Received-SPF: pass (google.com: domain of linux-kernel+bounces-207743-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
Date: Mon, 10 Jun 2024 08:46:51 +0200
From: Peter Zijlstra <peterz@infradead.org>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>, Sam Sun <samsun1006219@gmail.com>,
	linux-kernel@vger.kernel.org, x86@kernel.org,
	syzkaller-bugs@googlegroups.com, jpoimboe@kernel.org,
	jbaron@akamai.com, ardb@kernel.org, mingo@redhat.com,
	Borislav Petkov <bp@alien8.de>, dave.hansen@linux.intel.com,
	hpa@zytor.com, xrivendell7@gmail.com,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Tejun Heo <tj@kernel.org>
Subject: Re: [Linux kernel bug] WARNING in static_key_slow_inc_cpuslocked
Message-ID: <20240610064651.GS8774@noisy.programming.kicks-ass.net>
References: <20240609090431.3af238bc@gandalf.local.home>
 <87o78axlbm.ffs@tglx>
 <20240609102530.0a292b07@rorschach.local.home>
 <87le3exfx2.ffs@tglx>
 <87h6e2xdg1.ffs@tglx>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <87h6e2xdg1.ffs@tglx>

On Sun, Jun 09, 2024 at 06:56:14PM +0200, Thomas Gleixner wrote:

> Ok. Now I found if for real. It's in the jump label core:
> 
> CPU0                            CPU1
> 
> static_key_slow_dec()
>  static_key_slow_try_dec()
> 
>    key->enabled == 1
>    val = atomic_fetch_add_unless(&key->enabled, -1, 1);
>    if (val == 1)
>    	return false;
> 
>    jump_label_lock();
>    if (atomic_dec_and_test(&key->enabled)) {
>       --> key->enabled == 0
>       __jump_label_update()
> 
>                                 static_key_slow_dec()
>                                  static_key_slow_try_dec()
> 
>                                     key->enabled == 0
>                                     val = atomic_fetch_add_unless(&key->enabled, -1, 1);
> 
>                                     --> key->enabled == -1 <- FAIL
> 
> static_key_slow_try_dec() is buggy. It needs similar logic as
> static_key_slow_try_inc() to work correctly.
> 
> It's not only the 0, key->enabled can be -1 when the other CPU is in the
> slow path of enabling it.

Well, the -1 thing is in the 0->1 path, that is, the very first enabler.

That *should* not race with a disabler. If it does, there is external
confusion. (As I think the follow up email shows..)