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, 361 insertions, 0 deletions

diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
new file mode 100644
index 000000000..abb332dee
--- /dev/null
+++ b/net/sched/act_nat.c
@@ -0,0 +1,361 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Stateless NAT actions
+ *
+ * Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au>
+ */
+
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netfilter.h>
+#include <linux/rtnetlink.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/tc_act/tc_nat.h>
+#include <net/act_api.h>
+#include <net/pkt_cls.h>
+#include <net/icmp.h>
+#include <net/ip.h>
+#include <net/netlink.h>
+#include <net/tc_act/tc_nat.h>
+#include <net/tcp.h>
+#include <net/udp.h>
+#include <net/tc_wrapper.h>
+
+static struct tc_action_ops act_nat_ops;
+
+static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = {
+	[TCA_NAT_PARMS]	= { .len = sizeof(struct tc_nat) },
+};
+
+static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
+			struct tc_action **a, struct tcf_proto *tp,
+			u32 flags, struct netlink_ext_ack *extack)
+{
+	struct tc_action_net *tn = net_generic(net, act_nat_ops.net_id);
+	bool bind = flags & TCA_ACT_FLAGS_BIND;
+	struct tcf_nat_parms *nparm, *oparm;
+	struct nlattr *tb[TCA_NAT_MAX + 1];
+	struct tcf_chain *goto_ch = NULL;
+	struct tc_nat *parm;
+	int ret = 0, err;
+	struct tcf_nat *p;
+	u32 index;
+
+	if (nla == NULL)
+		return -EINVAL;
+
+	err = nla_parse_nested_deprecated(tb, TCA_NAT_MAX, nla, nat_policy,
+					  NULL);
+	if (err < 0)
+		return err;
+
+	if (tb[TCA_NAT_PARMS] == NULL)
+		return -EINVAL;
+	parm = nla_data(tb[TCA_NAT_PARMS]);
+	index = parm->index;
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
+	if (!err) {
+		ret = tcf_idr_create_from_flags(tn, index, est, a, &act_nat_ops,
+						bind, flags);
+		if (ret) {
+			tcf_idr_cleanup(tn, index);
+			return ret;
+		}
+		ret = ACT_P_CREATED;
+	} else if (err > 0) {
+		if (bind)
+			return ACT_P_BOUND;
+		if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
+			tcf_idr_release(*a, bind);
+			return -EEXIST;
+		}
+	} else {
+		return err;
+	}
+	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (err < 0)
+		goto release_idr;
+
+	nparm = kzalloc_obj(*nparm);
+	if (!nparm) {
+		err = -ENOMEM;
+		goto release_idr;
+	}
+
+	nparm->old_addr = parm->old_addr;
+	nparm->new_addr = parm->new_addr;
+	nparm->mask = parm->mask;
+	nparm->flags = parm->flags;
+	nparm->action = parm->action;
+
+	p = to_tcf_nat(*a);
+
+	spin_lock_bh(&p->tcf_lock);
+	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
+	oparm = rcu_replace_pointer(p->parms, nparm, lockdep_is_held(&p->tcf_lock));
+	spin_unlock_bh(&p->tcf_lock);
+
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+
+	if (oparm)
+		kfree_rcu(oparm, rcu);
+
+	return ret;
+release_idr:
+	tcf_idr_release(*a, bind);
+	return err;
+}
+
+TC_INDIRECT_SCOPE int tcf_nat_act(struct sk_buff *skb,
+				  const struct tc_action *a,
+				  struct tcf_result *res)
+{
+	struct tcf_nat *p = to_tcf_nat(a);
+	struct tcf_nat_parms *parms;
+	struct iphdr *iph;
+	__be32 old_addr;
+	__be32 new_addr;
+	__be32 mask;
+	__be32 addr;
+	int egress;
+	int action;
+	int ihl;
+	int noff;
+
+	tcf_lastuse_update(&p->tcf_tm);
+	tcf_action_update_bstats(&p->common, skb);
+
+	parms = rcu_dereference_bh(p->parms);
+	action = parms->action;
+	if (unlikely(action == TC_ACT_SHOT))
+		goto drop;
+
+	old_addr = parms->old_addr;
+	new_addr = parms->new_addr;
+	mask = parms->mask;
+	egress = parms->flags & TCA_NAT_FLAG_EGRESS;
+
+	noff = skb_network_offset(skb);
+	if (!pskb_may_pull(skb, sizeof(*iph) + noff))
+		goto drop;
+
+	iph = ip_hdr(skb);
+
+	if (egress)
+		addr = iph->saddr;
+	else
+		addr = iph->daddr;
+
+	if (!((old_addr ^ addr) & mask)) {
+		if (skb_try_make_writable(skb, sizeof(*iph) + noff))
+			goto drop;
+
+		new_addr &= mask;
+		new_addr |= addr & ~mask;
+
+		/* Rewrite IP header */
+		iph = ip_hdr(skb);
+		if (egress)
+			iph->saddr = new_addr;
+		else
+			iph->daddr = new_addr;
+
+		csum_replace4(&iph->check, addr, new_addr);
+	} else if ((iph->frag_off & htons(IP_OFFSET)) ||
+		   iph->protocol != IPPROTO_ICMP) {
+		goto out;
+	}
+
+	ihl = iph->ihl * 4;
+
+	/* It would be nice to share code with stateful NAT. */
+	switch (iph->frag_off & htons(IP_OFFSET) ? 0 : iph->protocol) {
+	case IPPROTO_TCP:
+	{
+		struct tcphdr *tcph;
+
+		if (!pskb_may_pull(skb, ihl + sizeof(*tcph) + noff) ||
+		    skb_try_make_writable(skb, ihl + sizeof(*tcph) + noff))
+			goto drop;
+
+		tcph = (void *)(skb_network_header(skb) + ihl);
+		inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr,
+					 true);
+		break;
+	}
+	case IPPROTO_UDP:
+	{
+		struct udphdr *udph;
+
+		if (!pskb_may_pull(skb, ihl + sizeof(*udph) + noff) ||
+		    skb_try_make_writable(skb, ihl + sizeof(*udph) + noff))
+			goto drop;
+
+		udph = (void *)(skb_network_header(skb) + ihl);
+		if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
+			inet_proto_csum_replace4(&udph->check, skb, addr,
+						 new_addr, true);
+			if (!udph->check)
+				udph->check = CSUM_MANGLED_0;
+		}
+		break;
+	}
+	case IPPROTO_ICMP:
+	{
+		struct icmphdr *icmph;
+
+		if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + noff))
+			goto drop;
+
+		icmph = (void *)(skb_network_header(skb) + ihl);
+
+		if (!icmp_is_err(icmph->type))
+			break;
+
+		if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + sizeof(*iph) +
+					noff))
+			goto drop;
+
+		icmph = (void *)(skb_network_header(skb) + ihl);
+		iph = (void *)(icmph + 1);
+		if (egress)
+			addr = iph->daddr;
+		else
+			addr = iph->saddr;
+
+		if ((old_addr ^ addr) & mask)
+			break;
+
+		if (skb_try_make_writable(skb, ihl + sizeof(*icmph) +
+					  sizeof(*iph) + noff))
+			goto drop;
+
+		icmph = (void *)(skb_network_header(skb) + ihl);
+		iph = (void *)(icmph + 1);
+
+		new_addr &= mask;
+		new_addr |= addr & ~mask;
+
+		/* XXX Fix up the inner checksums. */
+		if (egress)
+			iph->daddr = new_addr;
+		else
+			iph->saddr = new_addr;
+
+		inet_proto_csum_replace4(&icmph->checksum, skb, addr, new_addr,
+					 false);
+		break;
+	}
+	default:
+		break;
+	}
+
+out:
+	return action;
+
+drop:
+	tcf_action_inc_drop_qstats(&p->common);
+	return TC_ACT_SHOT;
+}
+
+static int tcf_nat_dump(struct sk_buff *skb, struct tc_action *a,
+			int bind, int ref)
+{
+	unsigned char *b = skb_tail_pointer(skb);
+	const struct tcf_nat *p = to_tcf_nat(a);
+	const struct tcf_nat_parms *parms;
+	struct tc_nat opt = {
+		.index    = p->tcf_index,
+		.refcnt   = refcount_read(&p->tcf_refcnt) - ref,
+		.bindcnt  = atomic_read(&p->tcf_bindcnt) - bind,
+	};
+	struct tcf_t t;
+
+	rcu_read_lock();
+
+	parms = rcu_dereference(p->parms);
+
+	opt.action = parms->action;
+	opt.old_addr = parms->old_addr;
+	opt.new_addr = parms->new_addr;
+	opt.mask = parms->mask;
+	opt.flags = parms->flags;
+
+	if (nla_put(skb, TCA_NAT_PARMS, sizeof(opt), &opt))
+		goto nla_put_failure;
+
+	tcf_tm_dump(&t, &p->tcf_tm);
+	if (nla_put_64bit(skb, TCA_NAT_TM, sizeof(t), &t, TCA_NAT_PAD))
+		goto nla_put_failure;
+	rcu_read_unlock();
+
+	return skb->len;
+
+nla_put_failure:
+	rcu_read_unlock();
+	nlmsg_trim(skb, b);
+	return -1;
+}
+
+static void tcf_nat_cleanup(struct tc_action *a)
+{
+	struct tcf_nat *p = to_tcf_nat(a);
+	struct tcf_nat_parms *parms;
+
+	parms = rcu_dereference_protected(p->parms, 1);
+	if (parms)
+		kfree_rcu(parms, rcu);
+}
+
+static struct tc_action_ops act_nat_ops = {
+	.kind		=	"nat",
+	.id		=	TCA_ID_NAT,
+	.owner		=	THIS_MODULE,
+	.act		=	tcf_nat_act,
+	.dump		=	tcf_nat_dump,
+	.init		=	tcf_nat_init,
+	.cleanup	=	tcf_nat_cleanup,
+	.size		=	sizeof(struct tcf_nat),
+};
+MODULE_ALIAS_NET_ACT("nat");
+
+static __net_init int nat_init_net(struct net *net)
+{
+	struct tc_action_net *tn = net_generic(net, act_nat_ops.net_id);
+
+	return tc_action_net_init(net, tn, &act_nat_ops);
+}
+
+static void __net_exit nat_exit_net(struct list_head *net_list)
+{
+	tc_action_net_exit(net_list, act_nat_ops.net_id);
+}
+
+static struct pernet_operations nat_net_ops = {
+	.init = nat_init_net,
+	.exit_batch = nat_exit_net,
+	.id   = &act_nat_ops.net_id,
+	.size = sizeof(struct tc_action_net),
+};
+
+MODULE_DESCRIPTION("Stateless NAT actions");
+MODULE_LICENSE("GPL");
+
+static int __init nat_init_module(void)
+{
+	return tcf_register_action(&act_nat_ops, &nat_net_ops);
+}
+
+static void __exit nat_cleanup_module(void)
+{
+	tcf_unregister_action(&act_nat_ops, &nat_net_ops);
+}
+
+module_init(nat_init_module);
+module_exit(nat_cleanup_module);