[dpdk-users] Issue with Trying to free already-free IRQ 0 error while lunching DPDK application (with QAT VFs) on VM (Wind River Linux).
Chinmaya Dwibedy
ckdwibedy at gmail.com
Mon Oct 24 17:04:37 CEST 2016
Hi ,
We have installed openstack-mitaka release on CentO7 system . It has two
Intel QAT devices. There are 32 VF devices available per QAT
Device/DH895xCC device. We have assigned 16 QAT VFs to a VM instance. We
are using dpdk-2.2.0. I have enabled CONFIG_RTE_LIBRTE_PMD_QAT in
common_linuxapp.
On VM (Wind River Linux) , run #echo "8086 0443" >
/sys/bus/pci/drivers/igb_uio/new_id to bind all the available 16 VFs to the
DPDK UIO driver. Thereafter checked the system logs (#dmesg) and #lspci
-vvd: 443 command and found that, 16 VFs devices are bound to igb_uio
kernel driver. ). I sincerely request your goodness to look into the below
stated error and suggest. Thanks in advance for your time and support.
The output of #dmesg.
[ 137.582054] igb_uio 0000:00:07.0: uio device registered with irq 0
[ 137.585057] igb_uio 0000:00:08.0: uio device registered with irq 0
[ 137.588095] igb_uio 0000:00:09.0: uio device registered with irq 0
[ 137.591310] igb_uio 0000:00:0a.0: uio device registered with irq 0
[ 137.594750] igb_uio 0000:00:0b.0: uio device registered with irq 0
[ 137.598360] igb_uio 0000:00:0c.0: uio device registered with irq 0
[ 137.602212] igb_uio 0000:00:0d.0: uio device registered with irq 0
[ 137.606270] igb_uio 0000:00:0e.0: uio device registered with irq 0
[ 137.610484] igb_uio 0000:00:0f.0: uio device registered with irq 0
[ 137.614896] igb_uio 0000:00:10.0: uio device registered with irq 0
[ 137.619908] igb_uio 0000:00:11.0: uio device registered with irq 0
[ 137.624511] igb_uio 0000:00:12.0: uio device registered with irq 0
[ 137.629430] igb_uio 0000:00:13.0: uio device registered with irq 0
[ 137.634559] igb_uio 0000:00:14.0: uio device registered with irq 0
[ 137.639911] igb_uio 0000:00:15.0: uio device registered with irq 0
[ 137.645436] igb_uio 0000:00:16.0: uio device registered with irq 0
The output of lspci -vvd:0443. It shows all VFs are in use by igb_uio.
00:07.0 Co-processor: Intel Corporation DH895XCC Series QAT Virtual Function
Subsystem: Intel Corporation Device 0000
Physical Slot: 7
Control: I/O- Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr-
Stepping- SERR- FastB2B- DisINTx-
Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort-
<TAbort- <MAbort- >SERR- <PERR- INTx-
Latency: 0
Region 0: Memory at feb18000 (64-bit, non-prefetchable) [size=4K]
Region 2: Memory at feb19000 (64-bit, non-prefetchable) [size=4K]
Capabilities: [90] MSI: Enable- Count=1/1 Maskable+ 64bit+
Address: 0000000000000000 Data: 0000
Masking: 00000000 Pending: 00000000
Kernel driver in use: igb_uio
00:08.0 Co-processor: Intel Corporation DH895XCC Series QAT Virtual Function
Subsystem: Intel Corporation Device 0000
Physical Slot: 8
Control: I/O- Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr-
Stepping- SERR- FastB2B- DisINTx-
Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort-
<TAbort- <MAbort- >SERR- <PERR- INTx-
Latency: 0
Region 0: Memory at feb1a000 (64-bit, non-prefetchable) [size=4K]
Region 2: Memory at feb1b000 (64-bit, non-prefetchable) [size=4K]
Capabilities: [90] MSI: Enable- Count=1/1 Maskable+ 64bit+
Address: 0000000000000000 Data: 0000
Masking: 00000000 Pending: 00000000
Kernel driver in use: igb_uio
Afterward when I lunch DPDK application , get the following errors (for all
the QAT VFs) in console.
EAL: PCI device 0000:00:07.0 on NUMA socket -1
EAL: probe driver: 8086:443 rte_qat_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:00:08.0 on NUMA socket -1
EAL: probe driver: 8086:443 rte_qat_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:00:09.0 on NUMA socket -1
EAL: probe driver: 8086:443 rte_qat_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:00:0a.0 on NUMA socket -1
EAL: probe driver: 8086:443 rte_qat_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:00:0b.0 on NUMA socket -1
EAL: probe driver: 8086:443 rte_qat_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:00:0c.0 on NUMA socket -1
EAL: probe driver: 8086:443 rte_qat_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:00:0d.0 on NUMA socket -1
EAL: probe driver: 8086:443 rte_qat_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:00:0e.0 on NUMA socket -1
EAL: probe driver: 8086:443 rte_qat_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:00:0f.0 on NUMA socket -1
EAL: probe driver: 8086:443 rte_qat_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:00:10.0 on NUMA socket -1
EAL: probe driver: 8086:443 rte_qat_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:00:11.0 on NUMA socket -1
EAL: probe driver: 8086:443 rte_qat_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:00:12.0 on NUMA socket -1
EAL: probe driver: 8086:443 rte_qat_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:00:13.0 on NUMA socket -1
EAL: probe driver: 8086:443 rte_qat_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:00:14.0 on NUMA socket -1
EAL: probe driver: 8086:443 rte_qat_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:00:15.0 on NUMA socket -1
EAL: probe driver: 8086:443 rte_qat_pmd
EAL: Not managed by a supported kernel driver, skipped
EAL: PCI device 0000:00:16.0 on NUMA socket -1
EAL: probe driver: 8086:443 rte_qat_pmd
EAL: Not managed by a supported kernel driver, skipped
Upon checking the #dmesg subsequently, find the following errors for all
QAT VFs (#dmesg).
[ 282.870718] ------------[ cut here ]------------
[ 282.870727] WARNING: CPU: 4 PID: 1626 at
/localdisk/jenkins/workspace/xMEG-OS/OS/.build/bitbake_build/tmp/work-shared/intel-x86-64/kernel-source/kernel/irq/manage.c:1352
__free_irq+0x97/0x1f0()
[ 282.870729] Trying to free already-free IRQ 0
[ 282.870730] Modules linked in: xt_DSCP sctp nfnetlink_queue nfnetlink
rte_kni(O) igb_uio(O-) uio bonding ipmi_devintf ipmi_msghandler
ip6table_mangle ip6table_filter ip6_tables iptable_mangle iptable_filter
ip_tables ixgbe cirrus serio_raw virtio_balloon ttm virtio_net mdio
acpi_cpufreq
[ 282.870745] CPU: 4 PID: 1626 Comm: rmmod Tainted: G O
4.1.21-WR8.0.0.6_cgl #1
[ 282.870747] Hardware name: Fedora Project OpenStack Nova, BIOS 0.5.1
01/01/2011
[ 282.870748] 0000000000000000 ffff880748c2fc58 ffffffff81787310
ffff880748c2fca8
[ 282.870751] ffffffff8199e2d0 ffff880748c2fc98 ffffffff81051fb0
ffff8806d7039348
[ 282.870753] 0000000000000000 0000000000000000 ffff880a94c088a4
ffff880a94c08800
[ 282.870755] Call Trace:
[ 282.870761] [<ffffffff81787310>] dump_stack+0x63/0x81
[ 282.870766] [<ffffffff81051fb0>] warn_slowpath_common+0x80/0xc0
[ 282.870768] [<ffffffff81052031>] warn_slowpath_fmt+0x41/0x50
[ 282.870770] [<ffffffff8109c4a7>] __free_irq+0x97/0x1f0
[ 282.870772] [<ffffffff8109c698>] free_irq+0x48/0xd0
[ 282.870775] [<ffffffffa01abf4a>] uio_unregister_device+0x3a/0x60 [uio]
[ 282.870778] [<ffffffffa01b2321>] igbuio_pci_remove+0x51/0xd0 [igb_uio]
[ 282.870783] [<ffffffff8131e328>] pci_device_remove+0x38/0xc0
[ 282.870787] [<ffffffff8140d04e>] __device_release_driver+0x7e/0x110
[ 282.870790] [<ffffffff8140d8d8>] driver_detach+0xb8/0xc0
[ 282.870792] [<ffffffff8140cd3b>] bus_remove_driver+0x4b/0xb0
[ 282.870794] [<ffffffff8140df3b>] driver_unregister+0x2b/0x60
[ 282.870796] [<ffffffff8131cf00>] pci_unregister_driver+0x20/0x90
[ 282.870799] [<ffffffffa01b29c3>] igbuio_pci_exit_module+0x10/0x12
[igb_uio]
[ 282.870805] [<ffffffff810bfb71>] SyS_delete_module+0x171/0x240
[ 282.870809] [<ffffffff8106be1c>] ? task_work_run+0xac/0xe0
[ 282.870813] [<ffffffff8178c832>] system_call_fastpath+0x16/0x75
[ 282.870814] ---[ end trace 1b9b73e493794378 ]---
[ 282.877798] ------------[ cut here ]------------
Regards,
Chinmaya
More information about the users
mailing list