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, 305 insertions, 0 deletions

diff --git a/samples/kobject/kset-example.c b/samples/kobject/kset-example.c
new file mode 100644
index 000000000..d0103904e
--- /dev/null
+++ b/samples/kobject/kset-example.c
@@ -0,0 +1,305 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Sample kset and ktype implementation
+ *
+ * Copyright (C) 2004-2007 Greg Kroah-Hartman <greg@kroah.com>
+ * Copyright (C) 2007 Novell Inc.
+ */
+#include <linux/kobject.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+/*
+ * This module shows how to create a kset in sysfs called
+ * /sys/kernel/kset_example
+ * Then three kobjects are created and assigned to this kset, "foo", "baz",
+ * and "bar".  In those kobjects, attributes of the same name are also
+ * created and if an integer is written to these files, it can be later
+ * read out of it.
+ */
+
+
+/*
+ * This is our "object" that we will create a few of and register them with
+ * sysfs.
+ */
+struct foo_obj {
+	struct kobject kobj;
+	int foo;
+	int baz;
+	int bar;
+};
+#define to_foo_obj(x) container_of(x, struct foo_obj, kobj)
+
+/* a custom attribute that works just for a struct foo_obj. */
+struct foo_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct foo_obj *foo, const struct foo_attribute *attr, char *buf);
+	ssize_t (*store)(struct foo_obj *foo, const struct foo_attribute *attr,
+			 const char *buf, size_t count);
+};
+#define to_foo_attr(x) container_of_const(x, struct foo_attribute, attr)
+
+/*
+ * The default show function that must be passed to sysfs.  This will be
+ * called by sysfs for whenever a show function is called by the user on a
+ * sysfs file associated with the kobjects we have registered.  We need to
+ * transpose back from a "default" kobject to our custom struct foo_obj and
+ * then call the show function for that specific object.
+ */
+static ssize_t foo_attr_show(struct kobject *kobj,
+			     struct attribute *attr,
+			     char *buf)
+{
+	const struct foo_attribute *attribute;
+	struct foo_obj *foo;
+
+	attribute = to_foo_attr(attr);
+	foo = to_foo_obj(kobj);
+
+	if (!attribute->show)
+		return -EIO;
+
+	return attribute->show(foo, attribute, buf);
+}
+
+/*
+ * Just like the default show function above, but this one is for when the
+ * sysfs "store" is requested (when a value is written to a file.)
+ */
+static ssize_t foo_attr_store(struct kobject *kobj,
+			      struct attribute *attr,
+			      const char *buf, size_t len)
+{
+	const struct foo_attribute *attribute;
+	struct foo_obj *foo;
+
+	attribute = to_foo_attr(attr);
+	foo = to_foo_obj(kobj);
+
+	if (!attribute->store)
+		return -EIO;
+
+	return attribute->store(foo, attribute, buf, len);
+}
+
+/* Our custom sysfs_ops that we will associate with our ktype later on */
+static const struct sysfs_ops foo_sysfs_ops = {
+	.show = foo_attr_show,
+	.store = foo_attr_store,
+};
+
+/*
+ * The release function for our object.  This is REQUIRED by the kernel to
+ * have.  We free the memory held in our object here.
+ *
+ * NEVER try to get away with just a "blank" release function to try to be
+ * smarter than the kernel.  Turns out, no one ever is...
+ */
+static void foo_release(struct kobject *kobj)
+{
+	struct foo_obj *foo;
+
+	foo = to_foo_obj(kobj);
+	kfree(foo);
+}
+
+/*
+ * The "foo" file where the .foo variable is read from and written to.
+ */
+static ssize_t foo_show(struct foo_obj *foo_obj, const struct foo_attribute *attr,
+			char *buf)
+{
+	return sysfs_emit(buf, "%d\n", foo_obj->foo);
+}
+
+static ssize_t foo_store(struct foo_obj *foo_obj, const struct foo_attribute *attr,
+			 const char *buf, size_t count)
+{
+	int ret;
+
+	ret = kstrtoint(buf, 10, &foo_obj->foo);
+	if (ret < 0)
+		return ret;
+
+	return count;
+}
+
+/* Sysfs attributes cannot be world-writable. */
+static const struct foo_attribute foo_attribute =
+	__ATTR(foo, 0664, foo_show, foo_store);
+
+/*
+ * More complex function where we determine which variable is being accessed by
+ * looking at the attribute for the "baz" and "bar" files.
+ */
+static ssize_t b_show(struct foo_obj *foo_obj, const struct foo_attribute *attr,
+		      char *buf)
+{
+	int var;
+
+	if (strcmp(attr->attr.name, "baz") == 0)
+		var = foo_obj->baz;
+	else
+		var = foo_obj->bar;
+	return sysfs_emit(buf, "%d\n", var);
+}
+
+static ssize_t b_store(struct foo_obj *foo_obj, const struct foo_attribute *attr,
+		       const char *buf, size_t count)
+{
+	int var, ret;
+
+	ret = kstrtoint(buf, 10, &var);
+	if (ret < 0)
+		return ret;
+
+	if (strcmp(attr->attr.name, "baz") == 0)
+		foo_obj->baz = var;
+	else
+		foo_obj->bar = var;
+	return count;
+}
+
+static const struct foo_attribute baz_attribute =
+	__ATTR(baz, 0664, b_show, b_store);
+static const struct foo_attribute bar_attribute =
+	__ATTR(bar, 0664, b_show, b_store);
+
+/*
+ * Create a group of attributes so that we can create and destroy them all
+ * at once.
+ */
+static const struct attribute *const foo_default_attrs[] = {
+	&foo_attribute.attr,
+	&baz_attribute.attr,
+	&bar_attribute.attr,
+	NULL,	/* need to NULL terminate the list of attributes */
+};
+
+static umode_t foo_default_attrs_is_visible(struct kobject *kobj,
+					    const struct attribute *attr,
+					    int n)
+{
+	/* Hide attributes with the same name as the kobject. */
+	if (strcmp(kobject_name(kobj), attr->name) == 0)
+		return 0;
+	return attr->mode;
+}
+
+static const struct attribute_group foo_default_group = {
+	.attrs_const		= foo_default_attrs,
+	.is_visible_const	= foo_default_attrs_is_visible,
+};
+__ATTRIBUTE_GROUPS(foo_default);
+
+/*
+ * Our own ktype for our kobjects.  Here we specify our sysfs ops, the
+ * release function, and the set of default attributes we want created
+ * whenever a kobject of this type is registered with the kernel.
+ */
+static const struct kobj_type foo_ktype = {
+	.sysfs_ops = &foo_sysfs_ops,
+	.release = foo_release,
+	.default_groups = foo_default_groups,
+};
+
+static struct kset *example_kset;
+static struct foo_obj *foo_obj;
+static struct foo_obj *bar_obj;
+static struct foo_obj *baz_obj;
+
+static struct foo_obj *create_foo_obj(const char *name)
+{
+	struct foo_obj *foo;
+	int retval;
+
+	/* allocate the memory for the whole object */
+	foo = kzalloc(sizeof(*foo), GFP_KERNEL);
+	if (!foo)
+		return NULL;
+
+	/*
+	 * As we have a kset for this kobject, we need to set it before calling
+	 * the kobject core.
+	 */
+	foo->kobj.kset = example_kset;
+
+	/*
+	 * Initialize and add the kobject to the kernel.  All the default files
+	 * will be created here.  As we have already specified a kset for this
+	 * kobject, we don't have to set a parent for the kobject, the kobject
+	 * will be placed beneath that kset automatically.
+	 */
+	retval = kobject_init_and_add(&foo->kobj, &foo_ktype, NULL, "%s", name);
+	if (retval) {
+		kobject_put(&foo->kobj);
+		return NULL;
+	}
+
+	/*
+	 * We are always responsible for sending the uevent that the kobject
+	 * was added to the system.
+	 */
+	kobject_uevent(&foo->kobj, KOBJ_ADD);
+
+	return foo;
+}
+
+static void destroy_foo_obj(struct foo_obj *foo)
+{
+	kobject_put(&foo->kobj);
+}
+
+static int __init example_init(void)
+{
+	/*
+	 * Create a kset with the name of "kset_example",
+	 * located under /sys/kernel/
+	 */
+	example_kset = kset_create_and_add("kset_example", NULL, kernel_kobj);
+	if (!example_kset)
+		return -ENOMEM;
+
+	/*
+	 * Create three objects and register them with our kset
+	 */
+	foo_obj = create_foo_obj("foo");
+	if (!foo_obj)
+		goto foo_error;
+
+	bar_obj = create_foo_obj("bar");
+	if (!bar_obj)
+		goto bar_error;
+
+	baz_obj = create_foo_obj("baz");
+	if (!baz_obj)
+		goto baz_error;
+
+	return 0;
+
+baz_error:
+	destroy_foo_obj(bar_obj);
+bar_error:
+	destroy_foo_obj(foo_obj);
+foo_error:
+	kset_unregister(example_kset);
+	return -EINVAL;
+}
+
+static void __exit example_exit(void)
+{
+	destroy_foo_obj(baz_obj);
+	destroy_foo_obj(bar_obj);
+	destroy_foo_obj(foo_obj);
+	kset_unregister(example_kset);
+}
+
+module_init(example_init);
+module_exit(example_exit);
+MODULE_DESCRIPTION("Sample kset and ktype implementation");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Greg Kroah-Hartman <greg@kroah.com>");