Files
linux/kernel/audit_fsnotify.c
Ricardo Robaina 81905b5acb audit: fix recursive locking deadlock in audit_dupe_exe()
A deadlock occurs in the audit subsystem when duplicating
executable-related rules.

When a file is moved (e.g., via do_renameat2()), the VFS layer locks
the parent directory (I_MUTEX_PARENT), which synchronously triggers an
fsnotify_move event. If an existing executable audit rule matches the
file being moved, the audit subsystem catches this event and calls
audit_dupe_exe() to duplicate the watch and update the rule. Then,
audit_alloc_mark() would call kern_path_parent() to resolve the path,
leading to a blind attempt to acquire the exact same I_MUTEX_PARENT lock
already held by the task, resulting in the following recursive locking
deadlock:

 ============================================
 WARNING: possible recursive locking detected
 6.12.0-55.27.1.el10_0.x86_64+debug #1 Not tainted
 --------------------------------------------
 mv/5099 is trying to acquire lock:
 ffff888132845358 (&inode->i_sb->s_type->i_mutex_dir_key/1){+.+.}-{3:3},
 at: __kern_path_locked+0x10a/0x2f0

 but task is already holding lock:
 ffff888132846b58 (&inode->i_sb->s_type->i_mutex_dir_key/1){+.+.}-{3:3},
 at: lock_two_directories+0x13f/0x2b0

 other info that might help us debug this:
  Possible unsafe locking scenario:

        CPU0
        ----
   lock(&inode->i_sb->s_type->i_mutex_dir_key/1);
   lock(&inode->i_sb->s_type->i_mutex_dir_key/1);

  *** DEADLOCK ***

  May be due to missing lock nesting notation

  6 locks held by mv/5099:
  #0: ffff888112a9c440 (sb_writers#13)
  at: do_renameat2+0x34c/0xbc0
  #1: ffff888112a9c790 (&type->s_vfs_rename_key#3)
  at: do_renameat2+0x415/0xbc0
  #2: ffff888132846b58 (&inode->i_sb->s_type->i_mutex_dir_key/1)
  at: lock_two_directories+0x13f/0x2b0
  #3: ffff888132845358 (&inode->i_sb->s_type->i_mutex_dir_key/5)
  at: lock_two_directories+0x175/0x2b0
  #4: ffffffffb3a1fb10 (&fsnotify_mark_srcu)
  at: fsnotify+0x454/0x28a0
  #5: ffffffffaf886230 (audit_filter_mutex)
  at: audit_update_watch+0x36/0x11e0

 stack backtrace:
 Call Trace:
  <TASK>
  dump_stack_lvl+0x6f/0xb0
  print_deadlock_bug.cold+0xbd/0xca
  validate_chain+0x83a/0xf00
  __lock_acquire+0xcac/0x1d20
  lock_acquire.part.0+0x11b/0x360
  down_write_nested+0x9f/0x230
  __kern_path_locked+0x10a/0x2f0
  kern_path_locked+0x26/0x40
  audit_alloc_mark+0xfb/0x4f0
  audit_dupe_exe+0x6c/0xe0
  audit_dupe_rule+0x6c2/0xc00
  audit_update_watch+0x4cc/0x11e0
  audit_watch_handle_event+0x12c/0x1b0
  send_to_group+0x5d0/0x8b0
  fsnotify+0x615/0x28a0
  fsnotify_move+0x1d8/0x630
  vfs_rename+0xdcd/0x1df0
  do_renameat2+0x9d4/0xbc0
  __x64_sys_renameat+0x192/0x260
  do_syscall_64+0x92/0x180
  entry_SYSCALL_64_after_hwframe+0x76/0x7e
 RIP: 0033:0x7f0491fe8c4e
 Code: 0f 1f 40 00 48 8b 15 c1 e1 16 00 f7 d8 64 89 02 b8 ff ff ff ff
 c3 66 0f 1f 44 00 00 f3 0f 1e fa 49 89 ca b8 08 01 00 00 0f 05 <48>
 3d 00 f0 ff ff 77 0a c3 66 0f 1f 84 00 00 00 00 00 48 8b 15 89
 RSP: 002b:00007ffc7210bf38 EFLAGS: 00000246 ORIG_RAX: 0000000000000108
 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f0491fe8c4e
 RDX: 0000000000000003 RSI: 00007ffc7210e6c8 RDI: 00000000ffffff9c
 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000001
 R10: 00005575eb2dae2a R11: 0000000000000246 R12: 00005575eb2dae2a
 R13: 00007ffc7210e6c8 R14: 0000000000000003 R15: 00000000ffffff9c
  </TASK>

The aforementioned deadlock can be consistently reproduced by running
the script below:

 audit-dupe-exe-deadlock.sh
 --------------------------
 #!/bin/bash
 auditctl -D
 mkdir -p /tmp/foo
 touch /tmp/file
 auditctl -a always,exit -F exe=/tmp/file -F path=/tmp/file -S all -k dr
 mv /tmp/file /tmp/foo/file
 rm -Rf /tmp/foo

This patch fixes the issue by introducing struct audit_watch_ctx to pass
the fsnotify event context down to audit_alloc_mark(). By utilizing the
already-resolved directory inode provided by the event, we bypass the
kern_path_parent() path resolution entirely, safely avoiding the
recursive lock. Furthermore, it explicitly allows duplicate fsnotify
marks (allow_dups = 1) during the rename update, allowing the new rule's
mark to safely coexist with the old rule's mark until the old rule is
freed.

P.S.: This issue was identified and reproduced during a comprehensive
code coverage analysis of the audit subsystem. The full report is
available at the link below:

https://people.redhat.com/rrobaina/audit-code-coverage-analysis.pdf

P.P.S: With the permission of both Ricardo and Nathan, I've squashed a
fixup patch from Nathan that addresses a compile time error when
CONFIG_AUDITSYSCALL=n.

Cc: stable@kernel.org
Fixes: 34d99af52a ("audit: implement audit by executable")
Acked-by: Waiman Long <longman@redhat.com>
Acked-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Ricardo Robaina <rrobaina@redhat.com>
[PM: move link metadata into the msg, apply fix from NC]
Signed-off-by: Paul Moore <paul@paul-moore.com>
2026-05-27 19:15:34 -04:00

205 lines
5.4 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/* audit_fsnotify.c -- tracking inodes
*
* Copyright 2003-2009,2014-2015 Red Hat, Inc.
* Copyright 2005 Hewlett-Packard Development Company, L.P.
* Copyright 2005 IBM Corporation
*/
#include <linux/kernel.h>
#include <linux/audit.h>
#include <linux/kthread.h>
#include <linux/mutex.h>
#include <linux/fs.h>
#include <linux/fsnotify_backend.h>
#include <linux/namei.h>
#include <linux/netlink.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/security.h>
#include "audit.h"
/*
* this mark lives on the parent directory of the inode in question.
* but dev, ino, and path are about the child
*/
struct audit_fsnotify_mark {
dev_t dev; /* associated superblock device */
u64 ino; /* associated inode number */
char *path; /* insertion path */
struct fsnotify_mark mark; /* fsnotify mark on the inode */
struct audit_krule *rule;
};
/* fsnotify handle. */
static struct fsnotify_group *audit_fsnotify_group;
/* fsnotify events we care about. */
#define AUDIT_FS_EVENTS (FS_MOVE | FS_CREATE | FS_DELETE | FS_DELETE_SELF |\
FS_MOVE_SELF)
static void audit_fsnotify_mark_free(struct audit_fsnotify_mark *audit_mark)
{
kfree(audit_mark->path);
kfree(audit_mark);
}
static void audit_fsnotify_free_mark(struct fsnotify_mark *mark)
{
struct audit_fsnotify_mark *audit_mark;
audit_mark = container_of(mark, struct audit_fsnotify_mark, mark);
audit_fsnotify_mark_free(audit_mark);
}
char *audit_mark_path(struct audit_fsnotify_mark *mark)
{
return mark->path;
}
int audit_mark_compare(struct audit_fsnotify_mark *mark, u64 ino, dev_t dev)
{
if (mark->ino == AUDIT_INO_UNSET)
return 0;
return (mark->ino == ino) && (mark->dev == dev);
}
static void audit_update_mark(struct audit_fsnotify_mark *audit_mark,
const struct inode *inode)
{
audit_mark->dev = inode ? inode->i_sb->s_dev : AUDIT_DEV_UNSET;
audit_mark->ino = inode ? inode->i_ino : AUDIT_INO_UNSET;
}
struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pathname,
int len, struct audit_watch_ctx *ctx)
{
struct audit_fsnotify_mark *audit_mark;
struct path path;
struct dentry *dentry;
struct inode *dir, *child;
int ret, allow_dups;
if (pathname[0] != '/' || pathname[len-1] == '/')
return ERR_PTR(-EINVAL);
if (!ctx) {
dentry = kern_path_parent(pathname, &path);
if (IS_ERR(dentry))
return ERR_CAST(dentry); /* returning an error */
dir = d_inode(path.dentry);
child = d_inode(dentry);
allow_dups = 0;
} else {
dir = ctx->dir;
child = ctx->child;
allow_dups = 1;
}
audit_mark = kzalloc_obj(*audit_mark);
if (unlikely(!audit_mark)) {
audit_mark = ERR_PTR(-ENOMEM);
goto out;
}
fsnotify_init_mark(&audit_mark->mark, audit_fsnotify_group);
audit_mark->mark.mask = AUDIT_FS_EVENTS;
audit_mark->path = pathname;
audit_mark->rule = krule;
audit_update_mark(audit_mark, child);
ret = fsnotify_add_inode_mark(&audit_mark->mark, dir, allow_dups);
if (ret < 0) {
audit_mark->path = NULL;
fsnotify_put_mark(&audit_mark->mark);
audit_mark = ERR_PTR(ret);
}
out:
if (!ctx) {
dput(dentry);
path_put(&path);
}
return audit_mark;
}
static void audit_mark_log_rule_change(struct audit_fsnotify_mark *audit_mark, char *op)
{
struct audit_buffer *ab;
struct audit_krule *rule = audit_mark->rule;
if (!audit_enabled)
return;
ab = audit_log_start(audit_context(), GFP_NOFS, AUDIT_CONFIG_CHANGE);
if (unlikely(!ab))
return;
audit_log_session_info(ab);
audit_log_format(ab, " op=%s path=", op);
audit_log_untrustedstring(ab, audit_mark->path);
audit_log_key(ab, rule->filterkey);
audit_log_format(ab, " list=%d res=1", rule->listnr);
audit_log_end(ab);
}
void audit_remove_mark(struct audit_fsnotify_mark *audit_mark)
{
fsnotify_destroy_mark(&audit_mark->mark, audit_fsnotify_group);
fsnotify_put_mark(&audit_mark->mark);
}
void audit_remove_mark_rule(struct audit_krule *krule)
{
struct audit_fsnotify_mark *mark = krule->exe;
audit_remove_mark(mark);
}
static void audit_autoremove_mark_rule(struct audit_fsnotify_mark *audit_mark)
{
struct audit_krule *rule = audit_mark->rule;
struct audit_entry *entry = container_of(rule, struct audit_entry, rule);
audit_mark_log_rule_change(audit_mark, "autoremove_rule");
audit_del_rule(entry);
}
/* Update mark data in audit rules based on fsnotify events. */
static int audit_mark_handle_event(struct fsnotify_mark *inode_mark, u32 mask,
struct inode *inode, struct inode *dir,
const struct qstr *dname, u32 cookie)
{
struct audit_fsnotify_mark *audit_mark;
audit_mark = container_of(inode_mark, struct audit_fsnotify_mark, mark);
if (WARN_ON_ONCE(inode_mark->group != audit_fsnotify_group))
return 0;
if (mask & (FS_CREATE|FS_MOVED_TO|FS_DELETE|FS_MOVED_FROM)) {
if (audit_compare_dname_path(dname, audit_mark->path, AUDIT_NAME_FULL))
return 0;
audit_update_mark(audit_mark, inode);
} else if (mask & (FS_DELETE_SELF|FS_UNMOUNT|FS_MOVE_SELF)) {
audit_autoremove_mark_rule(audit_mark);
}
return 0;
}
static const struct fsnotify_ops audit_mark_fsnotify_ops = {
.handle_inode_event = audit_mark_handle_event,
.free_mark = audit_fsnotify_free_mark,
};
static int __init audit_fsnotify_init(void)
{
audit_fsnotify_group = fsnotify_alloc_group(&audit_mark_fsnotify_ops,
FSNOTIFY_GROUP_DUPS);
if (IS_ERR(audit_fsnotify_group)) {
audit_fsnotify_group = NULL;
audit_panic("cannot create audit fsnotify group");
}
return 0;
}
device_initcall(audit_fsnotify_init);