[Kernel-packages] [Bug 1630304] [NEW] Ubuntu 16.10 KVM: Issue doing hotplug detach to SRIOV VF
Public bug reported: ---Problem Description--- I can not get hotplug attach to work in Ubuntu but if I try to detach a CX4 VF from a guest I am getting some issues: Like in this case: [ 474.393308] vfio-pci 0001:01:00.3: No device request channel registered, blocked until released by user [ 474.393543] pci 0001:01: 0.3: [PE# 006] Removing DMA window #0 [ 474.393553] pci 0001:01: 0.3: [PE# 006] Removing DMA window #1 [ 474.393906] mlx5_core 0001:01:00.3: enabling device ( -> 0002) [ 474.393939] mlx5_core 0001:01:00.3: Using 32-bit DMA via iommu [ 474.400360] pci 0001:01: 0.3: [PE# 006] Setting up window#0 0..7fff pg=1000 [ 474.400380] mlx5_core 0001:01:00.3: firmware version: 12.17.226 [ 474.401341] pci 0001:01: 0.3: [PE# 006] Enabling 64-bit DMA bypass [ 474.402284] EEH: Frozen PE#6 on PHB#1 detected [ 474.402475] EEH: PE location: Slot4, PHB location: N/A [ 474.403699] EEH: This PCI device has failed 1 times in the last hour [ 474.403700] EEH: Notify device drivers to shutdown [ 474.403707] mlx5_core 0001:01:00.3: mlx5_pci_err_detected was called [ 474.403711] mlx5_core 0001:01:00.3: 0001:01:00.3:mlx5_enter_error_state:115:(pid 779): start [ 474.403870] mlx5_core 0001:01:00.3: 0001:01:00.3:mlx5_enter_error_state:120:(pid 779): end One time I saw SSep 13 09:41:32 ltc-fire1 kernel: [70437.943722] vfio-pci 0001:01:00.3: No device request channel registered, blocked until released by user Sep 13 09:41:32 ltc-fire1 kernel: [70437.944076] mlx5_core 0001:01:00.3: enabling device ( -> 0002) Sep 13 09:41:32 ltc-fire1 kernel: [70437.944110] mlx5_core 0001:01:00.3: Using 32-bit DMA via iommu Sep 13 09:41:32 ltc-fire1 kernel: [70437.944145] pci 0001:01: 0.3: [PE# 006] Removing DMA window #0 Sep 13 09:41:32 ltc-fire1 kernel: [70437.944152] pci 0001:01: 0.3: [PE# 006] Removing DMA window #1 Sep 13 09:41:32 ltc-fire1 kernel: [70437.944195] mlx5_core 0001:01:00.3: firmware version: 12.17.226 Sep 13 09:41:32 ltc-fire1 kernel: [70437.944260] Unable to handle kernel paging request for data at address 0x Sep 13 09:41:32 ltc-fire1 kernel: [70437.944533] Faulting instruction address: 0xc05b37e0 Sep 13 09:41:32 ltc-fire1 kernel: [70437.944592] Oops: Kernel access of bad area, sig: 11 [#1] Sep 13 09:41:32 ltc-fire1 kernel: [70437.944636] SMP NR_CPUS=2048 NUMA PowerNV Sep 13 09:41:32 ltc-fire1 kernel: [70437.944851] Modules linked in: vfio_pci irqbypass vfio_iommu_spapr_tce vfio_virqfd vfio vfio_spapr_eeh xt_CHECKSUM iptable_mangle ipt_MASQUERADE nf_nat_masquerade_ipv4 iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack ipt_REJECT nf_reject_ipv4 xt_tcpudp kvm_hv kvm_pr kvm ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter rdma_ucm(OE) ib_ucm(OE) rdma_cm(OE) iw_cm(OE) configfs ib_ipoib(OE) ib_cm(OE) ib_uverbs(OE) ib_umad(OE) mlx5_ib(OE) mlx5_core(OE) mlx4_ib(OE) ib_sa(OE) ib_mad(OE) ib_core(OE) mlx4_en(OE) ib_addr(OE) ib_netlink(OE) mlx4_core(OE) mlx_compat(OE) bridge stp llc joydev input_leds mac_hid ofpart at24 cmdlinepart powernv_flash ipmi_powernv nvmem_core uio_pdrv_genirq opal_prd mtd ipmi_msghandler uio ibmpowernv powernv_rng binfmt_misc dm_multipath knem(OE) ip_tables x_tables autofs4 hid_generic usbhid hid uas usb_storage ast i2c_algo_bit ttm drm_kms_helper syscopyarea sysfillrect sysim gblt fb_sys_fops drm ahci devlink libahci [last unloaded: mlx4_core] Sep 13 09:41:32 ltc-fire1 kernel: [70437.946007] CPU: 40 PID: 12501 Comm: libvirtd Tainted: G OE 4.7.0unofficial #5 Sep 13 09:41:32 ltc-fire1 kernel: [70437.946074] task: c00ec319a200 ti: c00ec324c000 task.ti: c00ec324c000 Sep 13 09:41:32 ltc-fire1 kernel: [70437.946140] NIP: c05b37e0 LR: c05ad070 CTR: Sep 13 09:41:32 ltc-fire1 kernel: [70437.946208] REGS: c00ec324f100 TRAP: 0300 Tainted: G OE(4.7.0unofficial) Sep 13 09:41:32 ltc-fire1 kernel: [70437.946286] MSR: 90010280b033CR: 84028844 XER: 2000 Sep 13 09:41:32 ltc-fire1 kernel: [70437.946533] CFAR: c0008468 DAR: DSISR: 4000 SOFTE: 0 Sep 13 09:41:32 ltc-fire1 kernel: [70437.946533] GPR00: c05d19c8 c00ec324f380 c13bef00 Sep 13 09:41:32 ltc-fire1 kernel: [70437.946533] GPR04: Sep 13 09:41:32 ltc-fire1 kernel: [70437.946533] GPR08: f3803140 Sep 13 09:41:32 ltc-fire1 kernel: [70437.946533] GPR12: 24048840 cfb96800 c00ec0def080 c00ec0def000 Sep 13 09:41:32 ltc-fire1 kernel: [70437.946533] GPR16: 3fff93ef 0001 c00ec0def100 Sep 13 09:41:32 ltc-fire1 kernel: [70437.946533] GPR20: c00ec0def118 0001 Sep 13 09:41:32 ltc-fire1 kernel: [70437.946533] GPR24:
[Kernel-packages] [Bug 1630304] [NEW] Ubuntu 16.10 KVM: Issue doing hotplug detach to SRIOV VF
You have been subscribed to a public bug: ---Problem Description--- I can not get hotplug attach to work in Ubuntu but if I try to detach a CX4 VF from a guest I am getting some issues: Like in this case: [ 474.393308] vfio-pci 0001:01:00.3: No device request channel registered, blocked until released by user [ 474.393543] pci 0001:01: 0.3: [PE# 006] Removing DMA window #0 [ 474.393553] pci 0001:01: 0.3: [PE# 006] Removing DMA window #1 [ 474.393906] mlx5_core 0001:01:00.3: enabling device ( -> 0002) [ 474.393939] mlx5_core 0001:01:00.3: Using 32-bit DMA via iommu [ 474.400360] pci 0001:01: 0.3: [PE# 006] Setting up window#0 0..7fff pg=1000 [ 474.400380] mlx5_core 0001:01:00.3: firmware version: 12.17.226 [ 474.401341] pci 0001:01: 0.3: [PE# 006] Enabling 64-bit DMA bypass [ 474.402284] EEH: Frozen PE#6 on PHB#1 detected [ 474.402475] EEH: PE location: Slot4, PHB location: N/A [ 474.403699] EEH: This PCI device has failed 1 times in the last hour [ 474.403700] EEH: Notify device drivers to shutdown [ 474.403707] mlx5_core 0001:01:00.3: mlx5_pci_err_detected was called [ 474.403711] mlx5_core 0001:01:00.3: 0001:01:00.3:mlx5_enter_error_state:115:(pid 779): start [ 474.403870] mlx5_core 0001:01:00.3: 0001:01:00.3:mlx5_enter_error_state:120:(pid 779): end One time I saw SSep 13 09:41:32 ltc-fire1 kernel: [70437.943722] vfio-pci 0001:01:00.3: No device request channel registered, blocked until released by user Sep 13 09:41:32 ltc-fire1 kernel: [70437.944076] mlx5_core 0001:01:00.3: enabling device ( -> 0002) Sep 13 09:41:32 ltc-fire1 kernel: [70437.944110] mlx5_core 0001:01:00.3: Using 32-bit DMA via iommu Sep 13 09:41:32 ltc-fire1 kernel: [70437.944145] pci 0001:01: 0.3: [PE# 006] Removing DMA window #0 Sep 13 09:41:32 ltc-fire1 kernel: [70437.944152] pci 0001:01: 0.3: [PE# 006] Removing DMA window #1 Sep 13 09:41:32 ltc-fire1 kernel: [70437.944195] mlx5_core 0001:01:00.3: firmware version: 12.17.226 Sep 13 09:41:32 ltc-fire1 kernel: [70437.944260] Unable to handle kernel paging request for data at address 0x Sep 13 09:41:32 ltc-fire1 kernel: [70437.944533] Faulting instruction address: 0xc05b37e0 Sep 13 09:41:32 ltc-fire1 kernel: [70437.944592] Oops: Kernel access of bad area, sig: 11 [#1] Sep 13 09:41:32 ltc-fire1 kernel: [70437.944636] SMP NR_CPUS=2048 NUMA PowerNV Sep 13 09:41:32 ltc-fire1 kernel: [70437.944851] Modules linked in: vfio_pci irqbypass vfio_iommu_spapr_tce vfio_virqfd vfio vfio_spapr_eeh xt_CHECKSUM iptable_mangle ipt_MASQUERADE nf_nat_masquerade_ipv4 iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack ipt_REJECT nf_reject_ipv4 xt_tcpudp kvm_hv kvm_pr kvm ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter rdma_ucm(OE) ib_ucm(OE) rdma_cm(OE) iw_cm(OE) configfs ib_ipoib(OE) ib_cm(OE) ib_uverbs(OE) ib_umad(OE) mlx5_ib(OE) mlx5_core(OE) mlx4_ib(OE) ib_sa(OE) ib_mad(OE) ib_core(OE) mlx4_en(OE) ib_addr(OE) ib_netlink(OE) mlx4_core(OE) mlx_compat(OE) bridge stp llc joydev input_leds mac_hid ofpart at24 cmdlinepart powernv_flash ipmi_powernv nvmem_core uio_pdrv_genirq opal_prd mtd ipmi_msghandler uio ibmpowernv powernv_rng binfmt_misc dm_multipath knem(OE) ip_tables x_tables autofs4 hid_generic usbhid hid uas usb_storage ast i2c_algo_bit ttm drm_kms_helper syscopyarea sysfillrect sysim gblt fb_sys_fops drm ahci devlink libahci [last unloaded: mlx4_core] Sep 13 09:41:32 ltc-fire1 kernel: [70437.946007] CPU: 40 PID: 12501 Comm: libvirtd Tainted: G OE 4.7.0unofficial #5 Sep 13 09:41:32 ltc-fire1 kernel: [70437.946074] task: c00ec319a200 ti: c00ec324c000 task.ti: c00ec324c000 Sep 13 09:41:32 ltc-fire1 kernel: [70437.946140] NIP: c05b37e0 LR: c05ad070 CTR: Sep 13 09:41:32 ltc-fire1 kernel: [70437.946208] REGS: c00ec324f100 TRAP: 0300 Tainted: G OE(4.7.0unofficial) Sep 13 09:41:32 ltc-fire1 kernel: [70437.946286] MSR: 90010280b033CR: 84028844 XER: 2000 Sep 13 09:41:32 ltc-fire1 kernel: [70437.946533] CFAR: c0008468 DAR: DSISR: 4000 SOFTE: 0 Sep 13 09:41:32 ltc-fire1 kernel: [70437.946533] GPR00: c05d19c8 c00ec324f380 c13bef00 Sep 13 09:41:32 ltc-fire1 kernel: [70437.946533] GPR04: Sep 13 09:41:32 ltc-fire1 kernel: [70437.946533] GPR08: f3803140 Sep 13 09:41:32 ltc-fire1 kernel: [70437.946533] GPR12: 24048840 cfb96800 c00ec0def080 c00ec0def000 Sep 13 09:41:32 ltc-fire1 kernel: [70437.946533] GPR16: 3fff93ef 0001 c00ec0def100 Sep 13 09:41:32 ltc-fire1 kernel: [70437.946533] GPR20: c00ec0def118 0001 Sep 13 09:41:32 ltc-fire1 kernel: