From db6af4fdb150b45e1ba6b295ccfd3df482e022d2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Mar 2023 15:32:00 +0000 Subject: ipv6: raw: constify raw_v6_match() socket argument This clarifies raw_v6_match() intent. Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/ipv6/raw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv6/raw.c') diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index bac9ba747bde..6ac2f2690c44 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -64,7 +64,7 @@ struct raw_hashinfo raw_v6_hashinfo; EXPORT_SYMBOL_GPL(raw_v6_hashinfo); -bool raw_v6_match(struct net *net, struct sock *sk, unsigned short num, +bool raw_v6_match(struct net *net, const struct sock *sk, unsigned short num, const struct in6_addr *loc_addr, const struct in6_addr *rmt_addr, int dif, int sdif) { -- cgit v1.2.3 From b0e214d212030fe497d4d150bb3474e50ad5d093 Mon Sep 17 00:00:00 2001 From: Madhu Koriginja Date: Tue, 21 Mar 2023 21:28:44 +0530 Subject: netfilter: keep conntrack reference until IPsecv6 policy checks are done Keep the conntrack reference until policy checks have been performed for IPsec V6 NAT support, just like ipv4. The reference needs to be dropped before a packet is queued to avoid having the conntrack module unloadable. Fixes: 58a317f1061c ("netfilter: ipv6: add IPv6 NAT support") Signed-off-by: Madhu Koriginja Signed-off-by: Florian Westphal --- net/dccp/ipv6.c | 1 + net/ipv6/ip6_input.c | 14 ++++++-------- net/ipv6/raw.c | 5 ++--- net/ipv6/tcp_ipv6.c | 2 ++ net/ipv6/udp.c | 2 ++ 5 files changed, 13 insertions(+), 11 deletions(-) (limited to 'net/ipv6/raw.c') diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 47fb10834223..93c98990d726 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -784,6 +784,7 @@ lookup: if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; + nf_reset_ct(skb); return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4, refcounted) ? -1 : 0; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index e1ebf5e42ebe..d94041bb4287 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -404,10 +404,6 @@ resubmit_final: /* Only do this once for first final protocol */ have_final = true; - /* Free reference early: we don't need it any more, - and it may hold ip_conntrack module loaded - indefinitely. */ - nf_reset_ct(skb); skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); @@ -430,10 +426,12 @@ resubmit_final: goto discard; } } - if (!(ipprot->flags & INET6_PROTO_NOPOLICY) && - !xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { - SKB_DR_SET(reason, XFRM_POLICY); - goto discard; + if (!(ipprot->flags & INET6_PROTO_NOPOLICY)) { + if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { + SKB_DR_SET(reason, XFRM_POLICY); + goto discard; + } + nf_reset_ct(skb); } ret = INDIRECT_CALL_2(ipprot->handler, tcp_v6_rcv, udpv6_rcv, diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 6ac2f2690c44..4ab62a9c5c8e 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -194,10 +194,8 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC); /* Not releasing hash table! */ - if (clone) { - nf_reset_ct(clone); + if (clone) rawv6_rcv(sk, clone); - } } } rcu_read_unlock(); @@ -391,6 +389,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) kfree_skb_reason(skb, SKB_DROP_REASON_XFRM_POLICY); return NET_RX_DROP; } + nf_reset_ct(skb); if (!rp->checksum) skb->ip_summed = CHECKSUM_UNNECESSARY; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 35cf523c9efd..244cf86c4cbb 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1723,6 +1723,8 @@ process: if (drop_reason) goto discard_and_relse; + nf_reset_ct(skb); + if (tcp_filter(sk, skb)) { drop_reason = SKB_DROP_REASON_SOCKET_FILTER; goto discard_and_relse; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index d350e57c4792..4caa70a1b871 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -704,6 +704,7 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) drop_reason = SKB_DROP_REASON_XFRM_POLICY; goto drop; } + nf_reset_ct(skb); if (static_branch_unlikely(&udpv6_encap_needed_key) && up->encap_type) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); @@ -1027,6 +1028,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard; + nf_reset_ct(skb); if (udp_lib_checksum_complete(skb)) goto csum_error; -- cgit v1.2.3 From 0a78cf7264d29abeca098eae0b188a10aabc8a32 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 3 Apr 2023 12:49:58 -0700 Subject: raw: Fix NULL deref in raw_get_next(). Dae R. Jeong reported a NULL deref in raw_get_next() [0]. It seems that the repro was running these sequences in parallel so that one thread was iterating on a socket that was being freed in another netns. unshare(0x40060200) r0 = syz_open_procfs(0x0, &(0x7f0000002080)='net/raw\x00') socket$inet_icmp_raw(0x2, 0x3, 0x1) pread64(r0, &(0x7f0000000000)=""/10, 0xa, 0x10000000007f) After commit 0daf07e52709 ("raw: convert raw sockets to RCU"), we use RCU and hlist_nulls_for_each_entry() to iterate over SOCK_RAW sockets. However, we should use spinlock for slow paths to avoid the NULL deref. Also, SOCK_RAW does not use SLAB_TYPESAFE_BY_RCU, and the slab object is not reused during iteration in the grace period. In fact, the lockless readers do not check the nulls marker with get_nulls_value(). So, SOCK_RAW should use hlist instead of hlist_nulls. Instead of adding an unnecessary barrier by sk_nulls_for_each_rcu(), let's convert hlist_nulls to hlist and use sk_for_each_rcu() for fast paths and sk_for_each() and spinlock for /proc/net/raw. [0]: general protection fault, probably for non-canonical address 0xdffffc0000000005: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000028-0x000000000000002f] CPU: 2 PID: 20952 Comm: syz-executor.0 Not tainted 6.2.0-g048ec869bafd-dirty #7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 RIP: 0010:read_pnet include/net/net_namespace.h:383 [inline] RIP: 0010:sock_net include/net/sock.h:649 [inline] RIP: 0010:raw_get_next net/ipv4/raw.c:974 [inline] RIP: 0010:raw_get_idx net/ipv4/raw.c:986 [inline] RIP: 0010:raw_seq_start+0x431/0x800 net/ipv4/raw.c:995 Code: ef e8 33 3d 94 f7 49 8b 6d 00 4c 89 ef e8 b7 65 5f f7 49 89 ed 49 83 c5 98 0f 84 9a 00 00 00 48 83 c5 c8 48 89 e8 48 c1 e8 03 <42> 80 3c 30 00 74 08 48 89 ef e8 00 3d 94 f7 4c 8b 7d 00 48 89 ef RSP: 0018:ffffc9001154f9b0 EFLAGS: 00010206 RAX: 0000000000000005 RBX: 1ffff1100302c8fd RCX: 0000000000000000 RDX: 0000000000000028 RSI: ffffc9001154f988 RDI: ffffc9000f77a338 RBP: 0000000000000029 R08: ffffffff8a50ffb4 R09: fffffbfff24b6bd9 R10: fffffbfff24b6bd9 R11: 0000000000000000 R12: ffff88801db73b78 R13: fffffffffffffff9 R14: dffffc0000000000 R15: 0000000000000030 FS: 00007f843ae8e700(0000) GS:ffff888063700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055bb9614b35f CR3: 000000003c672000 CR4: 00000000003506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: seq_read_iter+0x4c6/0x10f0 fs/seq_file.c:225 seq_read+0x224/0x320 fs/seq_file.c:162 pde_read fs/proc/inode.c:316 [inline] proc_reg_read+0x23f/0x330 fs/proc/inode.c:328 vfs_read+0x31e/0xd30 fs/read_write.c:468 ksys_pread64 fs/read_write.c:665 [inline] __do_sys_pread64 fs/read_write.c:675 [inline] __se_sys_pread64 fs/read_write.c:672 [inline] __x64_sys_pread64+0x1e9/0x280 fs/read_write.c:672 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x4e/0xa0 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x478d29 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f843ae8dbe8 EFLAGS: 00000246 ORIG_RAX: 0000000000000011 RAX: ffffffffffffffda RBX: 0000000000791408 RCX: 0000000000478d29 RDX: 000000000000000a RSI: 0000000020000000 RDI: 0000000000000003 RBP: 00000000f477909a R08: 0000000000000000 R09: 0000000000000000 R10: 000010000000007f R11: 0000000000000246 R12: 0000000000791740 R13: 0000000000791414 R14: 0000000000791408 R15: 00007ffc2eb48a50 Modules linked in: ---[ end trace 0000000000000000 ]--- RIP: 0010:read_pnet include/net/net_namespace.h:383 [inline] RIP: 0010:sock_net include/net/sock.h:649 [inline] RIP: 0010:raw_get_next net/ipv4/raw.c:974 [inline] RIP: 0010:raw_get_idx net/ipv4/raw.c:986 [inline] RIP: 0010:raw_seq_start+0x431/0x800 net/ipv4/raw.c:995 Code: ef e8 33 3d 94 f7 49 8b 6d 00 4c 89 ef e8 b7 65 5f f7 49 89 ed 49 83 c5 98 0f 84 9a 00 00 00 48 83 c5 c8 48 89 e8 48 c1 e8 03 <42> 80 3c 30 00 74 08 48 89 ef e8 00 3d 94 f7 4c 8b 7d 00 48 89 ef RSP: 0018:ffffc9001154f9b0 EFLAGS: 00010206 RAX: 0000000000000005 RBX: 1ffff1100302c8fd RCX: 0000000000000000 RDX: 0000000000000028 RSI: ffffc9001154f988 RDI: ffffc9000f77a338 RBP: 0000000000000029 R08: ffffffff8a50ffb4 R09: fffffbfff24b6bd9 R10: fffffbfff24b6bd9 R11: 0000000000000000 R12: ffff88801db73b78 R13: fffffffffffffff9 R14: dffffc0000000000 R15: 0000000000000030 FS: 00007f843ae8e700(0000) GS:ffff888063700000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f92ff166000 CR3: 000000003c672000 CR4: 00000000003506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Fixes: 0daf07e52709 ("raw: convert raw sockets to RCU") Reported-by: syzbot Reported-by: Dae R. Jeong Link: https://lore.kernel.org/netdev/ZCA2mGV_cmq7lIfV@dragonet/ Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/net/raw.h | 4 ++-- net/ipv4/raw.c | 36 +++++++++++++++++++----------------- net/ipv4/raw_diag.c | 10 ++++------ net/ipv6/raw.c | 10 ++++------ 4 files changed, 29 insertions(+), 31 deletions(-) (limited to 'net/ipv6/raw.c') diff --git a/include/net/raw.h b/include/net/raw.h index 2c004c20ed99..3af5289fdead 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -37,7 +37,7 @@ int raw_rcv(struct sock *, struct sk_buff *); struct raw_hashinfo { spinlock_t lock; - struct hlist_nulls_head ht[RAW_HTABLE_SIZE] ____cacheline_aligned; + struct hlist_head ht[RAW_HTABLE_SIZE] ____cacheline_aligned; }; static inline u32 raw_hashfunc(const struct net *net, u32 proto) @@ -51,7 +51,7 @@ static inline void raw_hashinfo_init(struct raw_hashinfo *hashinfo) spin_lock_init(&hashinfo->lock); for (i = 0; i < RAW_HTABLE_SIZE; i++) - INIT_HLIST_NULLS_HEAD(&hashinfo->ht[i], i); + INIT_HLIST_HEAD(&hashinfo->ht[i]); } #ifdef CONFIG_PROC_FS diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 94df935ee0c5..8088a5011e7d 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -91,12 +91,12 @@ EXPORT_SYMBOL_GPL(raw_v4_hashinfo); int raw_hash_sk(struct sock *sk) { struct raw_hashinfo *h = sk->sk_prot->h.raw_hash; - struct hlist_nulls_head *hlist; + struct hlist_head *hlist; hlist = &h->ht[raw_hashfunc(sock_net(sk), inet_sk(sk)->inet_num)]; spin_lock(&h->lock); - __sk_nulls_add_node_rcu(sk, hlist); + sk_add_node_rcu(sk, hlist); sock_set_flag(sk, SOCK_RCU_FREE); spin_unlock(&h->lock); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); @@ -110,7 +110,7 @@ void raw_unhash_sk(struct sock *sk) struct raw_hashinfo *h = sk->sk_prot->h.raw_hash; spin_lock(&h->lock); - if (__sk_nulls_del_node_init_rcu(sk)) + if (sk_del_node_init_rcu(sk)) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); spin_unlock(&h->lock); } @@ -163,16 +163,15 @@ static int icmp_filter(const struct sock *sk, const struct sk_buff *skb) static int raw_v4_input(struct net *net, struct sk_buff *skb, const struct iphdr *iph, int hash) { - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; int sdif = inet_sdif(skb); + struct hlist_head *hlist; int dif = inet_iif(skb); int delivered = 0; struct sock *sk; hlist = &raw_v4_hashinfo.ht[hash]; rcu_read_lock(); - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { if (!raw_v4_match(net, sk, iph->protocol, iph->saddr, iph->daddr, dif, sdif)) continue; @@ -264,10 +263,9 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) { struct net *net = dev_net(skb->dev); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; int dif = skb->dev->ifindex; int sdif = inet_sdif(skb); + struct hlist_head *hlist; const struct iphdr *iph; struct sock *sk; int hash; @@ -276,7 +274,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) hlist = &raw_v4_hashinfo.ht[hash]; rcu_read_lock(); - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { iph = (const struct iphdr *)skb->data; if (!raw_v4_match(net, sk, iph->protocol, iph->daddr, iph->saddr, dif, sdif)) @@ -950,14 +948,13 @@ static struct sock *raw_get_first(struct seq_file *seq, int bucket) { struct raw_hashinfo *h = pde_data(file_inode(seq->file)); struct raw_iter_state *state = raw_seq_private(seq); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; + struct hlist_head *hlist; struct sock *sk; for (state->bucket = bucket; state->bucket < RAW_HTABLE_SIZE; ++state->bucket) { hlist = &h->ht[state->bucket]; - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each(sk, hlist) { if (sock_net(sk) == seq_file_net(seq)) return sk; } @@ -970,7 +967,7 @@ static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk) struct raw_iter_state *state = raw_seq_private(seq); do { - sk = sk_nulls_next(sk); + sk = sk_next(sk); } while (sk && sock_net(sk) != seq_file_net(seq)); if (!sk) @@ -989,9 +986,12 @@ static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos) } void *raw_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU) + __acquires(&h->lock) { - rcu_read_lock(); + struct raw_hashinfo *h = pde_data(file_inode(seq->file)); + + spin_lock(&h->lock); + return *pos ? raw_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } EXPORT_SYMBOL_GPL(raw_seq_start); @@ -1010,9 +1010,11 @@ void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos) EXPORT_SYMBOL_GPL(raw_seq_next); void raw_seq_stop(struct seq_file *seq, void *v) - __releases(RCU) + __releases(&h->lock) { - rcu_read_unlock(); + struct raw_hashinfo *h = pde_data(file_inode(seq->file)); + + spin_unlock(&h->lock); } EXPORT_SYMBOL_GPL(raw_seq_stop); diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c index 999321834b94..da3591a66a16 100644 --- a/net/ipv4/raw_diag.c +++ b/net/ipv4/raw_diag.c @@ -57,8 +57,7 @@ static bool raw_lookup(struct net *net, struct sock *sk, static struct sock *raw_sock_get(struct net *net, const struct inet_diag_req_v2 *r) { struct raw_hashinfo *hashinfo = raw_get_hashinfo(r); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; + struct hlist_head *hlist; struct sock *sk; int slot; @@ -68,7 +67,7 @@ static struct sock *raw_sock_get(struct net *net, const struct inet_diag_req_v2 rcu_read_lock(); for (slot = 0; slot < RAW_HTABLE_SIZE; slot++) { hlist = &hashinfo->ht[slot]; - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { if (raw_lookup(net, sk, r)) { /* * Grab it and keep until we fill @@ -142,9 +141,8 @@ static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, struct raw_hashinfo *hashinfo = raw_get_hashinfo(r); struct net *net = sock_net(skb->sk); struct inet_diag_dump_data *cb_data; - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; int num, s_num, slot, s_slot; + struct hlist_head *hlist; struct sock *sk = NULL; struct nlattr *bc; @@ -161,7 +159,7 @@ static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, num = 0; hlist = &hashinfo->ht[slot]; - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index bac9ba747bde..a327aa481df4 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -141,10 +141,9 @@ EXPORT_SYMBOL(rawv6_mh_filter_unregister); static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) { struct net *net = dev_net(skb->dev); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; const struct in6_addr *saddr; const struct in6_addr *daddr; + struct hlist_head *hlist; struct sock *sk; bool delivered = false; __u8 hash; @@ -155,7 +154,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) hash = raw_hashfunc(net, nexthdr); hlist = &raw_v6_hashinfo.ht[hash]; rcu_read_lock(); - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { int filtered; if (!raw_v6_match(net, sk, nexthdr, daddr, saddr, @@ -333,15 +332,14 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, u8 type, u8 code, int inner_offset, __be32 info) { struct net *net = dev_net(skb->dev); - struct hlist_nulls_head *hlist; - struct hlist_nulls_node *hnode; + struct hlist_head *hlist; struct sock *sk; int hash; hash = raw_hashfunc(net, nexthdr); hlist = &raw_v6_hashinfo.ht[hash]; rcu_read_lock(); - sk_nulls_for_each(sk, hnode, hlist) { + sk_for_each_rcu(sk, hlist) { /* Note: ipv6_hdr(skb) != skb->data */ const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data; -- cgit v1.2.3 From 3632679d9e4f879f49949bb5b050e0de553e4739 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Mon, 22 May 2023 14:08:20 +0200 Subject: ipv{4,6}/raw: fix output xfrm lookup wrt protocol With a raw socket bound to IPPROTO_RAW (ie with hdrincl enabled), the protocol field of the flow structure, build by raw_sendmsg() / rawv6_sendmsg()), is set to IPPROTO_RAW. This breaks the ipsec policy lookup when some policies are defined with a protocol in the selector. For ipv6, the sin6_port field from 'struct sockaddr_in6' could be used to specify the protocol. Just accept all values for IPPROTO_RAW socket. For ipv4, the sin_port field of 'struct sockaddr_in' could not be used without breaking backward compatibility (the value of this field was never checked). Let's add a new kind of control message, so that the userland could specify which protocol is used. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") CC: stable@vger.kernel.org Signed-off-by: Nicolas Dichtel Link: https://lore.kernel.org/r/20230522120820.1319391-1-nicolas.dichtel@6wind.com Signed-off-by: Paolo Abeni --- include/net/ip.h | 2 ++ include/uapi/linux/in.h | 1 + net/ipv4/ip_sockglue.c | 12 +++++++++++- net/ipv4/raw.c | 5 ++++- net/ipv6/raw.c | 3 ++- 5 files changed, 20 insertions(+), 3 deletions(-) (limited to 'net/ipv6/raw.c') diff --git a/include/net/ip.h b/include/net/ip.h index c3fffaa92d6e..acec504c469a 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -76,6 +76,7 @@ struct ipcm_cookie { __be32 addr; int oif; struct ip_options_rcu *opt; + __u8 protocol; __u8 ttl; __s16 tos; char priority; @@ -96,6 +97,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, ipcm->sockc.tsflags = inet->sk.sk_tsflags; ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; + ipcm->protocol = inet->inet_num; } #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb)) diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 4b7f2df66b99..e682ab628dfa 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -163,6 +163,7 @@ struct in_addr { #define IP_MULTICAST_ALL 49 #define IP_UNICAST_IF 50 #define IP_LOCAL_PORT_RANGE 51 +#define IP_PROTOCOL 52 #define MCAST_EXCLUDE 0 #define MCAST_INCLUDE 1 diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index b511ff0adc0a..8e97d8d4cc9d 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -317,7 +317,14 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, ipc->tos = val; ipc->priority = rt_tos2priority(ipc->tos); break; - + case IP_PROTOCOL: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) + return -EINVAL; + val = *(int *)CMSG_DATA(cmsg); + if (val < 1 || val > 255) + return -EINVAL; + ipc->protocol = val; + break; default: return -EINVAL; } @@ -1761,6 +1768,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_LOCAL_PORT_RANGE: val = inet->local_port_range.hi << 16 | inet->local_port_range.lo; break; + case IP_PROTOCOL: + val = inet_sk(sk)->inet_num; + break; default: sockopt_release_sock(sk); return -ENOPROTOOPT; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index ff712bf2a98d..eadf1c9ef7e4 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -532,6 +532,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } ipcm_init_sk(&ipc, inet); + /* Keep backward compat */ + if (hdrincl) + ipc.protocol = IPPROTO_RAW; if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); @@ -599,7 +602,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, RT_SCOPE_UNIVERSE, - hdrincl ? IPPROTO_RAW : sk->sk_protocol, + hdrincl ? ipc.protocol : sk->sk_protocol, inet_sk_flowi_flags(sk) | (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0, sk->sk_uid); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 7d0adb612bdd..44ee7a2e72ac 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -793,7 +793,8 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (!proto) proto = inet->inet_num; - else if (proto != inet->inet_num) + else if (proto != inet->inet_num && + inet->inet_num != IPPROTO_RAW) return -EINVAL; if (proto > 255) -- cgit v1.2.3