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, 204 insertions, 0 deletions

diff --git a/drivers/base/driver.c b/drivers/base/driver.c
new file mode 100644
index 000000000..5d9c39081
--- /dev/null
+++ b/drivers/base/driver.c
@@ -0,0 +1,204 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * driver.c - centralized device driver management
+ *
+ * Copyright (c) 2002-3 Patrick Mochel
+ * Copyright (c) 2002-3 Open Source Development Labs
+ * Copyright (c) 2007 Greg Kroah-Hartman <gregkh@suse.de>
+ * Copyright (c) 2007 Novell Inc.
+ */
+
+#include <linux/device/driver.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include "base.h"
+
+static struct device *next_device(struct klist_iter *i)
+{
+	struct klist_node *n = klist_next(i);
+	struct device *dev = NULL;
+	struct device_private *dev_prv;
+
+	if (n) {
+		dev_prv = to_device_private_driver(n);
+		dev = dev_prv->device;
+	}
+	return dev;
+}
+
+/**
+ * driver_for_each_device - Iterator for devices bound to a driver.
+ * @drv: Driver we're iterating.
+ * @start: Device to begin with
+ * @data: Data to pass to the callback.
+ * @fn: Function to call for each device.
+ *
+ * Iterate over the @drv's list of devices calling @fn for each one.
+ */
+int driver_for_each_device(struct device_driver *drv, struct device *start,
+			   void *data, device_iter_t fn)
+{
+	struct klist_iter i;
+	struct device *dev;
+	int error = 0;
+
+	if (!drv)
+		return -EINVAL;
+
+	klist_iter_init_node(&drv->p->klist_devices, &i,
+			     start ? &start->p->knode_driver : NULL);
+	while (!error && (dev = next_device(&i)))
+		error = fn(dev, data);
+	klist_iter_exit(&i);
+	return error;
+}
+EXPORT_SYMBOL_GPL(driver_for_each_device);
+
+/**
+ * driver_find_device - device iterator for locating a particular device.
+ * @drv: The device's driver
+ * @start: Device to begin with
+ * @data: Data to pass to match function
+ * @match: Callback function to check device
+ *
+ * This is similar to the driver_for_each_device() function above, but
+ * it returns a reference to a device that is 'found' for later use, as
+ * determined by the @match callback.
+ *
+ * The callback should return 0 if the device doesn't match and non-zero
+ * if it does.  If the callback returns non-zero, this function will
+ * return to the caller and not iterate over any more devices.
+ */
+struct device *driver_find_device(const struct device_driver *drv,
+				  struct device *start, const void *data,
+				  device_match_t match)
+{
+	struct klist_iter i;
+	struct device *dev;
+
+	if (!drv || !drv->p)
+		return NULL;
+
+	klist_iter_init_node(&drv->p->klist_devices, &i,
+			     (start ? &start->p->knode_driver : NULL));
+	while ((dev = next_device(&i))) {
+		if (match(dev, data)) {
+			get_device(dev);
+			break;
+		}
+	}
+	klist_iter_exit(&i);
+	return dev;
+}
+EXPORT_SYMBOL_GPL(driver_find_device);
+
+/**
+ * driver_create_file - create sysfs file for driver.
+ * @drv: driver.
+ * @attr: driver attribute descriptor.
+ */
+int driver_create_file(const struct device_driver *drv,
+		       const struct driver_attribute *attr)
+{
+	int error;
+
+	if (drv)
+		error = sysfs_create_file(&drv->p->kobj, &attr->attr);
+	else
+		error = -EINVAL;
+	return error;
+}
+EXPORT_SYMBOL_GPL(driver_create_file);
+
+/**
+ * driver_remove_file - remove sysfs file for driver.
+ * @drv: driver.
+ * @attr: driver attribute descriptor.
+ */
+void driver_remove_file(const struct device_driver *drv,
+			const struct driver_attribute *attr)
+{
+	if (drv)
+		sysfs_remove_file(&drv->p->kobj, &attr->attr);
+}
+EXPORT_SYMBOL_GPL(driver_remove_file);
+
+int driver_add_groups(const struct device_driver *drv,
+		      const struct attribute_group *const *groups)
+{
+	return sysfs_create_groups(&drv->p->kobj, groups);
+}
+
+void driver_remove_groups(const struct device_driver *drv,
+			  const struct attribute_group *const *groups)
+{
+	sysfs_remove_groups(&drv->p->kobj, groups);
+}
+
+/**
+ * driver_register - register driver with bus
+ * @drv: driver to register
+ *
+ * We pass off most of the work to the bus_add_driver() call,
+ * since most of the things we have to do deal with the bus
+ * structures.
+ */
+int driver_register(struct device_driver *drv)
+{
+	int ret;
+	struct device_driver *other;
+
+	if (!bus_is_registered(drv->bus)) {
+		pr_err("Driver '%s' was unable to register with bus_type '%s' because the bus was not initialized.\n",
+			   drv->name, drv->bus->name);
+		return -EINVAL;
+	}
+
+	if ((drv->bus->probe && drv->probe) ||
+	    (drv->bus->remove && drv->remove) ||
+	    (drv->bus->shutdown && drv->shutdown))
+		pr_warn("Driver '%s' needs updating - please use "
+			"bus_type methods\n", drv->name);
+
+	other = driver_find(drv->name, drv->bus);
+	if (other) {
+		pr_err("Error: Driver '%s' is already registered, "
+			"aborting...\n", drv->name);
+		return -EBUSY;
+	}
+
+	ret = bus_add_driver(drv);
+	if (ret)
+		return ret;
+	ret = driver_add_groups(drv, drv->groups);
+	if (ret) {
+		bus_remove_driver(drv);
+		return ret;
+	}
+	kobject_uevent(&drv->p->kobj, KOBJ_ADD);
+	deferred_probe_extend_timeout();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(driver_register);
+
+/**
+ * driver_unregister - remove driver from system.
+ * @drv: driver.
+ *
+ * Again, we pass off most of the work to the bus-level call.
+ */
+void driver_unregister(struct device_driver *drv)
+{
+	if (!drv || !drv->p) {
+		WARN(1, "Unexpected driver unregister!\n");
+		return;
+	}
+	driver_remove_groups(drv, drv->groups);
+	bus_remove_driver(drv);
+}
+EXPORT_SYMBOL_GPL(driver_unregister);