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, 136 insertions, 0 deletions

diff --git a/drivers/firmware/google/cbmem.c b/drivers/firmware/google/cbmem.c
new file mode 100644
index 000000000..4d20477ed
--- /dev/null
+++ b/drivers/firmware/google/cbmem.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * cbmem.c
+ *
+ * Driver for exporting cbmem entries in sysfs.
+ *
+ * Copyright 2022 Google LLC
+ */
+
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/device-id/coreboot.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+
+#include "coreboot_table.h"
+
+struct cbmem_entry {
+	char *mem_file_buf;
+	u32 size;
+};
+
+static struct cbmem_entry *to_cbmem_entry(struct kobject *kobj)
+{
+	return dev_get_drvdata(kobj_to_dev(kobj));
+}
+
+static ssize_t mem_read(struct file *filp, struct kobject *kobj,
+			const struct bin_attribute *bin_attr, char *buf, loff_t pos,
+			size_t count)
+{
+	struct cbmem_entry *entry = to_cbmem_entry(kobj);
+
+	return memory_read_from_buffer(buf, count, &pos, entry->mem_file_buf,
+				       entry->size);
+}
+
+static ssize_t mem_write(struct file *filp, struct kobject *kobj,
+			 const struct bin_attribute *bin_attr, char *buf, loff_t pos,
+			 size_t count)
+{
+	struct cbmem_entry *entry = to_cbmem_entry(kobj);
+
+	if (pos < 0 || pos >= entry->size)
+		return -EINVAL;
+	if (count > entry->size - pos)
+		count = entry->size - pos;
+
+	memcpy(entry->mem_file_buf + pos, buf, count);
+	return count;
+}
+static const BIN_ATTR_ADMIN_RW(mem, 0);
+
+static ssize_t address_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	struct coreboot_device *cbdev = dev_to_coreboot_device(dev);
+
+	return sysfs_emit(buf, "0x%llx\n", cbdev->cbmem_entry.address);
+}
+static DEVICE_ATTR_RO(address);
+
+static ssize_t size_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct coreboot_device *cbdev = dev_to_coreboot_device(dev);
+
+	return sysfs_emit(buf, "0x%x\n", cbdev->cbmem_entry.entry_size);
+}
+static DEVICE_ATTR_RO(size);
+
+static struct attribute *attrs[] = {
+	&dev_attr_address.attr,
+	&dev_attr_size.attr,
+	NULL,
+};
+
+static const struct bin_attribute *const bin_attrs[] = {
+	&bin_attr_mem,
+	NULL,
+};
+
+static const struct attribute_group cbmem_entry_group = {
+	.attrs = attrs,
+	.bin_attrs = bin_attrs,
+};
+
+static const struct attribute_group *dev_groups[] = {
+	&cbmem_entry_group,
+	NULL,
+};
+
+static int cbmem_entry_probe(struct coreboot_device *dev)
+{
+	struct cbmem_entry *entry;
+
+	entry = devm_kzalloc(&dev->dev, sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	dev_set_drvdata(&dev->dev, entry);
+	entry->mem_file_buf = devm_memremap(&dev->dev, dev->cbmem_entry.address,
+					    dev->cbmem_entry.entry_size,
+					    MEMREMAP_WB);
+	if (IS_ERR(entry->mem_file_buf))
+		return PTR_ERR(entry->mem_file_buf);
+
+	entry->size = dev->cbmem_entry.entry_size;
+
+	return 0;
+}
+
+static const struct coreboot_device_id cbmem_ids[] = {
+	{ .tag = LB_TAG_CBMEM_ENTRY },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(coreboot, cbmem_ids);
+
+static struct coreboot_driver cbmem_entry_driver = {
+	.probe = cbmem_entry_probe,
+	.drv = {
+		.name = "cbmem",
+		.dev_groups = dev_groups,
+	},
+	.id_table = cbmem_ids,
+};
+module_coreboot_driver(cbmem_entry_driver);
+
+MODULE_AUTHOR("Jack Rosenthal <jrosenth@chromium.org>");
+MODULE_DESCRIPTION("Driver for exporting CBMEM entries in sysfs");
+MODULE_LICENSE("GPL");