Hey Tejun, mind taking a glance? I think I might be doing something dumb here, but I'm not quite sure what and I haven't dealt much with struct request: (This is bcache on 3.1 with a raid10) scsi_setup_fs_cmnd() is triggering BUG_ON(!req->nr_phys_segments). I'm not finding the code where req->nr_phys_segments is set right now, but I'm guessing what's happening is it's getting set incorrectly because the bio(s) in the request have it set to 0, not -1. If that's the case, then the bug is that bio_split_front() (bcache/util.c) creates a new bio but doesn't initalize bio->bi_phys_segments, so just setting it to -1 so it gets recalculated later should fix it... That sound right to you? On Tue, Nov 29, 2011 at 02:10:57PM +0800, Brad Campbell wrote: > This happens immediately I try and attach a cache set to /dev/md10 : > > [ 73.287556] md: resync of RAID array md10 > [ 73.287614] md: minimum _guaranteed_ speed: 1000 KB/sec/disk. > [ 73.287620] ------------[ cut here ]------------ > [ 73.287628] kernel BUG at drivers/scsi/scsi_lib.c:1152! > [ 73.287633] invalid opcode: 0000 [#1] SMP > [ 73.287638] CPU 1 > [ 73.287641] Modules linked in: xt_state ipt_REJECT xt_CHECKSUM > iptable_mangle nfs ipt_MASQUERADE xt_tcpudp iptable_filter > iptable_nat nf_nat nf_conntrack_ipv4 nf_conntrack nf_defrag_ipv4 > ip_tables x_tables deflate zlib_deflate des_generic cbc ecb > crypto_blkcipher sha1_generic md5 hmac crypto_hash cryptomgr aead > crypto_algapi af_key fuse w83627ehf hwmon_vid netconsole configfs > vhost_net powernow_k8 mperf kvm_amd kvm xhci_hcd k10temp i2c_piix4 > ohci_hcd ehci_hcd usbcore ahci atl1c libahci megaraid_sas [last > unloaded: scsi_wait_scan] > [ 73.287694] > [ 73.287700] Pid: 1428, comm: md10_raid10 Not tainted > 3.1.0-g143cdea #1 To Be Filled By O.E.M. To Be Filled By > O.E.M./890GX Extreme4 R2.0 > [ 73.287711] RIP: 0010:[<ffffffff812adbfe>] [<ffffffff812adbfe>] > scsi_setup_fs_cmnd+0xae/0xf0 > [ 73.287726] RSP: 0018:ffff88041bb73be0 EFLAGS: 00010046 > [ 73.287731] RAX: 0000000000000000 RBX: ffff88041ba5c560 RCX: > 0000000000001000 > [ 73.287736] RDX: 0000000000000000 RSI: ffff88041ba5c560 RDI: > ffff88041bbf8000 > [ 73.287740] RBP: ffff88041bbf8000 R08: 0000000000000000 R09: > 0000000000000001 > [ 73.287745] R10: 4080000000000000 R11: dead000000100100 R12: > ffff88041bbf8000 > [ 73.287750] R13: 0000000000000808 R14: ffff88041bbf8048 R15: > ffff88041c029400 > [ 73.287756] FS: 00007fa5803717c0(0000) GS:ffff88042fc40000(0000) > knlGS:0000000000000000 > [ 73.287761] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b > [ 73.287766] CR2: 0000000001b7c1b8 CR3: 0000000418a24000 CR4: > 00000000000006e0 > [ 73.287770] DR0: 0000000000000000 DR1: 0000000000000000 DR2: > 0000000000000000 > [ 73.287774] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: > 0000000000000400 > [ 73.287780] Process md10_raid10 (pid: 1428, threadinfo > ffff88041bb72000, task ffff88041c760640) > [ 73.287784] Stack: > [ 73.287787] 0000000000000000 ffff88041ba5c560 ffff88041c603c30 > ffffffff812b86fc > [ 73.287794] 01ff88041bbf8800 ffff880400000001 ffff880400001000 > 0000000000000000 > [ 73.287800] ffff88041ba5c560 ffff88041ba5c560 ffff88041ba5c560 > ffff88041c603c30 > [ 73.287807] Call Trace: > [ 73.287816] [<ffffffff812b86fc>] ? sd_prep_fn+0x15c/0xa50 > [ 73.287825] [<ffffffff811c8be4>] ? blk_peek_request+0xb4/0x1d0 > [ 73.287832] [<ffffffff812ad120>] ? scsi_request_fn+0x50/0x4a0 > [ 73.287840] [<ffffffff811c9598>] ? blk_flush_plug_list+0x188/0x210 > [ 73.287847] [<ffffffff811c962b>] ? blk_finish_plug+0xb/0x30 > [ 73.287854] [<ffffffff812fae78>] ? raid10d+0x908/0xb50 > [ 73.287862] [<ffffffff81041183>] ? lock_timer_base+0x33/0x70 > [ 73.287870] [<ffffffff814089c5>] ? schedule_timeout+0x1c5/0x230 > [ 73.287878] [<ffffffff8130ec8f>] ? md_thread+0x10f/0x140 > [ 73.287886] [<ffffffff81050240>] ? wake_up_bit+0x40/0x40 > [ 73.287892] [<ffffffff8130eb80>] ? md_register_thread+0x100/0x100 > [ 73.287898] [<ffffffff8130eb80>] ? md_register_thread+0x100/0x100 > [ 73.287905] [<ffffffff8104fde6>] ? kthread+0x96/0xa0 > [ 73.287912] [<ffffffff8140bbf4>] ? kernel_thread_helper+0x4/0x10 > [ 73.287920] [<ffffffff8104fd50>] ? kthread_worker_fn+0x120/0x120 > [ 73.287926] [<ffffffff8140bbf0>] ? gs_change+0xb/0xb > [ 73.287929] Code: 80 00 00 00 00 48 83 c4 08 5b 5d c3 90 48 89 ef > be 20 00 00 00 e8 73 a2 ff ff 48 85 c0 48 89 c7 74 d7 48 89 83 d8 00 > 00 00 eb 8d <0f> 0b eb fe 48 8b 00 48 85 c0 0f 84 67 ff ff ff 48 8b > 40 50 48 > [ 73.287969] RIP [<ffffffff812adbfe>] scsi_setup_fs_cmnd+0xae/0xf0 > [ 73.287977] RSP <ffff88041bb73be0> > [ 73.287982] ---[ end trace 4ce4e575167cc0ff ]--- > [ 73.287986] Kernel panic - not syncing: Fatal exception > [ 73.287993] Pid: 1428, comm: md10_raid10 Tainted: G D > 3.1.0-g143cdea #1 > [ 73.287998] Call Trace: > [ 73.288005] [<ffffffff81407679>] ? panic+0x92/0x193 > [ 73.288012] [<ffffffff81035451>] ? kmsg_dump+0x41/0xf0 > [ 73.288021] [<ffffffff8100504d>] ? oops_end+0x8d/0xa0 > [ 73.288028] [<ffffffff81002e34>] ? do_invalid_op+0x84/0xa0 > [ 73.288035] [<ffffffff812adbfe>] ? scsi_setup_fs_cmnd+0xae/0xf0 > [ 73.288044] [<ffffffff811d698e>] ? cfq_set_request+0x15e/0x3b0 > [ 73.288050] [<ffffffff8140ba75>] ? invalid_op+0x15/0x20 > [ 73.288058] [<ffffffff812adbfe>] ? scsi_setup_fs_cmnd+0xae/0xf0 > [ 73.288064] [<ffffffff812b86fc>] ? sd_prep_fn+0x15c/0xa50 > [ 73.288071] [<ffffffff811c8be4>] ? blk_peek_request+0xb4/0x1d0 > [ 73.288078] [<ffffffff812ad120>] ? scsi_request_fn+0x50/0x4a0 > [ 73.288085] [<ffffffff811c9598>] ? blk_flush_plug_list+0x188/0x210 > [ 73.288092] [<ffffffff811c962b>] ? blk_finish_plug+0xb/0x30 > [ 73.288098] [<ffffffff812fae78>] ? raid10d+0x908/0xb50 > [ 73.288104] [<ffffffff81041183>] ? lock_timer_base+0x33/0x70 > [ 73.288112] [<ffffffff814089c5>] ? schedule_timeout+0x1c5/0x230 > [ 73.288119] [<ffffffff8130ec8f>] ? md_thread+0x10f/0x140 > [ 73.288126] [<ffffffff81050240>] ? wake_up_bit+0x40/0x40 > [ 73.288132] [<ffffffff8130eb80>] ? md_register_thread+0x100/0x100 > [ 73.288138] [<ffffffff8130eb80>] ? md_register_thread+0x100/0x100 > [ 73.288144] [<ffffffff8104fde6>] ? kthread+0x96/0xa0 > [ 73.288151] [<ffffffff8140bbf4>] ? kernel_thread_helper+0x4/0x10 > [ 73.288159] [<ffffffff8104fd50>] ? kthread_worker_fn+0x120/0x120 > [ 73.288165] [<ffffffff8140bbf0>] ? gs_change+0xb/0xb > [ 73.290590] Rebooting in 10 seconds.. > > I can attach the same cache set to /dev/sde and all is ok (the same > config I used to run the last set of benchmarks). > > Regards, > Brad > -- > To unsubscribe from this list: send the line "unsubscribe linux-bcache" in > the body of a message to majordomo@xxxxxxxxxxxxxxx > More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line "unsubscribe linux-bcache" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
