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, 329 insertions, 0 deletions

diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
new file mode 100644
index 000000000..0a88ede48
--- /dev/null
+++ b/fs/ramfs/inode.c
@@ -0,0 +1,329 @@
+/*
+ * Resizable simple ram filesystem for Linux.
+ *
+ * Copyright (C) 2000 Linus Torvalds.
+ *               2000 Transmeta Corp.
+ *
+ * Usage limits added by David Gibson, Linuxcare Australia.
+ * This file is released under the GPL.
+ */
+
+/*
+ * NOTE! This filesystem is probably most useful
+ * not as a real filesystem, but as an example of
+ * how virtual filesystems can be written.
+ *
+ * It doesn't get much simpler than this. Consider
+ * that this file implements the full semantics of
+ * a POSIX-compliant read-write filesystem.
+ *
+ * Note in particular how the filesystem does not
+ * need to implement any data structures of its own
+ * to keep track of the virtual data: using the VFS
+ * caches is sufficient.
+ */
+
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include <linux/highmem.h>
+#include <linux/time.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/backing-dev.h>
+#include <linux/ramfs.h>
+#include <linux/sched.h>
+#include <linux/parser.h>
+#include <linux/magic.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
+#include <linux/seq_file.h>
+#include "internal.h"
+
+struct ramfs_mount_opts {
+	umode_t mode;
+};
+
+struct ramfs_fs_info {
+	struct ramfs_mount_opts mount_opts;
+};
+
+#define RAMFS_DEFAULT_MODE	0755
+
+static const struct super_operations ramfs_ops;
+static const struct inode_operations ramfs_dir_inode_operations;
+
+struct inode *ramfs_get_inode(struct super_block *sb,
+				const struct inode *dir, umode_t mode, dev_t dev)
+{
+	struct inode * inode = new_inode(sb);
+
+	if (inode) {
+		inode->i_ino = get_next_ino();
+		inode_init_owner(&nop_mnt_idmap, inode, dir, mode);
+		inode->i_mapping->a_ops = &ram_aops;
+		mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
+		mapping_set_unevictable(inode->i_mapping);
+		simple_inode_init_ts(inode);
+		switch (mode & S_IFMT) {
+		default:
+			init_special_inode(inode, mode, dev);
+			break;
+		case S_IFREG:
+			inode->i_op = &ramfs_file_inode_operations;
+			inode->i_fop = &ramfs_file_operations;
+			break;
+		case S_IFDIR:
+			inode->i_op = &ramfs_dir_inode_operations;
+			inode->i_fop = &simple_dir_operations;
+
+			/* directory inodes start off with i_nlink == 2 (for "." entry) */
+			inc_nlink(inode);
+			break;
+		case S_IFLNK:
+			inode->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(inode);
+			break;
+		}
+	}
+	return inode;
+}
+
+/*
+ * File creation. Allocate an inode, and we're done..
+ */
+/* SMP-safe */
+static int
+ramfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
+	    struct dentry *dentry, umode_t mode, dev_t dev)
+{
+	struct inode * inode = ramfs_get_inode(dir->i_sb, dir, mode, dev);
+	int error = -ENOSPC;
+
+	if (inode) {
+		error = security_inode_init_security(inode, dir,
+						     &dentry->d_name, NULL,
+						     NULL);
+		if (error) {
+			iput(inode);
+			goto out;
+		}
+
+		d_make_persistent(dentry, inode);
+		error = 0;
+		inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
+	}
+out:
+	return error;
+}
+
+static struct dentry *ramfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
+				 struct dentry *dentry, umode_t mode)
+{
+	int retval = ramfs_mknod(&nop_mnt_idmap, dir, dentry, mode, 0);
+	if (!retval)
+		inc_nlink(dir);
+	return ERR_PTR(retval);
+}
+
+static int ramfs_create(struct mnt_idmap *idmap, struct inode *dir,
+			struct dentry *dentry, umode_t mode)
+{
+	return ramfs_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFREG, 0);
+}
+
+static int ramfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
+			 struct dentry *dentry, const char *symname)
+{
+	struct inode *inode;
+	int error = -ENOSPC;
+
+	inode = ramfs_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0);
+	if (inode) {
+		int l = strlen(symname)+1;
+
+		error = security_inode_init_security(inode, dir,
+						     &dentry->d_name, NULL,
+						     NULL);
+		if (error) {
+			iput(inode);
+			goto out;
+		}
+
+		error = page_symlink(inode, symname, l);
+		if (!error) {
+			d_make_persistent(dentry, inode);
+			inode_set_mtime_to_ts(dir,
+					      inode_set_ctime_current(dir));
+		} else
+			iput(inode);
+	}
+out:
+	return error;
+}
+
+static int ramfs_tmpfile(struct mnt_idmap *idmap,
+			 struct inode *dir, struct file *file, umode_t mode)
+{
+	struct inode *inode;
+	int error;
+
+	inode = ramfs_get_inode(dir->i_sb, dir, mode, 0);
+	if (!inode)
+		return -ENOSPC;
+
+	error = security_inode_init_security(inode, dir,
+					     &file_dentry(file)->d_name, NULL,
+					     NULL);
+	if (error) {
+		iput(inode);
+		goto out;
+	}
+
+	d_tmpfile(file, inode);
+out:
+	return finish_open_simple(file, error);
+}
+
+static const struct inode_operations ramfs_dir_inode_operations = {
+	.create		= ramfs_create,
+	.lookup		= simple_lookup,
+	.link		= simple_link,
+	.unlink		= simple_unlink,
+	.symlink	= ramfs_symlink,
+	.mkdir		= ramfs_mkdir,
+	.rmdir		= simple_rmdir,
+	.mknod		= ramfs_mknod,
+	.rename		= simple_rename,
+	.tmpfile	= ramfs_tmpfile,
+};
+
+/*
+ * Display the mount options in /proc/mounts.
+ */
+static int ramfs_show_options(struct seq_file *m, struct dentry *root)
+{
+	struct ramfs_fs_info *fsi = root->d_sb->s_fs_info;
+
+	if (fsi->mount_opts.mode != RAMFS_DEFAULT_MODE)
+		seq_printf(m, ",mode=%o", fsi->mount_opts.mode);
+	return 0;
+}
+
+static const struct super_operations ramfs_ops = {
+	.statfs		= simple_statfs,
+	.drop_inode	= inode_just_drop,
+	.show_options	= ramfs_show_options,
+};
+
+enum ramfs_param {
+	Opt_mode,
+};
+
+const struct fs_parameter_spec ramfs_fs_parameters[] = {
+	fsparam_u32oct("mode",	Opt_mode),
+	{}
+};
+
+static int ramfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct fs_parse_result result;
+	struct ramfs_fs_info *fsi = fc->s_fs_info;
+	int opt;
+
+	opt = fs_parse(fc, ramfs_fs_parameters, param, &result);
+	if (opt == -ENOPARAM) {
+		opt = vfs_parse_fs_param_source(fc, param);
+		if (opt != -ENOPARAM)
+			return opt;
+		/*
+		 * We might like to report bad mount options here;
+		 * but traditionally ramfs has ignored all mount options,
+		 * and as it is used as a !CONFIG_SHMEM simple substitute
+		 * for tmpfs, better continue to ignore other mount options.
+		 */
+		return 0;
+	}
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_mode:
+		fsi->mount_opts.mode = result.uint_32 & S_IALLUGO;
+		break;
+	}
+
+	return 0;
+}
+
+static int ramfs_fill_super(struct super_block *sb, struct fs_context *fc)
+{
+	struct ramfs_fs_info *fsi = sb->s_fs_info;
+	struct inode *inode;
+
+	sb->s_maxbytes		= MAX_LFS_FILESIZE;
+	sb->s_blocksize		= PAGE_SIZE;
+	sb->s_blocksize_bits	= PAGE_SHIFT;
+	sb->s_magic		= RAMFS_MAGIC;
+	sb->s_op		= &ramfs_ops;
+	sb->s_d_flags		= DCACHE_DONTCACHE;
+	sb->s_time_gran		= 1;
+
+	inode = ramfs_get_inode(sb, NULL, S_IFDIR | fsi->mount_opts.mode, 0);
+	sb->s_root = d_make_root(inode);
+	if (!sb->s_root)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int ramfs_get_tree(struct fs_context *fc)
+{
+	return get_tree_nodev(fc, ramfs_fill_super);
+}
+
+static void ramfs_free_fc(struct fs_context *fc)
+{
+	kfree(fc->s_fs_info);
+}
+
+static const struct fs_context_operations ramfs_context_ops = {
+	.free		= ramfs_free_fc,
+	.parse_param	= ramfs_parse_param,
+	.get_tree	= ramfs_get_tree,
+};
+
+int ramfs_init_fs_context(struct fs_context *fc)
+{
+	struct ramfs_fs_info *fsi;
+
+	fsi = kzalloc_obj(*fsi);
+	if (!fsi)
+		return -ENOMEM;
+
+	fsi->mount_opts.mode = RAMFS_DEFAULT_MODE;
+	fc->s_fs_info = fsi;
+	fc->ops = &ramfs_context_ops;
+	return 0;
+}
+
+void ramfs_kill_sb(struct super_block *sb)
+{
+	kfree(sb->s_fs_info);
+	kill_anon_super(sb);
+}
+
+static struct file_system_type ramfs_fs_type = {
+	.name		= "ramfs",
+	.init_fs_context = ramfs_init_fs_context,
+	.parameters	= ramfs_fs_parameters,
+	.kill_sb	= ramfs_kill_sb,
+	.fs_flags	= FS_USERNS_MOUNT,
+};
+
+static int __init init_ramfs_fs(void)
+{
+	return register_filesystem(&ramfs_fs_type);
+}
+fs_initcall(init_ramfs_fs);