Package: qemu-system-x86 Version: 1:2.6+dfsg-1+b1 On launching qemu VM with SRIOV VF of a 10Gig NIC, if we change the the number of active SRIOV VFs using the following cmd, sometimes, CPU gets stuck and the system stops responding (eventhough there are free cores) sudo tee /sys/bus/pci/devices/0000:05:00.1/sriov_numvfs <<< '2'
Serial console shows the following logs repeatedly for [1024611.293960] NMI watchdog: BUG: soft lockup - CPU#2 stuck for 22s! [qemu-system-x86:10483] [1024611.334758] Modules linked in: 8021q(E) garp(E) mrp(E) ixgbevf(E) nfnetlink_queue(E) nfnetlink_log(E) nfnetlink(E) bluetooth(E) rfkill(E) pci_stub(E) vhost_net(E) vhost(E) macvtap(E) macvlan(E) igb(E) ipt_REJECT(E) nf_reject_ipv4(E) xt_tcpudp(E) bridge(E) stp(E) llc(E) ebtable_filter(E) ebtables(E) ip6table_filter(E) ip6_tables(E) iptable_filter(E) ip_tables(E) x_tables(E) tun(E) openvswitch(E) nf_defrag_ipv6(E) nf_conntrack(E) binfmt_misc(E) nfsd(E) nfs_acl(E) rpcsec_gss_krb5(E) auth_rpcgss(E) nfsv4(E) dns_resolver(E) nfs(E) lockd(E) grace(E) sunrpc(E) fscache(E) nls_utf8(E) nls_cp437(E) vfat(E) fat(E) intel_rapl(E) x86_pkg_temp_thermal(E) intel_powerclamp(E) coretemp(E) kvm_intel(E) kvm(E) irqbypass(E) crct10dif_pclmul(E) iTCO_wdt(E) crc32_pclmul(E) iTCO_vendor_support(E) ghash_clmulni_intel(E) evdev(E) hmac(E) drbg(E) ansi_cprng(E) efi_pstore(E) hpwdt(E) mgag200(E) aesni_intel(E) lpc_ich(E) hpilo(E) ttm(E) drm_kms_helper(E) drm(E) ipmi_si(E) ipmi_msghandler(E) aes_x86_64(E) lrw(E) sb_edac(E) tpm_tis(E) gf128mul(E) tpm(E) glue_helper(E) edac_core(E) ablk_helper(E) shpchp(E) wmi(E) pcspkr(E) 8250_fintek(E) efivars(E) acpi_power_meter(E) mfd_core(E) cryptd(E) ioatdma(E) i2c_i801(E) acpi_cpufreq(E) processor(E) button(E) fuse(E) efivarfs(E) autofs4(E) ext4(E) crc16(E) mbcache(E) jbd2(E) btrfs(E) xor(E) raid6_pq(E) md_mod(E) sd_mod(E) sg(E) igbvf(E) i2c_algo_bit(E) xhci_pci(E) uhci_hcd(E) ehci_pci(E) xhci_hcd(E) ehci_hcd(E) bnx2x(E) ixgbe(E) dca(E) tg3(E) vxlan(E) usbcore(E) ip6_udp_tunnel(E) libphy(E) libcrc32c(E) hpsa(E) udp_tunnel(E) usb_common(E) crc32c_generic(E) ptp(E) scsi_transport_sas(E) crc32c_intel(E) pps_core(E) mdio(E) scsi_mod(E) fjes(E) [last unloaded: igb] [1024612.066092] CPU: 2 PID: 10483 Comm: qemu-system-x86 Tainted: G D EL 4.5.0-2-amd64 #1 Debian 4.5.4-1 [1024612.116744] Hardware name: HP ProLiant DL380 Gen9, BIOS P89 03/05/2015 [1024612.150122] task: ffff881054c81000 ti: ffff881054d10000 task.ti: ffff881054d10000 [1024612.188837] RIP: 0010:[<ffffffff810f3abb>] [<ffffffff810f3abb>] smp_call_function_single+0xdb/0x130 [1024612.234690] RSP: 0018:ffff881054d13af0 EFLAGS: 00000202 [1024612.262203] RAX: 0000000000000000 RBX: 000000000000000d RCX: 0000000000000830 [1024612.297304] RDX: 0000000000000003 RSI: 00000000000008fb RDI: 0000000000000830 [1024612.334902] RBP: ffffffffc0758660 R08: ffff881054d10000 R09: 0000000000000000 [1024612.370568] R10: ffff88085ba74c10 R11: 0000000000000000 R12: 0000000000000002 [1024612.406230] R13: 0000000000000002 R14: 0000000000000000 R15: 0000000000000002 [1024612.441781] FS: 00007f7b6dc39700(0000) GS:ffff88085f900000(0000) knlGS:0000000000000000 [1024612.482557] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [1024612.512068] CR2: 0000000000683880 CR3: 0000001054d16000 CR4: 00000000001426e0 [1024612.547352] Stack: [1024612.558591] 0000000000000400 0000000700000002 0000000000000000 ffffffffc0758660 [1024612.596821] ffff88062b2fc650 0000000000000003 00000000ccb15845 ffff88062b2f8140 [1024612.634361] ffff881054d13c40 ffffffffc0757b45 ffffffff810b27ad ffff88105f015980 [1024612.671121] Call Trace: [1024612.684079] [<ffffffffc0758660>] ? hardware_enable+0x190/0x190 [kvm_intel] [1024612.719882] [<ffffffffc0757b45>] ? vmx_vcpu_load+0x215/0x340 [kvm_intel] [1024612.755080] [<ffffffff810b27ad>] ? load_balance+0x1fd/0x8f0 [1024612.782636] [<ffffffffc0820ced>] ? kvm_vcpu_kick+0x6d/0x80 [kvm] [1024612.813787] [<ffffffffc083775b>] ? kvm_arch_vcpu_load+0x3b/0x210 [kvm] [1024612.847528] [<ffffffff8109e09c>] ? finish_task_switch+0x15c/0x220 [1024612.879123] [<ffffffff815b31ff>] ? __schedule+0x2ef/0x950 [1024612.907193] [<ffffffff815b3891>] ? schedule+0x31/0x80 [1024612.933272] [<ffffffffc082206f>] ? kvm_vcpu_block+0x7f/0x2d0 [kvm] [1024612.965665] [<ffffffff810b87f0>] ? wake_atomic_t_function+0x60/0x60 [1024612.997341] [<ffffffffc083d475>] ? kvm_arch_vcpu_ioctl_run+0x525/0x1530 [kvm] [1024613.033821] [<ffffffffc0824c36>] ? kvm_vcpu_ioctl+0x316/0x5d0 [kvm] [1024613.066237] [<ffffffff810b80de>] ? __wake_up_common+0x4e/0x90 [1024613.095747] [<ffffffff811fcb9d>] ? do_vfs_ioctl+0x9d/0x5c0 [1024613.125476] [<ffffffff811e9883>] ? vfs_write+0x143/0x1a0 [1024613.153488] [<ffffffff811fd134>] ? SyS_ioctl+0x74/0x80 [1024613.179481] [<ffffffff815b7632>] ? system_call_fast_compare_end+0xc/0x67 [1024613.212693] Code: 00 75 73 48 83 c4 38 5b 5d c3 48 8d 74 24 10 48 89 d1 89 df 48 89 ea e8 34 fe ff ff 8b 54 24 28 83 e2 01 74 ce f3 90 8b 54 24 28 <83> e2 01 75 f5 eb c1 8b 05 50 ab bb 00 85 c0 75 83 80 3d 21 b6 -- Regards H.Prem Anand
