Description of problem: running nested KVM -> ovirt -> vm1 -> dhcp network1 using <- vm2 Additional info: BUG: unable to handle kernel paging request at ffff87ffffffffff IP: [<ffffffffa01a7641>] __direct_map.isra.104+0xa1/0x210 [kvm] PGD 0 Oops: 0000 [#1] SMP Modules linked in: cpufreq_stats tcp_lp fuse ebtable_nat xt_CHECKSUM bridge stp llc nf_conntrack_netbios_ns nf_conntrack_broadcast ipt_MASQUERADE ip6table_mangle ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 iptable_nat nf_nat_ipv4 nf_nat rfcomm iptable_mangle bnep nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack ebtable_filter ebtables ip6table_filter ip6_tables be2iscsi iscsi_boot_sysfs bnx2i cnic uio cxgb4i cxgb4 cxgb3i cxgb3 mdio libcxgbi ib_iser rdma_cm ib_addr iw_cm ib_cm ib_sa ib_mad ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi vfat fat binfmt_misc arc4 snd_hda_codec_hdmi snd_hda_codec_conexant iwldvm mac80211 iTCO_wdt iTCO_vendor_support coretemp microcode joydev i2c_i801 uvcvideo snd_hda_intel videobuf2_vmalloc videobuf2_memops snd_hda_codec cdc_ncm usbnet videobuf2_core snd_hwdep mii videodev cdc_wdm snd_seq media cdc_acm snd_seq_device btusb snd_pcm bluetooth lpc_ich mfd_core iwlwifi snd_page_alloc snd_timer e1000e cfg80211 vhost_net tun macvtap mei macvlan kvm_intel thinkpad_acpi kvm tpm_tis snd tpm tpm_bios soundcore rfkill uinput crc32c_intel i915 sdhci_pci i2c_algo_bit ghash_clmulni_intel drm_kms_helper sdhci drm mmc_core i2c_core wmi video CPU 0 Pid: 2798, comm: qemu-kvm Not tainted 3.7.6-201.fc18.x86_64 #1 LENOVO 4236NGG/4236NGG RIP: 0010:[<ffffffffa01a7641>] [<ffffffffa01a7641>] __direct_map.isra.104+0xa1/0x210 [kvm] RSP: 0018:ffff8801dc1ebb58 EFLAGS: 00010293 RAX: 0000000000000004 RBX: 000ffffffffff000 RCX: 0000000000000027 RDX: 0000000122954000 RSI: 0000000000000000 RDI: 0000000000000003 RBP: ffff8801dc1ebc08 R08: ffff87ffffffffff R09: 00000000000bae77 R10: ffff87ffffffffff R11: 0000000000000000 R12: ffff8801d8ba8000 R13: 0000000000000001 R14: ffff880000000000 R15: 0000000000000001 FS: 00007f3867922700(0000) GS:ffff88021e200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff87ffffffffff CR3: 00000001d8bd7000 CR4: 00000000000427e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process qemu-kvm (pid: 2798, threadinfo ffff8801dc1ea000, task ffff8801e97d4560) Stack: 0000000000000000 0000000000000001 ffff8801dc1ebb78 ffffffffa0187550 ffff8801dc1ebb88 ffffffffa0187579 00ff8801dc1ebc08 00000000000bae77 0000000200000001 0000000000122954 ffff8801dc1ebbd8 00000000a01870a1 Call Trace: [<ffffffffa0187550>] ? __gfn_to_pfn+0x60/0x70 [kvm] [<ffffffffa0187579>] ? gfn_to_pfn_prot+0x19/0x20 [kvm] [<ffffffffa01a7eb0>] tdp_page_fault+0x1d0/0x210 [kvm] [<ffffffffa01a1f61>] kvm_mmu_page_fault+0x31/0x100 [kvm] [<ffffffffa022c4a6>] handle_ept_violation+0x66/0x120 [kvm_intel] [<ffffffffa023166c>] vmx_handle_exit+0xcc/0x780 [kvm_intel] [<ffffffff81096335>] ? sched_clock_cpu+0xc5/0x120 [<ffffffffa019ca2f>] kvm_arch_vcpu_ioctl_run+0x43f/0x1010 [kvm] [<ffffffffa022c73e>] ? vmx_vcpu_load+0x3e/0x1a0 [kvm_intel] [<ffffffffa0185202>] kvm_vcpu_ioctl+0x472/0x610 [kvm] [<ffffffff810ba1d0>] ? do_futex+0x100/0xad0 [<ffffffff8163a9f4>] ? __do_page_fault+0x244/0x4e0 [<ffffffff81125474>] ? perf_event_context_sched_in+0x94/0xc0 [<ffffffff811a64f9>] do_vfs_ioctl+0x99/0x580 [<ffffffff8128d0b7>] ? file_has_perm+0x97/0xb0 [<ffffffff811a6a71>] sys_ioctl+0x91/0xb0 [<ffffffff810dca8c>] ? __audit_syscall_exit+0x3ec/0x450 [<ffffffff8163f2d9>] system_call_fastpath+0x16/0x1b Code: 4d 89 f0 4c 03 45 b8 8d 4c ff 0c 48 89 d6 48 d3 ee 81 e6 ff 01 00 00 41 39 c5 4d 8d 14 f0 89 75 cc 4c 89 55 c0 0f 84 c7 00 00 00 <49> 8b 32 40 f6 c6 01 74 36 4c 8b 05 7f c4 02 00 49 89 f1 4d 21 RIP [<ffffffffa01a7641>] __direct_map.isra.104+0xa1/0x210 [kvm] RSP <ffff8801dc1ebb58> CR2: ffff87ffffffffff
Marcelo, any thoughts on this one?
Created attachment 740367 [details] Screenshot of kernel dump
Hi, I may have experienced similar issue during high memory load (compiling oVirt, running ecipse, chrome, .. etc) and running nested virtualization via qemu-kvm. It usually happens when the compiler enters the most memory intensive phase of compilation (also swapping heavily, I have only 8GB of RAM). In the attachment I include a screenshot of the kernel dump. Sorry for the bad quality.
Martin, Can you reproduce with the instructions at https://bugzilla.redhat.com/show_bug.cgi?id=924916? Marking this bug as a duplicate of that one. *** This bug has been marked as a duplicate of bug 924916 ***