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, 159 insertions, 0 deletions

diff --git a/include/net/llc.h b/include/net/llc.h
new file mode 100644
index 000000000..029ba8a22
--- /dev/null
+++ b/include/net/llc.h
@@ -0,0 +1,159 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef LLC_H
+#define LLC_H
+/*
+ * Copyright (c) 1997 by Procom Technology, Inc.
+ * 		 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br>
+ */
+
+#include <linux/if.h>
+#include <linux/if_ether.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/rculist_nulls.h>
+#include <linux/hash.h>
+#include <linux/jhash.h>
+
+#include <linux/atomic.h>
+
+struct net_device;
+struct packet_type;
+struct sk_buff;
+
+struct llc_addr {
+	unsigned char lsap;
+	unsigned char mac[IFHWADDRLEN];
+};
+
+#define LLC_SAP_STATE_INACTIVE	1
+#define LLC_SAP_STATE_ACTIVE	2
+
+#define LLC_SK_DEV_HASH_BITS 6
+#define LLC_SK_DEV_HASH_ENTRIES (1<<LLC_SK_DEV_HASH_BITS)
+
+#define LLC_SK_LADDR_HASH_BITS 6
+#define LLC_SK_LADDR_HASH_ENTRIES (1<<LLC_SK_LADDR_HASH_BITS)
+
+/**
+ * struct llc_sap - Defines the SAP component
+ *
+ * @station - station this sap belongs to
+ * @state - sap state
+ * @p_bit - only lowest-order bit used
+ * @f_bit - only lowest-order bit used
+ * @laddr - SAP value in this 'lsap'
+ * @node - entry in station sap_list
+ * @sk_list - LLC sockets this one manages
+ */
+struct llc_sap {
+	unsigned char	 state;
+	unsigned char	 p_bit;
+	unsigned char	 f_bit;
+	refcount_t		 refcnt;
+	int		 (*rcv_func)(struct sk_buff *skb,
+				     struct net_device *dev,
+				     struct packet_type *pt,
+				     struct net_device *orig_dev);
+	struct llc_addr	 laddr;
+	struct list_head node;
+	spinlock_t sk_lock;
+	int sk_count;
+	struct hlist_nulls_head sk_laddr_hash[LLC_SK_LADDR_HASH_ENTRIES];
+	struct hlist_head sk_dev_hash[LLC_SK_DEV_HASH_ENTRIES];
+	struct rcu_head rcu;
+};
+
+static inline
+struct hlist_head *llc_sk_dev_hash(struct llc_sap *sap, int ifindex)
+{
+	u32 bucket = hash_32(ifindex, LLC_SK_DEV_HASH_BITS);
+
+	return &sap->sk_dev_hash[bucket];
+}
+
+static inline
+u32 llc_sk_laddr_hashfn(struct llc_sap *sap, const struct llc_addr *laddr)
+{
+	return hash_32(jhash(laddr->mac, sizeof(laddr->mac), 0),
+		       LLC_SK_LADDR_HASH_BITS);
+}
+
+static inline
+struct hlist_nulls_head *llc_sk_laddr_hash(struct llc_sap *sap,
+					   const struct llc_addr *laddr)
+{
+	return &sap->sk_laddr_hash[llc_sk_laddr_hashfn(sap, laddr)];
+}
+
+#define LLC_DEST_INVALID         0      /* Invalid LLC PDU type */
+#define LLC_DEST_SAP             1      /* Type 1 goes here */
+#define LLC_DEST_CONN            2      /* Type 2 goes here */
+
+extern struct list_head llc_sap_list;
+
+int llc_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
+	    struct net_device *orig_dev);
+
+int llc_mac_hdr_init(struct sk_buff *skb, const unsigned char *sa,
+		     const unsigned char *da);
+
+void llc_add_pack(int type,
+		  void (*handler)(struct llc_sap *sap, struct sk_buff *skb));
+void llc_remove_pack(int type);
+
+void llc_set_station_handler(void (*handler)(struct sk_buff *skb));
+
+struct llc_sap *llc_sap_open(unsigned char lsap,
+			     int (*rcv)(struct sk_buff *skb,
+					struct net_device *dev,
+					struct packet_type *pt,
+					struct net_device *orig_dev));
+static inline void llc_sap_hold(struct llc_sap *sap)
+{
+	refcount_inc(&sap->refcnt);
+}
+
+static inline bool llc_sap_hold_safe(struct llc_sap *sap)
+{
+	return refcount_inc_not_zero(&sap->refcnt);
+}
+
+void llc_sap_close(struct llc_sap *sap);
+
+static inline void llc_sap_put(struct llc_sap *sap)
+{
+	if (refcount_dec_and_test(&sap->refcnt))
+		llc_sap_close(sap);
+}
+
+struct llc_sap *llc_sap_find(unsigned char sap_value);
+
+int llc_build_and_send_ui_pkt(struct llc_sap *sap, struct sk_buff *skb,
+			      const unsigned char *dmac, unsigned char dsap);
+
+void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb);
+void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb);
+
+void llc_station_init(void);
+void llc_station_exit(void);
+
+#ifdef CONFIG_PROC_FS
+int llc_proc_init(void);
+void llc_proc_exit(void);
+#else
+#define llc_proc_init()	(0)
+#define llc_proc_exit()	do { } while(0)
+#endif /* CONFIG_PROC_FS */
+#ifdef CONFIG_SYSCTL
+int llc_sysctl_init(void);
+void llc_sysctl_exit(void);
+
+extern int sysctl_llc2_ack_timeout;
+extern int sysctl_llc2_busy_timeout;
+extern int sysctl_llc2_p_timeout;
+extern int sysctl_llc2_rej_timeout;
+#else
+#define llc_sysctl_init() (0)
+#define llc_sysctl_exit() do { } while(0)
+#endif /* CONFIG_SYSCTL */
+#endif /* LLC_H */