>Number:         26004
>Category:       port-sparc64
>Synopsis:       kernel bug
>Confidential:   no
>Severity:       serious
>Priority:       high
>Responsible:    port-sparc64-maintainer
>State:          open
>Class:          sw-bug
>Submitter-Id:   net
>Arrival-Date:   Mon Jun 21 22:58:01 UTC 2004
>Closed-Date:
>Last-Modified:
>Originator:     Eric AUGE
>Release:        2.0E-BETA
>Organization:
-
>Environment:
NetBSD voodoo.no.phear.org 2.0_BETA NetBSD 2.0_BETA (VooDoo) #2: Sat May 29 17:44:11 CEST 2004  root@voodoo.no.phear.org:/usr/obj/sys/arch/sparc64/compile/VOODOO sparc64

>Description:
The machine still answers to ping requests, but no tcp connection is possible.

Here what i got displayed continously on the console port :

[...]
psycho0: correctable DMA error AFAR 1093dd40 AFSR 401900007f800000
psycho0: correctable DMA error AFAR 1093dd40 AFSR 401900007f800000
psycho0: correctable DMA error AFAR 1093dd40 AFSR 401900007f800000
psycho0: correctable DMA error AFAR 1093dd40 AFSR 401900007f800000
psycho0: correctable DMA error AFAR 1093dd40 AFSR 401900007f800000
[...]

[send break]

kdb breakpoint at 1337370
Stopped in pid 273.1 (acctwatch) at     netbsd:cpu_Debugger+0x4:        nop
db> bt
sab_intr(243d900, 1, e0017b70, 0, 1308250, e0017e00) at netbsd:sab_intr+0xa4
sparc64_ipi_flush_all(43, 5, 0, 0, 0, 43) at netbsd:sparc64_ipi_flush_all+0x238
printf(14962d0, 243dd34, 1093dd40, 401900007f800000, 2, 1) at netbsd:printf+0x3c
psycho_ce(243dd00, 0, e0017ed0, 401900007f800000, 12fd888, 1) at netbsd:psycho_ce+0x18
sparc64_ipi_flush_all(1475800, 6, e0017ed0, 0, 121b3fc, 1842658) at netbsd:sparc64_ipi_flush_all+0x238
sparc64_ipi_flush_all(11f8314, 0, 14752f0, 5dc, 0, 0) at netbsd:sparc64_ipi_flush_all+0x238
acctwatch(bd6cc00, 0, 0, 23f4e60, a, 40c79fd2) at netbsd:acctwatch+0x9c
proc_trampoline(0, 0, 0, 0, 0, 0) at netbsd:proc_trampoline+0x4
db> 

db> show mount
trap type 0x34: pc=124a5c0 npc=124a5c4 pstate=ffffffff99820016<PEF,PRIV,IE>
kernel trap 34: mem address not aligned
Type  'go' to resume
Faulted in DDB; continuing...
db> 

trap type 0x34: pc=124a5c0 npc=124a5c4 pstate=ffffffff99820006<PRIV,IE>
kernel trap 34: mem address not aligned
Type  'go' to resume
Faulted in DDB; continuing...
db> 

trap type 0x34: pc=124a5c0 npc=124a5c4 pstate=ffffffff99820006<PRIV,IE>
kernel trap 34: mem address not aligned
Type  'go' to resume
ok 

[reboot]
>How-To-Repeat:
No idea
>Fix:

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