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, 186 insertions, 0 deletions

diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h
new file mode 100644
index 000000000..e7b75e82e
--- /dev/null
+++ b/net/batman-adv/distributed-arp-table.h
@@ -0,0 +1,186 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) B.A.T.M.A.N. contributors:
+ *
+ * Antonio Quartulli
+ */
+
+#ifndef _NET_BATMAN_ADV_DISTRIBUTED_ARP_TABLE_H_
+#define _NET_BATMAN_ADV_DISTRIBUTED_ARP_TABLE_H_
+
+#include "main.h"
+
+#include <linux/compiler.h>
+#include <linux/netdevice.h>
+#include <linux/netlink.h>
+#include <linux/skbuff.h>
+#include <linux/types.h>
+#include <uapi/linux/batadv_packet.h>
+
+#include "originator.h"
+
+#ifdef CONFIG_BATMAN_ADV_DAT
+
+/* BATADV_DAT_ADDR_MAX - maximum address value in the DHT space */
+#define BATADV_DAT_ADDR_MAX ((batadv_dat_addr_t)~(batadv_dat_addr_t)0)
+
+void batadv_dat_status_update(struct net_device *net_dev);
+bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
+					   struct sk_buff *skb);
+bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv,
+					   struct sk_buff *skb, int hdr_size);
+void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv,
+					 struct sk_buff *skb);
+bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv,
+					 struct sk_buff *skb, int hdr_size);
+void batadv_dat_snoop_outgoing_dhcp_ack(struct batadv_priv *bat_priv,
+					struct sk_buff *skb,
+					__be16 proto,
+					unsigned short vid);
+void batadv_dat_snoop_incoming_dhcp_ack(struct batadv_priv *bat_priv,
+					struct sk_buff *skb, int hdr_size);
+bool batadv_dat_drop_broadcast_packet(struct batadv_priv *bat_priv,
+				      struct batadv_forw_packet *forw_packet);
+
+/**
+ * batadv_dat_init_orig_node_addr() - assign a DAT address to the orig_node
+ * @orig_node: the node to assign the DAT address to
+ */
+static inline void
+batadv_dat_init_orig_node_addr(struct batadv_orig_node *orig_node)
+{
+	u32 addr;
+
+	addr = batadv_choose_orig(orig_node->orig, BATADV_DAT_ADDR_MAX);
+	orig_node->dat_addr = (batadv_dat_addr_t)addr;
+}
+
+/**
+ * batadv_dat_init_own_addr() - assign a DAT address to the node itself
+ * @bat_priv: the bat priv with all the mesh interface information
+ * @primary_if: a pointer to the primary interface
+ */
+static inline void
+batadv_dat_init_own_addr(struct batadv_priv *bat_priv,
+			 struct batadv_hard_iface *primary_if)
+{
+	u32 addr;
+
+	addr = batadv_choose_orig(primary_if->net_dev->dev_addr,
+				  BATADV_DAT_ADDR_MAX);
+
+	bat_priv->dat.addr = (batadv_dat_addr_t)addr;
+}
+
+int batadv_dat_init(struct batadv_priv *bat_priv);
+void batadv_dat_free(struct batadv_priv *bat_priv);
+int batadv_dat_cache_dump(struct sk_buff *msg, struct netlink_callback *cb);
+
+/**
+ * batadv_dat_inc_counter() - increment the correct DAT packet counter
+ * @bat_priv: the bat priv with all the mesh interface information
+ * @subtype: the 4addr subtype of the packet to be counted
+ *
+ * Updates the ethtool statistics for the received packet if it is a DAT subtype
+ */
+static inline void batadv_dat_inc_counter(struct batadv_priv *bat_priv,
+					  u8 subtype)
+{
+	switch (subtype) {
+	case BATADV_P_DAT_DHT_GET:
+		batadv_inc_counter(bat_priv,
+				   BATADV_CNT_DAT_GET_RX);
+		break;
+	case BATADV_P_DAT_DHT_PUT:
+		batadv_inc_counter(bat_priv,
+				   BATADV_CNT_DAT_PUT_RX);
+		break;
+	}
+}
+
+#else
+
+static inline void batadv_dat_status_update(struct net_device *net_dev)
+{
+}
+
+static inline bool
+batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
+				      struct sk_buff *skb)
+{
+	return false;
+}
+
+static inline bool
+batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv,
+				      struct sk_buff *skb, int hdr_size)
+{
+	return false;
+}
+
+static inline bool
+batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv,
+				    struct sk_buff *skb)
+{
+	return false;
+}
+
+static inline bool
+batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv,
+				    struct sk_buff *skb, int hdr_size)
+{
+	return false;
+}
+
+static inline void
+batadv_dat_snoop_outgoing_dhcp_ack(struct batadv_priv *bat_priv,
+				   struct sk_buff *skb, __be16 proto,
+				   unsigned short vid)
+{
+}
+
+static inline void
+batadv_dat_snoop_incoming_dhcp_ack(struct batadv_priv *bat_priv,
+				   struct sk_buff *skb, int hdr_size)
+{
+}
+
+static inline bool
+batadv_dat_drop_broadcast_packet(struct batadv_priv *bat_priv,
+				 struct batadv_forw_packet *forw_packet)
+{
+	return false;
+}
+
+static inline void
+batadv_dat_init_orig_node_addr(struct batadv_orig_node *orig_node)
+{
+}
+
+static inline void batadv_dat_init_own_addr(struct batadv_priv *bat_priv,
+					    struct batadv_hard_iface *iface)
+{
+}
+
+static inline int batadv_dat_init(struct batadv_priv *bat_priv)
+{
+	return 0;
+}
+
+static inline void batadv_dat_free(struct batadv_priv *bat_priv)
+{
+}
+
+static inline int
+batadv_dat_cache_dump(struct sk_buff *msg, struct netlink_callback *cb)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void batadv_dat_inc_counter(struct batadv_priv *bat_priv,
+					  u8 subtype)
+{
+}
+
+#endif /* CONFIG_BATMAN_ADV_DAT */
+
+#endif /* _NET_BATMAN_ADV_DISTRIBUTED_ARP_TABLE_H_ */