From: <er...@he...> - 2003-09-17 19:05:30
|
On Wed, Sep 17, 2003 at 12:16:27PM -0400, Nicholas Henke wrote: > Hello~ > I am getting a repeatable oops with either 2.4.20 or 2.4.21 on bproc > 3.2.5 or 3.2.6. Attached is the oops trace. The oops is not fatal all of > the time, but left unchecked, it really makes a mess of things. Any > ideas? This traceback is 99% networking calls. The only BProc part is the call to sock_read. Plus, it seems to have died in an IRQ or something like that. This is almost certainly a network driver or network stack bug. Is it repeatable w/ different networking hardware? (Different hardware what uses a different driver.) - Erik > vmadump: 1.69 Erik Hendriks <er...@he...> > bproc: Beowulf Distributed Process Space Version 3.2.6 > bproc: (C) 1999-2002 Erik Hendriks <er...@he...> > do_IRQ: stack overflow: 924 > c024a365 0000039c 00000001 de92d280 de92d280 de92d280 dfba0e00 c02440a4 > de92d280 00000000 de92d280 de92d280 de92d280 dfba0e00 debac180 00000018 > 00000018 ffffff12 c01df575 00000010 00000202 de92d280 fffffff4 c01df5ec > Call Trace: [<c01df575>] skb_release_data [kernel] 0x15 (0xde57ca9c)) > [<c01df5ec>] kfree_skbmem [kernel] 0xc (0xde57cab0)) > [<c01df76e>] __kfree_skb [kernel] 0x11e (0xde57cac0)) > [<c022bcf2>] packet_rcv_spkt [kernel] 0x1b2 (0xde57cacc)) > [<c01df5ec>] kfree_skbmem [kernel] 0xc (0xde57caec)) > [<c01df76e>] __kfree_skb [kernel] 0x11e (0xde57cafc)) > [<c022bcf2>] packet_rcv_spkt [kernel] 0x1b2 (0xde57cb08)) > [<c01e32cf>] dev_queue_xmit_nit [kernel] 0x8f (0xde57cb28)) > [<c01ed560>] qdisc_restart [kernel] 0x60 (0xde57cb48)) > [<e08ff86a>] speedo_start_xmit [eepro100] 0x18a (0xde57cb54)) > [<c01e34ee>] dev_queue_xmit [kernel] 0x14e (0xde57cb70)) > [<c01ed514>] qdisc_restart [kernel] 0x14 (0xde57cb88)) > [<c01e34ee>] dev_queue_xmit [kernel] 0x14e (0xde57cbac)) > [<c01fb7a2>] ip_output [kernel] 0x102 (0xde57cbc4)) > [<c01fbbd0>] ip_queue_xmit [kernel] 0x3c0 (0xde57cbf8)) > [<c01fb7a2>] ip_output [kernel] 0x102 (0xde57cc00)) > [<c01fbbd0>] ip_queue_xmit [kernel] 0x3c0 (0xde57cc34)) > [<c02111be>] tcp_v4_send_check [kernel] 0x6e (0xde57cc98)) > [<c020bc15>] tcp_transmit_skb [kernel] 0x565 (0xde57ccc0)) > [<c01df40f>] alloc_skb [kernel] 0xef (0xde57cd1c)) > [<c020e191>] tcp_send_ack [kernel] 0xc1 (0xde57cd34)) > [<c01deea3>] sock_def_wakeup [kernel] 0x33 (0xde57cd4c)) > [<c020a85a>] tcp_rcv_synsent_state_process [kernel] 0x30a (0xde57cd58)) > [<c01fef70>] tcp_rfree [kernel] 0x0 (0xde57cd6c)) > [<c01def59>] sock_def_readable [kernel] 0x39 (0xde57cd74)) > [<c01fef70>] tcp_rfree [kernel] 0x0 (0xde57cd84)) > [<c020a0c9>] tcp_rcv_established [kernel] 0x429 (0xde57cd90)) > [<c020ab6e>] tcp_rcv_state_process [kernel] 0xbe (0xde57cde0)) > [<c01def59>] sock_def_readable [kernel] 0x39 (0xde57ce04)) > [<c01fef70>] tcp_rfree [kernel] 0x0 (0xde57ce14)) > [<c020a0c9>] tcp_rcv_established [kernel] 0x429 (0xde57ce20)) > [<c01fb7a2>] ip_output [kernel] 0x102 (0xde57ce5c)) > [<c02120f8>] tcp_v4_do_rcv [kernel] 0x38 (0xde57ce74)) > [<c01fbbd0>] ip_queue_xmit [kernel] 0x3c0 (0xde57ce90)) > [<c021264d>] tcp_v4_rcv [kernel] 0x46d (0xde57cea4)) > [<c01e07d4>] skb_checksum [kernel] 0x54 (0xde57ced8)) > [<c0212191>] tcp_v4_do_rcv [kernel] 0xd1 (0xde57cf04)) > [<c021202f>] tcp_v4_checksum_init [kernel] 0x7f (0xde57cf1c)) > [<c021264d>] tcp_v4_rcv [kernel] 0x46d (0xde57cf34)) > [<c01f88c3>] ip_local_deliver [kernel] 0xf3 (0xde57cf58)) > [<c01f606b>] ip_route_input [kernel] 0x3b (0xde57cf60)) > [<c01f8cb5>] ip_rcv [kernel] 0x355 (0xde57cfa0)) > [<c01df5ec>] kfree_skbmem [kernel] 0xc (0xde57cfd0)) > [<c01f88c3>] ip_local_deliver [kernel] 0xf3 (0xde57cfe8)) > [<c01f606b>] ip_route_input [kernel] 0x3b (0xde57cff0)) > [<c01f8cb5>] ip_rcv [kernel] 0x355 (0xde57d030)) > [<c01e37f0>] netif_rx [kernel] 0xc0 (0xde57d03c)) > [<c01df5ec>] kfree_skbmem [kernel] 0xc (0xde57d060)) > [<c01df76e>] __kfree_skb [kernel] 0x11e (0xde57d070)) > [<c022bcf2>] packet_rcv_spkt [kernel] 0x1b2 (0xde57d07c)) > [<c01ed514>] qdisc_restart [kernel] 0x14 (0xde57d0a0)) > [<c01e3e8f>] net_rx_action [kernel] 0x9f (0xde57d0b8)) > [<c01e3c99>] netif_receive_skb [kernel] 0x199 (0xde57d0d8)) > [<c01e3d49>] process_backlog [kernel] 0x79 (0xde57d118)) > [<c010a920>] do_IRQ [kernel] 0x100 (0xde57d134)) > [<c01e3e8f>] net_rx_action [kernel] 0x9f (0xde57d148)) > [<c012137b>] do_softirq [kernel] 0x6b (0xde57d180)) > [<c01e5374>] .text.lock.dev [kernel] 0x8e (0xde57d19c)) > [<c01f606b>] ip_route_input [kernel] 0x3b (0xde57d1bc)) > [<c01fb7a2>] ip_output [kernel] 0x102 (0xde57d1f8)) > [<c01fbbd0>] ip_queue_xmit [kernel] 0x3c0 (0xde57d22c)) > [<c01df76e>] __kfree_skb [kernel] 0x11e (0xde57d24c)) > [<c01e3a22>] net_tx_action [kernel] 0x62 (0xde57d258)) > [<c012137b>] do_softirq [kernel] 0x6b (0xde57d274)) > [<c0117ea0>] do_page_fault [kernel] 0x0 (0xde57d298)) > [<c0108d84>] error_code [kernel] 0x34 (0xde57d2a0)) > [<c02111be>] tcp_v4_send_check [kernel] 0x6e (0xde57d2cc)) > [<c020bc15>] tcp_transmit_skb [kernel] 0x565 (0xde57d2f4)) > [<c01e162c>] skb_copy_datagram_iovec [kernel] 0x4c (0xde57d334)) > [<c01df40f>] alloc_skb [kernel] 0xef (0xde57d350)) > [<c020e191>] tcp_send_ack [kernel] 0xc1 (0xde57d368)) > [<c01df5ec>] kfree_skbmem [kernel] 0xc (0xde57d374)) > [<c0202a75>] tcp_recvmsg [kernel] 0x7e5 (0xde57d38c)) > [<c021eac9>] inet_recvmsg [kernel] 0x39 (0xde57d3d0)) > [<c021eac9>] inet_recvmsg [kernel] 0x39 (0xde57d3f0)) > [<c01dbe91>] sock_recvmsg [kernel] 0x31 (0xde57d41c)) > [<c01dbf98>] sock_read [kernel] 0x88 (0xde57d484)) > [<e0918ab8>] k_read_u_f [bproc] 0x34 (0xde57d4c8)) > [<e0910316>] read_req_file_user [bproc] 0x5e (0xde57d4e8)) > [<e09106d0>] vmadump_read_file [bproc] 0x0 (0xde57d514)) > [<e0907134>] read_user [vmadump] 0x44 (0xde57d518)) > [<e0907eb7>] load_map [vmadump] 0x1ab (0xde57d548)) > [<e090717d>] read_kern [vmadump] 0x2d (0xde57d588)) > [<e0908385>] vmadump_thaw_proc [vmadump] 0x45d (0xde57d5a8)) > [<c01df40f>] alloc_skb [kernel] 0xef (0xde57d5c4)) > [<c01df76e>] __kfree_skb [kernel] 0x11e (0xde57d628)) > [<c0207570>] tcp_clean_rtx_queue [kernel] 0x1b0 (0xde57d630)) > [<c0208ad6>] tcp_data_queue [kernel] 0x2b6 (0xde57d674)) > [<c0207a98>] tcp_ack [kernel] 0x138 (0xde57d6a0)) > [<c020b4be>] tcp_rcv_state_process [kernel] 0xa0e (0xde57d6c4)) > [<c020e191>] tcp_send_ack [kernel] 0xc1 (0xde57d6dc)) > [<c01fef70>] tcp_rfree [kernel] 0x0 (0xde57d6f0)) > [<c020a0c9>] tcp_rcv_established [kernel] 0x429 (0xde57d6fc)) > [<c01e07d4>] skb_checksum [kernel] 0x54 (0xde57d7b4)) > [<c0212191>] tcp_v4_do_rcv [kernel] 0xd1 (0xde57d7e0)) > [<c021202f>] tcp_v4_checksum_init [kernel] 0x7f (0xde57d7f8)) > [<c021264d>] tcp_v4_rcv [kernel] 0x46d (0xde57d810)) > [<c01df5ec>] kfree_skbmem [kernel] 0xc (0xde57d8ac)) > [<c01f88c3>] ip_local_deliver [kernel] 0xf3 (0xde57d8c4)) > [<c01f606b>] ip_route_input [kernel] 0x3b (0xde57d8cc)) > [<c011d016>] ll_copy_to_user [kernel] 0x46 (0xde57d8dc)) > [<c011d016>] ll_copy_to_user [kernel] 0x46 (0xde57d8fc)) > [<c011d016>] ll_copy_to_user [kernel] 0x46 (0xde57d90c)) > [<c011d016>] ll_copy_to_user [kernel] 0x46 (0xde57d92c)) > [<c01e0fb8>] memcpy_toiovec [kernel] 0x38 (0xde57d950)) > [<c01e162c>] skb_copy_datagram_iovec [kernel] 0x4c (0xde57d974)) > [<c0201e5e>] cleanup_rbuf [kernel] 0xae (0xde57d994)) > [<c0201e5e>] cleanup_rbuf [kernel] 0xae (0xde57d9b4)) > [<c0202a75>] tcp_recvmsg [kernel] 0x7e5 (0xde57d9cc)) > [<c021eac9>] inet_recvmsg [kernel] 0x39 (0xde57da10)) > [<c021eac9>] inet_recvmsg [kernel] 0x39 (0xde57da30)) > [<c01dbe91>] sock_recvmsg [kernel] 0x31 (0xde57da5c)) > [<c01fefbe>] tcp_poll [kernel] 0x2e (0xde57da7c)) > [<c01dbf98>] sock_read [kernel] 0x88 (0xde57dac4)) > [<e0918ab8>] k_read_u_f [bproc] 0x34 (0xde57db08)) > [<e0910375>] read_req_file_kern [bproc] 0x2d (0xde57db58)) > [<e0911c32>] do_recv [bproc] 0x522 (0xde57db78)) > [<c01193cc>] schedule [kernel] 0x48c (0xde57dbc0)) > [<c0118e27>] schedule_timeout [kernel] 0x17 (0xde57dc14)) > [<c02120f8>] tcp_v4_do_rcv [kernel] 0x38 (0xde57dc34)) > [<c0201e5e>] cleanup_rbuf [kernel] 0xae (0xde57dc64)) > [<c0202a75>] tcp_recvmsg [kernel] 0x7e5 (0xde57dc7c)) > [<c021eac9>] inet_recvmsg [kernel] 0x39 (0xde57dce0)) > [<c01dbe91>] sock_recvmsg [kernel] 0x31 (0xde57dd0c)) > [<c021eb15>] inet_sendmsg [kernel] 0x35 (0xde57dd2c)) > [<c01dbe3c>] sock_sendmsg [kernel] 0x6c (0xde57dd40)) > [<c01dbf98>] sock_read [kernel] 0x88 (0xde57dd74)) > [<e09106d0>] vmadump_read_file [bproc] 0x0 (0xde57dda4)) > [<e09106b4>] vmadump_write_file [bproc] 0x0 (0xde57dda8)) > [<e0918ab8>] k_read_u_f [bproc] 0x34 (0xde57ddb8)) > [<c01261c3>] collect_signal [kernel] 0x93 (0xde57de0c)) > [<e0912236>] recv_process [bproc] 0x6a (0xde57de58)) > [<e0918be1>] k_close [bproc] 0xd (0xde57df38)) > [<e0917b70>] do_recv_proc_stub [bproc] 0x184 (0xde57df58)) > [<e090c319>] bproc_kernel_thread [bproc] 0x2d (0xde57dfb8)) > > bproc: connect: connect to 192.168.2.4:46219 failed; errno=111 |