+++ /dev/null
-From 6ce9726cde011d60974f784cd8e849820b062de2 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Thu, 20 Jul 2023 17:30:11 +0200
-Subject: bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-[ Upstream commit 9c02bec95954252c3c01bfbb3f7560e0b95ca955 ]
-
-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 <daniel@iogearbox.net>
-Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
-Cc: Joe Stringer <joe@cilium.io>
-Link: https://lore.kernel.org/bpf/CACAyw98+qycmpQzKupquhkxbvWK4OFyDuuLMBNROnfWMZxUWeA@mail.gmail.com/
-Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-7-7021b683cdae@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/net/inet6_hashtables.h | 56 +++++++++++++++++++++++++++++++---
- 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, 115 insertions(+), 21 deletions(-)
-
-diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
-index f89320b6fee31..475e672b4facc 100644
---- a/include/net/inet6_hashtables.h
-+++ b/include/net/inet6_hashtables.h
-@@ -94,6 +94,46 @@ 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,
-@@ -101,14 +141,20 @@ 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 f4b4102744a50..06f1ab600481e 100644
---- a/include/net/inet_hashtables.h
-+++ b/include/net/inet_hashtables.h
-@@ -382,6 +382,46 @@ 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,
-@@ -390,13 +430,18 @@ 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 640bd7a367779..68579cb022e25 100644
---- a/include/net/sock.h
-+++ b/include/net/sock.h
-@@ -2745,20 +2745,23 @@ 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 a887e582f0e78..b9c5a942bc545 100644
---- a/include/uapi/linux/bpf.h
-+++ b/include/uapi/linux/bpf.h
-@@ -3976,9 +3976,6 @@ 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 76432aa3b717c..6f1fab853e77e 100644
---- a/net/core/filter.c
-+++ b/net/core/filter.c
-@@ -6957,8 +6957,6 @@ 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 de672235ceee5..9149b7aeddc65 100644
---- a/net/ipv4/udp.c
-+++ b/net/ipv4/udp.c
-@@ -2446,7 +2446,11 @@ 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;
-@@ -2467,7 +2471,7 @@ 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 2c653ed1add1f..04dfc16425de9 100644
---- a/net/ipv6/udp.c
-+++ b/net/ipv6/udp.c
-@@ -969,7 +969,11 @@ 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;
-@@ -1003,7 +1007,7 @@ 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 8330e3ca8fbfb..39a209c4c65c4 100644
---- a/tools/include/uapi/linux/bpf.h
-+++ b/tools/include/uapi/linux/bpf.h
-@@ -3976,9 +3976,6 @@ 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
---
-2.40.1
-
+++ /dev/null
-From 9b7d85edbdcc2fbbf712f90893ba61c2e99134d0 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Thu, 20 Jul 2023 17:30:07 +0200
-Subject: net: export inet_lookup_reuseport and inet6_lookup_reuseport
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-[ Upstream commit ce796e60b3b196b61fcc565df195443cbb846ef0 ]
-
-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 <kuniyu@amazon.com>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-3-7021b683cdae@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Stable-dep-of: 9c02bec95954 ("bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- 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 56f1286583d3c..032ddab48f8f8 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 53c22b64e9724..6c7606b5cadfd 100644
---- a/include/net/inet_hashtables.h
-+++ b/include/net/inet_hashtables.h
-@@ -319,6 +319,11 @@ 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 2936676f86eb8..ce32401567647 100644
---- a/net/ipv4/inet_hashtables.c
-+++ b/net/ipv4/inet_hashtables.c
-@@ -252,10 +252,10 @@ 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;
-@@ -266,6 +266,7 @@ 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
-@@ -290,8 +291,8 @@ static struct sock *inet_lhash2_lookup(struct net *net,
- sk = (struct sock *)icsk;
- 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;
-
-@@ -320,7 +321,7 @@ 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 b4a5e01e12016..2267f973e2df3 100644
---- a/net/ipv6/inet6_hashtables.c
-+++ b/net/ipv6/inet6_hashtables.c
-@@ -113,12 +113,12 @@ 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;
-@@ -129,6 +129,7 @@ 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,
-@@ -146,8 +147,8 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
- sk = (struct sock *)icsk;
- 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;
-
-@@ -178,7 +179,7 @@ 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;
---
-2.40.1
-
+++ /dev/null
-From 430fce638025f2cbeed253cadc4471699844dddb Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Tue, 15 Aug 2023 09:53:41 +0100
-Subject: net: Fix slab-out-of-bounds in inet[6]_steal_sock
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-[ Upstream commit 8897562f67b3e61ad736cd5c9f307447d33280e4 ]
-
-Kumar reported a KASAN splat in tcp_v6_rcv:
-
- bash-5.2# ./test_progs -t btf_skc_cls_ingress
- ...
- [ 51.810085] BUG: KASAN: slab-out-of-bounds in tcp_v6_rcv+0x2d7d/0x3440
- [ 51.810458] Read of size 2 at addr ffff8881053f038c by task test_progs/226
-
-The problem is that inet[6]_steal_sock accesses sk->sk_protocol without
-accounting for request or timewait sockets. To fix this we can't just
-check sock_common->skc_reuseport since that flag is present on timewait
-sockets.
-
-Instead, add a fullsock check to avoid the out of bands access of sk_protocol.
-
-Fixes: 9c02bec95954 ("bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign")
-Reported-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Link: https://lore.kernel.org/r/20230815-bpf-next-v2-1-95126eaa4c1b@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/net/inet6_hashtables.h | 2 +-
- include/net/inet_hashtables.h | 2 +-
- 2 files changed, 2 insertions(+), 2 deletions(-)
-
-diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
-index 475e672b4facc..12780b8fb5630 100644
---- a/include/net/inet6_hashtables.h
-+++ b/include/net/inet6_hashtables.h
-@@ -107,7 +107,7 @@ struct sock *inet6_steal_sock(struct net *net, struct sk_buff *skb, int doff,
- if (!sk)
- return NULL;
-
-- if (!prefetched)
-+ if (!prefetched || !sk_fullsock(sk))
- return sk;
-
- if (sk->sk_protocol == IPPROTO_TCP) {
-diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
-index 06f1ab600481e..0cc2a88d1c37c 100644
---- a/include/net/inet_hashtables.h
-+++ b/include/net/inet_hashtables.h
-@@ -395,7 +395,7 @@ struct sock *inet_steal_sock(struct net *net, struct sk_buff *skb, int doff,
- if (!sk)
- return NULL;
-
-- if (!prefetched)
-+ if (!prefetched || !sk_fullsock(sk))
- return sk;
-
- if (sk->sk_protocol == IPPROTO_TCP) {
---
-2.40.1
-
+++ /dev/null
-From 74bdfab4fd7c641e55f7fe9d1be9687eeb01df67 Mon Sep 17 00:00:00 2001
-From: Lorenz Bauer <lmb@isovalent.com>
-Date: Mon, 31 Jul 2023 11:42:53 +0200
-Subject: net: remove duplicate INDIRECT_CALLABLE_DECLARE of udp[6]_ehashfn
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-commit 74bdfab4fd7c641e55f7fe9d1be9687eeb01df67 upstream.
-
-There are already INDIRECT_CALLABLE_DECLARE in the hashtable
-headers, no need to declare them again.
-
-Fixes: 0f495f761722 ("net: remove duplicate reuseport_lookup functions")
-Suggested-by: Martin Lau <martin.lau@linux.dev>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
-Link: https://lore.kernel.org/r/20230731-indir-call-v1-1-4cd0aeaee64f@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
----
- net/ipv4/inet_hashtables.c | 2 --
- net/ipv6/inet6_hashtables.c | 2 --
- 2 files changed, 4 deletions(-)
-
---- a/net/ipv4/inet_hashtables.c
-+++ b/net/ipv4/inet_hashtables.c
-@@ -253,8 +253,6 @@ static inline int compute_score(struct s
- 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,
---- a/net/ipv6/inet6_hashtables.c
-+++ b/net/ipv6/inet6_hashtables.c
-@@ -114,8 +114,6 @@ static inline int compute_score(struct s
- 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,
+++ /dev/null
-From 80dd0a17af4bad8ab1687e60f1a0800d59f41fc3 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Thu, 20 Jul 2023 17:30:08 +0200
-Subject: net: remove duplicate reuseport_lookup functions
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-[ Upstream commit 0f495f7617229772403e683033abc473f0f0553c ]
-
-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 <kuniyu@amazon.com>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-4-7021b683cdae@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Stable-dep-of: 9c02bec95954 ("bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- 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 032ddab48f8f8..f89320b6fee31 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 6c7606b5cadfd..f4b4102744a50 100644
---- a/include/net/inet_hashtables.h
-+++ b/include/net/inet_hashtables.h
-@@ -319,10 +319,19 @@ 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,
-@@ -393,10 +402,6 @@ 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 ce32401567647..0b2b652ad4898 100644
---- a/net/ipv4/inet_hashtables.c
-+++ b/net/ipv4/inet_hashtables.c
-@@ -28,9 +28,9 @@
- #include <net/tcp.h>
- #include <net/sock_reuseport.h>
-
--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.
-@@ -252,16 +253,20 @@ 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;
-@@ -292,7 +297,7 @@ 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;
-
-@@ -321,7 +326,8 @@ 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 198d8e07413d3..de672235ceee5 100644
---- a/net/ipv4/udp.c
-+++ b/net/ipv4/udp.c
-@@ -398,9 +398,9 @@ 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;
-
-@@ -410,22 +410,6 @@ 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,
-@@ -444,7 +428,14 @@ 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;
-@@ -483,7 +474,8 @@ 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 2267f973e2df3..21b4fc835487b 100644
---- a/net/ipv6/inet6_hashtables.c
-+++ b/net/ipv6/inet6_hashtables.c
-@@ -41,6 +41,7 @@ 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
-@@ -113,18 +114,22 @@ 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;
-@@ -148,7 +153,7 @@ 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;
-
-@@ -179,7 +184,8 @@ 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 d5d254ca2dfe6..2c653ed1add1f 100644
---- a/net/ipv6/udp.c
-+++ b/net/ipv6/udp.c
-@@ -68,11 +68,12 @@ 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;
-@@ -156,24 +157,6 @@ 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,
-@@ -191,7 +174,14 @@ 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;
-@@ -231,7 +221,8 @@ 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;
---
-2.40.1
-
udp-re-score-reuseport-groups-when-connected-sockets.patch
bpf-reject-unhashed-sockets-in-bpf_sk_assign.patch
ipv6-add-reasons-for-skb-drops-to-__udp6_lib_rcv.patch
-net-export-inet_lookup_reuseport-and-inet6_lookup_re.patch
-net-remove-duplicate-reuseport_lookup-functions.patch
-bpf-net-support-so_reuseport-sockets-with-bpf_sk_ass.patch
wifi-mt76-testmode-add-nla_policy-for-mt76_tm_attr_t.patch
spi-tegra20-sflash-fix-to-check-return-value-of-plat.patch
can-gs_usb-gs_usb_receive_bulk_callback-count-rx-ove.patch
bluetooth-fix-potential-use-after-free-when-clear-ke.patch
net-tcp-fix-unexcepted-socket-die-when-snd_wnd-is-0.patch
selftests-bpf-clean-up-fmod_ret-in-bench_rename-test.patch
-net-fix-slab-out-of-bounds-in-inet-6-_steal_sock.patch
net-memcg-fix-scope-of-sockmem-pressure-indicators.patch
ice-ice_aq_check_events-fix-off-by-one-check-when-fi.patch
crypto-caam-fix-unchecked-return-value-error.patch
usb-core-fix-oversight-in-superspeed-initialization.patch
x86-sgx-break-up-long-non-preemptible-delays-in-sgx_vepc_release.patch
perf-x86-uncore-correct-the-number-of-chas-on-emr.patch
-net-remove-duplicate-indirect_callable_declare-of-udp_ehashfn.patch
tracing-zero-the-pipe-cpumask-on-alloc-to-avoid-spurious-ebusy.patch
md-md-bitmap-remove-unnecessary-local-variable-in-backlog_store.patch
revert-drm-amdgpu-install-stub-fence-into-potential-unused-fence-pointers.patch
+++ /dev/null
-From d3beaba9fbe2a4e2efbcc3fbae860410c59e85e7 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Thu, 20 Jul 2023 17:30:11 +0200
-Subject: bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-[ Upstream commit 9c02bec95954252c3c01bfbb3f7560e0b95ca955 ]
-
-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 <daniel@iogearbox.net>
-Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
-Cc: Joe Stringer <joe@cilium.io>
-Link: https://lore.kernel.org/bpf/CACAyw98+qycmpQzKupquhkxbvWK4OFyDuuLMBNROnfWMZxUWeA@mail.gmail.com/
-Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-7-7021b683cdae@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/net/inet6_hashtables.h | 56 +++++++++++++++++++++++++++++++---
- 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, 115 insertions(+), 21 deletions(-)
-
-diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
-index f89320b6fee31..475e672b4facc 100644
---- a/include/net/inet6_hashtables.h
-+++ b/include/net/inet6_hashtables.h
-@@ -94,6 +94,46 @@ 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,
-@@ -101,14 +141,20 @@ 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 ddfa2e67fdb51..a1b8eb147ce73 100644
---- a/include/net/inet_hashtables.h
-+++ b/include/net/inet_hashtables.h
-@@ -442,6 +442,46 @@ 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,
-@@ -450,13 +490,18 @@ 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 d1f936ed97556..3a8b2cc23b914 100644
---- a/include/net/sock.h
-+++ b/include/net/sock.h
-@@ -2852,20 +2852,23 @@ 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 51b9aa640ad2a..1304bec5c97a0 100644
---- a/include/uapi/linux/bpf.h
-+++ b/include/uapi/linux/bpf.h
-@@ -4079,9 +4079,6 @@ 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 9fd7c88b5db4e..ccc97d54d9a8b 100644
---- a/net/core/filter.c
-+++ b/net/core/filter.c
-@@ -7257,8 +7257,6 @@ 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 87686c9e4efca..58c2f8df5fd70 100644
---- a/net/ipv4/udp.c
-+++ b/net/ipv4/udp.c
-@@ -2442,7 +2442,11 @@ 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;
-@@ -2463,7 +2467,7 @@ 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 3408376b1863b..91b757066c935 100644
---- a/net/ipv6/udp.c
-+++ b/net/ipv6/udp.c
-@@ -983,7 +983,11 @@ 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;
-@@ -1017,7 +1021,7 @@ 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 51b9aa640ad2a..1304bec5c97a0 100644
---- a/tools/include/uapi/linux/bpf.h
-+++ b/tools/include/uapi/linux/bpf.h
-@@ -4079,9 +4079,6 @@ 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
---
-2.40.1
-
+++ /dev/null
-From 54234a8d6225eeb23998faa12da812998995c956 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Thu, 20 Jul 2023 17:30:07 +0200
-Subject: net: export inet_lookup_reuseport and inet6_lookup_reuseport
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-[ Upstream commit ce796e60b3b196b61fcc565df195443cbb846ef0 ]
-
-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 <kuniyu@amazon.com>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-3-7021b683cdae@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Stable-dep-of: 9c02bec95954 ("bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- 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 56f1286583d3c..032ddab48f8f8 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 99bd823e97f62..8734f3488f5d0 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 c19b462662ad0..6ed92624c95c4 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 b64b49012655e..b7c56867314ed 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;
---
-2.40.1
-
+++ /dev/null
-From cb889400f6dac86d95708d710ed5885dc9b8d78f Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Tue, 15 Aug 2023 09:53:41 +0100
-Subject: net: Fix slab-out-of-bounds in inet[6]_steal_sock
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-[ Upstream commit 8897562f67b3e61ad736cd5c9f307447d33280e4 ]
-
-Kumar reported a KASAN splat in tcp_v6_rcv:
-
- bash-5.2# ./test_progs -t btf_skc_cls_ingress
- ...
- [ 51.810085] BUG: KASAN: slab-out-of-bounds in tcp_v6_rcv+0x2d7d/0x3440
- [ 51.810458] Read of size 2 at addr ffff8881053f038c by task test_progs/226
-
-The problem is that inet[6]_steal_sock accesses sk->sk_protocol without
-accounting for request or timewait sockets. To fix this we can't just
-check sock_common->skc_reuseport since that flag is present on timewait
-sockets.
-
-Instead, add a fullsock check to avoid the out of bands access of sk_protocol.
-
-Fixes: 9c02bec95954 ("bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign")
-Reported-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Link: https://lore.kernel.org/r/20230815-bpf-next-v2-1-95126eaa4c1b@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/net/inet6_hashtables.h | 2 +-
- include/net/inet_hashtables.h | 2 +-
- 2 files changed, 2 insertions(+), 2 deletions(-)
-
-diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
-index 475e672b4facc..12780b8fb5630 100644
---- a/include/net/inet6_hashtables.h
-+++ b/include/net/inet6_hashtables.h
-@@ -107,7 +107,7 @@ struct sock *inet6_steal_sock(struct net *net, struct sk_buff *skb, int doff,
- if (!sk)
- return NULL;
-
-- if (!prefetched)
-+ if (!prefetched || !sk_fullsock(sk))
- return sk;
-
- if (sk->sk_protocol == IPPROTO_TCP) {
-diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
-index a1b8eb147ce73..9414cb4e6e624 100644
---- a/include/net/inet_hashtables.h
-+++ b/include/net/inet_hashtables.h
-@@ -455,7 +455,7 @@ struct sock *inet_steal_sock(struct net *net, struct sk_buff *skb, int doff,
- if (!sk)
- return NULL;
-
-- if (!prefetched)
-+ if (!prefetched || !sk_fullsock(sk))
- return sk;
-
- if (sk->sk_protocol == IPPROTO_TCP) {
---
-2.40.1
-
+++ /dev/null
-From 74bdfab4fd7c641e55f7fe9d1be9687eeb01df67 Mon Sep 17 00:00:00 2001
-From: Lorenz Bauer <lmb@isovalent.com>
-Date: Mon, 31 Jul 2023 11:42:53 +0200
-Subject: net: remove duplicate INDIRECT_CALLABLE_DECLARE of udp[6]_ehashfn
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-commit 74bdfab4fd7c641e55f7fe9d1be9687eeb01df67 upstream.
-
-There are already INDIRECT_CALLABLE_DECLARE in the hashtable
-headers, no need to declare them again.
-
-Fixes: 0f495f761722 ("net: remove duplicate reuseport_lookup functions")
-Suggested-by: Martin Lau <martin.lau@linux.dev>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
-Link: https://lore.kernel.org/r/20230731-indir-call-v1-1-4cd0aeaee64f@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
----
- net/ipv4/inet_hashtables.c | 2 --
- net/ipv6/inet6_hashtables.c | 2 --
- 2 files changed, 4 deletions(-)
-
---- a/net/ipv4/inet_hashtables.c
-+++ b/net/ipv4/inet_hashtables.c
-@@ -333,8 +333,6 @@ static inline int compute_score(struct s
- 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,
---- a/net/ipv6/inet6_hashtables.c
-+++ b/net/ipv6/inet6_hashtables.c
-@@ -112,8 +112,6 @@ static inline int compute_score(struct s
- 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,
+++ /dev/null
-From 3cf7940a98d9e474fc7a560b2484a54d5c728b17 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Thu, 20 Jul 2023 17:30:08 +0200
-Subject: net: remove duplicate reuseport_lookup functions
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-[ Upstream commit 0f495f7617229772403e683033abc473f0f0553c ]
-
-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 <kuniyu@amazon.com>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-4-7021b683cdae@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Stable-dep-of: 9c02bec95954 ("bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- 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 032ddab48f8f8..f89320b6fee31 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 8734f3488f5d0..ddfa2e67fdb51 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 6ed92624c95c4..970da5b2bfe9c 100644
---- a/net/ipv4/inet_hashtables.c
-+++ b/net/ipv4/inet_hashtables.c
-@@ -28,9 +28,9 @@
- #include <net/tcp.h>
- #include <net/sock_reuseport.h>
-
--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 42c1f7d9a980a..87686c9e4efca 100644
---- a/net/ipv4/udp.c
-+++ b/net/ipv4/udp.c
-@@ -400,9 +400,9 @@ 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;
-
-@@ -412,22 +412,6 @@ 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,
-@@ -446,7 +430,14 @@ 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;
-@@ -485,7 +476,8 @@ 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 b7c56867314ed..3616225c89ef6 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 64b36c2ba774a..3408376b1863b 100644
---- a/net/ipv6/udp.c
-+++ b/net/ipv6/udp.c
-@@ -70,11 +70,12 @@ 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;
-@@ -159,24 +160,6 @@ 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,
-@@ -194,7 +177,14 @@ 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;
-@@ -234,7 +224,8 @@ 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;
---
-2.40.1
-
wifi-mt76-mt7921-fix-non-psc-channel-scan-fail.patch
udp-re-score-reuseport-groups-when-connected-sockets.patch
bpf-reject-unhashed-sockets-in-bpf_sk_assign.patch
-net-export-inet_lookup_reuseport-and-inet6_lookup_re.patch
-net-remove-duplicate-reuseport_lookup-functions.patch
-bpf-net-support-so_reuseport-sockets-with-bpf_sk_ass.patch
wifi-mt76-testmode-add-nla_policy-for-mt76_tm_attr_t.patch
spi-tegra20-sflash-fix-to-check-return-value-of-plat.patch
can-gs_usb-gs_usb_receive_bulk_callback-count-rx-ove.patch
net-tcp-fix-unexcepted-socket-die-when-snd_wnd-is-0.patch
selftests-bpf-fix-repeat-option-when-kfunc_call-veri.patch
selftests-bpf-clean-up-fmod_ret-in-bench_rename-test.patch
-net-fix-slab-out-of-bounds-in-inet-6-_steal_sock.patch
net-memcg-fix-scope-of-sockmem-pressure-indicators.patch
ice-ice_aq_check_events-fix-off-by-one-check-when-fi.patch
crypto-caam-fix-unchecked-return-value-error.patch
perf-x86-uncore-correct-the-number-of-chas-on-emr.patch
serial-sc16is7xx-remove-obsolete-out_thread-label.patch
serial-sc16is7xx-fix-regression-with-gpio-configurat.patch
-net-remove-duplicate-indirect_callable_declare-of-udp_ehashfn.patch
tracing-zero-the-pipe-cpumask-on-alloc-to-avoid-spurious-ebusy.patch
revert-drm-amd-display-do-not-set-drr-on-pipe-commit.patch
md-free-resources-in-__md_stop.patch
+++ /dev/null
-From 1c53f65cde5209d48cab6bec7b2592fa2b7e7f0f Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Thu, 20 Jul 2023 17:30:11 +0200
-Subject: bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-[ Upstream commit 9c02bec95954252c3c01bfbb3f7560e0b95ca955 ]
-
-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 <daniel@iogearbox.net>
-Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
-Cc: Joe Stringer <joe@cilium.io>
-Link: https://lore.kernel.org/bpf/CACAyw98+qycmpQzKupquhkxbvWK4OFyDuuLMBNROnfWMZxUWeA@mail.gmail.com/
-Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-7-7021b683cdae@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/net/inet6_hashtables.h | 56 +++++++++++++++++++++++++++++++---
- 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, 115 insertions(+), 21 deletions(-)
-
-diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
-index f89320b6fee31..475e672b4facc 100644
---- a/include/net/inet6_hashtables.h
-+++ b/include/net/inet6_hashtables.h
-@@ -94,6 +94,46 @@ 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,
-@@ -101,14 +141,20 @@ 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 ddfa2e67fdb51..a1b8eb147ce73 100644
---- a/include/net/inet_hashtables.h
-+++ b/include/net/inet_hashtables.h
-@@ -442,6 +442,46 @@ 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,
-@@ -450,13 +490,18 @@ 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 d0d796d51a504..299c484bd4035 100644
---- a/include/net/sock.h
-+++ b/include/net/sock.h
-@@ -2826,20 +2826,23 @@ 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 c994ff5b157cd..dc6db5c246dbe 100644
---- a/include/uapi/linux/bpf.h
-+++ b/include/uapi/linux/bpf.h
-@@ -4145,9 +4145,6 @@ 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 a9e93d528869f..d5ca1f4c75b3e 100644
---- a/net/core/filter.c
-+++ b/net/core/filter.c
-@@ -7335,8 +7335,6 @@ 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 aaba742f6d103..dd4259d998fc9 100644
---- a/net/ipv4/udp.c
-+++ b/net/ipv4/udp.c
-@@ -2459,7 +2459,11 @@ 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;
-@@ -2480,7 +2484,7 @@ 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 19f5a2fc8f378..3a36cc48353f2 100644
---- a/net/ipv6/udp.c
-+++ b/net/ipv6/udp.c
-@@ -992,7 +992,11 @@ 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;
-@@ -1026,7 +1030,7 @@ 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 c994ff5b157cd..dc6db5c246dbe 100644
---- a/tools/include/uapi/linux/bpf.h
-+++ b/tools/include/uapi/linux/bpf.h
-@@ -4145,9 +4145,6 @@ 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
---
-2.40.1
-
+++ /dev/null
-From 2e96dd1287139a03a298d686375ba0e638370ead Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Thu, 20 Jul 2023 17:30:07 +0200
-Subject: net: export inet_lookup_reuseport and inet6_lookup_reuseport
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-[ Upstream commit ce796e60b3b196b61fcc565df195443cbb846ef0 ]
-
-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 <kuniyu@amazon.com>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-3-7021b683cdae@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Stable-dep-of: 9c02bec95954 ("bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- 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 56f1286583d3c..032ddab48f8f8 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 99bd823e97f62..8734f3488f5d0 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 0819d6001b9ab..ecb838460629e 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 b64b49012655e..b7c56867314ed 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;
---
-2.40.1
-
+++ /dev/null
-From 14a7c473d8d22952b08334d2657356e4926a8251 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Tue, 15 Aug 2023 09:53:41 +0100
-Subject: net: Fix slab-out-of-bounds in inet[6]_steal_sock
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-[ Upstream commit 8897562f67b3e61ad736cd5c9f307447d33280e4 ]
-
-Kumar reported a KASAN splat in tcp_v6_rcv:
-
- bash-5.2# ./test_progs -t btf_skc_cls_ingress
- ...
- [ 51.810085] BUG: KASAN: slab-out-of-bounds in tcp_v6_rcv+0x2d7d/0x3440
- [ 51.810458] Read of size 2 at addr ffff8881053f038c by task test_progs/226
-
-The problem is that inet[6]_steal_sock accesses sk->sk_protocol without
-accounting for request or timewait sockets. To fix this we can't just
-check sock_common->skc_reuseport since that flag is present on timewait
-sockets.
-
-Instead, add a fullsock check to avoid the out of bands access of sk_protocol.
-
-Fixes: 9c02bec95954 ("bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign")
-Reported-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Link: https://lore.kernel.org/r/20230815-bpf-next-v2-1-95126eaa4c1b@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/net/inet6_hashtables.h | 2 +-
- include/net/inet_hashtables.h | 2 +-
- 2 files changed, 2 insertions(+), 2 deletions(-)
-
-diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
-index 475e672b4facc..12780b8fb5630 100644
---- a/include/net/inet6_hashtables.h
-+++ b/include/net/inet6_hashtables.h
-@@ -107,7 +107,7 @@ struct sock *inet6_steal_sock(struct net *net, struct sk_buff *skb, int doff,
- if (!sk)
- return NULL;
-
-- if (!prefetched)
-+ if (!prefetched || !sk_fullsock(sk))
- return sk;
-
- if (sk->sk_protocol == IPPROTO_TCP) {
-diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
-index a1b8eb147ce73..9414cb4e6e624 100644
---- a/include/net/inet_hashtables.h
-+++ b/include/net/inet_hashtables.h
-@@ -455,7 +455,7 @@ struct sock *inet_steal_sock(struct net *net, struct sk_buff *skb, int doff,
- if (!sk)
- return NULL;
-
-- if (!prefetched)
-+ if (!prefetched || !sk_fullsock(sk))
- return sk;
-
- if (sk->sk_protocol == IPPROTO_TCP) {
---
-2.40.1
-
+++ /dev/null
-From 74bdfab4fd7c641e55f7fe9d1be9687eeb01df67 Mon Sep 17 00:00:00 2001
-From: Lorenz Bauer <lmb@isovalent.com>
-Date: Mon, 31 Jul 2023 11:42:53 +0200
-Subject: net: remove duplicate INDIRECT_CALLABLE_DECLARE of udp[6]_ehashfn
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-commit 74bdfab4fd7c641e55f7fe9d1be9687eeb01df67 upstream.
-
-There are already INDIRECT_CALLABLE_DECLARE in the hashtable
-headers, no need to declare them again.
-
-Fixes: 0f495f761722 ("net: remove duplicate reuseport_lookup functions")
-Suggested-by: Martin Lau <martin.lau@linux.dev>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
-Link: https://lore.kernel.org/r/20230731-indir-call-v1-1-4cd0aeaee64f@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
----
- net/ipv4/inet_hashtables.c | 2 --
- net/ipv6/inet6_hashtables.c | 2 --
- 2 files changed, 4 deletions(-)
-
---- a/net/ipv4/inet_hashtables.c
-+++ b/net/ipv4/inet_hashtables.c
-@@ -333,8 +333,6 @@ static inline int compute_score(struct s
- 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,
---- a/net/ipv6/inet6_hashtables.c
-+++ b/net/ipv6/inet6_hashtables.c
-@@ -112,8 +112,6 @@ static inline int compute_score(struct s
- 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,
+++ /dev/null
-From 0b1126906102cec0e95f1c6e286c23db7d68ba76 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Thu, 20 Jul 2023 17:30:08 +0200
-Subject: net: remove duplicate reuseport_lookup functions
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-[ Upstream commit 0f495f7617229772403e683033abc473f0f0553c ]
-
-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 <kuniyu@amazon.com>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-4-7021b683cdae@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Stable-dep-of: 9c02bec95954 ("bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- 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 032ddab48f8f8..f89320b6fee31 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 8734f3488f5d0..ddfa2e67fdb51 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 ecb838460629e..0a7a726464d9d 100644
---- a/net/ipv4/inet_hashtables.c
-+++ b/net/ipv4/inet_hashtables.c
-@@ -28,9 +28,9 @@
- #include <net/tcp.h>
- #include <net/sock_reuseport.h>
-
--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 a3302136ce92e..aaba742f6d103 100644
---- a/net/ipv4/udp.c
-+++ b/net/ipv4/udp.c
-@@ -407,9 +407,9 @@ 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;
-
-@@ -419,22 +419,6 @@ 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,
-@@ -453,7 +437,14 @@ 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;
-@@ -492,7 +483,8 @@ 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 b7c56867314ed..3616225c89ef6 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 9c7457823eb97..19f5a2fc8f378 100644
---- a/net/ipv6/udp.c
-+++ b/net/ipv6/udp.c
-@@ -72,11 +72,12 @@ 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;
-@@ -161,24 +162,6 @@ 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,
-@@ -196,7 +179,14 @@ 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;
-@@ -236,7 +226,8 @@ 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;
---
-2.40.1
-
wifi-mt76-mt7996-fix-wa-event-ring-size.patch
udp-re-score-reuseport-groups-when-connected-sockets.patch
bpf-reject-unhashed-sockets-in-bpf_sk_assign.patch
-net-export-inet_lookup_reuseport-and-inet6_lookup_re.patch
-net-remove-duplicate-reuseport_lookup-functions.patch
-bpf-net-support-so_reuseport-sockets-with-bpf_sk_ass.patch
wifi-mt76-mt7915-fix-command-timeout-in-ap-stop-peri.patch
wifi-mt76-mt7915-fix-capabilities-in-non-ap-mode.patch
wifi-mt76-mt7915-remove-vht160-capability-on-mt7915.patch
net-tcp-fix-unexcepted-socket-die-when-snd_wnd-is-0.patch
selftests-bpf-fix-repeat-option-when-kfunc_call-veri.patch
selftests-bpf-clean-up-fmod_ret-in-bench_rename-test.patch
-net-fix-slab-out-of-bounds-in-inet-6-_steal_sock.patch
net-hns3-move-dump-regs-function-to-a-separate-file.patch
net-hns3-support-tlv-in-regs-data-for-hns3-pf-driver.patch
net-hns3-fix-wrong-rpu-tln-reg-issue.patch
memfd-do-not-eacces-old-memfd_create-users-with-vm.m.patch
memfd-improve-userspace-warnings-for-missing-exec-re.patch
revert-memfd-improve-userspace-warnings-for-missing-exec-related-flags.patch
-net-remove-duplicate-indirect_callable_declare-of-udp_ehashfn.patch
tracing-zero-the-pipe-cpumask-on-alloc-to-avoid-spurious-ebusy.patch
revert-drm-amd-display-do-not-set-drr-on-pipe-commit.patch
+++ /dev/null
-From 2d2c2b92cee4baec44fee3a848187a7bc2c33192 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Thu, 20 Jul 2023 17:30:11 +0200
-Subject: bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-[ Upstream commit 9c02bec95954252c3c01bfbb3f7560e0b95ca955 ]
-
-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 <daniel@iogearbox.net>
-Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
-Cc: Joe Stringer <joe@cilium.io>
-Link: https://lore.kernel.org/bpf/CACAyw98+qycmpQzKupquhkxbvWK4OFyDuuLMBNROnfWMZxUWeA@mail.gmail.com/
-Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-7-7021b683cdae@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/net/inet6_hashtables.h | 56 +++++++++++++++++++++++++++++++---
- 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, 115 insertions(+), 21 deletions(-)
-
-diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
-index f89320b6fee31..475e672b4facc 100644
---- a/include/net/inet6_hashtables.h
-+++ b/include/net/inet6_hashtables.h
-@@ -94,6 +94,46 @@ 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,
-@@ -101,14 +141,20 @@ 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 ddfa2e67fdb51..a1b8eb147ce73 100644
---- a/include/net/inet_hashtables.h
-+++ b/include/net/inet_hashtables.h
-@@ -442,6 +442,46 @@ 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,
-@@ -450,13 +490,18 @@ 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 e8927f2d47a3c..11d503417591e 100644
---- a/include/net/sock.h
-+++ b/include/net/sock.h
-@@ -2822,20 +2822,23 @@ 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 60a9d59beeabb..d8cbae8220256 100644
---- a/include/uapi/linux/bpf.h
-+++ b/include/uapi/linux/bpf.h
-@@ -4159,9 +4159,6 @@ 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 f1a5775400658..454da3538965a 100644
---- a/net/core/filter.c
-+++ b/net/core/filter.c
-@@ -7350,8 +7350,6 @@ 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 fd06e0e34bda3..f8b0fecc10659 100644
---- a/net/ipv4/udp.c
-+++ b/net/ipv4/udp.c
-@@ -2414,7 +2414,11 @@ 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;
-@@ -2435,7 +2439,7 @@ 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 a4b124e4bd3b4..82fdc69ee0813 100644
---- a/net/ipv6/udp.c
-+++ b/net/ipv6/udp.c
-@@ -992,7 +992,11 @@ 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;
-@@ -1026,7 +1030,7 @@ 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 60a9d59beeabb..d8cbae8220256 100644
---- a/tools/include/uapi/linux/bpf.h
-+++ b/tools/include/uapi/linux/bpf.h
-@@ -4159,9 +4159,6 @@ 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
---
-2.40.1
-
+++ /dev/null
-From 298fb569a0325974eb1bdd1b42d09794e5302728 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Thu, 20 Jul 2023 17:30:07 +0200
-Subject: net: export inet_lookup_reuseport and inet6_lookup_reuseport
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-[ Upstream commit ce796e60b3b196b61fcc565df195443cbb846ef0 ]
-
-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 <kuniyu@amazon.com>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-3-7021b683cdae@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Stable-dep-of: 9c02bec95954 ("bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- 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 56f1286583d3c..032ddab48f8f8 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 99bd823e97f62..8734f3488f5d0 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 0819d6001b9ab..ecb838460629e 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 b64b49012655e..b7c56867314ed 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;
---
-2.40.1
-
+++ /dev/null
-From bce242512ea4d551c42372ff4c01a8e11e7c23ff Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Tue, 15 Aug 2023 09:53:41 +0100
-Subject: net: Fix slab-out-of-bounds in inet[6]_steal_sock
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-[ Upstream commit 8897562f67b3e61ad736cd5c9f307447d33280e4 ]
-
-Kumar reported a KASAN splat in tcp_v6_rcv:
-
- bash-5.2# ./test_progs -t btf_skc_cls_ingress
- ...
- [ 51.810085] BUG: KASAN: slab-out-of-bounds in tcp_v6_rcv+0x2d7d/0x3440
- [ 51.810458] Read of size 2 at addr ffff8881053f038c by task test_progs/226
-
-The problem is that inet[6]_steal_sock accesses sk->sk_protocol without
-accounting for request or timewait sockets. To fix this we can't just
-check sock_common->skc_reuseport since that flag is present on timewait
-sockets.
-
-Instead, add a fullsock check to avoid the out of bands access of sk_protocol.
-
-Fixes: 9c02bec95954 ("bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign")
-Reported-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Link: https://lore.kernel.org/r/20230815-bpf-next-v2-1-95126eaa4c1b@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/net/inet6_hashtables.h | 2 +-
- include/net/inet_hashtables.h | 2 +-
- 2 files changed, 2 insertions(+), 2 deletions(-)
-
-diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
-index 475e672b4facc..12780b8fb5630 100644
---- a/include/net/inet6_hashtables.h
-+++ b/include/net/inet6_hashtables.h
-@@ -107,7 +107,7 @@ struct sock *inet6_steal_sock(struct net *net, struct sk_buff *skb, int doff,
- if (!sk)
- return NULL;
-
-- if (!prefetched)
-+ if (!prefetched || !sk_fullsock(sk))
- return sk;
-
- if (sk->sk_protocol == IPPROTO_TCP) {
-diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
-index a1b8eb147ce73..9414cb4e6e624 100644
---- a/include/net/inet_hashtables.h
-+++ b/include/net/inet_hashtables.h
-@@ -455,7 +455,7 @@ struct sock *inet_steal_sock(struct net *net, struct sk_buff *skb, int doff,
- if (!sk)
- return NULL;
-
-- if (!prefetched)
-+ if (!prefetched || !sk_fullsock(sk))
- return sk;
-
- if (sk->sk_protocol == IPPROTO_TCP) {
---
-2.40.1
-
+++ /dev/null
-From 74bdfab4fd7c641e55f7fe9d1be9687eeb01df67 Mon Sep 17 00:00:00 2001
-From: Lorenz Bauer <lmb@isovalent.com>
-Date: Mon, 31 Jul 2023 11:42:53 +0200
-Subject: net: remove duplicate INDIRECT_CALLABLE_DECLARE of udp[6]_ehashfn
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-commit 74bdfab4fd7c641e55f7fe9d1be9687eeb01df67 upstream.
-
-There are already INDIRECT_CALLABLE_DECLARE in the hashtable
-headers, no need to declare them again.
-
-Fixes: 0f495f761722 ("net: remove duplicate reuseport_lookup functions")
-Suggested-by: Martin Lau <martin.lau@linux.dev>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
-Link: https://lore.kernel.org/r/20230731-indir-call-v1-1-4cd0aeaee64f@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
----
- net/ipv4/inet_hashtables.c | 2 --
- net/ipv6/inet6_hashtables.c | 2 --
- 2 files changed, 4 deletions(-)
-
---- a/net/ipv4/inet_hashtables.c
-+++ b/net/ipv4/inet_hashtables.c
-@@ -333,8 +333,6 @@ static inline int compute_score(struct s
- 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,
---- a/net/ipv6/inet6_hashtables.c
-+++ b/net/ipv6/inet6_hashtables.c
-@@ -112,8 +112,6 @@ static inline int compute_score(struct s
- 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,
+++ /dev/null
-From 67de62b8bc6b539a86c5ad60349474c2847683f5 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Thu, 20 Jul 2023 17:30:08 +0200
-Subject: net: remove duplicate reuseport_lookup functions
-
-From: Lorenz Bauer <lmb@isovalent.com>
-
-[ Upstream commit 0f495f7617229772403e683033abc473f0f0553c ]
-
-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 <kuniyu@amazon.com>
-Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
-Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-4-7021b683cdae@isovalent.com
-Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
-Stable-dep-of: 9c02bec95954 ("bpf, net: Support SO_REUSEPORT sockets with bpf_sk_assign")
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- 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 032ddab48f8f8..f89320b6fee31 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 8734f3488f5d0..ddfa2e67fdb51 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 ecb838460629e..0a7a726464d9d 100644
---- a/net/ipv4/inet_hashtables.c
-+++ b/net/ipv4/inet_hashtables.c
-@@ -28,9 +28,9 @@
- #include <net/tcp.h>
- #include <net/sock_reuseport.h>
-
--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 b3aa68ea29de2..fd06e0e34bda3 100644
---- a/net/ipv4/udp.c
-+++ b/net/ipv4/udp.c
-@@ -407,9 +407,9 @@ 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;
-
-@@ -419,22 +419,6 @@ 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,
-@@ -453,7 +437,14 @@ 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;
-@@ -492,7 +483,8 @@ 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 b7c56867314ed..3616225c89ef6 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 3ffca158d3e11..a4b124e4bd3b4 100644
---- a/net/ipv6/udp.c
-+++ b/net/ipv6/udp.c
-@@ -72,11 +72,12 @@ 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;
-@@ -161,24 +162,6 @@ 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,
-@@ -196,7 +179,14 @@ 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;
-@@ -236,7 +226,8 @@ 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;
---
-2.40.1
-
wifi-mt76-mt7996-fix-wa-event-ring-size.patch
udp-re-score-reuseport-groups-when-connected-sockets.patch
bpf-reject-unhashed-sockets-in-bpf_sk_assign.patch
-net-export-inet_lookup_reuseport-and-inet6_lookup_re.patch
-net-remove-duplicate-reuseport_lookup-functions.patch
-bpf-net-support-so_reuseport-sockets-with-bpf_sk_ass.patch
wifi-mt76-mt7915-fix-command-timeout-in-ap-stop-peri.patch
wifi-mt76-mt7915-fix-capabilities-in-non-ap-mode.patch
wifi-mt76-mt7915-remove-vht160-capability-on-mt7915.patch
libbpf-set-close-on-exec-flag-on-gzopen.patch
selftests-bpf-fix-repeat-option-when-kfunc_call-veri.patch
selftests-bpf-clean-up-fmod_ret-in-bench_rename-test.patch
-net-fix-slab-out-of-bounds-in-inet-6-_steal_sock.patch
net-hns3-move-dump-regs-function-to-a-separate-file.patch
net-hns3-support-tlv-in-regs-data-for-hns3-pf-driver.patch
net-hns3-fix-wrong-rpu-tln-reg-issue.patch
memfd-replace-ratcheting-feature-from-vm.memfd_noexe.patch
memfd-improve-userspace-warnings-for-missing-exec-re.patch
revert-memfd-improve-userspace-warnings-for-missing-exec-related-flags.patch
-net-remove-duplicate-indirect_callable_declare-of-udp_ehashfn.patch
projects / thirdparty / kernel / stable-queue.git / commitdiff
