netdev - Re: [PATCH net] igb: fix deadlock caused by taking RTNL in RPM resume path

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20211129150920.4a400828@hermes.local>
Date:   Mon, 29 Nov 2021 15:09:20 -0800
From:   Stephen Hemminger <stephen@...workplumber.org>
To:     Heiner Kallweit <hkallweit1@...il.com>
Cc:     Jakub Kicinski <kuba@...nel.org>,
        David Miller <davem@...emloft.net>,
        Jesse Brandeburg <jesse.brandeburg@...el.com>,
        Tony Nguyen <anthony.l.nguyen@...el.com>,
        "netdev@...r.kernel.org" <netdev@...r.kernel.org>,
        intel-wired-lan <intel-wired-lan@...ts.osuosl.org>
Subject: Re: [PATCH net] igb: fix deadlock caused by taking RTNL in RPM
 resume path

On Mon, 29 Nov 2021 22:14:06 +0100
Heiner Kallweit <hkallweit1@...il.com> wrote:

> diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
> index dd208930f..8073cce73 100644
> --- a/drivers/net/ethernet/intel/igb/igb_main.c
> +++ b/drivers/net/ethernet/intel/igb/igb_main.c
> @@ -9254,7 +9254,7 @@ static int __maybe_unused igb_suspend(struct device *dev)
>  	return __igb_shutdown(to_pci_dev(dev), NULL, 0);
>  }
>  
> -static int __maybe_unused igb_resume(struct device *dev)
> +static int __maybe_unused __igb_resume(struct device *dev, bool rpm)
>  {
>  	struct pci_dev *pdev = to_pci_dev(dev);
>  	struct net_device *netdev = pci_get_drvdata(pdev);
> @@ -9297,17 +9297,24 @@ static int __maybe_unused igb_resume(struct device *dev)
>  
>  	wr32(E1000_WUS, ~0);
>  
> -	rtnl_lock();
> +	if (!rpm)
> +		rtnl_lock();
>  	if (!err && netif_running(netdev))
>  		err = __igb_open(netdev, true);
>  
>  	if (!err)
>  		netif_device_attach(netdev);
> -	rtnl_unlock();
> +	if (!rpm)
> +		rtnl_unlock();
>  
>  	return err;
>  }
>  
> +static int __maybe_unused igb_resume(struct device *dev)
> +{
> +	return __igb_resume(dev, false);
> +}
> +
>  static int __maybe_unused igb_runtime_idle(struct device *dev)
>  {
>  	struct net_device *netdev = dev_get_drvdata(dev);
> @@ -9326,7 +9333,7 @@ static int __maybe_unused igb_runtime_suspend(struct device *dev)
>  
>  static int __maybe_unused igb_runtime_resume(struct device *dev)
>  {
> -	return igb_resume(dev);
> +	return __igb_resume(dev, true);
>  }

Rather than conditional locking which is one of the seven deadly sins of SMP,
why not just have __igb_resume() be the locked version where lock is held by caller?