From f0ea27e7bfe1c34e1f451a63eb68faa1d4c3a86d Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Thu, 20 Jul 2023 17:30:05 +0200 Subject: [PATCH 1/8] udp: re-score reuseport groups when connected sockets are present Contrary to TCP, UDP reuseport groups can contain TCP_ESTABLISHED sockets. To support these properly we remember whether a group has a connected socket and skip the fast reuseport early-return. In effect we continue scoring all reuseport sockets and then choose the one with the highest score. The current code fails to re-calculate the score for the result of lookup_reuseport. According to Kuniyuki Iwashima: 1) SO_INCOMING_CPU is set -> selected sk might have +1 score 2) BPF prog returns ESTABLISHED and/or SO_INCOMING_CPU sk -> selected sk will have more than 8 Using the old score could trigger more lookups depending on the order that sockets are created. sk -> sk (SO_INCOMING_CPU) -> sk (ESTABLISHED) | | `-> select the next SO_INCOMING_CPU sk | `-> select itself (We should save this lookup) Fixes: efc6b6f6c311 ("udp: Improve load balancing for SO_REUSEPORT.") Reviewed-by: Kuniyuki Iwashima Signed-off-by: Lorenz Bauer Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-1-7021b683cdae@isovalent.com Signed-off-by: Martin KaFai Lau --- net/ipv4/udp.c | 20 +++++++++++++++----- net/ipv6/udp.c | 19 ++++++++++++++----- 2 files changed, 29 insertions(+), 10 deletions(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8c3ebd95f5b9..0d81339bda2f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -451,14 +451,24 @@ static struct sock *udp4_lib_lookup2(struct net *net, score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { - result = lookup_reuseport(net, sk, skb, - saddr, sport, daddr, hnum); + badness = score; + result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); + if (!result) { + result = sk; + continue; + } + /* Fall back to scoring if group has connections */ - if (result && !reuseport_has_conns(sk)) + if (!reuseport_has_conns(sk)) return result; - result = result ? : sk; - badness = score; + /* Reuseport logic returned an error, keep original score. */ + if (IS_ERR(result)) + continue; + + badness = compute_score(result, net, saddr, sport, + daddr, hnum, dif, sdif); + } } return result; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 95c75d8f73d5..556d74a7d7ab 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -194,14 +194,23 @@ static struct sock *udp6_lib_lookup2(struct net *net, score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { - result = lookup_reuseport(net, sk, skb, - saddr, sport, daddr, hnum); + badness = score; + result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); + if (!result) { + result = sk; + continue; + } + /* Fall back to scoring if group has connections */ - if (result && !reuseport_has_conns(sk)) + if (!reuseport_has_conns(sk)) return result; - result = result ? : sk; - badness = score; + /* Reuseport logic returned an error, keep original score. */ + if (IS_ERR(result)) + continue; + + badness = compute_score(sk, net, saddr, sport, + daddr, hnum, dif, sdif); } } return result; From 67312adc96b5a585970d03b62412847afe2c6b01 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Thu, 20 Jul 2023 17:30:06 +0200 Subject: [PATCH 2/8] bpf: reject unhashed sockets in bpf_sk_assign The semantics for bpf_sk_assign are as follows: sk = some_lookup_func() bpf_sk_assign(skb, sk) bpf_sk_release(sk) That is, the sk is not consumed by bpf_sk_assign. The function therefore needs to make sure that sk lives long enough to be consumed from __inet_lookup_skb. The path through the stack for a TCPv4 packet is roughly: netif_receive_skb_core: takes RCU read lock __netif_receive_skb_core: sch_handle_ingress: tcf_classify: bpf_sk_assign() deliver_ptype_list_skb: deliver_skb: ip_packet_type->func == ip_rcv: ip_rcv_core: ip_rcv_finish_core: dst_input: ip_local_deliver: ip_local_deliver_finish: ip_protocol_deliver_rcu: tcp_v4_rcv: __inet_lookup_skb: skb_steal_sock The existing helper takes advantage of the fact that everything happens in the same RCU critical section: for sockets with SOCK_RCU_FREE set bpf_sk_assign never takes a reference. skb_steal_sock then checks SOCK_RCU_FREE again and does sock_put if necessary. This approach assumes that SOCK_RCU_FREE is never set on a sk between bpf_sk_assign and skb_steal_sock, but this invariant is violated by unhashed UDP sockets. A new UDP socket is created in TCP_CLOSE state but without SOCK_RCU_FREE set. That flag is only added in udp_lib_get_port() which happens when a socket is bound. When bpf_sk_assign was added it wasn't possible to access unhashed UDP sockets from BPF, so this wasn't a problem. This changed in commit 0c48eefae712 ("sock_map: Lift socket state restriction for datagram sockets"), but the helper wasn't adjusted accordingly. The following sequence of events will therefore lead to a refcount leak: 1. Add socket(AF_INET, SOCK_DGRAM) to a sockmap. 2. Pull socket out of sockmap and bpf_sk_assign it. Since SOCK_RCU_FREE is not set we increment the refcount. 3. bind() or connect() the socket, setting SOCK_RCU_FREE. 4. skb_steal_sock will now set refcounted = false due to SOCK_RCU_FREE. 5. tcp_v4_rcv() skips sock_put(). Fix the problem by rejecting unhashed sockets in bpf_sk_assign(). This matches the behaviour of __inet_lookup_skb which is ultimately the goal of bpf_sk_assign(). Fixes: cf7fbe660f2d ("bpf: Add socket assign support") Cc: Joe Stringer Signed-off-by: Lorenz Bauer Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-2-7021b683cdae@isovalent.com Signed-off-by: Martin KaFai Lau --- net/core/filter.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/core/filter.c b/net/core/filter.c index 797e8f039696..b5b51ef48c5f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7353,6 +7353,8 @@ BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags) return -ENETUNREACH; if (unlikely(sk_fullsock(sk) && sk->sk_reuseport)) return -ESOCKTNOSUPPORT; + if (sk_unhashed(sk)) + return -EOPNOTSUPP; if (sk_is_refcounted(sk) && unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) return -ENOENT; From ce796e60b3b196b61fcc565df195443cbb846ef0 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Thu, 20 Jul 2023 17:30:07 +0200 Subject: [PATCH 3/8] net: export inet_lookup_reuseport and inet6_lookup_reuseport Rename the existing reuseport helpers for IPv4 and IPv6 so that they can be invoked in the follow up commit. Export them so that building DCCP and IPv6 as a module works. No change in functionality. Reviewed-by: Kuniyuki Iwashima Signed-off-by: Lorenz Bauer Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-3-7021b683cdae@isovalent.com Signed-off-by: Martin KaFai Lau --- include/net/inet6_hashtables.h | 7 +++++++ include/net/inet_hashtables.h | 5 +++++ net/ipv4/inet_hashtables.c | 15 ++++++++------- net/ipv6/inet6_hashtables.c | 19 ++++++++++--------- 4 files changed, 30 insertions(+), 16 deletions(-) diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 56f1286583d3..032ddab48f8f 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -48,6 +48,13 @@ struct sock *__inet6_lookup_established(struct net *net, const u16 hnum, const int dif, const int sdif); +struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, + struct sk_buff *skb, int doff, + const struct in6_addr *saddr, + __be16 sport, + const struct in6_addr *daddr, + unsigned short hnum); + struct sock *inet6_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 99bd823e97f6..8734f3488f5d 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -379,6 +379,11 @@ struct sock *__inet_lookup_established(struct net *net, const __be32 daddr, const u16 hnum, const int dif, const int sdif); +struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, + struct sk_buff *skb, int doff, + __be32 saddr, __be16 sport, + __be32 daddr, unsigned short hnum); + static inline struct sock * inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 0819d6001b9a..ecb838460629 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -332,10 +332,10 @@ 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 *inet_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; @@ -346,6 +346,7 @@ static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk, } return reuse_sk; } +EXPORT_SYMBOL_GPL(inet_lookup_reuseport); /* * Here are some nice properties to exploit here. The BSD API @@ -369,8 +370,8 @@ static struct sock *inet_lhash2_lookup(struct net *net, sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) { score = compute_score(sk, net, hnum, daddr, dif, sdif); if (score > hiscore) { - result = lookup_reuseport(net, sk, skb, doff, - saddr, sport, daddr, hnum); + result = inet_lookup_reuseport(net, sk, skb, doff, + saddr, sport, daddr, hnum); if (result) return result; @@ -399,7 +400,7 @@ static inline struct sock *inet_lookup_run_bpf(struct net *net, if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; - reuse_sk = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum); + reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum); if (reuse_sk) sk = reuse_sk; return sk; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b64b49012655..b7c56867314e 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -111,12 +111,12 @@ 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, - const struct in6_addr *saddr, - __be16 sport, - const struct in6_addr *daddr, - unsigned short hnum) +struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, + struct sk_buff *skb, int doff, + const struct in6_addr *saddr, + __be16 sport, + const struct in6_addr *daddr, + unsigned short hnum) { struct sock *reuse_sk = NULL; u32 phash; @@ -127,6 +127,7 @@ static inline struct sock *lookup_reuseport(struct net *net, struct sock *sk, } return reuse_sk; } +EXPORT_SYMBOL_GPL(inet6_lookup_reuseport); /* called with rcu_read_lock() */ static struct sock *inet6_lhash2_lookup(struct net *net, @@ -143,8 +144,8 @@ static struct sock *inet6_lhash2_lookup(struct net *net, sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) { score = compute_score(sk, net, hnum, daddr, dif, sdif); if (score > hiscore) { - result = lookup_reuseport(net, sk, skb, doff, - saddr, sport, daddr, hnum); + result = inet6_lookup_reuseport(net, sk, skb, doff, + saddr, sport, daddr, hnum); if (result) return result; @@ -175,7 +176,7 @@ static inline struct sock *inet6_lookup_run_bpf(struct net *net, if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; - reuse_sk = lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum); + reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum); if (reuse_sk) sk = reuse_sk; return sk; From 0f495f7617229772403e683033abc473f0f0553c Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Thu, 20 Jul 2023 17:30:08 +0200 Subject: [PATCH 4/8] net: remove duplicate reuseport_lookup functions There are currently four copies of reuseport_lookup: one each for (TCP, UDP)x(IPv4, IPv6). This forces us to duplicate all callers of those functions as well. This is already the case for sk_lookup helpers (inet,inet6,udp4,udp6)_lookup_run_bpf. There are two differences between the reuseport_lookup helpers: 1. They call different hash functions depending on protocol 2. UDP reuseport_lookup checks that sk_state != TCP_ESTABLISHED Move the check for sk_state into the caller and use the INDIRECT_CALL infrastructure to cut down the helpers to one per IP version. Reviewed-by: Kuniyuki Iwashima Signed-off-by: Lorenz Bauer Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-4-7021b683cdae@isovalent.com Signed-off-by: Martin KaFai Lau --- include/net/inet6_hashtables.h | 11 ++++++++- include/net/inet_hashtables.h | 15 ++++++++----- net/ipv4/inet_hashtables.c | 20 +++++++++++------ net/ipv4/udp.c | 34 +++++++++++----------------- net/ipv6/inet6_hashtables.c | 14 ++++++++---- net/ipv6/udp.c | 41 +++++++++++++--------------------- 6 files changed, 72 insertions(+), 63 deletions(-) diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 032ddab48f8f..f89320b6fee3 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -48,12 +48,21 @@ struct sock *__inet6_lookup_established(struct net *net, const u16 hnum, const int dif, const int sdif); +typedef u32 (inet6_ehashfn_t)(const struct net *net, + const struct in6_addr *laddr, const u16 lport, + const struct in6_addr *faddr, const __be16 fport); + +inet6_ehashfn_t inet6_ehashfn; + +INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn); + struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, - unsigned short hnum); + unsigned short hnum, + inet6_ehashfn_t *ehashfn); struct sock *inet6_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 8734f3488f5d..ddfa2e67fdb5 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -379,10 +379,19 @@ struct sock *__inet_lookup_established(struct net *net, const __be32 daddr, const u16 hnum, const int dif, const int sdif); +typedef u32 (inet_ehashfn_t)(const struct net *net, + const __be32 laddr, const __u16 lport, + const __be32 faddr, const __be16 fport); + +inet_ehashfn_t inet_ehashfn; + +INDIRECT_CALLABLE_DECLARE(inet_ehashfn_t udp_ehashfn); + struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, - __be32 daddr, unsigned short hnum); + __be32 daddr, unsigned short hnum, + inet_ehashfn_t *ehashfn); static inline struct sock * inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo, @@ -453,10 +462,6 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, refcounted); } -u32 inet6_ehashfn(const struct net *net, - const struct in6_addr *laddr, const u16 lport, - const struct in6_addr *faddr, const __be16 fport); - static inline void sk_daddr_set(struct sock *sk, __be32 addr) { sk->sk_daddr = addr; /* alias of inet_daddr */ diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index ecb838460629..0a7a726464d9 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -28,9 +28,9 @@ #include #include -static u32 inet_ehashfn(const struct net *net, const __be32 laddr, - const __u16 lport, const __be32 faddr, - const __be16 fport) +u32 inet_ehashfn(const struct net *net, const __be32 laddr, + const __u16 lport, const __be32 faddr, + const __be16 fport) { static u32 inet_ehash_secret __read_mostly; @@ -39,6 +39,7 @@ static u32 inet_ehashfn(const struct net *net, const __be32 laddr, return __inet_ehashfn(laddr, lport, faddr, fport, inet_ehash_secret + net_hash_mix(net)); } +EXPORT_SYMBOL_GPL(inet_ehashfn); /* This function handles inet_sock, but also timewait and request sockets * for IPv4/IPv6. @@ -332,16 +333,20 @@ static inline int compute_score(struct sock *sk, struct net *net, return score; } +INDIRECT_CALLABLE_DECLARE(inet_ehashfn_t udp_ehashfn); + struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, - __be32 daddr, unsigned short hnum) + __be32 daddr, unsigned short hnum, + inet_ehashfn_t *ehashfn) { struct sock *reuse_sk = NULL; u32 phash; if (sk->sk_reuseport) { - phash = inet_ehashfn(net, daddr, hnum, saddr, sport); + phash = INDIRECT_CALL_2(ehashfn, udp_ehashfn, inet_ehashfn, + net, daddr, hnum, saddr, sport); reuse_sk = reuseport_select_sock(sk, phash, skb, doff); } return reuse_sk; @@ -371,7 +376,7 @@ static struct sock *inet_lhash2_lookup(struct net *net, score = compute_score(sk, net, hnum, daddr, dif, sdif); if (score > hiscore) { result = inet_lookup_reuseport(net, sk, skb, doff, - saddr, sport, daddr, hnum); + saddr, sport, daddr, hnum, inet_ehashfn); if (result) return result; @@ -400,7 +405,8 @@ static inline struct sock *inet_lookup_run_bpf(struct net *net, if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; - reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum); + reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum, + inet_ehashfn); if (reuse_sk) sk = reuse_sk; return sk; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 0d81339bda2f..3abe8a1520da 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -406,9 +406,9 @@ static int compute_score(struct sock *sk, struct net *net, return score; } -static u32 udp_ehashfn(const struct net *net, const __be32 laddr, - const __u16 lport, const __be32 faddr, - const __be16 fport) +INDIRECT_CALLABLE_SCOPE +u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, + const __be32 faddr, const __be16 fport) { static u32 udp_ehash_secret __read_mostly; @@ -418,22 +418,6 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr, udp_ehash_secret + net_hash_mix(net)); } -static 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)); - } - return reuse_sk; -} - /* called with rcu_read_lock() */ static struct sock *udp4_lib_lookup2(struct net *net, __be32 saddr, __be16 sport, @@ -452,7 +436,14 @@ static struct sock *udp4_lib_lookup2(struct net *net, daddr, hnum, dif, sdif); if (score > badness) { badness = score; - result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); + + if (sk->sk_state == TCP_ESTABLISHED) { + result = sk; + continue; + } + + result = inet_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), + saddr, sport, daddr, hnum, udp_ehashfn); if (!result) { result = sk; continue; @@ -491,7 +482,8 @@ static struct sock *udp4_lookup_run_bpf(struct net *net, if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; - reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); + reuse_sk = inet_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), + saddr, sport, daddr, hnum, udp_ehashfn); if (reuse_sk) sk = reuse_sk; return sk; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b7c56867314e..3616225c89ef 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -39,6 +39,7 @@ u32 inet6_ehashfn(const struct net *net, return __inet6_ehashfn(lhash, lport, fhash, fport, inet6_ehash_secret + net_hash_mix(net)); } +EXPORT_SYMBOL_GPL(inet6_ehashfn); /* * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so @@ -111,18 +112,22 @@ static inline int compute_score(struct sock *sk, struct net *net, return score; } +INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn); + struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, - unsigned short hnum) + unsigned short hnum, + inet6_ehashfn_t *ehashfn) { struct sock *reuse_sk = NULL; u32 phash; if (sk->sk_reuseport) { - phash = inet6_ehashfn(net, daddr, hnum, saddr, sport); + phash = INDIRECT_CALL_INET(ehashfn, udp6_ehashfn, inet6_ehashfn, + net, daddr, hnum, saddr, sport); reuse_sk = reuseport_select_sock(sk, phash, skb, doff); } return reuse_sk; @@ -145,7 +150,7 @@ static struct sock *inet6_lhash2_lookup(struct net *net, score = compute_score(sk, net, hnum, daddr, dif, sdif); if (score > hiscore) { result = inet6_lookup_reuseport(net, sk, skb, doff, - saddr, sport, daddr, hnum); + saddr, sport, daddr, hnum, inet6_ehashfn); if (result) return result; @@ -176,7 +181,8 @@ static inline struct sock *inet6_lookup_run_bpf(struct net *net, if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; - reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum); + reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff, + saddr, sport, daddr, hnum, inet6_ehashfn); if (reuse_sk) sk = reuse_sk; return sk; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 556d74a7d7ab..918ca1771710 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -71,11 +71,12 @@ int udpv6_init_sock(struct sock *sk) return 0; } -static u32 udp6_ehashfn(const struct net *net, - const struct in6_addr *laddr, - const u16 lport, - const struct in6_addr *faddr, - const __be16 fport) +INDIRECT_CALLABLE_SCOPE +u32 udp6_ehashfn(const struct net *net, + const struct in6_addr *laddr, + const u16 lport, + const struct in6_addr *faddr, + const __be16 fport) { static u32 udp6_ehash_secret __read_mostly; static u32 udp_ipv6_hash_secret __read_mostly; @@ -160,24 +161,6 @@ static int compute_score(struct sock *sk, struct net *net, return score; } -static struct sock *lookup_reuseport(struct net *net, struct sock *sk, - struct sk_buff *skb, - const struct in6_addr *saddr, - __be16 sport, - const struct in6_addr *daddr, - unsigned int hnum) -{ - struct sock *reuse_sk = NULL; - u32 hash; - - if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) { - hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); - reuse_sk = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - } - return reuse_sk; -} - /* called with rcu_read_lock() */ static struct sock *udp6_lib_lookup2(struct net *net, const struct in6_addr *saddr, __be16 sport, @@ -195,7 +178,14 @@ static struct sock *udp6_lib_lookup2(struct net *net, daddr, hnum, dif, sdif); if (score > badness) { badness = score; - result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); + + if (sk->sk_state == TCP_ESTABLISHED) { + result = sk; + continue; + } + + result = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), + saddr, sport, daddr, hnum, udp6_ehashfn); if (!result) { result = sk; continue; @@ -235,7 +225,8 @@ static inline struct sock *udp6_lookup_run_bpf(struct net *net, if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; - reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); + reuse_sk = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), + saddr, sport, daddr, hnum, udp6_ehashfn); if (reuse_sk) sk = reuse_sk; return sk; From 2a61776366bd17db9ac8c93ec32b8e0ae6b11cf2 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Thu, 20 Jul 2023 17:30:09 +0200 Subject: [PATCH 5/8] net: document inet[6]_lookup_reuseport sk_state requirements The current implementation was extracted from inet[6]_lhash2_lookup in commit 80b373f74f9e ("inet: Extract helper for selecting socket from reuseport group") and commit 5df6531292b5 ("inet6: Extract helper for selecting socket from reuseport group"). In the original context, sk is always in TCP_LISTEN state and so did not have a separate check. Add documentation that specifies which sk_state are valid to pass to the function. Reviewed-by: Kuniyuki Iwashima Signed-off-by: Lorenz Bauer Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-5-7021b683cdae@isovalent.com Signed-off-by: Martin KaFai Lau --- net/ipv4/inet_hashtables.c | 15 +++++++++++++++ net/ipv6/inet6_hashtables.c | 15 +++++++++++++++ 2 files changed, 30 insertions(+) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 0a7a726464d9..e9cec4807694 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -335,6 +335,21 @@ static inline int compute_score(struct sock *sk, struct net *net, INDIRECT_CALLABLE_DECLARE(inet_ehashfn_t udp_ehashfn); +/** + * inet_lookup_reuseport() - execute reuseport logic on AF_INET socket if necessary. + * @net: network namespace. + * @sk: AF_INET socket, must be in TCP_LISTEN state for TCP or TCP_CLOSE for UDP. + * @skb: context for a potential SK_REUSEPORT program. + * @doff: header offset. + * @saddr: source address. + * @sport: source port. + * @daddr: destination address. + * @hnum: destination port in host byte order. + * @ehashfn: hash function used to generate the fallback hash. + * + * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to + * the selected sock or an error. + */ struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 3616225c89ef..f76dbbb29332 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -114,6 +114,21 @@ static inline int compute_score(struct sock *sk, struct net *net, INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn); +/** + * inet6_lookup_reuseport() - execute reuseport logic on AF_INET6 socket if necessary. + * @net: network namespace. + * @sk: AF_INET6 socket, must be in TCP_LISTEN state for TCP or TCP_CLOSE for UDP. + * @skb: context for a potential SK_REUSEPORT program. + * @doff: header offset. + * @saddr: source address. + * @sport: source port. + * @daddr: destination address. + * @hnum: destination port in host byte order. + * @ehashfn: hash function used to generate the fallback hash. + * + * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to + * the selected sock or an error. + */ struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, From 6c886db2e78ce1dee163d07240467770a235f33e Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Thu, 20 Jul 2023 17:30:10 +0200 Subject: [PATCH 6/8] net: remove duplicate sk_lookup helpers Now that inet[6]_lookup_reuseport are parameterised on the ehashfn we can remove two sk_lookup helpers. Reviewed-by: Kuniyuki Iwashima Signed-off-by: Lorenz Bauer Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-6-7021b683cdae@isovalent.com Signed-off-by: Martin KaFai Lau --- include/net/inet6_hashtables.h | 9 +++++++++ include/net/inet_hashtables.h | 7 +++++++ net/ipv4/inet_hashtables.c | 26 +++++++++++++------------- net/ipv4/udp.c | 32 +++++--------------------------- net/ipv6/inet6_hashtables.c | 31 ++++++++++++++++--------------- net/ipv6/udp.c | 34 +++++----------------------------- 6 files changed, 55 insertions(+), 84 deletions(-) diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index f89320b6fee3..a6722d6ef80f 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -73,6 +73,15 @@ struct sock *inet6_lookup_listener(struct net *net, const unsigned short hnum, const int dif, const int sdif); +struct sock *inet6_lookup_run_sk_lookup(struct net *net, + int protocol, + 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, + inet6_ehashfn_t *ehashfn); + static inline struct sock *__inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index ddfa2e67fdb5..c0532cc7587f 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -393,6 +393,13 @@ struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, __be32 daddr, unsigned short hnum, inet_ehashfn_t *ehashfn); +struct sock *inet_lookup_run_sk_lookup(struct net *net, + int protocol, + struct sk_buff *skb, int doff, + __be32 saddr, __be16 sport, + __be32 daddr, u16 hnum, const int dif, + inet_ehashfn_t *ehashfn); + static inline struct sock * inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index e9cec4807694..6a872b8fb0d3 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -403,25 +403,23 @@ 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, const int dif) +struct sock *inet_lookup_run_sk_lookup(struct net *net, + int protocol, + struct sk_buff *skb, int doff, + __be32 saddr, __be16 sport, + __be32 daddr, u16 hnum, const int dif, + inet_ehashfn_t *ehashfn) { struct sock *sk, *reuse_sk; bool no_reuseport; - if (hashinfo != net->ipv4.tcp_death_row.hashinfo) - return NULL; /* only TCP is supported */ - - no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP, saddr, sport, + no_reuseport = bpf_sk_lookup_run_v4(net, protocol, saddr, sport, daddr, hnum, dif, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum, - inet_ehashfn); + ehashfn); if (reuse_sk) sk = reuse_sk; return sk; @@ -439,9 +437,11 @@ struct sock *__inet_lookup_listener(struct net *net, 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, dif); + if (static_branch_unlikely(&bpf_sk_lookup_enabled) && + hashinfo == net->ipv4.tcp_death_row.hashinfo) { + result = inet_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff, + saddr, sport, daddr, hnum, dif, + inet_ehashfn); if (result) goto done; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 3abe8a1520da..456fb6ee6ee8 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -465,30 +465,6 @@ static struct sock *udp4_lib_lookup2(struct net *net, return result; } -static 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, const int dif) -{ - struct sock *sk, *reuse_sk; - bool no_reuseport; - - if (udptable != net->ipv4.udp_table) - return NULL; /* only UDP is supported */ - - no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, saddr, sport, - daddr, hnum, dif, &sk); - if (no_reuseport || IS_ERR_OR_NULL(sk)) - return sk; - - reuse_sk = inet_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), - saddr, sport, daddr, hnum, udp_ehashfn); - 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 */ @@ -513,9 +489,11 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, 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, dif); + if (static_branch_unlikely(&bpf_sk_lookup_enabled) && + udptable == net->ipv4.udp_table) { + sk = inet_lookup_run_sk_lookup(net, IPPROTO_UDP, skb, sizeof(struct udphdr), + saddr, sport, daddr, hnum, dif, + udp_ehashfn); if (sk) { result = sk; goto done; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index f76dbbb29332..7c9700c7c9c8 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -177,31 +177,30 @@ static struct sock *inet6_lhash2_lookup(struct net *net, return result; } -static inline struct sock *inet6_lookup_run_bpf(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 sock *inet6_lookup_run_sk_lookup(struct net *net, + int protocol, + 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, + inet6_ehashfn_t *ehashfn) { struct sock *sk, *reuse_sk; bool no_reuseport; - if (hashinfo != net->ipv4.tcp_death_row.hashinfo) - return NULL; /* only TCP is supported */ - - no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_TCP, saddr, sport, + no_reuseport = bpf_sk_lookup_run_v6(net, protocol, saddr, sport, daddr, hnum, dif, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff, - saddr, sport, daddr, hnum, inet6_ehashfn); + saddr, sport, daddr, hnum, ehashfn); if (reuse_sk) sk = reuse_sk; return sk; } +EXPORT_SYMBOL_GPL(inet6_lookup_run_sk_lookup); struct sock *inet6_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, @@ -215,9 +214,11 @@ struct sock *inet6_lookup_listener(struct net *net, unsigned int hash2; /* Lookup redirect from BPF */ - if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { - result = inet6_lookup_run_bpf(net, hashinfo, skb, doff, - saddr, sport, daddr, hnum, dif); + if (static_branch_unlikely(&bpf_sk_lookup_enabled) && + hashinfo == net->ipv4.tcp_death_row.hashinfo) { + result = inet6_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff, + saddr, sport, daddr, hnum, dif, + inet6_ehashfn); if (result) goto done; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 918ca1771710..4b8974a8c7a3 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -206,32 +206,6 @@ static struct sock *udp6_lib_lookup2(struct net *net, return result; } -static inline struct sock *udp6_lookup_run_bpf(struct net *net, - struct udp_table *udptable, - struct sk_buff *skb, - const struct in6_addr *saddr, - __be16 sport, - const struct in6_addr *daddr, - u16 hnum, const int dif) -{ - struct sock *sk, *reuse_sk; - bool no_reuseport; - - if (udptable != net->ipv4.udp_table) - return NULL; /* only UDP is supported */ - - no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_UDP, saddr, sport, - daddr, hnum, dif, &sk); - if (no_reuseport || IS_ERR_OR_NULL(sk)) - return sk; - - reuse_sk = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), - saddr, sport, daddr, hnum, udp6_ehashfn); - if (reuse_sk) - sk = reuse_sk; - return sk; -} - /* rcu_read_lock() must be held */ struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, @@ -256,9 +230,11 @@ struct sock *__udp6_lib_lookup(struct net *net, goto done; /* Lookup redirect from BPF */ - if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { - sk = udp6_lookup_run_bpf(net, udptable, skb, - saddr, sport, daddr, hnum, dif); + if (static_branch_unlikely(&bpf_sk_lookup_enabled) && + udptable == net->ipv4.udp_table) { + sk = inet6_lookup_run_sk_lookup(net, IPPROTO_UDP, skb, sizeof(struct udphdr), + saddr, sport, daddr, hnum, dif, + udp6_ehashfn); if (sk) { result = sk; goto done; From 9c02bec95954252c3c01bfbb3f7560e0b95ca955 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Thu, 20 Jul 2023 17:30:11 +0200 Subject: [PATCH 7/8] bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign Currently the bpf_sk_assign helper in tc BPF context refuses SO_REUSEPORT sockets. This means we can't use the helper to steer traffic to Envoy, which configures SO_REUSEPORT on its sockets. In turn, we're blocked from removing TPROXY from our setup. The reason that bpf_sk_assign refuses such sockets is that the bpf_sk_lookup helpers don't execute SK_REUSEPORT programs. Instead, one of the reuseport sockets is selected by hash. This could cause dispatch to the "wrong" socket: sk = bpf_sk_lookup_tcp(...) // select SO_REUSEPORT by hash bpf_sk_assign(skb, sk) // SK_REUSEPORT wasn't executed Fixing this isn't as simple as invoking SK_REUSEPORT from the lookup helpers unfortunately. In the tc context, L2 headers are at the start of the skb, while SK_REUSEPORT expects L3 headers instead. Instead, we execute the SK_REUSEPORT program when the assigned socket is pulled out of the skb, further up the stack. This creates some trickiness with regards to refcounting as bpf_sk_assign will put both refcounted and RCU freed sockets in skb->sk. reuseport sockets are RCU freed. We can infer that the sk_assigned socket is RCU freed if the reuseport lookup succeeds, but convincing yourself of this fact isn't straight forward. Therefore we defensively check refcounting on the sk_assign sock even though it's probably not required in practice. Fixes: 8e368dc72e86 ("bpf: Fix use of sk->sk_reuseport from sk_assign") Fixes: cf7fbe660f2d ("bpf: Add socket assign support") Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann Cc: Joe Stringer Link: https://lore.kernel.org/bpf/CACAyw98+qycmpQzKupquhkxbvWK4OFyDuuLMBNROnfWMZxUWeA@mail.gmail.com/ Reviewed-by: Kuniyuki Iwashima Signed-off-by: Lorenz Bauer Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-7-7021b683cdae@isovalent.com Signed-off-by: Martin KaFai Lau --- include/net/inet6_hashtables.h | 54 +++++++++++++++++++++++++++++++--- include/net/inet_hashtables.h | 49 ++++++++++++++++++++++++++++-- include/net/sock.h | 7 +++-- include/uapi/linux/bpf.h | 3 -- net/core/filter.c | 2 -- net/ipv4/udp.c | 8 +++-- net/ipv6/udp.c | 8 +++-- tools/include/uapi/linux/bpf.h | 3 -- 8 files changed, 114 insertions(+), 20 deletions(-) diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index a6722d6ef80f..284b5ce7205d 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -103,6 +103,46 @@ static inline struct sock *__inet6_lookup(struct net *net, daddr, hnum, dif, sdif); } +static inline +struct sock *inet6_steal_sock(struct net *net, struct sk_buff *skb, int doff, + const struct in6_addr *saddr, const __be16 sport, + const struct in6_addr *daddr, const __be16 dport, + bool *refcounted, inet6_ehashfn_t *ehashfn) +{ + struct sock *sk, *reuse_sk; + bool prefetched; + + sk = skb_steal_sock(skb, refcounted, &prefetched); + if (!sk) + return NULL; + + if (!prefetched) + return sk; + + if (sk->sk_protocol == IPPROTO_TCP) { + if (sk->sk_state != TCP_LISTEN) + return sk; + } else if (sk->sk_protocol == IPPROTO_UDP) { + if (sk->sk_state != TCP_CLOSE) + return sk; + } else { + return sk; + } + + reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff, + saddr, sport, daddr, ntohs(dport), + ehashfn); + if (!reuse_sk) + return sk; + + /* We've chosen a new reuseport sock which is never refcounted. This + * implies that sk also isn't refcounted. + */ + WARN_ON_ONCE(*refcounted); + + return reuse_sk; +} + static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be16 sport, @@ -110,14 +150,20 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, int iif, int sdif, bool *refcounted) { - struct sock *sk = skb_steal_sock(skb, refcounted); + struct net *net = dev_net(skb_dst(skb)->dev); + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + struct sock *sk; + sk = inet6_steal_sock(net, skb, doff, &ip6h->saddr, sport, &ip6h->daddr, dport, + refcounted, inet6_ehashfn); + if (IS_ERR(sk)) + return NULL; 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), + return __inet6_lookup(net, hashinfo, skb, + doff, &ip6h->saddr, sport, + &ip6h->daddr, ntohs(dport), iif, sdif, refcounted); } diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index c0532cc7587f..1177effabed3 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -449,6 +449,46 @@ static inline struct sock *inet_lookup(struct net *net, return sk; } +static inline +struct sock *inet_steal_sock(struct net *net, struct sk_buff *skb, int doff, + const __be32 saddr, const __be16 sport, + const __be32 daddr, const __be16 dport, + bool *refcounted, inet_ehashfn_t *ehashfn) +{ + struct sock *sk, *reuse_sk; + bool prefetched; + + sk = skb_steal_sock(skb, refcounted, &prefetched); + if (!sk) + return NULL; + + if (!prefetched) + return sk; + + if (sk->sk_protocol == IPPROTO_TCP) { + if (sk->sk_state != TCP_LISTEN) + return sk; + } else if (sk->sk_protocol == IPPROTO_UDP) { + if (sk->sk_state != TCP_CLOSE) + return sk; + } else { + return sk; + } + + reuse_sk = inet_lookup_reuseport(net, sk, skb, doff, + saddr, sport, daddr, ntohs(dport), + ehashfn); + if (!reuse_sk) + return sk; + + /* We've chosen a new reuseport sock which is never refcounted. This + * implies that sk also isn't refcounted. + */ + WARN_ON_ONCE(*refcounted); + + return reuse_sk; +} + static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, @@ -457,13 +497,18 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, const int sdif, bool *refcounted) { - struct sock *sk = skb_steal_sock(skb, refcounted); + struct net *net = dev_net(skb_dst(skb)->dev); const struct iphdr *iph = ip_hdr(skb); + struct sock *sk; + sk = inet_steal_sock(net, skb, doff, iph->saddr, sport, iph->daddr, dport, + refcounted, inet_ehashfn); + if (IS_ERR(sk)) + return NULL; if (sk) return sk; - return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb, + return __inet_lookup(net, hashinfo, skb, doff, iph->saddr, sport, iph->daddr, dport, inet_iif(skb), sdif, refcounted); diff --git a/include/net/sock.h b/include/net/sock.h index 7ae44bf866af..74cbfb15d289 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2815,20 +2815,23 @@ sk_is_refcounted(struct sock *sk) * skb_steal_sock - steal a socket from an sk_buff * @skb: sk_buff to steal the socket from * @refcounted: is set to true if the socket is reference-counted + * @prefetched: is set to true if the socket was assigned from bpf */ static inline struct sock * -skb_steal_sock(struct sk_buff *skb, bool *refcounted) +skb_steal_sock(struct sk_buff *skb, bool *refcounted, bool *prefetched) { if (skb->sk) { struct sock *sk = skb->sk; *refcounted = true; - if (skb_sk_is_prefetched(skb)) + *prefetched = skb_sk_is_prefetched(skb); + if (*prefetched) *refcounted = sk_is_refcounted(sk); skb->destructor = NULL; skb->sk = NULL; return sk; } + *prefetched = false; *refcounted = false; return NULL; } diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 739c15906a65..7fc98f4b63e9 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4198,9 +4198,6 @@ union bpf_attr { * **-EOPNOTSUPP** if the operation is not supported, for example * a call from outside of TC ingress. * - * **-ESOCKTNOSUPPORT** if the socket type is not supported - * (reuseport). - * * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags) * Description * Helper is overloaded depending on BPF program type. This diff --git a/net/core/filter.c b/net/core/filter.c index b5b51ef48c5f..7c37f4646c20 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7351,8 +7351,6 @@ BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags) return -EOPNOTSUPP; if (unlikely(dev_net(skb->dev) != sock_net(sk))) return -ENETUNREACH; - if (unlikely(sk_fullsock(sk) && sk->sk_reuseport)) - return -ESOCKTNOSUPPORT; if (sk_unhashed(sk)) return -EOPNOTSUPP; if (sk_is_refcounted(sk) && diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 456fb6ee6ee8..d89c4a39cf27 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2388,7 +2388,11 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (udp4_csum_init(skb, uh, proto)) goto csum_error; - sk = skb_steal_sock(skb, &refcounted); + sk = inet_steal_sock(net, skb, sizeof(struct udphdr), saddr, uh->source, daddr, uh->dest, + &refcounted, udp_ehashfn); + if (IS_ERR(sk)) + goto no_sk; + if (sk) { struct dst_entry *dst = skb_dst(skb); int ret; @@ -2409,7 +2413,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable); if (sk) return udp_unicast_rcv_skb(sk, skb, uh); - +no_sk: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; nf_reset_ct(skb); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 4b8974a8c7a3..00996f0f7cfe 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -964,7 +964,11 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, goto csum_error; /* Check if the socket is already available, e.g. due to early demux */ - sk = skb_steal_sock(skb, &refcounted); + sk = inet6_steal_sock(net, skb, sizeof(struct udphdr), saddr, uh->source, daddr, uh->dest, + &refcounted, udp6_ehashfn); + if (IS_ERR(sk)) + goto no_sk; + if (sk) { struct dst_entry *dst = skb_dst(skb); int ret; @@ -998,7 +1002,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, goto report_csum_error; return udp6_unicast_rcv_skb(sk, skb, uh); } - +no_sk: reason = SKB_DROP_REASON_NO_SOCKET; if (!uh->check) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 739c15906a65..7fc98f4b63e9 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4198,9 +4198,6 @@ union bpf_attr { * **-EOPNOTSUPP** if the operation is not supported, for example * a call from outside of TC ingress. * - * **-ESOCKTNOSUPPORT** if the socket type is not supported - * (reuseport). - * * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags) * Description * Helper is overloaded depending on BPF program type. This From 22408d58a42cb59b88dcec3694f477a838dd68ed Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 20 Jul 2023 17:30:12 +0200 Subject: [PATCH 8/8] selftests/bpf: Test that SO_REUSEPORT can be used with sk_assign helper We use two programs to check that the new reuseport logic is executed appropriately. The first is a TC clsact program which bpf_sk_assigns the skb to a UDP or TCP socket created by user space. Since the test communicates via lo we see both directions of packets in the eBPF. Traffic ingressing to the reuseport socket is identified by looking at the destination port. For TCP, we additionally need to make sure that we only assign the initial SYN packets towards our listening socket. The network stack then creates a request socket which transitions to ESTABLISHED after the 3WHS. The second is a reuseport program which shares the fact that it has been executed with user space. This tells us that the delayed lookup mechanism is working. Signed-off-by: Daniel Borkmann Co-developed-by: Lorenz Bauer Signed-off-by: Lorenz Bauer Cc: Joe Stringer Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-8-7021b683cdae@isovalent.com Signed-off-by: Martin KaFai Lau --- tools/testing/selftests/bpf/network_helpers.c | 3 + .../selftests/bpf/prog_tests/assign_reuse.c | 199 ++++++++++++++++++ .../selftests/bpf/progs/test_assign_reuse.c | 142 +++++++++++++ 3 files changed, 344 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/assign_reuse.c create mode 100644 tools/testing/selftests/bpf/progs/test_assign_reuse.c diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index a105c0cd008a..8a33bcea97de 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -423,6 +423,9 @@ struct nstoken *open_netns(const char *name) void close_netns(struct nstoken *token) { + if (!token) + return; + ASSERT_OK(setns(token->orig_netns_fd, CLONE_NEWNET), "setns"); close(token->orig_netns_fd); free(token); diff --git a/tools/testing/selftests/bpf/prog_tests/assign_reuse.c b/tools/testing/selftests/bpf/prog_tests/assign_reuse.c new file mode 100644 index 000000000000..989ee4d9785b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/assign_reuse.c @@ -0,0 +1,199 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ +#include +#include + +#include +#include + +#include "network_helpers.h" +#include "test_assign_reuse.skel.h" + +#define NS_TEST "assign_reuse" +#define LOOPBACK 1 +#define PORT 4443 + +static int attach_reuseport(int sock_fd, int prog_fd) +{ + return setsockopt(sock_fd, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, + &prog_fd, sizeof(prog_fd)); +} + +static __u64 cookie(int fd) +{ + __u64 cookie = 0; + socklen_t cookie_len = sizeof(cookie); + int ret; + + ret = getsockopt(fd, SOL_SOCKET, SO_COOKIE, &cookie, &cookie_len); + ASSERT_OK(ret, "cookie"); + ASSERT_GT(cookie, 0, "cookie_invalid"); + + return cookie; +} + +static int echo_test_udp(int fd_sv) +{ + struct sockaddr_storage addr = {}; + socklen_t len = sizeof(addr); + char buff[1] = {}; + int fd_cl = -1, ret; + + fd_cl = connect_to_fd(fd_sv, 100); + ASSERT_GT(fd_cl, 0, "create_client"); + ASSERT_EQ(getsockname(fd_cl, (void *)&addr, &len), 0, "getsockname"); + + ASSERT_EQ(send(fd_cl, buff, sizeof(buff), 0), 1, "send_client"); + + ret = recv(fd_sv, buff, sizeof(buff), 0); + if (ret < 0) { + close(fd_cl); + return errno; + } + + ASSERT_EQ(ret, 1, "recv_server"); + ASSERT_EQ(sendto(fd_sv, buff, sizeof(buff), 0, (void *)&addr, len), 1, "send_server"); + ASSERT_EQ(recv(fd_cl, buff, sizeof(buff), 0), 1, "recv_client"); + close(fd_cl); + return 0; +} + +static int echo_test_tcp(int fd_sv) +{ + char buff[1] = {}; + int fd_cl = -1, fd_sv_cl = -1; + + fd_cl = connect_to_fd(fd_sv, 100); + if (fd_cl < 0) + return errno; + + fd_sv_cl = accept(fd_sv, NULL, NULL); + ASSERT_GE(fd_sv_cl, 0, "accept_fd"); + + ASSERT_EQ(send(fd_cl, buff, sizeof(buff), 0), 1, "send_client"); + ASSERT_EQ(recv(fd_sv_cl, buff, sizeof(buff), 0), 1, "recv_server"); + ASSERT_EQ(send(fd_sv_cl, buff, sizeof(buff), 0), 1, "send_server"); + ASSERT_EQ(recv(fd_cl, buff, sizeof(buff), 0), 1, "recv_client"); + close(fd_sv_cl); + close(fd_cl); + return 0; +} + +void run_assign_reuse(int family, int sotype, const char *ip, __u16 port) +{ + DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook, + .ifindex = LOOPBACK, + .attach_point = BPF_TC_INGRESS, + ); + DECLARE_LIBBPF_OPTS(bpf_tc_opts, tc_opts, + .handle = 1, + .priority = 1, + ); + bool hook_created = false, tc_attached = false; + int ret, fd_tc, fd_accept, fd_drop, fd_map; + int *fd_sv = NULL; + __u64 fd_val; + struct test_assign_reuse *skel; + const int zero = 0; + + skel = test_assign_reuse__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + skel->rodata->dest_port = port; + + ret = test_assign_reuse__load(skel); + if (!ASSERT_OK(ret, "skel_load")) + goto cleanup; + + ASSERT_EQ(skel->bss->sk_cookie_seen, 0, "cookie_init"); + + fd_tc = bpf_program__fd(skel->progs.tc_main); + fd_accept = bpf_program__fd(skel->progs.reuse_accept); + fd_drop = bpf_program__fd(skel->progs.reuse_drop); + fd_map = bpf_map__fd(skel->maps.sk_map); + + fd_sv = start_reuseport_server(family, sotype, ip, port, 100, 1); + if (!ASSERT_NEQ(fd_sv, NULL, "start_reuseport_server")) + goto cleanup; + + ret = attach_reuseport(*fd_sv, fd_drop); + if (!ASSERT_OK(ret, "attach_reuseport")) + goto cleanup; + + fd_val = *fd_sv; + ret = bpf_map_update_elem(fd_map, &zero, &fd_val, BPF_NOEXIST); + if (!ASSERT_OK(ret, "bpf_sk_map")) + goto cleanup; + + ret = bpf_tc_hook_create(&tc_hook); + if (ret == 0) + hook_created = true; + ret = ret == -EEXIST ? 0 : ret; + if (!ASSERT_OK(ret, "bpf_tc_hook_create")) + goto cleanup; + + tc_opts.prog_fd = fd_tc; + ret = bpf_tc_attach(&tc_hook, &tc_opts); + if (!ASSERT_OK(ret, "bpf_tc_attach")) + goto cleanup; + tc_attached = true; + + if (sotype == SOCK_STREAM) + ASSERT_EQ(echo_test_tcp(*fd_sv), ECONNREFUSED, "drop_tcp"); + else + ASSERT_EQ(echo_test_udp(*fd_sv), EAGAIN, "drop_udp"); + ASSERT_EQ(skel->bss->reuseport_executed, 1, "program executed once"); + + skel->bss->sk_cookie_seen = 0; + skel->bss->reuseport_executed = 0; + ASSERT_OK(attach_reuseport(*fd_sv, fd_accept), "attach_reuseport(accept)"); + + if (sotype == SOCK_STREAM) + ASSERT_EQ(echo_test_tcp(*fd_sv), 0, "echo_tcp"); + else + ASSERT_EQ(echo_test_udp(*fd_sv), 0, "echo_udp"); + + ASSERT_EQ(skel->bss->sk_cookie_seen, cookie(*fd_sv), + "cookie_mismatch"); + ASSERT_EQ(skel->bss->reuseport_executed, 1, "program executed once"); +cleanup: + if (tc_attached) { + tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0; + ret = bpf_tc_detach(&tc_hook, &tc_opts); + ASSERT_OK(ret, "bpf_tc_detach"); + } + if (hook_created) { + tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS; + bpf_tc_hook_destroy(&tc_hook); + } + test_assign_reuse__destroy(skel); + free_fds(fd_sv, 1); +} + +void test_assign_reuse(void) +{ + struct nstoken *tok = NULL; + + SYS(out, "ip netns add %s", NS_TEST); + SYS(cleanup, "ip -net %s link set dev lo up", NS_TEST); + + tok = open_netns(NS_TEST); + if (!ASSERT_OK_PTR(tok, "netns token")) + return; + + if (test__start_subtest("tcpv4")) + run_assign_reuse(AF_INET, SOCK_STREAM, "127.0.0.1", PORT); + if (test__start_subtest("tcpv6")) + run_assign_reuse(AF_INET6, SOCK_STREAM, "::1", PORT); + if (test__start_subtest("udpv4")) + run_assign_reuse(AF_INET, SOCK_DGRAM, "127.0.0.1", PORT); + if (test__start_subtest("udpv6")) + run_assign_reuse(AF_INET6, SOCK_DGRAM, "::1", PORT); + +cleanup: + close_netns(tok); + SYS_NOFAIL("ip netns delete %s", NS_TEST); +out: + return; +} diff --git a/tools/testing/selftests/bpf/progs/test_assign_reuse.c b/tools/testing/selftests/bpf/progs/test_assign_reuse.c new file mode 100644 index 000000000000..4f2e2321ea06 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_assign_reuse.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +char LICENSE[] SEC("license") = "GPL"; + +__u64 sk_cookie_seen; +__u64 reuseport_executed; +union { + struct tcphdr tcp; + struct udphdr udp; +} headers; + +const volatile __u16 dest_port; + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} sk_map SEC(".maps"); + +SEC("sk_reuseport") +int reuse_accept(struct sk_reuseport_md *ctx) +{ + reuseport_executed++; + + if (ctx->ip_protocol == IPPROTO_TCP) { + if (ctx->data + sizeof(headers.tcp) > ctx->data_end) + return SK_DROP; + + if (__builtin_memcmp(&headers.tcp, ctx->data, sizeof(headers.tcp)) != 0) + return SK_DROP; + } else if (ctx->ip_protocol == IPPROTO_UDP) { + if (ctx->data + sizeof(headers.udp) > ctx->data_end) + return SK_DROP; + + if (__builtin_memcmp(&headers.udp, ctx->data, sizeof(headers.udp)) != 0) + return SK_DROP; + } else { + return SK_DROP; + } + + sk_cookie_seen = bpf_get_socket_cookie(ctx->sk); + return SK_PASS; +} + +SEC("sk_reuseport") +int reuse_drop(struct sk_reuseport_md *ctx) +{ + reuseport_executed++; + sk_cookie_seen = 0; + return SK_DROP; +} + +static int +assign_sk(struct __sk_buff *skb) +{ + int zero = 0, ret = 0; + struct bpf_sock *sk; + + sk = bpf_map_lookup_elem(&sk_map, &zero); + if (!sk) + return TC_ACT_SHOT; + ret = bpf_sk_assign(skb, sk, 0); + bpf_sk_release(sk); + return ret ? TC_ACT_SHOT : TC_ACT_OK; +} + +static bool +maybe_assign_tcp(struct __sk_buff *skb, struct tcphdr *th) +{ + if (th + 1 > (void *)(long)(skb->data_end)) + return TC_ACT_SHOT; + + if (!th->syn || th->ack || th->dest != bpf_htons(dest_port)) + return TC_ACT_OK; + + __builtin_memcpy(&headers.tcp, th, sizeof(headers.tcp)); + return assign_sk(skb); +} + +static bool +maybe_assign_udp(struct __sk_buff *skb, struct udphdr *uh) +{ + if (uh + 1 > (void *)(long)(skb->data_end)) + return TC_ACT_SHOT; + + if (uh->dest != bpf_htons(dest_port)) + return TC_ACT_OK; + + __builtin_memcpy(&headers.udp, uh, sizeof(headers.udp)); + return assign_sk(skb); +} + +SEC("tc") +int tc_main(struct __sk_buff *skb) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct ethhdr *eth; + + eth = (struct ethhdr *)(data); + if (eth + 1 > data_end) + return TC_ACT_SHOT; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = (struct iphdr *)(data + sizeof(*eth)); + + if (iph + 1 > data_end) + return TC_ACT_SHOT; + + if (iph->protocol == IPPROTO_TCP) + return maybe_assign_tcp(skb, (struct tcphdr *)(iph + 1)); + else if (iph->protocol == IPPROTO_UDP) + return maybe_assign_udp(skb, (struct udphdr *)(iph + 1)); + else + return TC_ACT_SHOT; + } else { + struct ipv6hdr *ip6h = (struct ipv6hdr *)(data + sizeof(*eth)); + + if (ip6h + 1 > data_end) + return TC_ACT_SHOT; + + if (ip6h->nexthdr == IPPROTO_TCP) + return maybe_assign_tcp(skb, (struct tcphdr *)(ip6h + 1)); + else if (ip6h->nexthdr == IPPROTO_UDP) + return maybe_assign_udp(skb, (struct udphdr *)(ip6h + 1)); + else + return TC_ACT_SHOT; + } +}