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, 135 insertions, 0 deletions

diff --git a/fs/zonefs/sysfs.c b/fs/zonefs/sysfs.c
new file mode 100644
index 000000000..ff9a688f1
--- /dev/null
+++ b/fs/zonefs/sysfs.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Simple file system for zoned block devices exposing zones as files.
+ *
+ * Copyright (C) 2022 Western Digital Corporation or its affiliates.
+ */
+#include <linux/fs.h>
+#include <linux/seq_file.h>
+#include <linux/blkdev.h>
+
+#include "zonefs.h"
+
+struct zonefs_sysfs_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct zonefs_sb_info *sbi, char *buf);
+};
+
+#define ZONEFS_SYSFS_ATTR_RO(name) \
+static struct zonefs_sysfs_attr zonefs_sysfs_attr_##name = __ATTR_RO(name)
+
+#define ATTR_LIST(name) &zonefs_sysfs_attr_##name.attr
+
+static ssize_t zonefs_sysfs_attr_show(struct kobject *kobj,
+				      struct attribute *attr, char *buf)
+{
+	struct zonefs_sb_info *sbi =
+		container_of(kobj, struct zonefs_sb_info, s_kobj);
+	struct zonefs_sysfs_attr *zonefs_attr =
+		container_of(attr, struct zonefs_sysfs_attr, attr);
+
+	if (!zonefs_attr->show)
+		return 0;
+
+	return zonefs_attr->show(sbi, buf);
+}
+
+static ssize_t max_wro_seq_files_show(struct zonefs_sb_info *sbi, char *buf)
+{
+	return sysfs_emit(buf, "%u\n", sbi->s_max_wro_seq_files);
+}
+ZONEFS_SYSFS_ATTR_RO(max_wro_seq_files);
+
+static ssize_t nr_wro_seq_files_show(struct zonefs_sb_info *sbi, char *buf)
+{
+	return sysfs_emit(buf, "%d\n", atomic_read(&sbi->s_wro_seq_files));
+}
+ZONEFS_SYSFS_ATTR_RO(nr_wro_seq_files);
+
+static ssize_t max_active_seq_files_show(struct zonefs_sb_info *sbi, char *buf)
+{
+	return sysfs_emit(buf, "%u\n", sbi->s_max_active_seq_files);
+}
+ZONEFS_SYSFS_ATTR_RO(max_active_seq_files);
+
+static ssize_t nr_active_seq_files_show(struct zonefs_sb_info *sbi, char *buf)
+{
+	return sysfs_emit(buf, "%d\n", atomic_read(&sbi->s_active_seq_files));
+}
+ZONEFS_SYSFS_ATTR_RO(nr_active_seq_files);
+
+static struct attribute *zonefs_sysfs_attrs[] = {
+	ATTR_LIST(max_wro_seq_files),
+	ATTR_LIST(nr_wro_seq_files),
+	ATTR_LIST(max_active_seq_files),
+	ATTR_LIST(nr_active_seq_files),
+	NULL,
+};
+ATTRIBUTE_GROUPS(zonefs_sysfs);
+
+static void zonefs_sysfs_sb_release(struct kobject *kobj)
+{
+	struct zonefs_sb_info *sbi =
+		container_of(kobj, struct zonefs_sb_info, s_kobj);
+
+	complete(&sbi->s_kobj_unregister);
+}
+
+static const struct sysfs_ops zonefs_sysfs_attr_ops = {
+	.show	= zonefs_sysfs_attr_show,
+};
+
+static const struct kobj_type zonefs_sb_ktype = {
+	.default_groups = zonefs_sysfs_groups,
+	.sysfs_ops	= &zonefs_sysfs_attr_ops,
+	.release	= zonefs_sysfs_sb_release,
+};
+
+static struct kobject *zonefs_sysfs_root;
+
+int zonefs_sysfs_register(struct super_block *sb)
+{
+	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
+	int ret;
+
+	super_set_sysfs_name_id(sb);
+	init_completion(&sbi->s_kobj_unregister);
+	ret = kobject_init_and_add(&sbi->s_kobj, &zonefs_sb_ktype,
+				   zonefs_sysfs_root, "%s", sb->s_id);
+	if (ret) {
+		kobject_put(&sbi->s_kobj);
+		wait_for_completion(&sbi->s_kobj_unregister);
+		return ret;
+	}
+
+	sbi->s_sysfs_registered = true;
+
+	return 0;
+}
+
+void zonefs_sysfs_unregister(struct super_block *sb)
+{
+	struct zonefs_sb_info *sbi = ZONEFS_SB(sb);
+
+	if (!sbi || !sbi->s_sysfs_registered)
+		return;
+
+	kobject_del(&sbi->s_kobj);
+	kobject_put(&sbi->s_kobj);
+	wait_for_completion(&sbi->s_kobj_unregister);
+}
+
+int __init zonefs_sysfs_init(void)
+{
+	zonefs_sysfs_root = kobject_create_and_add("zonefs", fs_kobj);
+	if (!zonefs_sysfs_root)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void zonefs_sysfs_exit(void)
+{
+	kobject_put(zonefs_sysfs_root);
+	zonefs_sysfs_root = NULL;
+}