Revision 9cc02ede696272c5271a401e4f27c262359bc2f6 authored by Duoming Zhou on 29 June 2022, 00:26:40 UTC, committed by Paolo Abeni on 30 June 2022, 09:07:30 UTC
There are UAF bugs in rose_heartbeat_expiry(), rose_timer_expiry()
and rose_idletimer_expiry(). The root cause is that del_timer()
could not stop the timer handler that is running and the refcount
of sock is not managed properly.

One of the UAF bugs is shown below:

    (thread 1)          |        (thread 2)
                        |  rose_bind
                        |  rose_connect
                        |    rose_start_heartbeat
rose_release            |    (wait a time)
  case ROSE_STATE_0     |
  rose_destroy_socket   |  rose_heartbeat_expiry
    rose_stop_heartbeat |
    sock_put(sk)        |    ...
  sock_put(sk) // FREE  |
                        |    bh_lock_sock(sk) // USE

The sock is deallocated by sock_put() in rose_release() and
then used by bh_lock_sock() in rose_heartbeat_expiry().

Although rose_destroy_socket() calls rose_stop_heartbeat(),
it could not stop the timer that is running.

The KASAN report triggered by POC is shown below:

BUG: KASAN: use-after-free in _raw_spin_lock+0x5a/0x110
Write of size 4 at addr ffff88800ae59098 by task swapper/3/0
...
Call Trace:
 <IRQ>
 dump_stack_lvl+0xbf/0xee
 print_address_description+0x7b/0x440
 print_report+0x101/0x230
 ? irq_work_single+0xbb/0x140
 ? _raw_spin_lock+0x5a/0x110
 kasan_report+0xed/0x120
 ? _raw_spin_lock+0x5a/0x110
 kasan_check_range+0x2bd/0x2e0
 _raw_spin_lock+0x5a/0x110
 rose_heartbeat_expiry+0x39/0x370
 ? rose_start_heartbeat+0xb0/0xb0
 call_timer_fn+0x2d/0x1c0
 ? rose_start_heartbeat+0xb0/0xb0
 expire_timers+0x1f3/0x320
 __run_timers+0x3ff/0x4d0
 run_timer_softirq+0x41/0x80
 __do_softirq+0x233/0x544
 irq_exit_rcu+0x41/0xa0
 sysvec_apic_timer_interrupt+0x8c/0xb0
 </IRQ>
 <TASK>
 asm_sysvec_apic_timer_interrupt+0x1b/0x20
RIP: 0010:default_idle+0xb/0x10
RSP: 0018:ffffc9000012fea0 EFLAGS: 00000202
RAX: 000000000000bcae RBX: ffff888006660f00 RCX: 000000000000bcae
RDX: 0000000000000001 RSI: ffffffff843a11c0 RDI: ffffffff843a1180
RBP: dffffc0000000000 R08: dffffc0000000000 R09: ffffed100da36d46
R10: dfffe9100da36d47 R11: ffffffff83cf0950 R12: 0000000000000000
R13: 1ffff11000ccc1e0 R14: ffffffff8542af28 R15: dffffc0000000000
...
Allocated by task 146:
 __kasan_kmalloc+0xc4/0xf0
 sk_prot_alloc+0xdd/0x1a0
 sk_alloc+0x2d/0x4e0
 rose_create+0x7b/0x330
 __sock_create+0x2dd/0x640
 __sys_socket+0xc7/0x270
 __x64_sys_socket+0x71/0x80
 do_syscall_64+0x43/0x90
 entry_SYSCALL_64_after_hwframe+0x46/0xb0

Freed by task 152:
 kasan_set_track+0x4c/0x70
 kasan_set_free_info+0x1f/0x40
 ____kasan_slab_free+0x124/0x190
 kfree+0xd3/0x270
 __sk_destruct+0x314/0x460
 rose_release+0x2fa/0x3b0
 sock_close+0xcb/0x230
 __fput+0x2d9/0x650
 task_work_run+0xd6/0x160
 exit_to_user_mode_loop+0xc7/0xd0
 exit_to_user_mode_prepare+0x4e/0x80
 syscall_exit_to_user_mode+0x20/0x40
 do_syscall_64+0x4f/0x90
 entry_SYSCALL_64_after_hwframe+0x46/0xb0

This patch adds refcount of sock when we use functions
such as rose_start_heartbeat() and so on to start timer,
and decreases the refcount of sock when timer is finished
or deleted by functions such as rose_stop_heartbeat()
and so on. As a result, the UAF bugs could be mitigated.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Duoming Zhou <duoming@zju.edu.cn>
Tested-by: Duoming Zhou <duoming@zju.edu.cn>
Link: https://lore.kernel.org/r/20220629002640.5693-1-duoming@zju.edu.cn
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
1 parent f8ebb3a
Raw File
syscall.c
// SPDX-License-Identifier: GPL-2.0
#include <linux/ptrace.h>
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
#include <linux/export.h>
#include <asm/syscall.h>

static int collect_syscall(struct task_struct *target, struct syscall_info *info)
{
	unsigned long args[6] = { };
	struct pt_regs *regs;

	if (!try_get_task_stack(target)) {
		/* Task has no stack, so the task isn't in a syscall. */
		memset(info, 0, sizeof(*info));
		info->data.nr = -1;
		return 0;
	}

	regs = task_pt_regs(target);
	if (unlikely(!regs)) {
		put_task_stack(target);
		return -EAGAIN;
	}

	info->sp = user_stack_pointer(regs);
	info->data.instruction_pointer = instruction_pointer(regs);

	info->data.nr = syscall_get_nr(target, regs);
	if (info->data.nr != -1L)
		syscall_get_arguments(target, regs, args);

	info->data.args[0] = args[0];
	info->data.args[1] = args[1];
	info->data.args[2] = args[2];
	info->data.args[3] = args[3];
	info->data.args[4] = args[4];
	info->data.args[5] = args[5];

	put_task_stack(target);
	return 0;
}

/**
 * task_current_syscall - Discover what a blocked task is doing.
 * @target:		thread to examine
 * @info:		structure with the following fields:
 *			 .sp        - filled with user stack pointer
 *			 .data.nr   - filled with system call number or -1
 *			 .data.args - filled with @maxargs system call arguments
 *			 .data.instruction_pointer - filled with user PC
 *
 * If @target is blocked in a system call, returns zero with @info.data.nr
 * set to the call's number and @info.data.args filled in with its
 * arguments. Registers not used for system call arguments may not be available
 * and it is not kosher to use &struct user_regset calls while the system
 * call is still in progress.  Note we may get this result if @target
 * has finished its system call but not yet returned to user mode, such
 * as when it's stopped for signal handling or syscall exit tracing.
 *
 * If @target is blocked in the kernel during a fault or exception,
 * returns zero with *@info.data.nr set to -1 and does not fill in
 * @info.data.args. If so, it's now safe to examine @target using
 * &struct user_regset get() calls as long as we're sure @target won't return
 * to user mode.
 *
 * Returns -%EAGAIN if @target does not remain blocked.
 */
int task_current_syscall(struct task_struct *target, struct syscall_info *info)
{
	unsigned long ncsw;
	unsigned int state;

	if (target == current)
		return collect_syscall(target, info);

	state = READ_ONCE(target->__state);
	if (unlikely(!state))
		return -EAGAIN;

	ncsw = wait_task_inactive(target, state);
	if (unlikely(!ncsw) ||
	    unlikely(collect_syscall(target, info)) ||
	    unlikely(wait_task_inactive(target, state) != ncsw))
		return -EAGAIN;

	return 0;
}
back to top