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, 90 insertions, 0 deletions

diff --git a/drivers/acpi/hed.c b/drivers/acpi/hed.c
new file mode 100644
index 000000000..48562f53d
--- /dev/null
+++ b/drivers/acpi/hed.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * ACPI Hardware Error Device (PNP0C33) Driver
+ *
+ * Copyright (C) 2010, Intel Corp.
+ *	Author: Huang Ying <ying.huang@intel.com>
+ *
+ * ACPI Hardware Error Device is used to report some hardware errors
+ * notified via SCI, mainly the corrected errors.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/acpi.h>
+#include <linux/platform_device.h>
+#include <acpi/hed.h>
+
+static const struct acpi_device_id acpi_hed_ids[] = {
+	{"PNP0C33", 0},
+	{"", 0},
+};
+MODULE_DEVICE_TABLE(acpi, acpi_hed_ids);
+
+static bool hed_present;
+
+static BLOCKING_NOTIFIER_HEAD(acpi_hed_notify_list);
+
+int register_acpi_hed_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&acpi_hed_notify_list, nb);
+}
+EXPORT_SYMBOL_GPL(register_acpi_hed_notifier);
+
+void unregister_acpi_hed_notifier(struct notifier_block *nb)
+{
+	blocking_notifier_chain_unregister(&acpi_hed_notify_list, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_acpi_hed_notifier);
+
+/*
+ * SCI to report hardware error is forwarded to the listeners of HED,
+ * it is used by HEST Generic Hardware Error Source with notify type
+ * SCI.
+ */
+static void acpi_hed_notify(acpi_handle handle, u32 event, void *data)
+{
+	blocking_notifier_call_chain(&acpi_hed_notify_list, 0, NULL);
+}
+
+static int acpi_hed_probe(struct platform_device *pdev)
+{
+	int err;
+
+	/* Only one hardware error device */
+	if (hed_present)
+		return -EINVAL;
+
+	err = devm_acpi_install_notify_handler(&pdev->dev, ACPI_DEVICE_NOTIFY,
+					       acpi_hed_notify, NULL);
+	if (err)
+		return err;
+
+	hed_present = true;
+	return 0;
+}
+
+static void acpi_hed_remove(struct platform_device *pdev)
+{
+	hed_present = false;
+}
+
+static struct platform_driver acpi_hed_driver = {
+	.probe = acpi_hed_probe,
+	.remove = acpi_hed_remove,
+	.driver = {
+		.name = "acpi-hardware-error-device",
+		.acpi_match_table = acpi_hed_ids,
+	},
+};
+
+static int __init acpi_hed_driver_init(void)
+{
+	return platform_driver_register(&acpi_hed_driver);
+}
+subsys_initcall(acpi_hed_driver_init);
+
+MODULE_AUTHOR("Huang Ying");
+MODULE_DESCRIPTION("ACPI Hardware Error Device Driver");
+MODULE_LICENSE("GPL");