Thanks to the various patches that have come out on the list this week, I''ve got a patched 2.6.18 running on my PPC64 machines, and have a build of the full lustre package (mostly via adding non- __KERNEL__ defines for PAGE_SIZE). I am able to build a little loopback FS and mount it, but umount gives me a segfault. dmesg output follows. --bob LDISKFS FS on loop0, internal journal LDISKFS-fs: mounted filesystem with ordered data mode. LDISKFS-fs: mballoc enabled Lustre: MGS MGS started Lustre: disk data: Lustre: server: testfs-MDT0000 Lustre: uuid: Lustre: fs: testfs Lustre: index: 0000 Lustre: config: 2 Lustre: flags: 0x5 Lustre: diskfs: ldiskfs Lustre: options: errors=remount-ro,iopen_nopriv,user_xattr Lustre: params: Lustre: comment: Lustre: Enabling user_xattr Lustre: testfs-MDT0000: new disk, initializing Lustre: MDT testfs-MDT0000 now serving dev (testfs-MDT0000/4246d087- fdff-4e77-a816-c94ec2b39d32) with recovery enabled Lustre: 0 UP mgs MGS MGS 5 Lustre: 1 UP mgc MGC192.5.200.37@tcp 085d3850-4845-72a4-1b2a- a7001bce076c 6 Lustre: 2 UP mdt MDS MDS_uuid 3 Lustre: 3 UP lov testfs-mdtlov testfs-mdtlov_UUID 4 Lustre: 4 UP mds testfs-MDT0000 testfs-MDT0000_UUID 3 Lustre: mount /dev/loop0 complete Unable to handle kernel paging request for data at address 0x100000000 Faulting instruction address: 0xd0000000006e61b0 Oops: Kernel access of bad area, sig: 11 [#1] SMP NR_CPUS=2 Modules linked in: mds fsfilt_ldiskfs mgs mgc ldiskfs lustre mdc lquota lov ksocklnd ptlrpc obdclass lnet lvfs libcfs autofs4 eth1394 evdev NIP: D0000000006E61B0 LR: D0000000006E61AC CTR: C00000000002CCAC REGS: c000000178d279c0 TRAP: 0300 Not tainted (2.6.18) MSR: 9000000000009032 <EE,ME,IR,DR> CR: 22000428 XER: 00000000 DAR: 0000000100000000, DSISR: 0000000040000000 TASK = c00000000fbd0040[3442] ''umount'' THREAD: c000000178d24000 CPU: 0 GPR00: D0000000006E61AC C000000178D27C40 D000000000731FF8 D0000000008D1600 GPR04: D0000000006FF7DB C00000017720104F 000000000000006C 0000000000000000 GPR08: 000000000000056B 0000000000000000 00000000453FD59B C00000000002CCAC GPR12: D0000000008BF8C8 C0000000004F1780 00000FFFFF98389C 00000FFFFF983890 GPR16: 000000001005A6F8 00000000100843F0 0000000000000000 0000000000000000 GPR20: 0000000000000000 0000000010110168 0000000010110148 000000001010FEA8 GPR24: 00000FFFFF94CE27 000000001010FFC8 0000000010020080 0000000000000000 GPR28: 0000000000000000 C00000000FACCC00 D00000000072F958 0000000100000000 NIP [D0000000006E61B0] .server_umount_begin+0x14c/0x208 [obdclass] LR [D0000000006E61AC] .server_umount_begin+0x148/0x208 [obdclass] Call Trace: [C000000178D27C40] [D0000000006E61AC] .server_umount_begin +0x148/0x208 [obdclass] (unreliable) [C000000178D27CC0] [C0000000000CD454] .sys_umount+0x164/0x300 [C000000178D27E30] [C00000000000871C] syscall_exit+0x0/0x40 Instruction dump: 7809bfe3 4182002c 3ca00100 e8de8020 e8fe8058 e93e8060 38600000 38800200 60a50004 3900056b 48015a49 e8410028 <e81f0002> 782904a0 21694000 2bab3000 <1>Unable to handle kernel paging request for data at address 0x100000000 Faulting instruction address: 0xd0000000006e61b0 Oops: Kernel access of bad area, sig: 11 [#2] SMP NR_CPUS=2 Modules linked in: mds fsfilt_ldiskfs mgs mgc ldiskfs lustre mdc lquota lov ksocklnd ptlrpc obdclass lnet lvfs libcfs autofs4 eth1394 evdev NIP: D0000000006E61B0 LR: D0000000006E61AC CTR: C00000000002CCAC REGS: c000000178d279c0 TRAP: 0300 Not tainted (2.6.18) MSR: 9000000000009032 <EE,ME,IR,DR> CR: 24000448 XER: 00000000 DAR: 0000000100000000, DSISR: 0000000040000000 TASK = c00000007e030040[3445] ''umount'' THREAD: c000000178d24000 CPU: 0 GPR00: D0000000006E61AC C000000178D27C40 D000000000731FF8 D0000000008D1600 GPR04: D0000000006FF7DB C0000001772010A9 000000000000006C 0000000000000000 GPR08: 000000000000056B 0000000000000000 00000000453FD5CA C00000000002CCAC GPR12: D0000000008BF8C8 C0000000004F1780 00000FFFFF98389C 00000FFFFF983890 GPR16: 000000001005A6F8 00000000100843F0 0000000000000000 0000000000000000 GPR20: 0000000000000000 0000000010110608 0000000010110628 0000000010110388 GPR24: 00000FFFFFF96E27 0000000010110488 0000000010020080 0000000000000000 GPR28: 0000000000000001 C00000000FACCC00 D00000000072F958 0000000100000000 NIP [D0000000006E61B0] .server_umount_begin+0x14c/0x208 [obdclass] LR [D0000000006E61AC] .server_umount_begin+0x148/0x208 [obdclass] Call Trace: [C000000178D27C40] [D0000000006E61AC] .server_umount_begin +0x148/0x208 [obdclass] (unreliable) [C000000178D27CC0] [C0000000000CD454] .sys_umount+0x164/0x300 [C000000178D27E30] [C00000000000871C] syscall_exit+0x0/0x40 Instruction dump: 7809bfe3 4182002c 3ca00100 e8de8020 e8fe8058 e93e8060 38600000 38800200 60a50004 3900056b 48015a49 e8410028 <e81f0002> 782904a0 21694000 2bab3000