Re: forcedeth received irq with unknown events

[Carl-Daniel Hailfinger <c-d.hailfinger.kernel.2004@gmx.net>]

[-- Attachment #1: Type: text/plain, Size: 1689 bytes --]

Carl-Daniel Hailfinger wrote:
> Simon Peter wrote:
> 
>>Hi there!
>>
>>Since i plugged the DSL-Modem directly to my onboard nForce2 network
>>card (it's a Shuttle AN35-400 Mobo), i constantly get the following
>>messages in my syslog:
>>
>>Apr 29 14:15:02 server kernel: eth0: received irq with unknown events
>>0x1. Please report
>>Apr 29 14:15:33 server last message repeated 28 times
>>Apr 29 14:15:55 server last message repeated 23 times
>>
>>The message seems to be displaying more frequently the more traffic is
>>on the link.
> 
> 
> This 0x1 event is a receive error. It seems only users with cable modems
> have this problem. I've got no idea why it happens with cable modems and
> nothing else, but it could indeed be crappy hardware on the modem side.
> 
> What we don't know yet is if the receive error is hard or soft. Soft
> errors generally can be recovered from, so it would be a shame throwing
> the packets away.
> 
> 
>>Formerly, the nForce2 board was connected to a 100mbps switch to my LAN
>>and i didn't get any of these messages.
> 
> 
> Your switch didn't let the malformed/incorrect packets through, so you
> computer didn't see them.
> 
> 
> 
>>If you need any more info to get this fixed, just reply!
> 
> 
> Could you please try the attached patch (will create LOTS of debug
> messages) for a few minutes and mail the relevant part of your
> /var/log/messages to me privately (it will be >100 kB, so I don't want to
> burden the list with it).

This time with a patch that actually should apply. (for both 2.4 and 2.6)
The previous patch was obsolete since some functions were renamed for
better backtraces.

Thanks,
Carl-Daniel
-- 
http://www.hailfinger.org/

[-- Attachment #2: forcedeth_0x1event_rx_patch3.diff --]
[-- Type: text/plain, Size: 3061 bytes --]

===== drivers/net/forcedeth.c 1.1 vs edited =====
--- 1.1/drivers/net/forcedeth.c	Thu Feb  5 02:11:13 2004
+++ edited/drivers/net/forcedeth.c	Tue Mar  2 21:04:06 2004
@@ -120,6 +120,7 @@
 #define NVREG_IRQSTAT_MIIEVENT	0x040
 #define NVREG_IRQSTAT_MASK		0x1ff
 	NvRegIrqMask = 0x004,
+#define NVREG_IRQ_RX_ERR		0x0001
 #define NVREG_IRQ_RX			0x0002
 #define NVREG_IRQ_RX_NOBUF		0x0004
 #define NVREG_IRQ_TX_ERR		0x0008
@@ -129,7 +130,7 @@
 #define NVREG_IRQ_TX1			0x0100
 #define NVREG_IRQMASK_WANTED_1		0x005f
 #define NVREG_IRQMASK_WANTED_2		0x0147
-#define NVREG_IRQ_UNKNOWN		(~(NVREG_IRQ_RX|NVREG_IRQ_RX_NOBUF|NVREG_IRQ_TX_ERR|NVREG_IRQ_TX2|NVREG_IRQ_TIMER|NVREG_IRQ_LINK|NVREG_IRQ_TX1))
+#define NVREG_IRQ_UNKNOWN		(~(NVREG_IRQ_RX_ERR|NVREG_IRQ_RX|NVREG_IRQ_RX_NOBUF|NVREG_IRQ_TX_ERR|NVREG_IRQ_TX2|NVREG_IRQ_TIMER|NVREG_IRQ_LINK|NVREG_IRQ_TX1))
 
 	NvRegUnknownSetupReg6 = 0x008,
 #define NVREG_UNKSETUP6_VAL		3
@@ -847,7 +848,7 @@
 
 		i = np->cur_rx % RX_RING;
 		prd = &np->rx_ring[i];
-		dprintk(KERN_DEBUG "%s: nv_rx_process: looking at packet %d, Flags 0x%x.\n",
+		printk(KERN_INFO "%s: nv_rx_process: looking at packet %d, Flags 0x%x.\n",
 					dev->name, np->cur_rx, prd->Flags);
 
 		if (prd->Flags & cpu_to_le16(NV_RX_AVAIL))
@@ -880,25 +881,30 @@
 		len = le16_to_cpu(prd->Length);
 
 		if (prd->Flags & cpu_to_le16(NV_RX_MISSEDFRAME)) {
+			printk(KERN_INFO "%s: nv_rx_process: missed frame\n", dev->name);
 			np->stats.rx_missed_errors++;
 			np->stats.rx_errors++;
 			goto next_pkt;
 		}
 		if (prd->Flags & cpu_to_le16(NV_RX_ERROR1|NV_RX_ERROR2|NV_RX_ERROR3|NV_RX_ERROR4)) {
+			printk(KERN_INFO "%s: nv_rx_process: error 1-4\n", dev->name);
 			np->stats.rx_errors++;
 			goto next_pkt;
 		}
 		if (prd->Flags & cpu_to_le16(NV_RX_CRCERR)) {
+			printk(KERN_INFO "%s: nv_rx_process: crc error\n", dev->name);
 			np->stats.rx_crc_errors++;
 			np->stats.rx_errors++;
 			goto next_pkt;
 		}
 		if (prd->Flags & cpu_to_le16(NV_RX_OVERFLOW)) {
+			printk(KERN_INFO "%s: nv_rx_process: overflow\n", dev->name);
 			np->stats.rx_over_errors++;
 			np->stats.rx_errors++;
 			goto next_pkt;
 		}
 		if (prd->Flags & cpu_to_le16(NV_RX_ERROR)) {
+			printk(KERN_INFO "%s: nv_rx_process: generic error\n", dev->name);
 			/* framing errors are soft errors, the rest is fatal. */
 			if (prd->Flags & cpu_to_le16(NV_RX_FRAMINGERR)) {
 				if (prd->Flags & cpu_to_le16(NV_RX_SUBSTRACT1)) {
@@ -1096,7 +1102,7 @@
 			spin_unlock(&np->lock);
 		}
 
-		if (events & (NVREG_IRQ_RX|NVREG_IRQ_RX_NOBUF)) {
+		if (events & (NVREG_IRQ_RX|NVREG_IRQ_RX_NOBUF|NVREG_IRQ_RX_ERR)) {
 			nv_rx_process(dev);
 			if (nv_alloc_rx(dev)) {
 				spin_lock(&np->lock);
@@ -1110,6 +1116,10 @@
 			spin_lock(&np->lock);
 			nv_link_irq(dev);
 			spin_unlock(&np->lock);
+		}
+		if (events & (NVREG_IRQ_RX_ERR)) {
+			printk(KERN_INFO "%s: received irq with events 0x%x. Probably RX fail. Trying to get diagnostics.\n",
+						dev->name, events);
 		}
 		if (events & (NVREG_IRQ_TX_ERR)) {
 			dprintk(KERN_DEBUG "%s: received irq with events 0x%x. Probably TX fail.\n",