From 034dd340b08be1f2f0477ad16131d609f9dbd53c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 30 Aug 2026 09:22:00 -0700 Subject: Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Fix error output of boot instance creation failure Currently if a boot instance creation fails, instead of printing out the name of the instance that failed, it prints "(null)". That is because it prints "cur_str" that had already been processed by strsep(). Print the saved name instead. While at it, print the error code of the failure. - Fix use-after-free for same named historgrams Histograms can be named so that they can be used in multiple events. But if the named histogram has a variable attached, the second event that uses the named histogram which duplicates it and needs to free the original after duplication leaves the old variable in place and still visible. If another histogram uses than variable, it will use the stale one which will try to reference the freed duplicate histogram and crash the kernel. Free the duplicate variables along with the duplicated histogram data. - Check return value of kthread_run() in event self test The events self tests uses a kthread for testing but does not check if it succeeded in creating a kthread. If the kthread creation were to fail, the code will still try to call kthread_stop() on the error returned. - Fix race between reading trace_pipe and updating subbuffer size If a user is reading the trace_pipe file at the same time they update the ring buffer sub-buffer size, can cause the trace_pipe read to read stale data. Add trace_access_lock() around updating the ring buffer sub-buffer size. - Fix eventfs_inode on failure path in creation of the events directory In the creation of the "events" directory, if after allocating the eventfs_inode a failure is detected, it calls cleanup_ei() which calls free_ei(). The free_ei() will test if eventfs_inode being freed has no children. It is a bug if it does. But on the failure case of the creation of the "events" directory, the children lists have not yet been initialized and the free will trigger a warning because list_empty() on an uninitialized list returns false. Move the initialization into init_ei() where it makes more sense and makes sure that a created eventfs_inode has its lists initialized upon creation. - Check return value of kthread_run() in ftrace direct sample code The sample code that shows how to use the ftrace direct calls does not test the return of kthread_run() to see if it succeeds. Return a failure if the kthread_run() doesn't succeed. - Clear user events state on fork in case of alloc failure On fork, the child gets a pointer to the parent's user events state. It makes a copy of it then updates the child's pointer to it. But if the allocation fails, the duplication function leaves the child with a pointer to its parent's descriptor. When the child cleans up its data, it will free the parent's descriptor while the parent is still using it. In the duplication function, set the child's user_event_mm to NULL before testing if the allocation succeeded, and when it exits it will not free the parent's descriptor. - Fix retry exhaustion in simple ring buffer reader swap simple_ring_buffer_swap_reader_page() starts with retry set to 8 and post-decrements it only after a failed link replacement. On the final attempt, a successful replacement leaves retry at zero, while a failed replacement leaves it at -1. But the check for success expects the retry value to be non-zero and exits with an error on zero. This is the opposite result. Fix it. - Fail nicely when the remote swap_reader_page() returns an error Currently, if the swap_reader_page() of a remote buffer fails, it triggers a WARN_ON_ONCE() and continues normally. Instead, have it exit with an error and a pr_warn() print instead of a full WARNING. * tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: ring-buffer: Stop remote reader update when page swap fails tracing: Fix retry exhaustion in simple ring buffer reader swap tracing/user_events: Clear copied tracing state before fork duplication samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify eventfs: Initialize ei->children and ei->list in init_ei() tracing: Fix use-after-free in trace_pipe read on sub-buffer order change tracing: Fix crash passing ERR_PTR to kthread_stop() tracing: Fix use-after-free with same-name named triggers tracing: Fix logged instance name on creation failure --- net/ipv6/syncookies.c | 289 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 289 insertions(+) create mode 100644 net/ipv6/syncookies.c (limited to 'net/ipv6/syncookies.c') diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c new file mode 100644 index 000000000..b581cb1ee --- /dev/null +++ b/net/ipv6/syncookies.c @@ -0,0 +1,289 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * IPv6 Syncookies implementation for the Linux kernel + * + * Authors: + * Glenn Griffin + * + * Based on IPv4 implementation by Andi Kleen + * linux/net/ipv4/syncookies.c + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#define COOKIEBITS 24 /* Upper bits store count */ +#define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1) + +static siphash_aligned_key_t syncookie6_secret[2]; + +/* RFC 2460, Section 8.3: + * [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..] + * + * Due to IPV6_MIN_MTU=1280 the lowest possible MSS is 1220, which allows + * using higher values than ipv4 tcp syncookies. + * The other values are chosen based on ethernet (1500 and 9k MTU), plus + * one that accounts for common encap (PPPoe) overhead. Table must be sorted. + */ +static __u16 const msstab[] = { + 1280 - 60, /* IPV6_MIN_MTU - 60 */ + 1480 - 60, + 1500 - 60, + 9000 - 60, +}; + +static u32 cookie_hash(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __be16 sport, __be16 dport, u32 count, int c) +{ + const struct { + struct in6_addr saddr; + struct in6_addr daddr; + u32 count; + __be16 sport; + __be16 dport; + } __aligned(SIPHASH_ALIGNMENT) combined = { + .saddr = *saddr, + .daddr = *daddr, + .count = count, + .sport = sport, + .dport = dport + }; + + net_get_random_once(syncookie6_secret, sizeof(syncookie6_secret)); + return siphash(&combined, offsetofend(typeof(combined), dport), + &syncookie6_secret[c]); +} + +static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __be16 sport, __be16 dport, __u32 sseq, + __u32 data) +{ + u32 count = tcp_cookie_time(); + return (cookie_hash(saddr, daddr, sport, dport, 0, 0) + + sseq + (count << COOKIEBITS) + + ((cookie_hash(saddr, daddr, sport, dport, count, 1) + data) + & COOKIEMASK)); +} + +static __u32 check_tcp_syn_cookie(__u32 cookie, const struct in6_addr *saddr, + const struct in6_addr *daddr, __be16 sport, + __be16 dport, __u32 sseq) +{ + __u32 diff, count = tcp_cookie_time(); + + cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq; + + diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS); + if (diff >= MAX_SYNCOOKIE_AGE) + return (__u32)-1; + + return (cookie - + cookie_hash(saddr, daddr, sport, dport, count - diff, 1)) + & COOKIEMASK; +} + +u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, + const struct tcphdr *th, __u16 *mssp) +{ + int mssind; + const __u16 mss = *mssp; + + for (mssind = ARRAY_SIZE(msstab) - 1; mssind ; mssind--) + if (mss >= msstab[mssind]) + break; + + *mssp = msstab[mssind]; + + return secure_tcp_syn_cookie(&iph->saddr, &iph->daddr, th->source, + th->dest, ntohl(th->seq), mssind); +} +EXPORT_SYMBOL_GPL(__cookie_v6_init_sequence); + +__u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mssp) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); + + return __cookie_v6_init_sequence(iph, th, mssp); +} + +int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th) +{ + __u32 cookie = ntohl(th->ack_seq) - 1; + __u32 seq = ntohl(th->seq) - 1; + __u32 mssind; + + mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr, + th->source, th->dest, seq); + + return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0; +} +EXPORT_SYMBOL_GPL(__cookie_v6_check); + +static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + struct tcp_options_received tcp_opt; + u32 tsoff = 0; + int mss; + + if (tcp_synq_no_recent_overflow(sk)) + goto out; + + mss = __cookie_v6_check(ipv6_hdr(skb), tcp_hdr(skb)); + if (!mss) { + __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESFAILED); + goto out; + } + + __NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESRECV); + + /* check for timestamp cookie support */ + memset(&tcp_opt, 0, sizeof(tcp_opt)); + tcp_parse_options(net, skb, &tcp_opt, 0, NULL); + + if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { + union tcp_seq_and_ts_off st; + + st = secure_tcpv6_seq_and_ts_off(net, + ipv6_hdr(skb)->daddr.s6_addr32, + ipv6_hdr(skb)->saddr.s6_addr32, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); + tsoff = st.ts_off; + tcp_opt.rcv_tsecr -= tsoff; + } + + if (!cookie_timestamp_decode(net, &tcp_opt)) + goto out; + + return cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, sk, skb, + &tcp_opt, mss, tsoff); +out: + return ERR_PTR(-EINVAL); +} + +struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) +{ + const struct tcphdr *th = tcp_hdr(skb); + struct ipv6_pinfo *np = inet6_sk(sk); + struct tcp_sock *tp = tcp_sk(sk); + struct inet_request_sock *ireq; + struct net *net = sock_net(sk); + struct request_sock *req; + struct dst_entry *dst; + struct sock *ret = sk; + __u8 rcv_wscale; + int full_space; + SKB_DR(reason); + + if (!READ_ONCE(net->ipv4.sysctl_tcp_syncookies) || + !th->ack || th->rst) + goto out; + + if (cookie_bpf_ok(skb)) { + req = cookie_bpf_check(sk, skb); + } else { + req = cookie_tcp_check(net, sk, skb); + if (IS_ERR(req)) + goto out; + } + if (!req) { + SKB_DR_SET(reason, NO_SOCKET); + goto out_drop; + } + + ireq = inet_rsk(req); + + ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; + ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; + + if (security_inet_conn_request(sk, skb, req)) { + SKB_DR_SET(reason, SECURITY_HOOK); + goto out_free; + } + + if (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) || + np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || + np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { + refcount_inc(&skb->users); + ireq->pktopts = skb; + } + + /* So that link locals have meaning */ + if (!sk->sk_bound_dev_if && + ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) + ireq->ir_iif = tcp_v6_iif(skb); + + tcp_ao_syncookie(sk, skb, req, AF_INET6); + + /* + * We need to lookup the dst_entry to get the correct window size. + * This is taken from tcp_v6_syn_recv_sock. Somebody please enlighten + * me if there is a preferred way. + */ + { + struct in6_addr *final_p, final; + struct flowi6 fl6; + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_TCP; + fl6.daddr = ireq->ir_v6_rmt_addr; + final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final); + fl6.saddr = ireq->ir_v6_loc_addr; + fl6.flowi6_oif = ireq->ir_iif; + fl6.flowi6_mark = ireq->ir_mark; + fl6.fl6_dport = ireq->ir_rmt_port; + fl6.fl6_sport = inet_sk(sk)->inet_sport; + fl6.flowi6_uid = sk_uid(sk); + security_req_classify_flow(req, flowi6_to_flowi_common(&fl6)); + + ip6_ecmp_set_mp_hash(net, &fl6, tcp_rsk(req)->txhash); + + dst = ip6_dst_lookup_flow(net, sk, &fl6, final_p); + if (IS_ERR(dst)) { + SKB_DR_SET(reason, IP_OUTNOROUTES); + goto out_free; + } + } + + req->rsk_window_clamp = READ_ONCE(tp->window_clamp) ? :dst_metric(dst, RTAX_WINDOW); + /* limit the window selection if the user enforce a smaller rx buffer */ + full_space = tcp_full_space(sk); + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && + (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0)) + req->rsk_window_clamp = full_space; + + tcp_select_initial_window(sk, full_space, req->mss, + &req->rsk_rcv_wnd, &req->rsk_window_clamp, + ireq->wscale_ok, &rcv_wscale, + dst_metric(dst, RTAX_INITRWND)); + + /* req->syncookie is set true only if ACK is validated + * by BPF kfunc, then, rcv_wscale is already configured. + */ + if (!req->syncookie) + ireq->rcv_wscale = rcv_wscale; + ireq->ecn_ok &= cookie_ecn_ok(net, dst); + tcp_rsk(req)->accecn_ok = ireq->ecn_ok && cookie_accecn_ok(th); + + ret = tcp_get_cookie_sock(sk, skb, req, dst); + if (!ret) { + SKB_DR_SET(reason, NO_SOCKET); + goto out_drop; + } +out: + return ret; +out_free: + reqsk_free(req); +out_drop: + sk_skb_reason_drop(sk, skb, reason); + return NULL; +} -- cgit v1.3.1