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, 94 insertions, 0 deletions

diff --git a/drivers/acpi/bgrt.c b/drivers/acpi/bgrt.c
new file mode 100644
index 000000000..0fdd581ef
--- /dev/null
+++ b/drivers/acpi/bgrt.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * BGRT boot graphic support
+ * Authors: Matthew Garrett, Josh Triplett <josh@joshtriplett.org>
+ * Copyright 2012 Red Hat, Inc <mjg@redhat.com>
+ * Copyright 2012 Intel Corporation
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/sysfs.h>
+#include <linux/efi-bgrt.h>
+
+static void *bgrt_image;
+static struct kobject *bgrt_kobj;
+
+#define BGRT_SHOW(_name, _member) \
+	static ssize_t _name##_show(struct kobject *kobj,			\
+				    struct kobj_attribute *attr, char *buf)	\
+	{									\
+		return sysfs_emit(buf, "%d\n", bgrt_tab._member);		\
+	}									\
+	static struct kobj_attribute bgrt_attr_##_name = __ATTR_RO(_name)
+
+BGRT_SHOW(version, version);
+BGRT_SHOW(status, status);
+BGRT_SHOW(type, image_type);
+BGRT_SHOW(xoffset, image_offset_x);
+BGRT_SHOW(yoffset, image_offset_y);
+
+static __ro_after_init BIN_ATTR_SIMPLE_RO(image);
+
+static struct attribute *bgrt_attributes[] = {
+	&bgrt_attr_version.attr,
+	&bgrt_attr_status.attr,
+	&bgrt_attr_type.attr,
+	&bgrt_attr_xoffset.attr,
+	&bgrt_attr_yoffset.attr,
+	NULL,
+};
+
+static const struct bin_attribute *const bgrt_bin_attributes[] = {
+	&bin_attr_image,
+	NULL,
+};
+
+static const struct attribute_group bgrt_attribute_group = {
+	.attrs = bgrt_attributes,
+	.bin_attrs = bgrt_bin_attributes,
+};
+
+int __init acpi_parse_bgrt(struct acpi_table_header *table)
+{
+	efi_bgrt_init(table);
+	return 0;
+}
+
+static int __init bgrt_init(void)
+{
+	int ret;
+
+	if (!bgrt_tab.image_address)
+		return -ENODEV;
+
+	bgrt_image = memremap(bgrt_tab.image_address, bgrt_image_size,
+			      MEMREMAP_WB);
+	if (!bgrt_image) {
+		pr_notice("Ignoring BGRT: failed to map image memory\n");
+		return -ENOMEM;
+	}
+
+	bin_attr_image.private = bgrt_image;
+	bin_attr_image.size = bgrt_image_size;
+
+	bgrt_kobj = kobject_create_and_add("bgrt", acpi_kobj);
+	if (!bgrt_kobj) {
+		ret = -EINVAL;
+		goto out_memmap;
+	}
+
+	ret = sysfs_create_group(bgrt_kobj, &bgrt_attribute_group);
+	if (ret)
+		goto out_kobject;
+
+	return 0;
+
+out_kobject:
+	kobject_put(bgrt_kobj);
+out_memmap:
+	memunmap(bgrt_image);
+	return ret;
+}
+device_initcall(bgrt_init);