x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 408 insertions, 0 deletions

diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
new file mode 100644
index 000000000..b111b51d6
--- /dev/null
+++ b/net/ipv6/inet6_hashtables.c
@@ -0,0 +1,408 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		Generic INET6 transport hashtables
+ *
+ * Authors:	Lotsa people, from code originally in tcp, generalised here
+ *		by Arnaldo Carvalho de Melo <acme@mandriva.com>
+ */
+
+#include <linux/module.h>
+#include <linux/random.h>
+
+#include <net/addrconf.h>
+#include <net/hotdata.h>
+#include <net/inet_connection_sock.h>
+#include <net/inet_hashtables.h>
+#include <net/inet6_hashtables.h>
+#include <net/secure_seq.h>
+#include <net/ip.h>
+#include <net/sock_reuseport.h>
+#include <net/tcp.h>
+
+void inet6_init_ehash_secret(void)
+{
+	net_get_random_sleepable_once(&inet6_ehash_secret,
+				      sizeof(inet6_ehash_secret));
+	net_get_random_sleepable_once(&tcp_ipv6_hash_secret,
+				      sizeof(tcp_ipv6_hash_secret));
+}
+
+u32 inet6_ehashfn(const struct net *net,
+		  const struct in6_addr *laddr, const u16 lport,
+		  const struct in6_addr *faddr, const __be16 fport)
+{
+	u32 a, b, c;
+
+	/*
+	 * Please look at jhash() implementation for reference.
+	 * Hash laddr + faddr + lport/fport + net_hash_mix.
+	 * Notes:
+	 * We combine laddr[0] (high order 32 bits of local address)
+	 * with net_hash_mix() to hash a multiple of 3 words.
+	 *
+	 * We do not include JHASH_INITVAL + 36 contribution
+	 * to initial values of a, b, c.
+	 */
+
+	a = b = c = tcp_ipv6_hash_secret;
+
+	a += (__force u32)laddr->s6_addr32[0] ^ net_hash_mix(net);
+	b += (__force u32)laddr->s6_addr32[1];
+	c += (__force u32)laddr->s6_addr32[2];
+	__jhash_mix(a, b, c);
+
+	a += (__force u32)laddr->s6_addr32[3];
+	b += (__force u32)faddr->s6_addr32[0];
+	c += (__force u32)faddr->s6_addr32[1];
+	__jhash_mix(a, b, c);
+
+	a += (__force u32)faddr->s6_addr32[2];
+	b += (__force u32)faddr->s6_addr32[3];
+	c += (__force u32)fport;
+	__jhash_final(a, b, c);
+
+	/* Note: We need to add @lport instead of fully hashing it.
+	 * See commits 9544d60a2605 ("inet: change lport contribution
+	 * to inet_ehashfn() and inet6_ehashfn()") and d4438ce68bf1
+	 * ("inet: call inet6_ehashfn() once from inet6_hash_connect()")
+	 * for references.
+	 */
+	return lport + c;
+}
+EXPORT_SYMBOL_GPL(inet6_ehashfn);
+
+/*
+ * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so
+ * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM
+ *
+ * The sockhash lock must be held as a reader here.
+ */
+struct sock *__inet6_lookup_established(const struct net *net,
+					const struct in6_addr *saddr,
+					const __be16 sport,
+					const struct in6_addr *daddr,
+					const u16 hnum,
+					const int dif, const int sdif)
+{
+	const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
+	const struct hlist_nulls_node *node;
+	struct inet_ehash_bucket *head;
+	struct inet_hashinfo *hashinfo;
+	unsigned int hash, slot;
+	struct sock *sk;
+
+	hashinfo = net->ipv4.tcp_death_row.hashinfo;
+	hash = inet6_ehashfn(net, daddr, hnum, saddr, sport);
+	slot = hash & hashinfo->ehash_mask;
+	head = &hashinfo->ehash[slot];
+begin:
+	sk_nulls_for_each_rcu(sk, node, &head->chain) {
+		if (sk->sk_hash != hash)
+			continue;
+		if (!inet6_match(net, sk, saddr, daddr, ports, dif, sdif))
+			continue;
+		if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
+			goto out;
+
+		if (unlikely(!inet6_match(net, sk, saddr, daddr, ports, dif, sdif))) {
+			sock_gen_put(sk);
+			goto begin;
+		}
+		goto found;
+	}
+	if (get_nulls_value(node) != slot)
+		goto begin;
+out:
+	sk = NULL;
+found:
+	return sk;
+}
+EXPORT_SYMBOL(__inet6_lookup_established);
+
+static inline int compute_score(struct sock *sk, const struct net *net,
+				const unsigned short hnum,
+				const struct in6_addr *daddr,
+				const int dif, const int sdif)
+{
+	int score = -1;
+
+	if (net_eq(sock_net(sk), net) &&
+	    READ_ONCE(inet_sk(sk)->inet_num) == hnum &&
+	    sk->sk_family == PF_INET6) {
+		if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
+			return -1;
+
+		if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
+			return -1;
+
+		score =  sk->sk_bound_dev_if ? 2 : 1;
+		if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
+			score++;
+	}
+	return score;
+}
+
+/**
+ * inet6_lookup_reuseport() - execute reuseport logic on AF_INET6 socket if necessary.
+ * @net: network namespace.
+ * @sk: AF_INET6 socket, must be in TCP_LISTEN state for TCP or TCP_CLOSE for UDP.
+ * @skb: context for a potential SK_REUSEPORT program.
+ * @doff: header offset.
+ * @saddr: source address.
+ * @sport: source port.
+ * @daddr: destination address.
+ * @hnum: destination port in host byte order.
+ * @ehashfn: hash function used to generate the fallback hash.
+ *
+ * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to
+ *         the selected sock or an error.
+ */
+struct sock *inet6_lookup_reuseport(const 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,
+				    inet6_ehashfn_t *ehashfn)
+{
+	struct sock *reuse_sk = NULL;
+	u32 phash;
+
+	if (sk->sk_reuseport) {
+		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;
+}
+EXPORT_SYMBOL_GPL(inet6_lookup_reuseport);
+
+/* called with rcu_read_lock() */
+static struct sock *inet6_lhash2_lookup(const struct net *net,
+		struct inet_listen_hashbucket *ilb2,
+		struct sk_buff *skb, int doff,
+		const struct in6_addr *saddr,
+		const __be16 sport, const struct in6_addr *daddr,
+		const unsigned short hnum, const int dif, const int sdif)
+{
+	struct sock *sk, *result = NULL;
+	struct hlist_nulls_node *node;
+	int score, hiscore = 0;
+
+	sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) {
+		score = compute_score(sk, net, hnum, daddr, dif, sdif);
+		if (score > hiscore) {
+			result = inet6_lookup_reuseport(net, sk, skb, doff,
+							saddr, sport, daddr, hnum, inet6_ehashfn);
+			if (result)
+				return result;
+
+			result = sk;
+			hiscore = score;
+		}
+	}
+
+	return result;
+}
+
+struct sock *inet6_lookup_run_sk_lookup(const struct net *net,
+					int protocol,
+					struct sk_buff *skb, int doff,
+					const struct in6_addr *saddr,
+					const __be16 sport,
+					const struct in6_addr *daddr,
+					const u16 hnum, const int dif,
+					inet6_ehashfn_t *ehashfn)
+{
+	struct sock *sk, *reuse_sk;
+	bool no_reuseport;
+
+	no_reuseport = bpf_sk_lookup_run_v6(net, protocol, saddr, sport,
+					    daddr, hnum, dif, &sk);
+	if (no_reuseport || IS_ERR_OR_NULL(sk))
+		return sk;
+
+	reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff,
+					  saddr, sport, daddr, hnum, ehashfn);
+	if (reuse_sk)
+		sk = reuse_sk;
+	return sk;
+}
+EXPORT_SYMBOL_GPL(inet6_lookup_run_sk_lookup);
+
+struct sock *inet6_lookup_listener(const struct net *net,
+				   struct sk_buff *skb, int doff,
+				   const struct in6_addr *saddr,
+				   const __be16 sport,
+				   const struct in6_addr *daddr,
+				   const unsigned short hnum,
+				   const int dif, const int sdif)
+{
+	struct inet_listen_hashbucket *ilb2;
+	struct inet_hashinfo *hashinfo;
+	struct sock *result = NULL;
+	unsigned int hash2;
+
+	/* Lookup redirect from BPF */
+	if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
+		result = inet6_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff,
+						    saddr, sport, daddr, hnum, dif,
+						    inet6_ehashfn);
+		if (result)
+			goto done;
+	}
+
+	hashinfo = net->ipv4.tcp_death_row.hashinfo;
+	hash2 = ipv6_portaddr_hash(net, daddr, hnum);
+	ilb2 = inet_lhash2_bucket(hashinfo, hash2);
+
+	result = inet6_lhash2_lookup(net, ilb2, skb, doff,
+				     saddr, sport, daddr, hnum,
+				     dif, sdif);
+	if (result)
+		goto done;
+
+	/* Lookup lhash2 with in6addr_any */
+	hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
+	ilb2 = inet_lhash2_bucket(hashinfo, hash2);
+
+	result = inet6_lhash2_lookup(net, ilb2, skb, doff,
+				     saddr, sport, &in6addr_any, hnum,
+				     dif, sdif);
+done:
+	if (IS_ERR(result))
+		return NULL;
+	return result;
+}
+EXPORT_SYMBOL_GPL(inet6_lookup_listener);
+
+struct sock *inet6_lookup(const 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,
+			  const int dif)
+{
+	struct sock *sk;
+	bool refcounted;
+
+	sk = __inet6_lookup(net, skb, doff, saddr, sport, daddr,
+			    ntohs(dport), dif, 0, &refcounted);
+	if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt))
+		sk = NULL;
+	return sk;
+}
+EXPORT_SYMBOL_GPL(inet6_lookup);
+
+static int __inet6_check_established(struct inet_timewait_death_row *death_row,
+				     struct sock *sk, const __u16 lport,
+				     struct inet_timewait_sock **twp,
+				     bool rcu_lookup,
+				     u32 hash)
+{
+	struct inet_hashinfo *hinfo = death_row->hashinfo;
+	struct inet_sock *inet = inet_sk(sk);
+	const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr;
+	const struct in6_addr *saddr = &sk->sk_v6_daddr;
+	const int dif = sk->sk_bound_dev_if;
+	struct net *net = sock_net(sk);
+	const int sdif = l3mdev_master_ifindex_by_index(net, dif);
+	const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
+	struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
+	struct inet_timewait_sock *tw = NULL;
+	const struct hlist_nulls_node *node;
+	struct sock *sk2;
+	spinlock_t *lock;
+
+	if (rcu_lookup) {
+		sk_nulls_for_each(sk2, node, &head->chain) {
+			if (sk2->sk_hash != hash ||
+			    !inet6_match(net, sk2, saddr, daddr,
+					 ports, dif, sdif))
+				continue;
+			if (sk2->sk_state == TCP_TIME_WAIT)
+				break;
+			return -EADDRNOTAVAIL;
+		}
+		return 0;
+	}
+
+	lock = inet_ehash_lockp(hinfo, hash);
+	spin_lock(lock);
+
+	sk_nulls_for_each(sk2, node, &head->chain) {
+		if (sk2->sk_hash != hash)
+			continue;
+
+		if (likely(inet6_match(net, sk2, saddr, daddr, ports,
+				       dif, sdif))) {
+			if (sk2->sk_state == TCP_TIME_WAIT) {
+				tw = inet_twsk(sk2);
+				if (tcp_twsk_unique(sk, sk2, twp))
+					break;
+			}
+			goto not_unique;
+		}
+	}
+
+	/* Must record num and sport now. Otherwise we will see
+	 * in hash table socket with a funny identity.
+	 */
+	inet->inet_num = lport;
+	inet->inet_sport = htons(lport);
+	sk->sk_hash = hash;
+	WARN_ON(!sk_unhashed(sk));
+	__sk_nulls_add_node_rcu(sk, &head->chain);
+	if (tw) {
+		sk_nulls_del_node_init_rcu((struct sock *)tw);
+		__NET_INC_STATS(net, LINUX_MIB_TIMEWAITRECYCLED);
+	}
+	spin_unlock(lock);
+	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
+
+	if (twp) {
+		*twp = tw;
+	} else if (tw) {
+		/* Silly. Should hash-dance instead... */
+		inet_twsk_deschedule_put(tw);
+	}
+	return 0;
+
+not_unique:
+	spin_unlock(lock);
+	return -EADDRNOTAVAIL;
+}
+
+static u64 inet6_sk_port_offset(const struct sock *sk)
+{
+	const struct inet_sock *inet = inet_sk(sk);
+
+	return secure_ipv6_port_ephemeral(sk->sk_v6_rcv_saddr.s6_addr32,
+					  sk->sk_v6_daddr.s6_addr32,
+					  inet->inet_dport);
+}
+
+int inet6_hash_connect(struct inet_timewait_death_row *death_row,
+		       struct sock *sk)
+{
+	const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr;
+	const struct in6_addr *saddr = &sk->sk_v6_daddr;
+	const struct inet_sock *inet = inet_sk(sk);
+	const struct net *net = sock_net(sk);
+	u64 port_offset = 0;
+	u32 hash_port0;
+
+	if (!inet_sk(sk)->inet_num)
+		port_offset = inet6_sk_port_offset(sk);
+
+	inet6_init_ehash_secret();
+
+	hash_port0 = inet6_ehashfn(net, daddr, 0, saddr, inet->inet_dport);
+
+	return __inet_hash_connect(death_row, sk, port_offset, hash_port0,
+				   __inet6_check_established);
+}
+EXPORT_SYMBOL_GPL(inet6_hash_connect);