Files
linux/fs/notify/fdinfo.c
Jakub Acs a7c4bb43bf fs/notify: call exportfs_encode_fid with s_umount
Calling intotify_show_fdinfo() on fd watching an overlayfs inode, while
the overlayfs is being unmounted, can lead to dereferencing NULL ptr.

This issue was found by syzkaller.

Race Condition Diagram:

Thread 1                           Thread 2
--------                           --------

generic_shutdown_super()
 shrink_dcache_for_umount
  sb->s_root = NULL

                    |
                    |             vfs_read()
                    |              inotify_fdinfo()
                    |               * inode get from mark *
                    |               show_mark_fhandle(m, inode)
                    |                exportfs_encode_fid(inode, ..)
                    |                 ovl_encode_fh(inode, ..)
                    |                  ovl_check_encode_origin(inode)
                    |                   * deref i_sb->s_root *
                    |
                    |
                    v
 fsnotify_sb_delete(sb)

Which then leads to:

[   32.133461] Oops: general protection fault, probably for non-canonical address 0xdffffc0000000006: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN NOPTI
[   32.134438] KASAN: null-ptr-deref in range [0x0000000000000030-0x0000000000000037]
[   32.135032] CPU: 1 UID: 0 PID: 4468 Comm: systemd-coredum Not tainted 6.17.0-rc6 #22 PREEMPT(none)

<snip registers, unreliable trace>

[   32.143353] Call Trace:
[   32.143732]  ovl_encode_fh+0xd5/0x170
[   32.144031]  exportfs_encode_inode_fh+0x12f/0x300
[   32.144425]  show_mark_fhandle+0xbe/0x1f0
[   32.145805]  inotify_fdinfo+0x226/0x2d0
[   32.146442]  inotify_show_fdinfo+0x1c5/0x350
[   32.147168]  seq_show+0x530/0x6f0
[   32.147449]  seq_read_iter+0x503/0x12a0
[   32.148419]  seq_read+0x31f/0x410
[   32.150714]  vfs_read+0x1f0/0x9e0
[   32.152297]  ksys_read+0x125/0x240

IOW ovl_check_encode_origin derefs inode->i_sb->s_root, after it was set
to NULL in the unmount path.

Fix it by protecting calling exportfs_encode_fid() from
show_mark_fhandle() with s_umount lock.

This form of fix was suggested by Amir in [1].

[1]: https://lore.kernel.org/all/CAOQ4uxhbDwhb+2Brs1UdkoF0a3NSdBAOQPNfEHjahrgoKJpLEw@mail.gmail.com/

Fixes: c45beebfde ("ovl: support encoding fid from inode with no alias")
Signed-off-by: Jakub Acs <acsjakub@amazon.de>
Cc: Jan Kara <jack@suse.cz>
Cc: Amir Goldstein <amir73il@gmail.com>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Christian Brauner <brauner@kernel.org>
Cc: linux-unionfs@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Jan Kara <jack@suse.cz>
2025-10-06 16:31:52 +02:00

154 lines
4.2 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/fsnotify_backend.h>
#include <linux/idr.h>
#include <linux/init.h>
#include <linux/inotify.h>
#include <linux/fanotify.h>
#include <linux/kernel.h>
#include <linux/namei.h>
#include <linux/sched.h>
#include <linux/types.h>
#include <linux/seq_file.h>
#include <linux/exportfs.h>
#include "inotify/inotify.h"
#include "fanotify/fanotify.h"
#include "fdinfo.h"
#include "fsnotify.h"
#include "../internal.h"
#if defined(CONFIG_PROC_FS)
#if defined(CONFIG_INOTIFY_USER) || defined(CONFIG_FANOTIFY)
static void show_fdinfo(struct seq_file *m, struct file *f,
void (*show)(struct seq_file *m,
struct fsnotify_mark *mark))
{
struct fsnotify_group *group = f->private_data;
struct fsnotify_mark *mark;
fsnotify_group_lock(group);
list_for_each_entry(mark, &group->marks_list, g_list) {
show(m, mark);
if (seq_has_overflowed(m))
break;
}
fsnotify_group_unlock(group);
}
#if defined(CONFIG_EXPORTFS)
static void show_mark_fhandle(struct seq_file *m, struct inode *inode)
{
DEFINE_FLEX(struct file_handle, f, f_handle, handle_bytes, MAX_HANDLE_SZ);
int size, ret, i;
size = f->handle_bytes >> 2;
if (!super_trylock_shared(inode->i_sb))
return;
ret = exportfs_encode_fid(inode, (struct fid *)f->f_handle, &size);
up_read(&inode->i_sb->s_umount);
if ((ret == FILEID_INVALID) || (ret < 0))
return;
f->handle_type = ret;
f->handle_bytes = size * sizeof(u32);
seq_printf(m, "fhandle-bytes:%x fhandle-type:%x f_handle:",
f->handle_bytes, f->handle_type);
for (i = 0; i < f->handle_bytes; i++)
seq_printf(m, "%02x", (int)f->f_handle[i]);
}
#else
static void show_mark_fhandle(struct seq_file *m, struct inode *inode)
{
}
#endif
#ifdef CONFIG_INOTIFY_USER
static void inotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
{
struct inotify_inode_mark *inode_mark;
struct inode *inode;
if (mark->connector->type != FSNOTIFY_OBJ_TYPE_INODE)
return;
inode_mark = container_of(mark, struct inotify_inode_mark, fsn_mark);
inode = igrab(fsnotify_conn_inode(mark->connector));
if (inode) {
seq_printf(m, "inotify wd:%x ino:%lx sdev:%x mask:%x ignored_mask:0 ",
inode_mark->wd, inode->i_ino, inode->i_sb->s_dev,
inotify_mark_user_mask(mark));
show_mark_fhandle(m, inode);
seq_putc(m, '\n');
iput(inode);
}
}
void inotify_show_fdinfo(struct seq_file *m, struct file *f)
{
show_fdinfo(m, f, inotify_fdinfo);
}
#endif /* CONFIG_INOTIFY_USER */
#ifdef CONFIG_FANOTIFY
static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
{
unsigned int mflags = fanotify_mark_user_flags(mark);
struct inode *inode;
if (mark->connector->type == FSNOTIFY_OBJ_TYPE_INODE) {
inode = igrab(fsnotify_conn_inode(mark->connector));
if (!inode)
return;
seq_printf(m, "fanotify ino:%lx sdev:%x mflags:%x mask:%x ignored_mask:%x ",
inode->i_ino, inode->i_sb->s_dev,
mflags, mark->mask, mark->ignore_mask);
show_mark_fhandle(m, inode);
seq_putc(m, '\n');
iput(inode);
} else if (mark->connector->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
struct mount *mnt = fsnotify_conn_mount(mark->connector);
seq_printf(m, "fanotify mnt_id:%x mflags:%x mask:%x ignored_mask:%x\n",
mnt->mnt_id, mflags, mark->mask, mark->ignore_mask);
} else if (mark->connector->type == FSNOTIFY_OBJ_TYPE_SB) {
struct super_block *sb = fsnotify_conn_sb(mark->connector);
seq_printf(m, "fanotify sdev:%x mflags:%x mask:%x ignored_mask:%x\n",
sb->s_dev, mflags, mark->mask, mark->ignore_mask);
} else if (mark->connector->type == FSNOTIFY_OBJ_TYPE_MNTNS) {
struct mnt_namespace *mnt_ns = fsnotify_conn_mntns(mark->connector);
seq_printf(m, "fanotify mnt_ns:%u mflags:%x mask:%x ignored_mask:%x\n",
mnt_ns->ns.inum, mflags, mark->mask, mark->ignore_mask);
}
}
void fanotify_show_fdinfo(struct seq_file *m, struct file *f)
{
struct fsnotify_group *group = f->private_data;
seq_printf(m, "fanotify flags:%x event-flags:%x\n",
group->fanotify_data.flags & FANOTIFY_INIT_FLAGS,
group->fanotify_data.f_flags);
show_fdinfo(m, f, fanotify_fdinfo);
}
#endif /* CONFIG_FANOTIFY */
#endif /* CONFIG_INOTIFY_USER || CONFIG_FANOTIFY */
#endif /* CONFIG_PROC_FS */