Re: [PATCH] af_packet: Don't use skb after dev_queue_xmit()

[Michael Breuer <mbreuer@majjas.com>]

On 1/6/2010 4:10 PM, Stephen Hemminger wrote:
> On Wed, 06 Jan 2010 14:49:38 -0500
> Michael Breuer<mbreuer@majjas.com>  wrote:
>
>    
>> This patch at first behaved similarly to the previous one - seemed to be
>> running a bit better... until the adapter went down :(
>>
>> This is the syslog output at the time the network failed:
>> Jan  6 14:11:01 mail kernel: sky2 0000:06:00.0: error interrupt
>> status=0x40000008
>> Jan  6 14:11:01 mail kernel: sky2 software interrupt status 0x40000008
>>      
> Could you go back to baseline sky2 driver.  The display code might be buggy.
> These bits indicate an error in the MAC. The interrupt source enabled
> is Transmit FIFO underrun.
>
> Looking at how vendor driver handles this.
> It looks like the Yukon EC_U chip doesn't really do Jumbo frames correctly.
> Maybe not enough internal buffering to ensure that the whole packet
> is in the chip.  Of course, none of this is in the chip manual.
>
> Does this help
> --------------
> --- a/drivers/net/sky2.c	2010-01-06 12:48:43.012318966 -0800
> +++ b/drivers/net/sky2.c	2010-01-06 13:05:31.273987255 -0800
> @@ -792,33 +792,21 @@ static void sky2_set_tx_stfwd(struct sky
>   {
>   	struct net_device *dev = hw->dev[port];
>
> -	if ( (hw->chip_id == CHIP_ID_YUKON_EX&&
> -	      hw->chip_rev != CHIP_REV_YU_EX_A0) ||
> -	     hw->chip_id>= CHIP_ID_YUKON_FE_P) {
> -		/* Yukon-Extreme B0 and further Extreme devices */
> -		/* enable Store&  Forward mode for TX */
> -
> -		if (dev->mtu<= ETH_DATA_LEN)
> -			sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T),
> -				     TX_JUMBO_DIS | TX_STFW_ENA);
> -
> -		else
> -			sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T),
> -				     TX_JUMBO_ENA| TX_STFW_ENA);
> -	} else {
> -		if (dev->mtu<= ETH_DATA_LEN)
> -			sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T), TX_STFW_ENA);
> -		else {
> -			/* set Tx GMAC FIFO Almost Empty Threshold */
> -			sky2_write32(hw, SK_REG(port, TX_GMF_AE_THR),
> -				     (ECU_JUMBO_WM<<  16) | ECU_AE_THR);
> -
> -			sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T), TX_STFW_DIS);
> -
> -			/* Can't do offload because of lack of store/forward */
> -			dev->features&= ~(NETIF_F_TSO | NETIF_F_SG | NETIF_F_ALL_CSUM);
> -		}
> -	}
> +       if ( (hw->chip_id == CHIP_ID_YUKON_EX&&  hw->chip_rev != CHIP_REV_YU_EX_A0) ||
> +	    hw->chip_id>= CHIP_ID_YUKON_FE_P) {
> +	       /* Yukon-Extreme B0 and further Extreme devices */
> +	       /* enable Store&  Forward mode for TX */
> +	       sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T), TX_STFW_ENA);
> +       } else if (dev->mtu>  ETH_DATA_LEN) {
> +	       /* set Tx GMAC FIFO Almost Empty Threshold */
> +	       sky2_write32(hw, SK_REG(port, TX_GMF_AE_THR),
> +			    (ECU_JUMBO_WM<<  16) | ECU_AE_THR);
> +	       /* disable Store&  Forward mode for TX */
> +	       sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T), TX_STFW_DIS);
> +       } else {
> +	       /* enable Store&  Forward mode for TX */
> +	       sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T), TX_STFW_ENA);
> +       }
>   }
>
>   static void sky2_mac_init(struct sky2_hw *hw, unsigned port)
> @@ -2185,11 +2173,16 @@ static int sky2_change_mtu(struct net_de
>   	if (new_mtu<  ETH_ZLEN || new_mtu>  ETH_JUMBO_MTU)
>   		return -EINVAL;
>
> +	/* MTU>  1500 on yukon FE and FE+ not allowed */
>   	if (new_mtu>  ETH_DATA_LEN&&
>   	(hw->chip_id == CHIP_ID_YUKON_FE ||
>   	     hw->chip_id == CHIP_ID_YUKON_FE_P))
>   		return -EINVAL;
>
> +	/* TSO on Yukon Ultra and MTU>  1500 not supported */
> +	if (new_mtu>  ETH_DATA_LEN&&  hw->chip_id == CHIP_ID_YUKON_EC_U)
> +		dev->features&= ~NETIF_F_TSO;
> +
>   	if (!netif_running(dev)) {
>   		dev->mtu = new_mtu;
>   		return 0;
> @@ -2233,6 +2226,15 @@ static int sky2_change_mtu(struct net_de
>   	if (err)
>   		dev_close(dev);
>   	else {
> +		/* WA for dev. #4.209 */
> +		if (hw->chip_id == CHIP_ID_YUKON_EC_U&&
> +		    hw->chip_rev == CHIP_REV_YU_EC_U_A1) {
> +			/* enable/disable Store&  Forward mode for TX */
> +			sky2_write32(hw, SK_REG(port, TX_GMF_CTRL_T),
> +				     sky2->speed != SPEED_1000
> +				     ? TX_STFW_ENA : TX_STFW_DIS);
> +		}
> +
>   		gma_write16(hw, port, GM_GP_CTRL, ctl);
>
>   		netif_wake_queue(dev);
> --- a/drivers/net/sky2.h	2010-01-06 12:48:48.632247424 -0800
> +++ b/drivers/net/sky2.h	2010-01-06 12:59:57.322078964 -0800
> @@ -1901,8 +1901,8 @@ enum {
>   	TX_VLAN_TAG_ON	= 1<<25,/* enable  VLAN tagging */
>   	TX_VLAN_TAG_OFF	= 1<<24,/* disable VLAN tagging */
>
> -	TX_JUMBO_ENA	= 1<<23,/* PCI Jumbo Mode enable (Yukon-EC Ultra) */
> -	TX_JUMBO_DIS	= 1<<22,/* PCI Jumbo Mode enable (Yukon-EC Ultra) */
> +	TX_PCI_JUM_ENA	= 1<<23,/* Enable  PCI Jumbo Mode (Yukon-EC Ultra) */
> +	TX_PCI_JUM_DIS	= 1<<22,/* Disable PCI Jumbo Mode (Yukon-EC Ultra) */
>
>   	GMF_WSP_TST_ON	= 1<<18,/* Write Shadow Pointer Test On */
>   	GMF_WSP_TST_OFF	= 1<<17,/* Write Shadow Pointer Test Off */
>    
I'll try this a bit later today. However, early on, I saw the same 
issues with MTU=1500. Also, maybe I'm missing something, but I can only 
recreate the issue with a high receive rate. Given the interaction with 
DHCP, for example, I'm thinking that there is some precondition that is 
as yet unknown. May be buggy hardware, or perhaps a race condition 
resulting in a corrupt i/o buffer somewhere. I'm wondering whether 
there's some useful place to insert some diagnostics on the RX side - at 
least we can see if there are any consistent events on the RX side 
preceding the TX error.