On Wednesday, September 01, 2010 1:11:31 pm pluknet wrote: > On 1 September 2010 20:06, John Baldwin <[email protected]> wrote: > > On Wednesday, September 01, 2010 11:53:09 am pluknet wrote: > >> Hi. > >> > >> This is reproducible from time to time on boot when > >> handling SIOCAIFADDR called from ifconfig on igb > >> on fresh (and not so fresh) 8-STABLE. > >> > >> How can I help with debugging? > >> > >> Kernel page fault with the following non-sleepable locks held: > >> exclusive sleep mutex igb0 (IGB Core Lock) r = 0 (0xc2655534) locked @ > >> /usr/src/sys/modules/igb/../../dev/e1000/if_igb.c:965 > >> KDB: stack backtrace: > >> db_trace_self_wrapper(c08b5055,cce577b8,c060db15,3c5,0,...) at > >> db_trace_self_wrapper+0x26 > >> kdb_backtrace(3c5,0,ffffffff,c0a94864,cce577f0,...) at kdb_backtrace+0x29 > >> _witness_debugger(c08b74fe,cce57804,4,1,0,...) at _witness_debugger+0x25 > >> witness_warn(5,0,c08e3140,cce5782c,c2956000,...) at witness_warn+0x1fe > >> trap(cce57890) at trap+0x195 > >> calltrap() at calltrap+0x6 > >> --- trap 0xc, eip = 0xc3192477, esp = 0xcce578d0, ebp = 0xcce578e0 --- > >> e1000_clear_hw_cntrs_base_generic(c2651004,64,c3185850,c2651000,0,...) > >> at e1000_clear_hw_cntrs_base_generic+0x3e7 > > > > Can you use gdb on your kernel.debug to map this to a source file and line? > > > > Here it is (btw, it took about 10-15 reboots to reproduce after adding > swap and dumpon setup). > Hmm.. don't see where it might access an invalid pointer. > > #0 doadump () at pcpu.h:231 > #1 0xc04a3679 in db_fncall (dummy1=1, dummy2=0, dummy3=-1062122144, > dummy4=0xcce636a8 "") at /usr/src/sys/ddb/db_command.c:548 > #2 0xc04a3a71 in db_command (last_cmdp=0xc093d19c, cmd_table=0x0, dopager=1) > at /usr/src/sys/ddb/db_command.c:445 > #3 0xc04a3bca in db_command_loop () at /usr/src/sys/ddb/db_command.c:498 > #4 0xc04a5aed in db_trap (type=12, code=0) at /usr/src/sys/ddb/db_main.c:229 > #5 0xc05fa64e in kdb_trap (type=12, code=0, tf=0xcce63890) > at /usr/src/sys/kern/subr_kdb.c:535 > #6 0xc084dcdf in trap_fatal (frame=0xcce63890, eva=3428511744) > at /usr/src/sys/i386/i386/trap.c:929 > #7 0xc084e553 in trap (frame=0xcce63890) at /usr/src/sys/i386/i386/trap.c:328 > #8 0xc082f66c in calltrap () at /usr/src/sys/i386/i386/exception.s:166 > #9 0xc318c477 in e1000_clear_hw_cntrs_base_generic (hw=0xc2655004) > at /usr/src/sys/modules/igb/../../dev/e1000/e1000_mac.c:643 > #10 0xc317ec82 in igb_init_locked (adapter=0xc2655000) > at /usr/src/sys/modules/igb/../../dev/e1000/if_igb.c:1202 > #11 0xc31801e5 in igb_ioctl (ifp=0xc2943c00, command=2149607692, > data=0xc29db600 "╢╤\235бд╤\235бт╤\235б") > at /usr/src/sys/modules/igb/../../dev/e1000/if_igb.c:966 > #12 0xc0696c4e in in_ifinit (ifp=0xc2943c00, ia=0xc29db600, > sin=Variable "sin" is not available. > ) > at /usr/src/sys/netinet/in.c:848 > #13 0xc06980cb in in_control (so=0xc2a5d9a8, cmd=2151704858, > data=0xc2649400 "igb0", ifp=0xc2943c00, td=0xc29b8280) > ---Type <return> to continue, or q <return> to quit--- > at /usr/src/sys/netinet/in.c:563 > #14 0xc067c860 in ifioctl (so=0xc2a5d9a8, cmd=2151704858, > data=0xc2649400 "igb0", td=0xc29b8280) at /usr/src/sys/net/if.c:2523 > #15 0xc0617395 in soo_ioctl (fp=0xc29ce310, cmd=2151704858, data=0xc2649400, > active_cred=0xc254b100, td=0xc29b8280) > at /usr/src/sys/kern/sys_socket.c:212 > #16 0xc06113dd in kern_ioctl (td=0xc29b8280, fd=3, com=2151704858, > data=0xc2649400 "igb0") at file.h:262 > #17 0xc0611564 in ioctl (td=0xc29b8280, uap=0xcce63cf8) > at /usr/src/sys/kern/sys_generic.c:678 > #18 0xc084e160 in syscall (frame=0xcce63d38) > at /usr/src/sys/i386/i386/trap.c:1111 > #19 0xc082f6d1 in Xint0x80_syscall () > at /usr/src/sys/i386/i386/exception.s:264 > #20 0x00000033 in ?? () > Previous frame inner to this frame (corrupt stack?) > > (kgdb) f 9 > #9 0xc318c477 in e1000_clear_hw_cntrs_base_generic (hw=0xc2655004) > at /usr/src/sys/modules/igb/../../dev/e1000/e1000_mac.c:643 > 643 E1000_READ_REG(hw, E1000_SYMERRS); > (kgdb) list > 638 void e1000_clear_hw_cntrs_base_generic(struct e1000_hw *hw) > 639 { > 640 DEBUGFUNC("e1000_clear_hw_cntrs_base_generic"); > 641 > 642 E1000_READ_REG(hw, E1000_CRCERRS); > 643 E1000_READ_REG(hw, E1000_SYMERRS); > 644 E1000_READ_REG(hw, E1000_MPC); > 645 E1000_READ_REG(hw, E1000_SCC); > 646 E1000_READ_REG(hw, E1000_ECOL); > 647 E1000_READ_REG(hw, E1000_MCC); > > (kgdb) p *(struct e1000_osdep *)hw->back > $6 = {mem_bus_space_tag = 1, mem_bus_space_handle = 3428495360, > io_bus_space_tag = 0, io_bus_space_handle = 0, flash_bus_space_tag = 0, > flash_bus_space_handle = 0, dev = 0xc261a600} > > (kgdb) p *hw > [...] > power_down = 0xc3186340 <e1000_null_phy_generic>}, type = e1000_phy_vf, > [...] > > (kgdb) p (struct e1000_mac_info *)hw->mac.type > $8 = (struct e1000_mac_info *) 0x1a > > (kgdb) p *(struct e1000_mac_info *)hw->mac > $10 = {ops = {init_params = 0x8be58955, id_led_init = 0x80c70845, > blink_led = 0x390, check_for_link = 0, check_mng_mode = 0x2d480c7, > cleanup_led = 0, clear_hw_cntrs = 0x80c70000, clear_vfta = 0x2d0, > get_bus_info = 0, set_lan_id = 0x2c880c7, get_link_up_info = 0, > led_on = 0xc7660000, led_off = 0xbe80, update_mc_addr_list = 0x66008000, > reset_hw = 0x2c480c7, init_hw = 0x10000, shutdown_serdes = 0xf05840c7, > power_up_serdes = 0xc7c31a4f, setup_link = 0x50003040, > setup_physical_interface = 0x40c7c31a, setup_led = 0x1a539048, > write_vfta = 0x4c40c7c3, > config_collision_dist = 0xc31a5360 <e1000_init_hw_vf>, > rar_set = 0x901c40c7, read_mac_addr = 0xc7c31a55, > validate_mdi_setting = 0x55103840, mng_host_if_write = 0x40c7c31a, > mng_write_cmd_header = 0x1a502044, mng_enable_host_if = 0x6c40c7c3, > wait_autoneg = 0xc31a52a0 <e1000_rar_set_vf>}, addr = "�...@p@R\032", > perm_addr = "ц1ю]ц\215", type = 182, collision_delta = 666668288, > ledctl_default = 0, ledctl_mode1 = 2347075925, ledctl_mode2 = 1086785605, > mc_filter_type = 441389072, tx_packet_delta = 3095447491, > txcw = 3758096387, current_ifs_val = 6734, ifs_max_val = 51139, > ifs_min_val = 5248, ifs_ratio = 3, ifs_step_size = 45056, > mta_reg_count = 6734, uta_reg_count = 51139, mta_shadow = {1879048196, > 1573067352, 7769539, 4294883413, 3851026431, 3062743901, 0, 1575323989, > 645172675, 666668288, 0, 2311074133, 2311282149, 666668534, 0, > 2347075925, 2160527429, 1016, 4, 66879687, 393216, 3224436736, > 4136223581, 1474660693, 3968029526, 209554260, 504397187, 1170701942, > ---Type <return> to continue, or q <return> to quit--- > 503317428, 273008384, 30, 3339212171, 45125, 3071213568, 48770, 98615552, > 838817933, 4294672841, 3187671040, 8, 3526433396, 2298593923, 3400929240, > 4282247379, 1962934272, 573167, 3458793472, 88585743, 72857103, > 4052345043, 3490314963, 565204363, 4280641240, 1149855247, 1301002325, > 29524752, 967857545, 2199679946, 2817197767, 3239069067, 3364032736, > 3024455939, 2232436107, 2038763456, 2348810239, 1166870613, 608487348, > 12, 608487168, 4104, 608471296, 605325572, 68719359, 3296919552, > 1600019284, 3029189469, 38, 666668288, 0, 2212858197, 1300961516, > 1169624848, 139823884, 83379655, 2231369728, 4232415689, 1170671476, > 16778488, 4165307648, 203703495, 0, 136594631, 2, 69485705, 4280554633, > 268434, 2311309568, 666668534, 0, 2212858197, 3071219948, 1166740565, > 4165322504, 5, 203703495, 0, 2382124425, 1153955925, 133156, 1418264576, > 76088356, 412155684, 3372220420, 649366979, 0, 2212858197, 1435180268, > 4166879500, 2299026827, 1170734197, 1780, 33194752, 812861556, > 3354686861, 795716, 3338665984, 17310788, 2298478592}, > rar_entry_count = 9332, forced_speed_duplex = 4 '\004', > adaptive_ifs = -1811995620, has_fwsm = 1048, > arc_subsystem_valid = 745848965, asf_firmware_present = -1946657397, > autoneg = -326501259, autoneg_failed = -158743715, > get_link_status = 1946352259, in_ifs_mode = 66749261, > report_tx_early = -1096, serdes_link_state = 3353703935, > serdes_has_link = 455749, tx_pkt_filtering = 1300299778} > > (kgdb) p *hw > $13 = {back = 0xc2659498, hw_addr = 0xc265949c "", flash_address = 0x0, > io_base = 0, mac = {ops = { > init_params = 0xc31a4f10 <e1000_init_mac_params_vf>, id_led_init = 0,
Hmm, this is a VF interface. I know that VF adapters have a different set of stats than all the other e1000 adapters. Perhaps that is related? Maybe make the call to e1000_clear_hw_cntrs_base_generic() in igb_init_locked() conditional on 'if (adapter->hw.mac.type != e1000_vfadapt)'? -- John Baldwin _______________________________________________ [email protected] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[email protected]"
