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, 250 insertions, 0 deletions

diff --git a/drivers/block/rnbd/rnbd-srv-sysfs.c b/drivers/block/rnbd/rnbd-srv-sysfs.c
new file mode 100644
index 000000000..647800944
--- /dev/null
+++ b/drivers/block/rnbd/rnbd-srv-sysfs.c
@@ -0,0 +1,250 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * RDMA Network Block Driver
+ *
+ * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved.
+ * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved.
+ * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved.
+ */
+#undef pr_fmt
+#define pr_fmt(fmt) KBUILD_MODNAME " L" __stringify(__LINE__) ": " fmt
+
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/stat.h>
+#include <linux/list.h>
+#include <linux/moduleparam.h>
+#include <linux/device.h>
+
+#include "rnbd-srv.h"
+
+static struct device *rnbd_dev;
+static const struct class rnbd_dev_class = {
+	.name = "rnbd-server",
+};
+static struct kobject *rnbd_devs_kobj;
+
+static void rnbd_srv_dev_release(struct kobject *kobj)
+{
+	struct rnbd_srv_dev *dev;
+
+	dev = container_of(kobj, struct rnbd_srv_dev, dev_kobj);
+
+	kfree(dev);
+}
+
+static const struct kobj_type dev_ktype = {
+	.sysfs_ops = &kobj_sysfs_ops,
+	.release = rnbd_srv_dev_release
+};
+
+int rnbd_srv_create_dev_sysfs(struct rnbd_srv_dev *dev,
+			       struct block_device *bdev)
+{
+	struct kobject *bdev_kobj;
+	int ret;
+
+	ret = kobject_init_and_add(&dev->dev_kobj, &dev_ktype,
+				   rnbd_devs_kobj, "%pg", bdev);
+	if (ret) {
+		kobject_put(&dev->dev_kobj);
+		return ret;
+	}
+
+	dev->dev_sessions_kobj = kobject_create_and_add("sessions",
+							&dev->dev_kobj);
+	if (!dev->dev_sessions_kobj) {
+		ret = -ENOMEM;
+		goto free_dev_kobj;
+	}
+
+	bdev_kobj = &disk_to_dev(bdev->bd_disk)->kobj;
+	ret = sysfs_create_link(&dev->dev_kobj, bdev_kobj, "block_dev");
+	if (ret)
+		goto put_sess_kobj;
+
+	return 0;
+
+put_sess_kobj:
+	kobject_put(dev->dev_sessions_kobj);
+free_dev_kobj:
+	kobject_del(&dev->dev_kobj);
+	kobject_put(&dev->dev_kobj);
+	return ret;
+}
+
+void rnbd_srv_destroy_dev_sysfs(struct rnbd_srv_dev *dev)
+{
+	sysfs_remove_link(&dev->dev_kobj, "block_dev");
+	kobject_del(dev->dev_sessions_kobj);
+	kobject_put(dev->dev_sessions_kobj);
+	kobject_del(&dev->dev_kobj);
+	kobject_put(&dev->dev_kobj);
+}
+
+static ssize_t read_only_show(struct kobject *kobj, struct kobj_attribute *attr,
+			      char *page)
+{
+	struct rnbd_srv_sess_dev *sess_dev;
+
+	sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj);
+
+	return sysfs_emit(page, "%d\n", sess_dev->readonly);
+}
+
+static struct kobj_attribute rnbd_srv_dev_session_ro_attr =
+	__ATTR_RO(read_only);
+
+static ssize_t access_mode_show(struct kobject *kobj,
+				struct kobj_attribute *attr,
+				char *page)
+{
+	struct rnbd_srv_sess_dev *sess_dev;
+
+	sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj);
+
+	return sysfs_emit(page, "%s\n",
+			  rnbd_access_modes[sess_dev->access_mode].str);
+}
+
+static struct kobj_attribute rnbd_srv_dev_session_access_mode_attr =
+	__ATTR_RO(access_mode);
+
+static ssize_t mapping_path_show(struct kobject *kobj,
+				 struct kobj_attribute *attr, char *page)
+{
+	struct rnbd_srv_sess_dev *sess_dev;
+
+	sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj);
+
+	return sysfs_emit(page, "%s\n", sess_dev->pathname);
+}
+
+static struct kobj_attribute rnbd_srv_dev_session_mapping_path_attr =
+	__ATTR_RO(mapping_path);
+
+static ssize_t rnbd_srv_dev_session_force_close_show(struct kobject *kobj,
+					struct kobj_attribute *attr, char *page)
+{
+	return sysfs_emit(page, "Usage: echo 1 > %s\n",
+			  attr->attr.name);
+}
+
+static ssize_t rnbd_srv_dev_session_force_close_store(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					const char *buf, size_t count)
+{
+	struct rnbd_srv_sess_dev *sess_dev;
+
+	sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj);
+
+	if (!sysfs_streq(buf, "1")) {
+		rnbd_srv_err(sess_dev, "%s: invalid value: '%s'\n",
+			      attr->attr.name, buf);
+		return -EINVAL;
+	}
+
+	rnbd_srv_info(sess_dev, "force close requested\n");
+	rnbd_srv_sess_dev_force_close(sess_dev, attr);
+
+	return count;
+}
+
+static struct kobj_attribute rnbd_srv_dev_session_force_close_attr =
+	__ATTR(force_close, 0644,
+	       rnbd_srv_dev_session_force_close_show,
+	       rnbd_srv_dev_session_force_close_store);
+
+static struct attribute *rnbd_srv_default_dev_sessions_attrs[] = {
+	&rnbd_srv_dev_session_access_mode_attr.attr,
+	&rnbd_srv_dev_session_ro_attr.attr,
+	&rnbd_srv_dev_session_mapping_path_attr.attr,
+	&rnbd_srv_dev_session_force_close_attr.attr,
+	NULL,
+};
+
+static struct attribute_group rnbd_srv_default_dev_session_attr_group = {
+	.attrs = rnbd_srv_default_dev_sessions_attrs,
+};
+
+void rnbd_srv_destroy_dev_session_sysfs(struct rnbd_srv_sess_dev *sess_dev)
+{
+	sysfs_remove_group(&sess_dev->kobj,
+			   &rnbd_srv_default_dev_session_attr_group);
+
+	kobject_del(&sess_dev->kobj);
+	kobject_put(&sess_dev->kobj);
+}
+
+static void rnbd_srv_sess_dev_release(struct kobject *kobj)
+{
+	struct rnbd_srv_sess_dev *sess_dev;
+
+	sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj);
+	rnbd_destroy_sess_dev(sess_dev, sess_dev->keep_id);
+}
+
+static const struct kobj_type rnbd_srv_sess_dev_ktype = {
+	.sysfs_ops	= &kobj_sysfs_ops,
+	.release	= rnbd_srv_sess_dev_release,
+};
+
+int rnbd_srv_create_dev_session_sysfs(struct rnbd_srv_sess_dev *sess_dev)
+{
+	int ret;
+
+	ret = kobject_init_and_add(&sess_dev->kobj, &rnbd_srv_sess_dev_ktype,
+				   sess_dev->dev->dev_sessions_kobj, "%s",
+				   sess_dev->sess->sessname);
+	if (ret) {
+		kobject_put(&sess_dev->kobj);
+		return ret;
+	}
+
+	ret = sysfs_create_group(&sess_dev->kobj,
+				 &rnbd_srv_default_dev_session_attr_group);
+	if (ret) {
+		kobject_del(&sess_dev->kobj);
+		kobject_put(&sess_dev->kobj);
+	}
+
+	return ret;
+}
+
+int rnbd_srv_create_sysfs_files(void)
+{
+	int err;
+
+	err = class_register(&rnbd_dev_class);
+	if (err)
+		return err;
+
+	rnbd_dev = device_create(&rnbd_dev_class, NULL,
+				 MKDEV(0, 0), NULL, "ctl");
+	if (IS_ERR(rnbd_dev)) {
+		err = PTR_ERR(rnbd_dev);
+		goto cls_destroy;
+	}
+	rnbd_devs_kobj = kobject_create_and_add("devices", &rnbd_dev->kobj);
+	if (!rnbd_devs_kobj) {
+		err = -ENOMEM;
+		goto dev_destroy;
+	}
+
+	return 0;
+
+dev_destroy:
+	device_destroy(&rnbd_dev_class, MKDEV(0, 0));
+cls_destroy:
+	class_unregister(&rnbd_dev_class);
+
+	return err;
+}
+
+void rnbd_srv_destroy_sysfs_files(void)
+{
+	kobject_del(rnbd_devs_kobj);
+	kobject_put(rnbd_devs_kobj);
+	device_destroy(&rnbd_dev_class, MKDEV(0, 0));
+	class_unregister(&rnbd_dev_class);
+}