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, 149 insertions, 0 deletions

diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h
new file mode 100644
index 000000000..41d9fc696
--- /dev/null
+++ b/include/net/ipv6_frag.h
@@ -0,0 +1,149 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _IPV6_FRAG_H
+#define _IPV6_FRAG_H
+#include <linux/icmpv6.h>
+#include <linux/kernel.h>
+#include <net/addrconf.h>
+#include <net/ipv6.h>
+#include <net/inet_frag.h>
+
+enum ip6_defrag_users {
+	IP6_DEFRAG_LOCAL_DELIVER,
+	IP6_DEFRAG_CONNTRACK_IN,
+	__IP6_DEFRAG_CONNTRACK_IN	= IP6_DEFRAG_CONNTRACK_IN + USHRT_MAX,
+	IP6_DEFRAG_CONNTRACK_OUT,
+	__IP6_DEFRAG_CONNTRACK_OUT	= IP6_DEFRAG_CONNTRACK_OUT + USHRT_MAX,
+	IP6_DEFRAG_CONNTRACK_BRIDGE_IN,
+	__IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX,
+};
+
+/*
+ *	Equivalent of ipv4 struct ip
+ */
+struct frag_queue {
+	struct inet_frag_queue	q;
+
+	int			iif;
+	__u16			nhoffset;
+	u8			ecn;
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+static inline void ip6frag_init(struct inet_frag_queue *q, const void *a)
+{
+	struct frag_queue *fq = container_of(q, struct frag_queue, q);
+	const struct frag_v6_compare_key *key = a;
+
+	q->key.v6 = *key;
+	fq->ecn = 0;
+}
+
+static inline u32 ip6frag_key_hashfn(const void *data, u32 len, u32 seed)
+{
+	return jhash2(data,
+		      sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static inline u32 ip6frag_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+	const struct inet_frag_queue *fq = data;
+
+	return jhash2((const u32 *)&fq->key.v6,
+		      sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static inline int
+ip6frag_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+	const struct frag_v6_compare_key *key = arg->key;
+	const struct inet_frag_queue *fq = ptr;
+
+	return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+static inline void
+ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq)
+{
+	struct net_device *dev = NULL;
+	struct sk_buff *head;
+	int refs = 1;
+
+	rcu_read_lock();
+	spin_lock(&fq->q.lock);
+
+	if (fq->q.flags & INET_FRAG_COMPLETE)
+		goto out;
+
+	fq->q.flags |= INET_FRAG_DROP;
+	inet_frag_kill(&fq->q, &refs);
+
+	/* Paired with the WRITE_ONCE() in fqdir_pre_exit(). */
+	if (READ_ONCE(fq->q.fqdir->dead)) {
+		inet_frag_queue_flush(&fq->q, 0);
+		goto out;
+	}
+
+	dev = dev_get_by_index_rcu(net, fq->iif);
+	if (!dev)
+		goto out;
+
+	__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
+	__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
+
+	/* Don't send error if the first segment did not arrive. */
+	if (!(fq->q.flags & INET_FRAG_FIRST_IN))
+		goto out;
+
+	/* sk_buff::dev and sk_buff::rbnode are unionized. So we
+	 * pull the head out of the tree in order to be able to
+	 * deal with head->dev.
+	 */
+	head = inet_frag_pull_head(&fq->q);
+	if (!head)
+		goto out;
+
+	head->dev = dev;
+	spin_unlock(&fq->q.lock);
+
+	icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
+	kfree_skb_reason(head, SKB_DROP_REASON_FRAG_REASM_TIMEOUT);
+	goto out_rcu_unlock;
+
+out:
+	spin_unlock(&fq->q.lock);
+out_rcu_unlock:
+	rcu_read_unlock();
+	inet_frag_putn(&fq->q, refs);
+}
+
+/* Check if the upper layer header is truncated in the first fragment. */
+static inline bool
+ipv6frag_thdr_truncated(struct sk_buff *skb, int start, u8 *nexthdrp)
+{
+	u8 nexthdr = *nexthdrp;
+	__be16 frag_off;
+	int offset;
+
+	offset = ipv6_skip_exthdr(skb, start, &nexthdr, &frag_off);
+	if (offset < 0 || (frag_off & htons(IP6_OFFSET)))
+		return false;
+	switch (nexthdr) {
+	case NEXTHDR_TCP:
+		offset += sizeof(struct tcphdr);
+		break;
+	case NEXTHDR_UDP:
+		offset += sizeof(struct udphdr);
+		break;
+	case NEXTHDR_ICMP:
+		offset += sizeof(struct icmp6hdr);
+		break;
+	default:
+		offset += 1;
+	}
+	if (offset > skb->len)
+		return true;
+	return false;
+}
+
+#endif
+#endif