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, 290 insertions, 0 deletions

diff --git a/drivers/base/soc.c b/drivers/base/soc.c
new file mode 100644
index 000000000..af7d71393
--- /dev/null
+++ b/drivers/base/soc.c
@@ -0,0 +1,290 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) ST-Ericsson SA 2011
+ *
+ * Author: Lee Jones <lee.jones@linaro.org> for ST-Ericsson.
+ */
+
+#include <linux/err.h>
+#include <linux/glob.h>
+#include <linux/idr.h>
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/stat.h>
+#include <linux/sysfs.h>
+#include <linux/sys_soc.h>
+
+static DEFINE_IDA(soc_ida);
+
+/* Prototype to allow declarations of DEVICE_ATTR(<foo>) before soc_info_show */
+static ssize_t soc_info_show(struct device *dev, struct device_attribute *attr,
+			     char *buf);
+
+struct soc_device {
+	struct device dev;
+	struct soc_device_attribute *attr;
+	int soc_dev_num;
+};
+
+static const struct bus_type soc_bus_type = {
+	.name  = "soc",
+};
+static bool soc_bus_registered;
+
+static DEVICE_ATTR(machine,		0444, soc_info_show,  NULL);
+static DEVICE_ATTR(family,		0444, soc_info_show,  NULL);
+static DEVICE_ATTR(serial_number,	0444, soc_info_show,  NULL);
+static DEVICE_ATTR(soc_id,		0444, soc_info_show,  NULL);
+static DEVICE_ATTR(revision,		0444, soc_info_show,  NULL);
+
+struct device *soc_device_to_device(struct soc_device *soc_dev)
+{
+	return &soc_dev->dev;
+}
+
+static umode_t soc_attribute_mode(struct kobject *kobj,
+				struct attribute *attr,
+				int index)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct soc_device *soc_dev = container_of(dev, struct soc_device, dev);
+
+	if ((attr == &dev_attr_machine.attr) && soc_dev->attr->machine)
+		return attr->mode;
+	if ((attr == &dev_attr_family.attr) && soc_dev->attr->family)
+		return attr->mode;
+	if ((attr == &dev_attr_revision.attr) && soc_dev->attr->revision)
+		return attr->mode;
+	if ((attr == &dev_attr_serial_number.attr) && soc_dev->attr->serial_number)
+		return attr->mode;
+	if ((attr == &dev_attr_soc_id.attr) && soc_dev->attr->soc_id)
+		return attr->mode;
+
+	/* Unknown or unfilled attribute */
+	return 0;
+}
+
+static ssize_t soc_info_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	struct soc_device *soc_dev = container_of(dev, struct soc_device, dev);
+	const char *output;
+
+	if (attr == &dev_attr_machine)
+		output = soc_dev->attr->machine;
+	else if (attr == &dev_attr_family)
+		output = soc_dev->attr->family;
+	else if (attr == &dev_attr_revision)
+		output = soc_dev->attr->revision;
+	else if (attr == &dev_attr_serial_number)
+		output = soc_dev->attr->serial_number;
+	else if (attr == &dev_attr_soc_id)
+		output = soc_dev->attr->soc_id;
+	else
+		return -EINVAL;
+
+	return sysfs_emit(buf, "%s\n", output);
+}
+
+static struct attribute *soc_attr[] = {
+	&dev_attr_machine.attr,
+	&dev_attr_family.attr,
+	&dev_attr_serial_number.attr,
+	&dev_attr_soc_id.attr,
+	&dev_attr_revision.attr,
+	NULL,
+};
+
+static const struct attribute_group soc_attr_group = {
+	.attrs = soc_attr,
+	.is_visible = soc_attribute_mode,
+};
+
+static void soc_release(struct device *dev)
+{
+	struct soc_device *soc_dev = container_of(dev, struct soc_device, dev);
+
+	ida_free(&soc_ida, soc_dev->soc_dev_num);
+	kfree(soc_dev->dev.groups);
+	kfree(soc_dev);
+}
+
+int soc_attr_read_machine(struct soc_device_attribute *soc_dev_attr)
+{
+	if (soc_dev_attr->machine)
+		return -EBUSY;
+
+	return of_machine_read_model(&soc_dev_attr->machine);
+}
+EXPORT_SYMBOL_GPL(soc_attr_read_machine);
+
+static struct soc_device_attribute *early_soc_dev_attr;
+
+struct soc_device *soc_device_register(struct soc_device_attribute *soc_dev_attr)
+{
+	struct soc_device *soc_dev;
+	const struct attribute_group **soc_attr_groups;
+	int ret;
+
+	soc_attr_read_machine(soc_dev_attr);
+
+	if (!soc_bus_registered) {
+		if (early_soc_dev_attr)
+			return ERR_PTR(-EBUSY);
+		early_soc_dev_attr = soc_dev_attr;
+		return NULL;
+	}
+
+	soc_dev = kzalloc_obj(*soc_dev);
+	if (!soc_dev) {
+		ret = -ENOMEM;
+		goto out1;
+	}
+
+	soc_attr_groups = kzalloc_objs(*soc_attr_groups, 3);
+	if (!soc_attr_groups) {
+		ret = -ENOMEM;
+		goto out2;
+	}
+	soc_attr_groups[0] = &soc_attr_group;
+	soc_attr_groups[1] = soc_dev_attr->custom_attr_group;
+
+	/* Fetch a unique (reclaimable) SOC ID. */
+	ret = ida_alloc(&soc_ida, GFP_KERNEL);
+	if (ret < 0)
+		goto out3;
+	soc_dev->soc_dev_num = ret;
+
+	soc_dev->attr = soc_dev_attr;
+	soc_dev->dev.bus = &soc_bus_type;
+	soc_dev->dev.groups = soc_attr_groups;
+	soc_dev->dev.release = soc_release;
+
+	dev_set_name(&soc_dev->dev, "soc%d", soc_dev->soc_dev_num);
+
+	ret = device_register(&soc_dev->dev);
+	if (ret) {
+		put_device(&soc_dev->dev);
+		return ERR_PTR(ret);
+	}
+
+	return soc_dev;
+
+out3:
+	kfree(soc_attr_groups);
+out2:
+	kfree(soc_dev);
+out1:
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(soc_device_register);
+
+/* Ensure soc_dev->attr is freed after calling soc_device_unregister. */
+void soc_device_unregister(struct soc_device *soc_dev)
+{
+	device_unregister(&soc_dev->dev);
+	early_soc_dev_attr = NULL;
+}
+EXPORT_SYMBOL_GPL(soc_device_unregister);
+
+static int __init soc_bus_register(void)
+{
+	struct soc_device *soc_dev;
+	int ret;
+
+	ret = bus_register(&soc_bus_type);
+	if (ret)
+		return ret;
+	soc_bus_registered = true;
+
+	if (early_soc_dev_attr) {
+		soc_dev = soc_device_register(early_soc_dev_attr);
+		if (IS_ERR(soc_dev)) {
+			ret = PTR_ERR(soc_dev);
+			goto err_unregister_bus;
+		}
+	}
+
+	return 0;
+
+err_unregister_bus:
+	soc_bus_registered = false;
+	bus_unregister(&soc_bus_type);
+	return ret;
+}
+core_initcall(soc_bus_register);
+
+static int soc_device_match_attr(const struct soc_device_attribute *attr,
+				 const struct soc_device_attribute *match)
+{
+	if (match->machine &&
+	    (!attr->machine || !glob_match(match->machine, attr->machine)))
+		return 0;
+
+	if (match->family &&
+	    (!attr->family || !glob_match(match->family, attr->family)))
+		return 0;
+
+	if (match->revision &&
+	    (!attr->revision || !glob_match(match->revision, attr->revision)))
+		return 0;
+
+	if (match->soc_id &&
+	    (!attr->soc_id || !glob_match(match->soc_id, attr->soc_id)))
+		return 0;
+
+	return 1;
+}
+
+static int soc_device_match_one(struct device *dev, void *arg)
+{
+	struct soc_device *soc_dev = container_of(dev, struct soc_device, dev);
+
+	return soc_device_match_attr(soc_dev->attr, arg);
+}
+
+/*
+ * soc_device_match - identify the SoC in the machine
+ * @matches: zero-terminated array of possible matches
+ *
+ * returns the first matching entry of the argument array, or NULL
+ * if none of them match.
+ *
+ * This function is meant as a helper in place of of_match_node()
+ * in cases where either no device tree is available or the information
+ * in a device node is insufficient to identify a particular variant
+ * by its compatible strings or other properties. For new devices,
+ * the DT binding should always provide unique compatible strings
+ * that allow the use of of_match_node() instead.
+ *
+ * The calling function can use the .data entry of the
+ * soc_device_attribute to pass a structure or function pointer for
+ * each entry.
+ */
+const struct soc_device_attribute *soc_device_match(
+	const struct soc_device_attribute *matches)
+{
+	int ret;
+
+	if (!matches)
+		return NULL;
+
+	while (matches->machine || matches->family || matches->revision ||
+	       matches->soc_id) {
+		ret = bus_for_each_dev(&soc_bus_type, NULL, (void *)matches,
+				       soc_device_match_one);
+		if (ret < 0 && early_soc_dev_attr)
+			ret = soc_device_match_attr(early_soc_dev_attr,
+						    matches);
+		if (ret < 0)
+			return NULL;
+		if (ret)
+			return matches;
+
+		matches++;
+	}
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(soc_device_match);