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, 181 insertions, 0 deletions

diff --git a/drivers/base/isa.c b/drivers/base/isa.c
new file mode 100644
index 000000000..4e9f68080
--- /dev/null
+++ b/drivers/base/isa.c
@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ISA bus.
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/dma-mapping.h>
+#include <linux/isa.h>
+
+static struct device *isa_bus;
+
+struct isa_dev {
+	struct device dev;
+	struct device *next;
+	unsigned int id;
+};
+
+#define to_isa_dev(x) container_of((x), struct isa_dev, dev)
+
+static int isa_bus_match(struct device *dev, const struct device_driver *driver)
+{
+	struct isa_driver *isa_driver = to_isa_driver(driver);
+
+	if (dev->platform_data == isa_driver) {
+		if (!isa_driver->match ||
+			isa_driver->match(dev, to_isa_dev(dev)->id))
+			return 1;
+		dev->platform_data = NULL;
+	}
+	return 0;
+}
+
+static int isa_bus_probe(struct device *dev)
+{
+	struct isa_driver *isa_driver = dev->platform_data;
+
+	if (isa_driver && isa_driver->probe)
+		return isa_driver->probe(dev, to_isa_dev(dev)->id);
+
+	return 0;
+}
+
+static void isa_bus_remove(struct device *dev)
+{
+	struct isa_driver *isa_driver = dev->platform_data;
+
+	if (isa_driver && isa_driver->remove)
+		isa_driver->remove(dev, to_isa_dev(dev)->id);
+}
+
+static void isa_bus_shutdown(struct device *dev)
+{
+	struct isa_driver *isa_driver = dev->platform_data;
+
+	if (isa_driver && isa_driver->shutdown)
+		isa_driver->shutdown(dev, to_isa_dev(dev)->id);
+}
+
+static int isa_bus_suspend(struct device *dev, pm_message_t state)
+{
+	struct isa_driver *isa_driver = dev->platform_data;
+
+	if (isa_driver && isa_driver->suspend)
+		return isa_driver->suspend(dev, to_isa_dev(dev)->id, state);
+
+	return 0;
+}
+
+static int isa_bus_resume(struct device *dev)
+{
+	struct isa_driver *isa_driver = dev->platform_data;
+
+	if (isa_driver && isa_driver->resume)
+		return isa_driver->resume(dev, to_isa_dev(dev)->id);
+
+	return 0;
+}
+
+static const struct bus_type isa_bus_type = {
+	.name		= "isa",
+	.match		= isa_bus_match,
+	.probe		= isa_bus_probe,
+	.remove		= isa_bus_remove,
+	.shutdown	= isa_bus_shutdown,
+	.suspend	= isa_bus_suspend,
+	.resume		= isa_bus_resume
+};
+
+static void isa_dev_release(struct device *dev)
+{
+	kfree(to_isa_dev(dev));
+}
+
+void isa_unregister_driver(struct isa_driver *isa_driver)
+{
+	struct device *dev = isa_driver->devices;
+
+	while (dev) {
+		struct device *tmp = to_isa_dev(dev)->next;
+		device_unregister(dev);
+		dev = tmp;
+	}
+	driver_unregister(&isa_driver->driver);
+}
+EXPORT_SYMBOL_GPL(isa_unregister_driver);
+
+int isa_register_driver(struct isa_driver *isa_driver, unsigned int ndev)
+{
+	int error;
+	unsigned int id;
+
+	isa_driver->driver.bus	= &isa_bus_type;
+	isa_driver->devices	= NULL;
+
+	error = driver_register(&isa_driver->driver);
+	if (error)
+		return error;
+
+	for (id = 0; id < ndev; id++) {
+		struct isa_dev *isa_dev;
+
+		isa_dev = kzalloc_obj(*isa_dev);
+		if (!isa_dev) {
+			error = -ENOMEM;
+			break;
+		}
+
+		isa_dev->dev.parent	= isa_bus;
+		isa_dev->dev.bus	= &isa_bus_type;
+
+		dev_set_name(&isa_dev->dev, "%s.%u",
+			     isa_driver->driver.name, id);
+		isa_dev->dev.platform_data	= isa_driver;
+		isa_dev->dev.release		= isa_dev_release;
+		isa_dev->id			= id;
+
+		isa_dev->dev.coherent_dma_mask = DMA_BIT_MASK(24);
+		isa_dev->dev.dma_mask = &isa_dev->dev.coherent_dma_mask;
+
+		error = device_register(&isa_dev->dev);
+		if (error) {
+			put_device(&isa_dev->dev);
+			break;
+		}
+
+		isa_dev->next = isa_driver->devices;
+		isa_driver->devices = &isa_dev->dev;
+	}
+
+	if (!error && !isa_driver->devices)
+		error = -ENODEV;
+
+	if (error)
+		isa_unregister_driver(isa_driver);
+
+	return error;
+}
+EXPORT_SYMBOL_GPL(isa_register_driver);
+
+static int __init isa_bus_init(void)
+{
+	int error;
+
+	error = bus_register(&isa_bus_type);
+	if (error)
+		return error;
+
+	isa_bus = root_device_register("isa");
+	if (IS_ERR(isa_bus)) {
+		bus_unregister(&isa_bus_type);
+		return PTR_ERR(isa_bus);
+	}
+
+	return 0;
+}
+
+postcore_initcall(isa_bus_init);