29394 2013-09-25 19:20:02 +0400 падение ядра при включении mtu 9000 2015-10-13 14:33:31 +0300 1 1 3 Distributions Branch p6 kernel-image-std-def не указана x86_64 Linux NEW P3 normal --- 1 max cas leonid qa-p6 oldest_to_newest 142814 0 max 2013-09-25 19:20:02 +0400 Повторяется стабильно на 3.0.26 и 3.0.96 (kernel-image-std-def-3.0.96-alt0.M60P.1.x86_64.rpm) особенность - работа из-под специальной вендорской версии KVM При этом при mtu == 1500 падений нет. 2013-09-25 18.49.12:<: [ 24.826807] divide error: 0000 [#1] SMP 2013-09-25 18.49.12:<: [ 24.828955] CPU 0 2013-09-25 18.49.12:<: [ 24.828955] Modules linked in: shpchp pciehp acpiphp pci_hotplug ipv6 8021q garp stp dm_multipath scsi_dh dm_mod rtc ftdi_sio usbserial e1000e pcspkr e1000 psmouse serio_raw uhci_hcd usbcore i2c_piix4 i2c_core evdev processor l 2013-09-25 18.49.12:<: + 2tp_eth l2tp_netlink l2tp_core button tun ext4 mbcache jbd2 crc16 sg sd_mod sr_mod cdrom crc_t10dif pata_acpi ata_generic ata_piix libata scsi_mod 2013-09-25 18.49.12:<: [ 24.828955] 2013-09-25 18.49.12:<: [ 24.828955] Pid: 2339, comm: kworker/0:2 Not tainted 3.0.96-std-def-alt0.M60P.1 #1 Crossbeam Systems, Inc. X-80/XVM 2013-09-25 18.49.12:<: [ 24.828955] RIP: 0010:[<ffffffffa03f0816>] [<ffffffffa03f0816>] e1000_intr_msix_rx+0x26/0xa0 [e1000e] 2013-09-25 18.49.12:<: [ 24.828955] RSP: 0018:ffff88013fc03eb8 EFLAGS: 00010046 2013-09-25 18.49.12:<: [ 24.828955] RAX: 000000003b9aca00 RBX: ffff880295738f40 RCX: ffff880296dc5540 2013-09-25 18.49.12:<: [ 24.828955] RDX: 0000000000000000 RSI: ffff880294e28780 RDI: 0000000000000000 2013-09-25 18.49.12:<: [ 24.828955] RBP: ffff88013fc03eb8 R08: ffff880295365980 R09: ffff88013b000220 2013-09-25 18.49.12:<: [ 24.828955] R10: 0000000000000002 R11: 0000000000000000 R12: 0000000000000037 2013-09-25 18.49.12:<: [ 24.828955] R13: 0000000000000037 R14: 0000000000000000 R15: ffff880294e28c70 2013-09-25 18.49.12:<: [ 24.828955] FS: 0000000000000000(0000) GS:ffff88013fc00000(0000) knlGS:0000000000000000 2013-09-25 18.49.12:<: [ 24.828955] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b 2013-09-25 18.49.12:<: [ 24.828955] CR2: 00007f82a8647000 CR3: 0000000136e3c000 CR4: 00000000000006f0 2013-09-25 18.49.12:<: [ 24.828955] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 2013-09-25 18.49.12:<: [ 24.828955] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 2013-09-25 18.49.12:<: [ 24.828955] Process kworker/0:2 (pid: 2339, threadinfo ffff880136e5e000, task ffff8801369f2040) 2013-09-25 18.49.12:<: [ 24.828955] Stack: 2013-09-25 18.49.12:<: [ 24.828955] ffff88013fc03f08 ffffffff810c5fbd ffff880295365980 000000003fc03f30 2013-09-25 18.49.12:<: [ 24.828955] ffffffff8106334f ffff880295365980 ffff8802953659f4 0000000000000037 2013-09-25 18.49.12:<: [ 24.828955] ffff880136e5fcf8 ffff880294e28c70 ffff88013fc03f38 ffffffff810c6185 2013-09-25 18.49.12:<: [ 24.828955] Call Trace: 2013-09-25 18.49.12:<: [ 24.828955] <IRQ> 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff810c5fbd>] handle_irq_event_percpu+0x5d/0x1f0 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff8106334f>] ? __do_softirq+0xff/0x1c0 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff810c6185>] handle_irq_event+0x35/0x60 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff810c87ff>] handle_edge_irq+0x6f/0x110 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff8100d284>] handle_irq+0x44/0xa0 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff8100cf08>] do_IRQ+0x58/0xe0 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff8141cbd3>] common_interrupt+0x13/0x13 2013-09-25 18.49.12:<: [ 24.828955] <EOI> 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffffa03f479c>] ? e1000_watchdog_task+0x1bc/0x6f0 [e1000e] 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffffa03e9821>] ? e1000e_get_phy_info_m88+0x111/0x140 [e1000e] 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffffa03f45e0>] ? e1000_update_mng_vlan+0xa0/0xa0 [e1000e] 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff81077be3>] process_one_work+0x123/0x430 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff81078733>] worker_thread+0x163/0x340 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff810785d0>] ? manage_workers.clone.22+0x240/0x240 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff8107d586>] kthread+0x96/0xa0 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff814256a4>] kernel_thread_helper+0x4/0x10 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff8107d4f0>] ? kthread_worker_fn+0x190/0x190 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff814256a0>] ? gs_change+0x13/0x13 2013-09-25 18.49.12:<: [ 24.828955] Code: 80 00 00 00 00 48 81 c6 80 07 00 00 55 48 8b 8e 90 04 00 00 48 89 e5 8b 79 4c 85 ff 74 2a 8b 79 44 31 d2 b8 00 ca 9a 3b c1 e7 08 <f7> f7 0f b7 51 48 48 03 96 f8 04 00 00 89 02 48 8b 86 90 04 00 2013-09-25 18.49.12:<: [ 24.828955] RIP [<ffffffffa03f0816>] e1000_intr_msix_rx+0x26/0xa0 [e1000e] 2013-09-25 18.49.12:<: [ 24.828955] RSP <ffff88013fc03eb8> 2013-09-25 18.49.12:<: [ 24.828955] ---[ end trace f624deef40413cba ]--- 2013-09-25 18.49.12:<: [ 24.828955] Kernel panic - not syncing: Fatal exception in interrupt 2013-09-25 18.49.12:<: [ 24.828955] Pid: 2339, comm: kworker/0:2 Tainted: G D 3.0.96-std-def-alt0.M60P.1 #1 2013-09-25 18.49.12:<: [ 24.828955] Call Trace: 2013-09-25 18.49.12:<: [ 24.828955] <IRQ> [<ffffffff81419a25>] panic+0x8c/0x197 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff8141db12>] oops_end+0xe2/0xf0 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff8100e806>] die+0x56/0x90 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff8141d234>] do_trap+0xc4/0x170 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff8100bd1a>] do_divide_error+0x8a/0xb0 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffffa03f0816>] ? e1000_intr_msix_rx+0x26/0xa0 [e1000e] 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff814254bb>] divide_error+0x1b/0x20 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffffa03f0816>] ? e1000_intr_msix_rx+0x26/0xa0 [e1000e] 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff810c5fbd>] handle_irq_event_percpu+0x5d/0x1f0 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff8106334f>] ? __do_softirq+0xff/0x1c0 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff810c6185>] handle_irq_event+0x35/0x60 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff810c87ff>] handle_edge_irq+0x6f/0x110 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff8100d284>] handle_irq+0x44/0xa0 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff8100cf08>] do_IRQ+0x58/0xe0 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff8141cbd3>] common_interrupt+0x13/0x13 2013-09-25 18.49.12:<: [ 24.828955] <EOI> [<ffffffffa03f479c>] ? e1000_watchdog_task+0x1bc/0x6f0 [e1000e] 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffffa03e9821>] ? e1000e_get_phy_info_m88+0x111/0x140 [e1000e] 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffffa03f45e0>] ? e1000_update_mng_vlan+0xa0/0xa0 [e1000e] 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff81077be3>] process_one_work+0x123/0x430 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff81078733>] worker_thread+0x163/0x340 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff810785d0>] ? manage_workers.clone.22+0x240/0x240 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff8107d586>] kthread+0x96/0xa0 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff814256a4>] kernel_thread_helper+0x4/0x10 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff8107d4f0>] ? kthread_worker_fn+0x190/0x190 2013-09-25 18.49.12:<: [ 24.828955] [<ffffffff814256a0>] ? gs_change+0x13/0x13 153125 1 leonid 2015-10-13 14:33:31 +0300 A patch which fixes this issue was sent to the appropriate mailing lists. See here: https://lkml.org/lkml/2015/10/13/213