Re: [PATCH 3/3] drivers/net/ftgmac100: fix DHCP potential failure with systemd

[Florian Fainelli <f.fainelli@gmail.com>]

On 2/23/2022 3:39 AM, Heyi Guo wrote:
> Hi Florian,
> 
> 在 2022/2/23 下午1:00, Florian Fainelli 写道:
>>
>>
>> On 2/22/2022 7:14 PM, Heyi Guo wrote:
>>> DHCP failures were observed with systemd 247.6. The issue could be
>>> reproduced by rebooting Aspeed 2600 and then running ifconfig ethX
>>> down/up.
>>>
>>> It is caused by below procedures in the driver:
>>>
>>> 1. ftgmac100_open() enables net interface and call phy_start()
>>> 2. When PHY is link up, it calls netif_carrier_on() and then
>>> adjust_link callback
>>> 3. ftgmac100_adjust_link() will schedule the reset task
>>> 4. ftgmac100_reset_task() will then reset the MAC in another schedule
>>>
>>> After step 2, systemd will be notified to send DHCP discover packet,
>>> while the packet might be corrupted by MAC reset operation in step 4.
>>>
>>> Call ftgmac100_reset() directly instead of scheduling task to fix the
>>> issue.
>>>
>>> Signed-off-by: Heyi Guo <guoheyi@linux.alibaba.com>
>>> ---
>>> Cc: Andrew Lunn <andrew@lunn.ch>
>>> Cc: "David S. Miller" <davem@davemloft.net>
>>> Cc: Jakub Kicinski <kuba@kernel.org>
>>> Cc: Joel Stanley <joel@jms.id.au>
>>> Cc: Guangbin Huang <huangguangbin2@huawei.com>
>>> Cc: Hao Chen <chenhao288@hisilicon.com>
>>> Cc: Arnd Bergmann <arnd@arndb.de>
>>> Cc: Dylan Hung <dylan_hung@aspeedtech.com>
>>> Cc: netdev@vger.kernel.org
>>>
>>>
>>> ---
>>>   drivers/net/ethernet/faraday/ftgmac100.c | 13 +++++++++++--
>>>   1 file changed, 11 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/drivers/net/ethernet/faraday/ftgmac100.c 
>>> b/drivers/net/ethernet/faraday/ftgmac100.c
>>> index c1deb6e5d26c5..d5356db7539a4 100644
>>> --- a/drivers/net/ethernet/faraday/ftgmac100.c
>>> +++ b/drivers/net/ethernet/faraday/ftgmac100.c
>>> @@ -1402,8 +1402,17 @@ static void ftgmac100_adjust_link(struct 
>>> net_device *netdev)
>>>       /* Disable all interrupts */
>>>       iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
>>>   -    /* Reset the adapter asynchronously */
>>> -    schedule_work(&priv->reset_task);
>>> +    /* Release phy lock to allow ftgmac100_reset to aquire it, 
>>> keeping lock
>>
>> typo: acquire
>>
> Thanks for the catch :)
>>> +     * order consistent to prevent dead lock.
>>> +     */
>>> +    if (netdev->phydev)
>>> +        mutex_unlock(&netdev->phydev->lock);
>>> +
>>> +    ftgmac100_reset(priv);
>>> +
>>> +    if (netdev->phydev)
>>> +        mutex_lock(&netdev->phydev->lock);
>>
>> Do you really need to perform a full MAC reset whenever the link goes 
>> up or down? Instead cannot you just extract the maccr configuration 
>> which adjusts the speed and be done with it?
> 
> This is the original behavior and not changed in this patch set, and I'm 
> not familiar with the hardware design of ftgmac100, so I'd like to limit 
> the changes to the code which really causes practical issues.

This unlocking and re-locking seems superfluous when you could introduce 
a version of ftgmac100_reset() which does not acquire the PHY device 
mutex, and have that version called from ftgmac100_adjust_link(). For 
every other call site, you would acquire it. Something like this for 
instance:


diff --git a/drivers/net/ethernet/faraday/ftgmac100.c 
b/drivers/net/ethernet/faraday/ftgmac100.c
index 691605c15265..98179c3fd9ee 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -1038,7 +1038,7 @@ static void ftgmac100_adjust_link(struct 
net_device *netdev)
         iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);

         /* Reset the adapter asynchronously */
-       schedule_work(&priv->reset_task);
+       ftgmac100_reset(priv, false);
  }

  static int ftgmac100_mii_probe(struct net_device *netdev)
@@ -1410,10 +1410,8 @@ static int ftgmac100_init_all(struct ftgmac100 
*priv, bool ignore_alloc_err)
         return err;
  }

-static void ftgmac100_reset_task(struct work_struct *work)
+static void ftgmac100_reset_task(struct ftgmac100_priv *priv, bool 
lock_phy)
  {
-       struct ftgmac100 *priv = container_of(work, struct ftgmac100,
-                                             reset_task);
         struct net_device *netdev = priv->netdev;
         int err;

@@ -1421,7 +1419,7 @@ static void ftgmac100_reset_task(struct 
work_struct *work)

         /* Lock the world */
         rtnl_lock();
-       if (netdev->phydev)
+       if (netdev->phydev && lock_phy)
                 mutex_lock(&netdev->phydev->lock);
         if (priv->mii_bus)
                 mutex_lock(&priv->mii_bus->mdio_lock);
@@ -1454,11 +1452,19 @@ static void ftgmac100_reset_task(struct 
work_struct *work)
   bail:
         if (priv->mii_bus)
                 mutex_unlock(&priv->mii_bus->mdio_lock);
-       if (netdev->phydev)
+       if (netdev->phydev && lock_phy)
                 mutex_unlock(&netdev->phydev->lock);
         rtnl_unlock();
  }

+static void ftgmac100_reset_task(struct work_struct *work)
+{
+       struct ftgmac100 *priv = container_of(work, struct ftgmac100,
+                                             reset_task);
+
+       ftgmac100_reset(priv, true);
+}
+
  static int ftgmac100_open(struct net_device *netdev)
  {
         struct ftgmac100 *priv = netdev_priv(netdev)
-- 
Florian