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, 76 insertions, 0 deletions

diff --git a/include/net/selftests.h b/include/net/selftests.h
new file mode 100644
index 000000000..c36e07406
--- /dev/null
+++ b/include/net/selftests.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NET_SELFTESTS
+#define _NET_SELFTESTS
+
+#include <linux/ethtool.h>
+#include <linux/netdevice.h>
+
+struct net_packet_attrs {
+	const unsigned char *src;
+	const unsigned char *dst;
+	u32 ip_src;
+	u32 ip_dst;
+	bool tcp;
+	u16 sport;
+	u16 dport;
+	int timeout;
+	int size;
+	int max_size;
+	u8 id;
+	u16 queue_mapping;
+	bool bad_csum;
+};
+
+struct net_test_priv {
+	struct net_packet_attrs *packet;
+	struct packet_type pt;
+	struct completion comp;
+	int double_vlan;
+	int vlan_id;
+	int ok;
+};
+
+struct netsfhdr {
+	__be32 version;
+	__be64 magic;
+	u8 id;
+} __packed;
+
+#define NET_TEST_PKT_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \
+			   sizeof(struct netsfhdr))
+#define NET_TEST_PKT_MAGIC	0xdeadcafecafedeadULL
+#define NET_LB_TIMEOUT		msecs_to_jiffies(200)
+
+#if IS_ENABLED(CONFIG_NET_SELFTESTS)
+
+struct sk_buff *net_test_get_skb(struct net_device *ndev, u8 id,
+				 struct net_packet_attrs *attr);
+void net_selftest(struct net_device *ndev, struct ethtool_test *etest,
+		  u64 *buf);
+int net_selftest_get_count(void);
+void net_selftest_get_strings(u8 *data);
+
+#else
+
+static inline struct sk_buff *net_test_get_skb(struct net_device *ndev, u8 id,
+					       struct net_packet_attrs *attr)
+{
+	return NULL;
+}
+
+static inline void net_selftest(struct net_device *ndev, struct ethtool_test *etest,
+				u64 *buf)
+{
+}
+
+static inline int net_selftest_get_count(void)
+{
+	return 0;
+}
+
+static inline void net_selftest_get_strings(u8 *data)
+{
+}
+
+#endif
+#endif /* _NET_SELFTESTS */