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, 108 insertions, 0 deletions

diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h
new file mode 100644
index 000000000..ab21d032f
--- /dev/null
+++ b/net/openvswitch/conntrack.h
@@ -0,0 +1,108 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2015 Nicira, Inc.
+ */
+
+#ifndef OVS_CONNTRACK_H
+#define OVS_CONNTRACK_H 1
+
+#include "flow.h"
+
+struct ovs_conntrack_info;
+struct ovs_ct_limit_info;
+enum ovs_key_attr;
+
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+int ovs_ct_init(struct net *);
+void ovs_ct_exit_start(struct net *net);
+void ovs_ct_exit_finish(struct net *net);
+bool ovs_ct_verify(struct net *, enum ovs_key_attr attr);
+int ovs_ct_copy_action(struct net *, const struct nlattr *,
+		       const struct sw_flow_key *, struct sw_flow_actions **,
+		       bool log);
+int ovs_ct_action_to_attr(const struct ovs_conntrack_info *, struct sk_buff *);
+
+int ovs_ct_execute(struct net *, struct sk_buff *, struct sw_flow_key *,
+		   const struct ovs_conntrack_info *);
+int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key);
+
+void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key,
+		     bool post_ct);
+int ovs_ct_put_key(const struct sw_flow_key *swkey,
+		   const struct sw_flow_key *output, struct sk_buff *skb);
+void ovs_ct_free_action(const struct nlattr *a);
+
+#define CT_SUPPORTED_MASK (OVS_CS_F_NEW | OVS_CS_F_ESTABLISHED | \
+			   OVS_CS_F_RELATED | OVS_CS_F_REPLY_DIR | \
+			   OVS_CS_F_INVALID | OVS_CS_F_TRACKED | \
+			   OVS_CS_F_SRC_NAT | OVS_CS_F_DST_NAT)
+#else
+#include <linux/errno.h>
+
+static inline int ovs_ct_init(struct net *net) { return 0; }
+
+static inline void ovs_ct_exit_start(struct net *net) { }
+static inline void ovs_ct_exit_finish(struct net *net) { }
+
+static inline bool ovs_ct_verify(struct net *net, int attr)
+{
+	return false;
+}
+
+static inline int ovs_ct_copy_action(struct net *net, const struct nlattr *nla,
+				     const struct sw_flow_key *key,
+				     struct sw_flow_actions **acts, bool log)
+{
+	return -ENOTSUPP;
+}
+
+static inline int ovs_ct_action_to_attr(const struct ovs_conntrack_info *info,
+					struct sk_buff *skb)
+{
+	return -ENOTSUPP;
+}
+
+static inline int ovs_ct_execute(struct net *net, struct sk_buff *skb,
+				 struct sw_flow_key *key,
+				 const struct ovs_conntrack_info *info)
+{
+	kfree_skb(skb);
+	return -ENOTSUPP;
+}
+
+static inline int ovs_ct_clear(struct sk_buff *skb,
+			       struct sw_flow_key *key)
+{
+	return -ENOTSUPP;
+}
+
+static inline void ovs_ct_fill_key(const struct sk_buff *skb,
+				   struct sw_flow_key *key,
+				   bool post_ct)
+{
+	key->ct_state = 0;
+	key->ct_zone = 0;
+	key->ct.mark = 0;
+	memset(&key->ct.labels, 0, sizeof(key->ct.labels));
+	/* Clear 'ct_orig_proto' to mark the non-existence of original
+	 * direction key fields.
+	 */
+	key->ct_orig_proto = 0;
+}
+
+static inline int ovs_ct_put_key(const struct sw_flow_key *swkey,
+				 const struct sw_flow_key *output,
+				 struct sk_buff *skb)
+{
+	return 0;
+}
+
+static inline void ovs_ct_free_action(const struct nlattr *a) { }
+
+#define CT_SUPPORTED_MASK 0
+#endif /* CONFIG_NF_CONNTRACK */
+
+#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
+extern struct genl_family dp_ct_limit_genl_family;
+#endif
+#endif /* ovs_conntrack.h */