[ewg] crash in mthca with ofed-1.4.1

Steve Wise swise at opengridcomputing.com
Wed Mar 4 09:03:14 PST 2009


I just put on the 20090303-0200 kernel build and hit this on boot up 
when loading mthca.  Is this a new bug?
 

Distro:  RH5.2
HW: x86_64
OFA Drivers: ofa_1_4_kernel-20090303-0200


----


divide error: 0000 [1] SMP
last sysfs file: /block/sda/sda1/dev
CPU 0
Modules linked in: sg ib_mthca(U) cxgb3(U) i2c_i801 ide_cd ib_mad(U) 
ib_core(U) shpchp e1000e pcspkr i2c_core serio_raw cdrom dm_snapshot 
dm_zero dm_mirror dm_mod ata_piix libata sd_mod scsi_mod ext3 jbd 
uhci_hcd ohci_hcd ehci_hcd
Pid: 830, comm: modprobe Tainted: G      2.6.18-92.el5 #1
RIP: 0010:[<ffffffff8821ba09>]  [<ffffffff8821ba09>] 
:ib_mthca:mthca_QUERY_DEV_LIM+0x140/0x817
RSP: 0018:ffff81018d7a9998  EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffff81018be0c000 RCX: 0000000000000004
RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff81018f7bf5b0
RBP: ffff81018d7a9b38 R08: 0000000000000000 R09: 0000000000000003
R10: ffff81018d7a99ff R11: 000000000000ea60 R12: ffff81018d7a99ff
R13: ffff81018d7a9d35 R14: 000000000000ea60 R15: ffff81018f7bf000
FS:  00002afa157a1240(0000) GS:ffffffff8039e000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 000000001486e528 CR3: 000000018d777000 CR4: 00000000000006e0
Process modprobe (pid: 830, threadinfo ffff81018d7a8000, task 
ffff81018d3c6080)
Stack:  ffff81018f7bf000 ffff81018d80fb80 000000008d7a9d35 ffff81018f7bf000
 ffff81018d7a9b38 ffff81018d7a9b38 ffff81018d7a9d35 ffff81018fa55000
 0000000000000002 ffffffff882182b7 0000000000000000 ffffffff8821a982
Call Trace:
 [<ffffffff882182b7>] :ib_mthca:mthca_dev_lim+0x1e/0x36c
 [<ffffffff8821a982>] :ib_mthca:mthca_cmd+0x1b/0x20
 [<ffffffff8821891a>] :ib_mthca:mthca_init_hca+0x315/0xe38
 [<ffffffff80021f44>] __up_read+0x19/0x7f
 [<ffffffff80066852>] do_page_fault+0x4fe/0x830
 [<ffffffff80142f55>] __next_cpu+0x19/0x28
 [<ffffffff800790f1>] physflat_send_IPI_allbutself+0x41/0x46
 [<ffffffff800790f1>] physflat_send_IPI_allbutself+0x41/0x46
 [<ffffffff80075470>] __smp_call_function+0x62/0x8b
 [<ffffffff8007537b>] do_flush_tlb_all+0x0/0x6a
 [<ffffffff800755a6>] smp_call_function+0x32/0x47
 [<ffffffff801026e1>] sysfs_new_dirent+0x63/0x6f
 [<ffffffff80102761>] sysfs_make_dirent+0x1b/0x8f
 [<ffffffff8010208e>] sysfs_add_file+0x76/0x85
 [<ffffffff801ada1a>] device_create_file+0x31/0x39
 [<ffffffff801b22f7>] dma_pool_create+0x113/0x14b
 [<ffffffff88219e1f>] :ib_mthca:__mthca_init_one+0x50a/0x793
 [<ffffffff8821a120>] :ib_mthca:mthca_init_one+0x78/0x8d
 [<ffffffff8014f559>] pci_device_probe+0x100/0x180
 [<ffffffff801af29b>] driver_probe_device+0x52/0xaa
 [<ffffffff801af3ca>] __driver_attach+0x65/0xb6
 [<ffffffff801af365>] __driver_attach+0x0/0xb6
 [<ffffffff801aecdc>] bus_for_each_dev+0x43/0x6e
 [<ffffffff801ae922>] bus_add_driver+0x7e/0x130
 [<ffffffff8014f731>] __pci_register_driver+0x4b/0x6c
 [<ffffffff8818d1bc>] :ib_mthca:mthca_init+0x15b/0x16e
 [<ffffffff800a3dd0>] sys_init_module+0xaf/0x1e8
 [<ffffffff8005d116>] system_call+0x7e/0x83


Code: 48 f7 f6 eb 07 c0 ea 04 88 d1 d3 e0 89 45 38 0f b6 4b 21 41
RIP  [<ffffffff8821ba09>] :ib_mthca:mthca_QUERY_DEV_LIM+0x140/0x817
 RSP <ffff81018d7a9998>
 <0>Kernel panic - not syncing: Fatal exception




More information about the ewg mailing list