
}
+static inline struct sock *udp4_lookup_run_bpf(struct net *net,
+ struct udp_table *udptable,
+ struct sk_buff *skb,
+ __be32 saddr, __be16 sport,
+ __be32 daddr, u16 hnum)
+{
+ struct sock *sk, *reuse_sk;
+ bool no_reuseport;
+
+ if (udptable != &udp_table)
+ return NULL; /* only UDP is supported */
+
+ no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP,
+ saddr, sport, daddr, hnum, &sk);
+ if (no_reuseport || IS_ERR_OR_NULL(sk))
+ return sk;
+
+ reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum);
+ if (reuse_sk)
+ sk = reuse_sk;
+ return sk;
+}
+
/* UDP is nearly always wildcards out the wazoo, it makes no sense to try
* harder than this. -DaveM
*/
@@ -449,27 +487,45 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
__be16 sport, __be32 daddr, __be16 dport, int dif,
int sdif, struct udp_table *udptable, struct sk_buff *skb)
{
- struct sock *result;
unsigned short hnum = ntohs(dport);
unsigned int hash2, slot2;
struct udp_hslot *hslot2;
+ struct sock *result, *sk;
hash2 = ipv4_portaddr_hash(net, daddr, hnum);
slot2 = hash2 & udptable->mask;
hslot2 = &udptable->hash2[slot2];
+ /* Lookup connected or non-wildcard socket */
result = udp4_lib_lookup2(net, saddr, sport,
daddr, hnum, dif, sdif,
hslot2, skb);
- if (!result) {
- hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
- slot2 = hash2 & udptable->mask;
- hslot2 = &udptable->hash2[slot2];
-
- result = udp4_lib_lookup2(net, saddr, sport,
- htonl(INADDR_ANY), hnum, dif, sdif,
- hslot2, skb);
+ if (!IS_ERR_OR_NULL(result) && result->sk_state == TCP_ESTABLISHED)
+ goto done;
+
+ /* Lookup redirect from BPF */
+ if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
+ sk = udp4_lookup_run_bpf(net, udptable, skb,
+ saddr, sport, daddr, hnum);
+ if (sk) {
+ result = sk;
+ goto done;
+ }
}
+
+ /* Got non-wildcard socket or error on first lookup */
+ if (result)
+ goto done;
+
+ /* Lookup wildcard sockets */
+ hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
+ slot2 = hash2 & udptable->mask;
+ hslot2 = &udptable->hash2[slot2];
+
+ result = udp4_lib_lookup2(net, saddr, sport,
+ htonl(INADDR_ANY), hnum, dif, sdif,
+ hslot2, skb);
+done:
if (IS_ERR(result))
return NULL;
return result;
@@ -3153,7 +3209,7 @@ static void bpf_iter_fini_udp(void *priv_data)
bpf_iter_fini_seq_net(priv_data);
}
-static const struct bpf_iter_reg udp_reg_info = {
+static struct bpf_iter_reg udp_reg_info = {
.target = "udp",
.seq_ops = &bpf_iter_udp_seq_ops,
.init_seq_private = bpf_iter_init_udp,
@@ -3168,6 +3224,7 @@ static const struct bpf_iter_reg udp_reg_info = {
static void __init bpf_iter_register(void)
{
+ udp_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_UDP];
if (bpf_iter_reg_target(&udp_reg_info))
pr_warn("Warning: could not register bpf iterator udp\n");
}
generated by cgit v1.2.3 (git 2.39.0) at 2024-09-04 23:50:10 +0300