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, 111 insertions, 0 deletions

diff --git a/net/ieee802154/sysfs.c b/net/ieee802154/sysfs.c
new file mode 100644
index 000000000..6708160eb
--- /dev/null
+++ b/net/ieee802154/sysfs.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *
+ * Authors:
+ * Alexander Aring <aar@pengutronix.de>
+ *
+ * Based on: net/wireless/sysfs.c
+ */
+
+#include <linux/device.h>
+#include <linux/rtnetlink.h>
+
+#include <net/cfg802154.h>
+
+#include "core.h"
+#include "sysfs.h"
+#include "rdev-ops.h"
+
+static inline struct cfg802154_registered_device *
+dev_to_rdev(struct device *dev)
+{
+	return container_of(dev, struct cfg802154_registered_device,
+			    wpan_phy.dev);
+}
+
+#define SHOW_FMT(name, fmt, member)					\
+static ssize_t name ## _show(struct device *dev,			\
+			     struct device_attribute *attr,		\
+			     char *buf)					\
+{									\
+	return sprintf(buf, fmt "\n", dev_to_rdev(dev)->member);	\
+}									\
+static DEVICE_ATTR_RO(name)
+
+SHOW_FMT(index, "%d", wpan_phy_idx);
+
+static ssize_t name_show(struct device *dev,
+			 struct device_attribute *attr,
+			 char *buf)
+{
+	struct wpan_phy *wpan_phy = &dev_to_rdev(dev)->wpan_phy;
+
+	return sprintf(buf, "%s\n", dev_name(&wpan_phy->dev));
+}
+static DEVICE_ATTR_RO(name);
+
+static void wpan_phy_release(struct device *dev)
+{
+	struct cfg802154_registered_device *rdev = dev_to_rdev(dev);
+
+	cfg802154_dev_free(rdev);
+}
+
+static struct attribute *pmib_attrs[] = {
+	&dev_attr_index.attr,
+	&dev_attr_name.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(pmib);
+
+#ifdef CONFIG_PM_SLEEP
+static int wpan_phy_suspend(struct device *dev)
+{
+	struct cfg802154_registered_device *rdev = dev_to_rdev(dev);
+	int ret = 0;
+
+	if (rdev->ops->suspend) {
+		rtnl_lock();
+		ret = rdev_suspend(rdev);
+		rtnl_unlock();
+	}
+
+	return ret;
+}
+
+static int wpan_phy_resume(struct device *dev)
+{
+	struct cfg802154_registered_device *rdev = dev_to_rdev(dev);
+	int ret = 0;
+
+	if (rdev->ops->resume) {
+		rtnl_lock();
+		ret = rdev_resume(rdev);
+		rtnl_unlock();
+	}
+
+	return ret;
+}
+
+static SIMPLE_DEV_PM_OPS(wpan_phy_pm_ops, wpan_phy_suspend, wpan_phy_resume);
+#define WPAN_PHY_PM_OPS (&wpan_phy_pm_ops)
+#else
+#define WPAN_PHY_PM_OPS NULL
+#endif
+
+const struct class wpan_phy_class = {
+	.name = "ieee802154",
+	.dev_release = wpan_phy_release,
+	.dev_groups = pmib_groups,
+	.pm = WPAN_PHY_PM_OPS,
+};
+
+int wpan_phy_sysfs_init(void)
+{
+	return class_register(&wpan_phy_class);
+}
+
+void wpan_phy_sysfs_exit(void)
+{
+	class_unregister(&wpan_phy_class);
+}