Hi Matt, > This is most likely to be the cache aliasing bug I'm hunting. What are > the dimensions of your cache? Here's the kernel messages up to the cache initialization: [ 0.000000] Linux version 2.6.30.2 (dlarson@UbuntuDale) (gcc version 4.3.4 (GCC) ) #2 Fri Sep 11 08:13:33 CDT 2009 [ 0.000000] Boot params: [ 0.000000] ... MOUNT_ROOT_RDONLY - 00000001 [ 0.000000] ... RAMDISK_FLAGS - 00000000 [ 0.000000] ... ORIG_ROOT_DEV - 00000200 [ 0.000000] ... LOADER_TYPE - 00000001 [ 0.000000] ... INITRD_START - 00000000 [ 0.000000] ... INITRD_SIZE - 00000000 [ 0.000000] Early serial console at MMIO 0x18000008 (options '115200n8') [ 0.000000] console [uart0] enabled [ 0.000000] Booting machvec: jci7763 [ 0.000000] Node 0: start_pfn = 0x8000, low = 0x10000 [ 0.000000] Zone PFN ranges: [ 0.000000] Normal 0x00008000 -> 0x00010000 [ 0.000000] Movable zone start PFN for each node [ 0.000000] early_node_map[1] active PFN ranges [ 0.000000] 0: 0x00008000 -> 0x00010000 [ 0.000000] Built 1 zonelists in Zone order, mobility grouping on. Total pages: 32512 [ 0.000000] Kernel command line: earlycon=uart,mmio,0x18000008,115200n8 console=ttyS0,115200n8 root=/dev/nfs rw rootfstype=nfs nfsroot9.222.11.56:/n40root ip=dhcp [ 0.000000] NR_IRQS:256 [ 0.000000] PID hash table entries: 512 (order: 9, 2048 bytes) [ 0.000000] Using tmu for system timer [ 0.009785] Dentry cache hash table entries: 16384 (order: 4, 65536 bytes) [ 0.027415] Inode-cache hash table entries: 8192 (order: 3, 32768 bytes) [ 0.066315] Memory: 127232k/131072k available (1341k kernel code, 424k data, 80k init) [ 0.085260] PVR200a00 CVRs440010 PRR000a10 [ 0.096690] I-cache : n_ways=4 n_sets%6 way_incr92 [ 0.109171] I-cache : entry_mask=0x00001fe0 alias_mask=0x00001000 n_aliases=2 [ 0.126200] D-cache : n_ways=4 n_sets%6 way_incr92 [ 0.138681] D-cache : entry_mask=0x00001fe0 alias_mask=0x00001000 n_aliases=2 [ 0.156627] Calibrating delay loop (skipped)... 266.66 BogoMIPS PRESET (lpjS3333) [ 0.175518] Mount-cache hash table entries: 512 [ 0.187776] CPU: SH7763 [ 0.198888] net_namespace: 296 bytes [ 0.208654] NET: Registered protocol family 16 [ 0.247770] bio: create slab at 0 [ 0.264336] SCSI subsystem initialized [ 0.288467] NET: Registered protocol family 2 >Can you tried building a kernel from the > sh/cachetlb branch at, > > git://git.kernel.org/pub/scm/linux/kernel/git/lethal/sh-2.6.git > > and see if the issue persists? Paul has made some changes recently that > might work around this problem. I'll give this a shot on Monday. I do have a clone of that repository. -- To unsubscribe from this list: send the line "unsubscribe linux-sh" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html