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, 151 insertions, 0 deletions

diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c
new file mode 100644
index 000000000..c2065abf7
--- /dev/null
+++ b/net/bluetooth/hci_sysfs.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Bluetooth HCI driver model support. */
+
+#include <linux/module.h>
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+
+static const struct class bt_class = {
+	.name = "bluetooth",
+};
+
+static void bt_link_release(struct device *dev)
+{
+	struct hci_conn *conn = to_hci_conn(dev);
+	struct device *parent = dev->parent;
+
+	kfree(conn);
+	put_device(parent);
+}
+
+static const struct device_type bt_link = {
+	.name    = "link",
+	.release = bt_link_release,
+};
+
+/*
+ * The rfcomm tty device will possibly retain even when conn
+ * is down, and sysfs doesn't support move zombie device,
+ * so we should move the device before conn device is destroyed.
+ */
+static int __match_tty(struct device *dev, const void *data)
+{
+	return !strncmp(dev_name(dev), "rfcomm", 6);
+}
+
+void hci_conn_init_sysfs(struct hci_conn *conn)
+{
+	struct hci_dev *hdev = conn->hdev;
+
+	bt_dev_dbg(hdev, "conn %p", conn);
+
+	conn->dev.type = &bt_link;
+	conn->dev.class = &bt_class;
+	conn->dev.parent = get_device(&hdev->dev);
+
+	device_initialize(&conn->dev);
+}
+
+void hci_conn_add_sysfs(struct hci_conn *conn)
+{
+	struct hci_dev *hdev = conn->hdev;
+
+	bt_dev_dbg(hdev, "conn %p", conn);
+
+	if (device_is_registered(&conn->dev))
+		return;
+
+	dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle);
+
+	if (device_add(&conn->dev) < 0)
+		bt_dev_err(hdev, "failed to register connection device");
+}
+
+void hci_conn_del_sysfs(struct hci_conn *conn)
+{
+	struct hci_dev *hdev = conn->hdev;
+
+	bt_dev_dbg(hdev, "conn %p", conn);
+
+	if (!device_is_registered(&conn->dev)) {
+		/* If device_add() has *not* succeeded, use *only* put_device()
+		 * to drop the reference count.
+		 */
+		put_device(&conn->dev);
+		return;
+	}
+
+	/* If there are devices using the connection as parent reset it to NULL
+	 * before unregistering the device.
+	 */
+	while (1) {
+		struct device *dev;
+
+		dev = device_find_child(&conn->dev, NULL, __match_tty);
+		if (!dev)
+			break;
+		device_move(dev, NULL, DPM_ORDER_DEV_LAST);
+		put_device(dev);
+	}
+
+	device_unregister(&conn->dev);
+}
+
+static void bt_host_release(struct device *dev)
+{
+	struct hci_dev *hdev = to_hci_dev(dev);
+
+	if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) {
+		hci_release_dev(hdev);
+	} else {
+		cleanup_srcu_struct(&hdev->srcu);
+		kfree(hdev);
+	}
+	module_put(THIS_MODULE);
+}
+
+static ssize_t reset_store(struct device *dev, struct device_attribute *attr,
+			   const char *buf, size_t count)
+{
+	struct hci_dev *hdev = to_hci_dev(dev);
+
+	if (hdev->reset)
+		hdev->reset(hdev);
+
+	return count;
+}
+static DEVICE_ATTR_WO(reset);
+
+static struct attribute *bt_host_attrs[] = {
+	&dev_attr_reset.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(bt_host);
+
+static const struct device_type bt_host = {
+	.name    = "host",
+	.release = bt_host_release,
+	.groups = bt_host_groups,
+};
+
+void hci_init_sysfs(struct hci_dev *hdev)
+{
+	struct device *dev = &hdev->dev;
+
+	dev->type = &bt_host;
+	dev->class = &bt_class;
+
+	__module_get(THIS_MODULE);
+	device_initialize(dev);
+}
+
+int __init bt_sysfs_init(void)
+{
+	return class_register(&bt_class);
+}
+
+void bt_sysfs_cleanup(void)
+{
+	class_unregister(&bt_class);
+}