Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Tue, 7 Jan 2020 22:41:53 +0800
From:   Changbin Du <changbin.du@gmail.com>
To:     Changbin Du <changbin.du@gmail.com>
Cc:     Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
        hpa@zytor.com, x86@kernel.org,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        linux-kernel@vger.kernel.org
Subject: Re: [PATCH] x86/nmi: remove the irqwork from long duration nmi
 handler
Message-ID: <20200107144153.ysspbqtuwbywpjnm@mail.google.com>
References: <20200101072017.82990-1-changbin.du@gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20200101072017.82990-1-changbin.du@gmail.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Hi, Thomas,
Have you checked this one? I think this even can consider as a fix.

On Wed, Jan 01, 2020 at 03:20:17PM +0800, Changbin Du wrote:
> First, printk is NMI context safe now since the safe printk has been
> implemented. The safe printk already has an irqwork to make NMI context
> safe.
> 
> Second, the NMI irqwork actually does not work if a NMI handler causes
> panic by watchdog timeout. This NMI irqwork have no chance to run in such
> case, while the safe printk will flush its per-cpu buffer before panic.
> 
> Signed-off-by: Changbin Du <changbin.du@gmail.com>
> ---
>  arch/x86/include/asm/nmi.h |  1 -
>  arch/x86/kernel/nmi.c      | 20 +++++++++-----------
>  2 files changed, 9 insertions(+), 12 deletions(-)
> 
> diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
> index 75ded1d13d98..9d5d949e662e 100644
> --- a/arch/x86/include/asm/nmi.h
> +++ b/arch/x86/include/asm/nmi.h
> @@ -41,7 +41,6 @@ struct nmiaction {
>  	struct list_head	list;
>  	nmi_handler_t		handler;
>  	u64			max_duration;
> -	struct irq_work		irq_work;
>  	unsigned long		flags;
>  	const char		*name;
>  };
> diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
> index e676a9916c49..aa15d4f2340f 100644
> --- a/arch/x86/kernel/nmi.c
> +++ b/arch/x86/kernel/nmi.c
> @@ -104,18 +104,22 @@ static int __init nmi_warning_debugfs(void)
>  }
>  fs_initcall(nmi_warning_debugfs);
>  
> -static void nmi_max_handler(struct irq_work *w)
> +static void nmi_check_duration(struct nmiaction *action, u64 duration)
>  {
> -	struct nmiaction *a = container_of(w, struct nmiaction, irq_work);
>  	int remainder_ns, decimal_msecs;
> -	u64 whole_msecs = READ_ONCE(a->max_duration);
> +	u64 whole_msecs = READ_ONCE(action->max_duration);
> +
> +	if (duration < nmi_longest_ns || duration < action->max_duration)
> +		return;
> +
> +	action->max_duration = duration;
>  
>  	remainder_ns = do_div(whole_msecs, (1000 * 1000));
>  	decimal_msecs = remainder_ns / 1000;
>  
>  	printk_ratelimited(KERN_INFO
>  		"INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n",
> -		a->handler, whole_msecs, decimal_msecs);
> +		action->handler, whole_msecs, decimal_msecs);
>  }
>  
>  static int nmi_handle(unsigned int type, struct pt_regs *regs)
> @@ -142,11 +146,7 @@ static int nmi_handle(unsigned int type, struct pt_regs *regs)
>  		delta = sched_clock() - delta;
>  		trace_nmi_handler(a->handler, (int)delta, thishandled);
>  
> -		if (delta < nmi_longest_ns || delta < a->max_duration)
> -			continue;
> -
> -		a->max_duration = delta;
> -		irq_work_queue(&a->irq_work);
> +		nmi_check_duration(a, delta);
>  	}
>  
>  	rcu_read_unlock();
> @@ -164,8 +164,6 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action)
>  	if (!action->handler)
>  		return -EINVAL;
>  
> -	init_irq_work(&action->irq_work, nmi_max_handler);
> -
>  	raw_spin_lock_irqsave(&desc->lock, flags);
>  
>  	/*
> -- 
> 2.24.0
> 

-- 
Cheers,
Changbin Du