kern/118879: bge has checksum problems on the 5703 chipset

[Aaron Seelye]

>Number:         118879
>Category:       kern
>Synopsis:       bge has checksum problems on the 5703 chipset
>Confidential:   no
>Severity:       non-critical
>Priority:       low
>Responsible:    freebsd-bugs
>State:          open
>Quarter:        
>Keywords:       
>Date-Required:
>Class:          sw-bug
>Submitter-Id:   current-users
>Arrival-Date:   Thu Dec 20 05:50:01 UTC 2007
>Closed-Date:
>Last-Modified:
>Originator:     Aaron Seelye
>Release:        6.3-PRERELEASE
>Organization:
Eltopia.com
>Environment:
FreeBSD phone1.eltopia.net 6.3-PRERELEASE FreeBSD 6.3-PRERELEASE #1: Wed Dec 19 20:53:59 PST 2007     toor at phone1.eltopia.net:/usr/obj/usr/src/sys/PHONE  i386
>Description:
Watching outgoing udp packets (from openser) on port 5060 via tshark, I was finding that they were just about all saying that there was a checksum error.  Looking at the source of if_bge.c, I found that the 5700 B0 chipset had a similar problem, so I extended the fix to all the variants of the 5703, as I didn't know which of the 5703s are broken.  This is replicable on a Dell 2650.  Below is a relevant portion of the dmesg regarding the interfaces.  You'll find a patch attached to this pr, but as I'm not anything close to a programmer, I wouldn't doubt if someone would have a better way of doing this.


Dec 19 21:05:30 phone1 kernel: bge0: <Broadcom BCM5703 A2, ASIC rev. 0x1002> mem 0xfcd10000-0xfcd1ffff irq 28 at device 6.0 on pci3
Dec 19 21:05:30 phone1 kernel: miibus0: <MII bus> on bge0
Dec 19 21:05:30 phone1 kernel: brgphy0: <BCM5703 10/100/1000baseTX PHY> on miibus0
Dec 19 21:05:30 phone1 kernel: brgphy0:  10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, 1000baseT, 1000baseT-FDX, auto
Dec 19 21:05:30 phone1 kernel: bge0: Ethernet address: 00:0d:56:71:54:14
Dec 19 21:05:30 phone1 kernel: bge1: <Broadcom BCM5703 A2, ASIC rev. 0x1002> mem 0xfcd00000-0xfcd0ffff irq 29 at device 8.0 on pci3
Dec 19 21:05:30 phone1 kernel: miibus1: <MII bus> on bge1
Dec 19 21:05:30 phone1 kernel: brgphy1: <BCM5703 10/100/1000baseTX PHY> on miibus1
Dec 19 21:05:30 phone1 kernel: brgphy1:  10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, 1000baseT, 1000baseT-FDX, auto
Dec 19 21:05:30 phone1 kernel: bge1: Ethernet address: 00:0d:56:71:54:15

>How-To-Repeat:
Detailed in description above.
>Fix:
Patch is attached.

Patch attached with submission follows:

--- if_bge.c.old	2007-05-08 09:18:21.000000000 -0700
+++ if_bge.c	2007-12-19 20:11:10.000000000 -0800
@@ -2433,6 +2433,36 @@
 		ifp->if_hwassist = 0;
 	}
 
+	if (sc->bge_chipid == BGE_CHIPID_BCM5703_A0) {
+		ifp->if_capabilities &= ~IFCAP_HWCSUM;
+		ifp->if_capenable &= IFCAP_HWCSUM;
+		ifp->if_hwassist = 0;
+	}
+
+	if (sc->bge_chipid == BGE_CHIPID_BCM5703_A1) {
+		ifp->if_capabilities &= ~IFCAP_HWCSUM;
+		ifp->if_capenable &= IFCAP_HWCSUM;
+		ifp->if_hwassist = 0;
+	}
+
+	if (sc->bge_chipid == BGE_CHIPID_BCM5703_A2) {
+		ifp->if_capabilities &= ~IFCAP_HWCSUM;
+		ifp->if_capenable &= IFCAP_HWCSUM;
+		ifp->if_hwassist = 0;
+	}
+
+	if (sc->bge_chipid == BGE_CHIPID_BCM5703_A3) {
+		ifp->if_capabilities &= ~IFCAP_HWCSUM;
+		ifp->if_capenable &= IFCAP_HWCSUM;
+		ifp->if_hwassist = 0;
+	}
+
+	if (sc->bge_chipid == BGE_CHIPID_BCM5703_B0) {
+		ifp->if_capabilities &= ~IFCAP_HWCSUM;
+		ifp->if_capenable &= IFCAP_HWCSUM;
+		ifp->if_hwassist = 0;
+	}
+
 	/*
 	 * Figure out what sort of media we have by checking the
 	 * hardware config word in the first 32k of NIC internal memory,


>Release-Note:
>Audit-Trail:
>Unformatted: