Re: e100 NETDEV WATCHDOG transmit timeout since 2.6.4

Re: e100 NETDEV WATCHDOG transmit timeout since 2.6.4

[Mike Keehan]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset=us-ascii, Size: 1526 bytes --]

I am getting these too in recent kernels, but only on a
10Mhz half-duplex network. I have to manually down
and up the interface to recover.

On a 100Mhz switched network, the e100 is OK (at least 12hours+).

Mike.

NETDEV WATCHDOG: eth0: transmit timed out
--- Mike@Keehan.net wrote:
> ----- Forwarded message from Eamonn Hamilton
> <EAMONN.HAMILTON@saic.com> -----
> 
> Subject: e100 NETDEV WATCHDOG transmit timeout since 2.6.4
> From: Eamonn Hamilton <EAMONN.HAMILTON@saic.com>
> To: linux-kernel@vger.kernel.org
> Date: Tue, 20 Apr 2004 10:13:33 +0100
> 
> Hi,
> 
> Since 2.6.4 my ethernet interface is timing out after successfully
> operating for 30 minutes or so, and is reset by the watchdog and runs
> for another 30 minutes or so. This behaviour is only since 2.6.4 when
> I
> believe a rewrite of the code was done. I've tried it with acpi
> disabled, and got the same results if this helps.
> 
> Anybody got any ideas?
> 
> Cheers,
> Eamonn
> -- 
> Eamonn Hamilton <hamiltonea@uk-aberdeen.mail.saic.com>
> 
> -
> To unsubscribe from this list: send the line "unsubscribe
> linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/
> 
> 
> 
> ----- End forwarded message -----



	
		
__________________________________
Do you Yahoo!?
Yahoo! Photos: High-quality 4x6 digital prints for 25¢
http://photos.yahoo.com/ph/print_splash

Re: e100 NETDEV WATCHDOG transmit timeout since 2.6.4

[Scott Feldman]

On Tue, 20 Apr 2004, Mike Keehan wrote:

> I am getting these too in recent kernels, but only on a
> 10Mhz half-duplex network. I have to manually down
> and up the interface to recover.
>
> On a 100Mhz switched network, the e100 is OK (at least 12hours+).


Mike/Eamonn,

Give this patch a try.  This adds a required workaround for ICH when
working at 10/Half.  (Guessing you have an ICH system).

--- linux-2.5/drivers/net/e100.c	2004-04-20 15:52:24.000000000 -0700
+++ linux-2.5/drivers/net/e100.c.mod	2004-04-20 15:55:32.000000000 -0700
@@ -287,6 +287,7 @@ enum scb_cmd_hi {
 };

 enum scb_cmd_lo {
+	cuc_nop        = 0x00,
 	ruc_start      = 0x01,
 	ruc_load_base  = 0x06,
 	cuc_start      = 0x10,
@@ -514,10 +515,11 @@ struct nic {
 	/* End: frequently used values: keep adjacent for cache effect */

 	enum {
-		ich           = (1 << 0),
-		promiscuous   = (1 << 1),
-		multicast_all = (1 << 2),
-		wol_magic     = (1 << 3),
+		ich                = (1 << 0),
+		promiscuous        = (1 << 1),
+		multicast_all      = (1 << 2),
+		wol_magic          = (1 << 3),
+		ich_10h_workaround = (1 << 4),
 	} flags					____cacheline_aligned;

 	enum mac mac;
@@ -1225,6 +1227,12 @@ static void e100_watchdog(unsigned long
 		/* Issue a multicast command to workaround a 557 lock up */
 		e100_set_multicast_list(nic->netdev);

+	if(nic->flags & ich && cmd.speed==SPEED_10 && cmd.duplex==DUPLEX_HALF)
+		/* Need SW workaround for ICH[x] 10Mbps/half duplex Tx hang. */
+		nic->flags |= ich_10h_workaround;
+	else
+		nic->flags &= ~ich_10h_workaround;
+
 	mod_timer(&nic->watchdog, jiffies + E100_WATCHDOG_PERIOD);
 }

@@ -1244,7 +1252,17 @@ static inline void e100_xmit_prepare(str
 static int e100_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct nic *nic = netdev->priv;
-	int err = e100_exec_cb(nic, skb, e100_xmit_prepare);
+	int err;
+
+	if(nic->flags & ich_10h_workaround) {
+		/* SW workaround for ICH[x] 10Mbps/half duplex Tx hang.
+		   Issue a NOP command followed by a 1us delay before
+		   issuing the Tx command. */
+		e100_exec_cmd(nic, cuc_nop, 0);
+		udelay(1);
+	}
+
+	err = e100_exec_cb(nic, skb, e100_xmit_prepare);

 	switch(err) {
 	case -ENOSPC:

Re: e100 NETDEV WATCHDOG transmit timeout since 2.6.4

[Eamonn Hamilton]

Hi Scott,

Thanks for the patch - a bit of manual fumbling to get it applied, but
it seems to work ok so far ( ~46 minutes, so it's not exactly definitive
:)

Certainly it doesn't make things worse in my case at least.

Cheers,
Eamonn

On Wed, 2004-04-21 at 00:04, Scott Feldman wrote:
> On Tue, 20 Apr 2004, Mike Keehan wrote:
> 
> > I am getting these too in recent kernels, but only on a
> > 10Mhz half-duplex network. I have to manually down
> > and up the interface to recover.
> >
> > On a 100Mhz switched network, the e100 is OK (at least 12hours+).
> 
> 
> Mike/Eamonn,
> 
> Give this patch a try.  This adds a required workaround for ICH when
> working at 10/Half.  (Guessing you have an ICH system).
> 
> --- linux-2.5/drivers/net/e100.c	2004-04-20 15:52:24.000000000 -0700
> +++ linux-2.5/drivers/net/e100.c.mod	2004-04-20 15:55:32.000000000 -0700
> @@ -287,6 +287,7 @@ enum scb_cmd_hi {
>  };
> 
>  enum scb_cmd_lo {
> +	cuc_nop        = 0x00,
>  	ruc_start      = 0x01,
>  	ruc_load_base  = 0x06,
>  	cuc_start      = 0x10,
> @@ -514,10 +515,11 @@ struct nic {
>  	/* End: frequently used values: keep adjacent for cache effect */
> 
>  	enum {
> -		ich           = (1 << 0),
> -		promiscuous   = (1 << 1),
> -		multicast_all = (1 << 2),
> -		wol_magic     = (1 << 3),
> +		ich                = (1 << 0),
> +		promiscuous        = (1 << 1),
> +		multicast_all      = (1 << 2),
> +		wol_magic          = (1 << 3),
> +		ich_10h_workaround = (1 << 4),
>  	} flags					____cacheline_aligned;
> 
>  	enum mac mac;
> @@ -1225,6 +1227,12 @@ static void e100_watchdog(unsigned long
>  		/* Issue a multicast command to workaround a 557 lock up */
>  		e100_set_multicast_list(nic->netdev);
> 
> +	if(nic->flags & ich && cmd.speed==SPEED_10 && cmd.duplex==DUPLEX_HALF)
> +		/* Need SW workaround for ICH[x] 10Mbps/half duplex Tx hang. */
> +		nic->flags |= ich_10h_workaround;
> +	else
> +		nic->flags &= ~ich_10h_workaround;
> +
>  	mod_timer(&nic->watchdog, jiffies + E100_WATCHDOG_PERIOD);
>  }
> 
> @@ -1244,7 +1252,17 @@ static inline void e100_xmit_prepare(str
>  static int e100_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
>  {
>  	struct nic *nic = netdev->priv;
> -	int err = e100_exec_cb(nic, skb, e100_xmit_prepare);
> +	int err;
> +
> +	if(nic->flags & ich_10h_workaround) {
> +		/* SW workaround for ICH[x] 10Mbps/half duplex Tx hang.
> +		   Issue a NOP command followed by a 1us delay before
> +		   issuing the Tx command. */
> +		e100_exec_cmd(nic, cuc_nop, 0);
> +		udelay(1);
> +	}
> +
> +	err = e100_exec_cb(nic, skb, e100_xmit_prepare);
> 
>  	switch(err) {
>  	case -ENOSPC:
-- 
Eamonn Hamilton

Senior Technical Designer
Technical Projects and Design (North)

Tel : +44 (0) 1224 333833
Fax : +44 (0) 1224 840032
Email eamonn.hamilton@saic.com

Re: e100 NETDEV WATCHDOG transmit timeout since 2.6.4

[Mike Keehan]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset=us-ascii, Size: 3077 bytes --]

HI Scott,

That's a lot better.  

I've been running OK for about four hours on the half duplex network.
The only time that the wathcdog timed out was when I was using
KDE's Konqueror to look at files on a SMB mounted directory
(from an NT 4 system).

Previously the network connection would fail within minutes when
using ssh or ftp to another Linux box.  Now, they have worked
consistently for hours.

Cheers,

   Mike.

--- Scott Feldman <scott.feldman@intel.com> wrote:
> 
> 
> On Tue, 20 Apr 2004, Mike Keehan wrote:
> 
> > I am getting these too in recent kernels, but only on a
> > 10Mhz half-duplex network. I have to manually down
> > and up the interface to recover.
> >
> > On a 100Mhz switched network, the e100 is OK (at least 12hours+).
> 
> 
> Mike/Eamonn,
> 
> Give this patch a try.  This adds a required workaround for ICH when
> working at 10/Half.  (Guessing you have an ICH system).
> 
> --- linux-2.5/drivers/net/e100.c	2004-04-20 15:52:24.000000000 -0700
> +++ linux-2.5/drivers/net/e100.c.mod	2004-04-20 15:55:32.000000000
> -0700
> @@ -287,6 +287,7 @@ enum scb_cmd_hi {
>  };
> 
>  enum scb_cmd_lo {
> +	cuc_nop        = 0x00,
>  	ruc_start      = 0x01,
>  	ruc_load_base  = 0x06,
>  	cuc_start      = 0x10,
> @@ -514,10 +515,11 @@ struct nic {
>  	/* End: frequently used values: keep adjacent for cache effect */
> 
>  	enum {
> -		ich           = (1 << 0),
> -		promiscuous   = (1 << 1),
> -		multicast_all = (1 << 2),
> -		wol_magic     = (1 << 3),
> +		ich                = (1 << 0),
> +		promiscuous        = (1 << 1),
> +		multicast_all      = (1 << 2),
> +		wol_magic          = (1 << 3),
> +		ich_10h_workaround = (1 << 4),
>  	} flags					____cacheline_aligned;
> 
>  	enum mac mac;
> @@ -1225,6 +1227,12 @@ static void e100_watchdog(unsigned long
>  		/* Issue a multicast command to workaround a 557 lock up */
>  		e100_set_multicast_list(nic->netdev);
> 
> +	if(nic->flags & ich && cmd.speed==SPEED_10 &&
> cmd.duplex==DUPLEX_HALF)
> +		/* Need SW workaround for ICH[x] 10Mbps/half duplex Tx hang. */
> +		nic->flags |= ich_10h_workaround;
> +	else
> +		nic->flags &= ~ich_10h_workaround;
> +
>  	mod_timer(&nic->watchdog, jiffies + E100_WATCHDOG_PERIOD);
>  }
> 
> @@ -1244,7 +1252,17 @@ static inline void e100_xmit_prepare(str
>  static int e100_xmit_frame(struct sk_buff *skb, struct net_device
> *netdev)
>  {
>  	struct nic *nic = netdev->priv;
> -	int err = e100_exec_cb(nic, skb, e100_xmit_prepare);
> +	int err;
> +
> +	if(nic->flags & ich_10h_workaround) {
> +		/* SW workaround for ICH[x] 10Mbps/half duplex Tx hang.
> +		   Issue a NOP command followed by a 1us delay before
> +		   issuing the Tx command. */
> +		e100_exec_cmd(nic, cuc_nop, 0);
> +		udelay(1);
> +	}
> +
> +	err = e100_exec_cb(nic, skb, e100_xmit_prepare);
> 
>  	switch(err) {
>  	case -ENOSPC:
> 



	
		
__________________________________
Do you Yahoo!?
Yahoo! Photos: High-quality 4x6 digital prints for 25¢
http://photos.yahoo.com/ph/print_splash