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, 168 insertions, 0 deletions

diff --git a/drivers/of/kobj.c b/drivers/of/kobj.c
new file mode 100644
index 000000000..9f17305f1
--- /dev/null
+++ b/drivers/of/kobj.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/of.h>
+#include <linux/slab.h>
+
+#include <kunit/visibility.h>
+
+#include "of_private.h"
+
+/* true when node is initialized */
+static int of_node_is_initialized(const struct device_node *node)
+{
+	return node && node->kobj.state_initialized;
+}
+
+/* true when node is attached (i.e. present on sysfs) */
+int of_node_is_attached(const struct device_node *node)
+{
+	return node && node->kobj.state_in_sysfs;
+}
+
+
+#ifndef CONFIG_OF_DYNAMIC
+static void of_node_release(struct kobject *kobj)
+{
+	/* Without CONFIG_OF_DYNAMIC, no nodes gets freed */
+}
+#endif /* CONFIG_OF_DYNAMIC */
+
+const struct kobj_type of_node_ktype = {
+	.release = of_node_release,
+};
+EXPORT_SYMBOL_IF_KUNIT(of_node_ktype);
+
+static ssize_t of_node_property_read(struct file *filp, struct kobject *kobj,
+				const struct bin_attribute *bin_attr, char *buf,
+				loff_t offset, size_t count)
+{
+	struct property *pp = container_of(bin_attr, struct property, attr);
+	return memory_read_from_buffer(buf, count, &offset, pp->value, pp->length);
+}
+
+/* always return newly allocated name, caller must free after use */
+static const char *safe_name(const struct kobject *kobj, const char *orig_name)
+{
+	const char *name = orig_name;
+	struct kernfs_node *kn;
+	int i = 0;
+
+	/* don't be a hero. After 16 tries give up */
+	while (i < 16 && (kn = sysfs_get_dirent(kobj->sd, name))) {
+		sysfs_put(kn);
+		if (name != orig_name)
+			kfree(name);
+		name = kasprintf(GFP_KERNEL, "%s#%i", orig_name, ++i);
+	}
+
+	if (name == orig_name) {
+		name = kstrdup(orig_name, GFP_KERNEL);
+	} else {
+		pr_warn("Duplicate name in %s, renamed to \"%s\"\n",
+			kobject_name(kobj), name);
+	}
+	return name;
+}
+
+int __of_add_property_sysfs(struct device_node *np, struct property *pp)
+{
+	int rc;
+
+	/* Important: Don't leak passwords */
+	bool secure = strncmp(pp->name, "security-", 9) == 0;
+
+	if (!IS_ENABLED(CONFIG_SYSFS))
+		return 0;
+
+	if (!of_kset || !of_node_is_attached(np))
+		return 0;
+
+	sysfs_bin_attr_init(&pp->attr);
+	pp->attr.attr.name = safe_name(&np->kobj, pp->name);
+	pp->attr.attr.mode = secure ? 0400 : 0444;
+	pp->attr.size = secure ? 0 : pp->length;
+	pp->attr.read = of_node_property_read;
+
+	rc = sysfs_create_bin_file(&np->kobj, &pp->attr);
+	WARN(rc, "error adding attribute %s to node %pOF\n", pp->name, np);
+	return rc;
+}
+
+void __of_sysfs_remove_bin_file(struct device_node *np, const struct property *prop)
+{
+	if (!IS_ENABLED(CONFIG_SYSFS))
+		return;
+
+	sysfs_remove_bin_file(&np->kobj, &prop->attr);
+	kfree(prop->attr.attr.name);
+}
+
+void __of_remove_property_sysfs(struct device_node *np, const struct property *prop)
+{
+	/* at early boot, bail here and defer setup to of_init() */
+	if (of_kset && of_node_is_attached(np))
+		__of_sysfs_remove_bin_file(np, prop);
+}
+
+void __of_update_property_sysfs(struct device_node *np, struct property *newprop,
+		const struct property *oldprop)
+{
+	/* At early boot, bail out and defer setup to of_init() */
+	if (!of_kset)
+		return;
+
+	if (oldprop)
+		__of_sysfs_remove_bin_file(np, oldprop);
+	__of_add_property_sysfs(np, newprop);
+}
+
+int __of_attach_node_sysfs(struct device_node *np)
+{
+	const char *name;
+	struct kobject *parent;
+	struct property *pp;
+	int rc;
+
+	if (!IS_ENABLED(CONFIG_SYSFS) || !of_kset)
+		return 0;
+
+	np->kobj.kset = of_kset;
+	if (!np->parent) {
+		/* Nodes without parents are new top level trees */
+		name = safe_name(&of_kset->kobj, "base");
+		parent = NULL;
+	} else {
+		name = safe_name(&np->parent->kobj, kbasename(np->full_name));
+		parent = &np->parent->kobj;
+	}
+	if (!name)
+		return -ENOMEM;
+
+	rc = kobject_add(&np->kobj, parent, "%s", name);
+	kfree(name);
+	if (rc)
+		return rc;
+
+	for_each_property_of_node(np, pp)
+		__of_add_property_sysfs(np, pp);
+
+	of_node_get(np);
+	return 0;
+}
+
+void __of_detach_node_sysfs(struct device_node *np)
+{
+	struct property *pp;
+
+	BUG_ON(!of_node_is_initialized(np));
+	if (!of_kset)
+		return;
+
+	/* only remove properties if on sysfs */
+	if (of_node_is_attached(np)) {
+		for_each_property_of_node(np, pp)
+			__of_sysfs_remove_bin_file(np, pp);
+		kobject_del(&np->kobj);
+	}
+
+	of_node_put(np);
+}