Hi, I have recently had a couple of seemingly hard hangs requiring reboot by reset button. I could not ping the box. Until now, the console log (log level 7) was empty/normal... This morning I finally seem to have found out what the failures are... an rmap bug for real mem > 4G... First, some info on my system... Kernel 2.6.24 SMP on AMD Athlon 64 X2 4000 top - 09:44:55 up 24 min, 42 users, load average: 0.05, 0.11, 0.16 Tasks: 206 total, 3 running, 203 sleeping, 0 stopped, 0 zombie Cpu(s): 0.3%us, 1.3%sy, 0.0%ni, 96.2%id, 0.0%wa, 0.0%hi, 2.2%si, 0.0%st Mem: 8248340k total, 3769556k used, 4478784k free, 82732k buffers Swap: 7828572k total, 0k used, 7828572k free, 3254360k cached *** top used was about 6.2G w 0k Swap usage. I was working on local X (there were also 2 remote xdm KDE sessions as well) when my openoffice edit acted strangely. A couple minutes later, X completely locked up. A remote ssh session allowed me to do a normal shutdown. On reboot, I found the bug log in the console log, included below Before digging into this myself (don't really have enought time), I thought I'd submit it here... my .config is tar gz'd as an attachment Any input would be appreciated... Thnx much, johnh . =========================================================== John Heil South Coast Software Custom firmware, device drivers and board bring up services Ph: 1-714-774-6952 Fx: 1-714-774-7053 www.sc-software.com email: johnhscs@sc-software.com =========================================================== Feb 6 09:09:47 sc-software kernel: Eeek! page_mapcount(page) went negative! (-1) Feb 6 09:09:47 sc-software kernel: page pfn = 12b1b1 Feb 6 09:09:47 sc-software kernel: page->flags = 80080014 Feb 6 09:09:47 sc-software kernel: page->count = 0 Feb 6 09:09:47 sc-software kernel: page->mapping = 00000000 Feb 6 09:09:47 sc-software kernel: vma->vm_ops = 0x0 Feb 6 09:09:47 sc-software kernel: ------------[ cut here ]------------ Feb 6 09:09:47 sc-software kernel: kernel BUG at mm/rmap.c:631! Feb 6 09:09:47 sc-software kernel: invalid opcode: 0000 [#2] PREEMPT SMP Feb 6 09:09:47 sc-software kernel: Modules linked in: shpchp pci_hotplug ohci1394 ieee1394 Feb 6 09:09:47 sc-software kernel: Feb 6 09:09:47 sc-software kernel: Pid: 3710, comm: X Tainted: G D (2.6.24 #1) Feb 6 09:09:47 sc-software kernel: EIP: 0060:[] EFLAGS: 00213246 CPU: 0 Feb 6 09:09:47 sc-software kernel: EIP is at page_remove_rmap+0xe6/0x110 Feb 6 09:09:47 sc-software kernel: EAX: 00000000 EBX: c516deb8 ECX: c01280a8 EDX: 00000001 Feb 6 09:09:47 sc-software kernel: ESI: f7120ee4 EDI: 11605000 EBP: f1b31d70 ESP: f1b31d60 Feb 6 09:09:47 sc-software kernel: DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068 Feb 6 09:09:47 sc-software kernel: Process X (pid: 3710, ti=f1b30000 task=f0586aa0 task.ti=f1b30000) Feb 6 09:09:47 sc-software kernel: Stack: c074dda2 00000000 c516deb8 f0662028 f1b31db4 c01683ce 2b1b1065 00000001 Feb 6 09:09:47 sc-software kernel: 00000000 00000000 2b1b1065 00000001 c1a9657c fffffffb ffffffff f71cb300 Feb 6 09:09:47 sc-software kernel: f7120ee4 c8e36180 1a004000 11800000 f07fe460 f1b31df8 c016858d 11600000 Feb 6 09:09:47 sc-software kernel: Call Trace: Feb 6 09:09:47 sc-software kernel: [] show_trace_log_lvl+0x1a/0x30 Feb 6 09:09:47 sc-software kernel: [] show_stack_log_lvl+0x9a/0xc0 Feb 6 09:09:47 sc-software kernel: [] show_registers+0xc7/0x250 Feb 6 09:09:47 sc-software kernel: [] die+0x11f/0x220 Feb 6 09:09:47 sc-software kernel: [] do_trap+0x91/0xd0 Feb 6 09:09:47 sc-software kernel: [] do_invalid_op+0x89/0xa0 Feb 6 09:09:47 sc-software kernel: [] error_code+0x72/0x78 Feb 6 09:09:47 sc-software kernel: [] zap_pte_range+0x22e/0x320 Feb 6 09:09:47 sc-software kernel: [] unmap_page_range+0xcd/0x180 Feb 6 09:09:47 sc-software kernel: [] unmap_vmas+0xcd/0x210 Feb 6 09:09:47 sc-software kernel: [] exit_mmap+0x76/0x120 Feb 6 09:09:47 sc-software kernel: [] mmput+0x39/0xa0 Feb 6 09:09:47 sc-software kernel: [] exit_mm+0x8e/0xf0 Feb 6 09:09:47 sc-software kernel: [] do_exit+0x153/0x350 Feb 6 09:09:47 sc-software kernel: [] do_group_exit+0x29/0x70 Feb 6 09:09:47 sc-software kernel: [] get_signal_to_deliver+0x242/0x2e0 Feb 6 09:09:47 sc-software kernel: [] do_signal+0x5c/0x170 Feb 6 09:09:47 sc-software kernel: [] do_notify_resume+0x3c/0x40 Feb 6 09:09:47 sc-software kernel: [] work_notifysig+0x13/0x1a Feb 6 09:09:47 sc-software kernel: ======================= Feb 6 09:09:47 sc-software kernel: Code: bb dd 74 c0 e8 dc 2f fe ff 8b 46 44 85 c0 75 1f 8b 46 4c 85 c0 74 14 8b 40 10 85 c0 74 0d 8b 50 2c b8 14 ec 74 c0 e8 ba 2f fe ff <0f> 0b eb fe 8b 50 0c b8 38 ec 74 c0 e8 a9 2f fe ff 8b 46 44 8b Feb 6 09:09:47 sc-software kernel: EIP: [] page_remove_rmap+0xe6/0x110 SS:ESP 0068:f1b31d60 Feb 6 09:09:47 sc-software kernel: ---[ end trace 791c1b0a2eb87d50 ]--- Feb 6 09:09:47 sc-software kernel: Fixing recursive fault but reboot is needed! Feb 6 09:09:47 sc-software kernel: BUG: scheduling while atomic: X/3710/0x00000003 Feb 6 09:09:47 sc-software kernel: INFO: lockdep is turned off. Feb 6 09:09:47 sc-software kernel: Pid: 3710, comm: X Tainted: G D 2.6.24 #1 Feb 6 09:09:47 sc-software kernel: [] show_trace_log_lvl+0x1a/0x30 Feb 6 09:09:47 sc-software kernel: [] show_trace+0x12/0x20 Feb 6 09:09:47 sc-software kernel: [] dump_stack+0x6d/0x80 Feb 6 09:09:47 sc-software kernel: [] __schedule_bug+0x66/0x70 Feb 6 09:09:47 sc-software kernel: [] __sched_text_start+0x295/0x490 Feb 6 09:09:47 sc-software kernel: [] do_exit+0x26b/0x350 Feb 6 09:09:47 sc-software kernel: [] die+0x213/0x220 Feb 6 09:09:47 sc-software kernel: [] do_trap+0x91/0xd0 Feb 6 09:09:47 sc-software kernel: [] do_invalid_op+0x89/0xa0 Feb 6 09:09:47 sc-software kernel: [] error_code+0x72/0x78 Feb 6 09:09:47 sc-software kernel: [] zap_pte_range+0x22e/0x320 Feb 6 09:09:47 sc-software kernel: [] unmap_page_range+0xcd/0x180 Feb 6 09:09:47 sc-software kernel: [] unmap_vmas+0xcd/0x210 Feb 6 09:09:47 sc-software kernel: [] exit_mmap+0x76/0x120 Feb 6 09:09:47 sc-software kernel: [] mmput+0x39/0xa0 Feb 6 09:09:47 sc-software kernel: [] exit_mm+0x8e/0xf0 Feb 6 09:09:47 sc-software kernel: [] do_exit+0x153/0x350 Feb 6 09:09:47 sc-software kernel: [] do_group_exit+0x29/0x70 Feb 6 09:09:47 sc-software kernel: [] get_signal_to_deliver+0x242/0x2e0 Feb 6 09:09:47 sc-software kernel: [] do_signal+0x5c/0x170 Feb 6 09:09:47 sc-software kernel: [] do_notify_resume+0x3c/0x40 Feb 6 09:09:47 sc-software kernel: [] work_notifysig+0x13/0x1a Feb 6 09:09:47 sc-software kernel: =======================