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, 177 insertions, 0 deletions

diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
new file mode 100644
index 000000000..d8cac1cbf
--- /dev/null
+++ b/fs/configfs/mount.c
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * mount.c - operations for initializing and mounting configfs.
+ *
+ * Based on sysfs:
+ * 	sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel
+ *
+ * configfs Copyright (C) 2005 Oracle.  All rights reserved.
+ */
+
+#include <linux/fs.h>
+#include <linux/magic.h>
+#include <linux/module.h>
+#include <linux/mount.h>
+#include <linux/fs_context.h>
+#include <linux/pagemap.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+
+#include <linux/configfs.h>
+#include "configfs_internal.h"
+
+static struct vfsmount *configfs_mount = NULL;
+struct kmem_cache *configfs_dir_cachep;
+static int configfs_mnt_count = 0;
+
+
+static void configfs_free_inode(struct inode *inode)
+{
+	if (S_ISLNK(inode->i_mode))
+		kfree(inode->i_link);
+	free_inode_nonrcu(inode);
+}
+
+static const struct super_operations configfs_ops = {
+	.statfs		= simple_statfs,
+	.drop_inode	= inode_just_drop,
+	.free_inode	= configfs_free_inode,
+};
+
+static struct config_group configfs_root_group = {
+	.cg_item = {
+		.ci_namebuf	= "root",
+		.ci_name	= configfs_root_group.cg_item.ci_namebuf,
+	},
+};
+
+int configfs_is_root(struct config_item *item)
+{
+	return item == &configfs_root_group.cg_item;
+}
+
+static struct configfs_dirent configfs_root = {
+	.s_sibling	= LIST_HEAD_INIT(configfs_root.s_sibling),
+	.s_children	= LIST_HEAD_INIT(configfs_root.s_children),
+	.s_element	= &configfs_root_group.cg_item,
+	.s_type		= CONFIGFS_ROOT,
+	.s_iattr	= NULL,
+};
+
+static int configfs_fill_super(struct super_block *sb, struct fs_context *fc)
+{
+	struct inode *inode;
+	struct dentry *root;
+
+	sb->s_blocksize = PAGE_SIZE;
+	sb->s_blocksize_bits = PAGE_SHIFT;
+	sb->s_magic = CONFIGFS_MAGIC;
+	sb->s_op = &configfs_ops;
+	sb->s_time_gran = 1;
+
+	inode = configfs_new_inode(S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO,
+				   &configfs_root, sb);
+	if (inode) {
+		inode->i_op = &configfs_root_inode_operations;
+		inode->i_fop = &configfs_dir_operations;
+		/* directory inodes start off with i_nlink == 2 (for "." entry) */
+		inc_nlink(inode);
+	} else {
+		pr_debug("could not get root inode\n");
+		return -ENOMEM;
+	}
+
+	root = d_make_root(inode);
+	if (!root) {
+		pr_debug("%s: could not get root dentry!\n",__func__);
+		return -ENOMEM;
+	}
+	config_group_init(&configfs_root_group);
+	configfs_root_group.cg_item.ci_dentry = root;
+	root->d_fsdata = &configfs_root;
+	sb->s_root = root;
+	set_default_d_op(sb, &configfs_dentry_ops); /* the rest get that */
+	sb->s_d_flags |= DCACHE_DONTCACHE;
+	return 0;
+}
+
+static int configfs_get_tree(struct fs_context *fc)
+{
+	return get_tree_single(fc, configfs_fill_super);
+}
+
+static const struct fs_context_operations configfs_context_ops = {
+	.get_tree	= configfs_get_tree,
+};
+
+static int configfs_init_fs_context(struct fs_context *fc)
+{
+	fc->ops = &configfs_context_ops;
+	return 0;
+}
+
+static struct file_system_type configfs_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "configfs",
+	.init_fs_context = configfs_init_fs_context,
+	.kill_sb	= kill_anon_super,
+};
+MODULE_ALIAS_FS("configfs");
+
+struct dentry *configfs_pin_fs(void)
+{
+	int err = simple_pin_fs(&configfs_fs_type, &configfs_mount,
+			     &configfs_mnt_count);
+	return err ? ERR_PTR(err) : configfs_mount->mnt_root;
+}
+
+void configfs_release_fs(void)
+{
+	simple_release_fs(&configfs_mount, &configfs_mnt_count);
+}
+
+
+static int __init configfs_init(void)
+{
+	int err = -ENOMEM;
+
+	configfs_dir_cachep = kmem_cache_create("configfs_dir_cache",
+						sizeof(struct configfs_dirent),
+						0, 0, NULL);
+	if (!configfs_dir_cachep)
+		goto out;
+
+	err = sysfs_create_mount_point(kernel_kobj, "config");
+	if (err)
+		goto out2;
+
+	err = register_filesystem(&configfs_fs_type);
+	if (err)
+		goto out3;
+
+	return 0;
+out3:
+	pr_err("Unable to register filesystem!\n");
+	sysfs_remove_mount_point(kernel_kobj, "config");
+out2:
+	kmem_cache_destroy(configfs_dir_cachep);
+	configfs_dir_cachep = NULL;
+out:
+	return err;
+}
+
+static void __exit configfs_exit(void)
+{
+	unregister_filesystem(&configfs_fs_type);
+	sysfs_remove_mount_point(kernel_kobj, "config");
+	kmem_cache_destroy(configfs_dir_cachep);
+	configfs_dir_cachep = NULL;
+}
+
+MODULE_AUTHOR("Oracle");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("0.0.2");
+MODULE_DESCRIPTION("Simple RAM filesystem for user driven kernel subsystem configuration.");
+
+core_initcall(configfs_init);
+module_exit(configfs_exit);