linux-kernel - Re: [PATCH 1/2] r8169: Implement dynamic ASPM mechanism

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]

Date:   Fri, 6 Aug 2021 20:47:30 +0200
From:   Heiner Kallweit <hkallweit1@...il.com>
To:     Kai-Heng Feng <kai.heng.feng@...onical.com>, nic_swsd@...ltek.com
Cc:     "David S. Miller" <davem@...emloft.net>,
        Jakub Kicinski <kuba@...nel.org>,
        "open list:8169 10/100/1000 GIGABIT ETHERNET DRIVER" 
        <netdev@...r.kernel.org>, open list <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH 1/2] r8169: Implement dynamic ASPM mechanism

On 03.08.2021 17:28, Kai-Heng Feng wrote:
> r8169 NICs on some platforms have abysmal speed when ASPM is enabled.
> Same issue can be observed with older vendor drivers.
> 
> The issue is however solved by the latest vendor driver. There's a new
> mechanism, which disables r8169's internal ASPM when the NIC has
> substantial network traffic, and vice versa.
> 
> So implement the same mechanism here to resolve the issue.
> 
> Signed-off-by: Kai-Heng Feng <kai.heng.feng@...onical.com>
> ---
>  drivers/net/ethernet/realtek/r8169_main.c | 36 +++++++++++++++++++++++
>  1 file changed, 36 insertions(+)
> 
> diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
> index c7af5bc3b8af..e257d3cd885e 100644
> --- a/drivers/net/ethernet/realtek/r8169_main.c
> +++ b/drivers/net/ethernet/realtek/r8169_main.c
> @@ -624,6 +624,10 @@ struct rtl8169_private {
>  
>  	unsigned supports_gmii:1;
>  	unsigned aspm_manageable:1;
> +	unsigned aspm_enabled:1;
> +	struct timer_list aspm_timer;
> +	u32 aspm_packet_count;
> +
>  	dma_addr_t counters_phys_addr;
>  	struct rtl8169_counters *counters;
>  	struct rtl8169_tc_offsets tc_offset;
> @@ -2671,6 +2675,8 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
>  		RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
>  	}
>  
> +	tp->aspm_enabled = enable;
> +
>  	udelay(10);
>  }
>  
> @@ -4408,6 +4414,7 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp,
>  
>  	dirty_tx = tp->dirty_tx;
>  
> +	tp->aspm_packet_count += tp->cur_tx - dirty_tx;
>  	while (READ_ONCE(tp->cur_tx) != dirty_tx) {
>  		unsigned int entry = dirty_tx % NUM_TX_DESC;
>  		u32 status;
> @@ -4552,6 +4559,8 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, int budget
>  		rtl8169_mark_to_asic(desc);
>  	}
>  
> +	tp->aspm_packet_count += count;
> +
>  	return count;
>  }
>  
> @@ -4659,8 +4668,31 @@ static int r8169_phy_connect(struct rtl8169_private *tp)
>  	return 0;
>  }
>  
> +#define ASPM_PACKET_THRESHOLD 10
> +#define ASPM_TIMER_INTERVAL 1000
> +
> +static void rtl8169_aspm_timer(struct timer_list *timer)
> +{
> +	struct rtl8169_private *tp = from_timer(tp, timer, aspm_timer);
> +	bool enable;
> +
> +	enable = tp->aspm_packet_count <= ASPM_PACKET_THRESHOLD;
> +
> +	if (tp->aspm_enabled != enable) {
> +		rtl_unlock_config_regs(tp);
> +		rtl_hw_aspm_clkreq_enable(tp, enable);
> +		rtl_lock_config_regs(tp);
> +	}
> +
> +	tp->aspm_packet_count = 0;
> +
> +	mod_timer(timer, jiffies + msecs_to_jiffies(ASPM_TIMER_INTERVAL));
> +}
> +
>  static void rtl8169_down(struct rtl8169_private *tp)
>  {
> +	del_timer_sync(&tp->aspm_timer);
> +
>  	/* Clear all task flags */
>  	bitmap_zero(tp->wk.flags, RTL_FLAG_MAX);
>  
> @@ -4687,6 +4719,10 @@ static void rtl8169_up(struct rtl8169_private *tp)
>  	rtl_reset_work(tp);
>  
>  	phy_start(tp->phydev);
> +
> +	timer_setup(&tp->aspm_timer, rtl8169_aspm_timer, 0);
> +	mod_timer(&tp->aspm_timer,
> +		  jiffies + msecs_to_jiffies(ASPM_TIMER_INTERVAL));
>  }
>  
>  static int rtl8169_close(struct net_device *dev)
> 

I have one more question / concern regarding this workaround:
If bigger traffic starts and results in a congestion (let's call it like that
because we don't know in detail what happens in the chip), then it may take
up to a second until ASPM gets disabled and traffic gets back to normal.
This second is good enough to prevent that the timeout watchdog fires.
However in this second supposedly traffic is very limited, if possible at all.
Means if we have a network traffic pattern with alternating quiet and busy
periods then we may see a significant impact on performance.
Is this something that you tested?