[Bug 1311] [dpdk-23.11] vhost_virtio_user_interrupt_with_power_monitor: Launch dpdk-l3fwd-power core dumped on SPR

bugzilla at dpdk.org bugzilla at dpdk.org
Thu Nov 9 10:22:14 CET 2023


https://bugs.dpdk.org/show_bug.cgi?id=1311

            Bug ID: 1311
           Summary: [dpdk-23.11]
                    vhost_virtio_user_interrupt_with_power_monitor: Launch
                    dpdk-l3fwd-power core dumped on SPR
           Product: DPDK
           Version: 23.11
          Hardware: All
                OS: All
            Status: UNCONFIRMED
          Severity: normal
          Priority: Normal
         Component: vhost/virtio
          Assignee: dev at dpdk.org
          Reporter: linglix.chen at intel.com
  Target Milestone: ---

[Environment]
DPDK version: dpdk 23.11-rc1: 5f9426b061
OS: Ubuntu 22.04.3 LTS/5.15.0-84-generic
Compiler: gcc version 11.4.0
Hardware platform: SPR(Intel(R) Xeon(R) Platinum 8490H)
NIC hardware: Ethernet Controller E810-C for QSFP 1592
NIC firmware: 4.40 0x8001c2f1 1.3492.0
NIC kdriver: ice-1.13.0_rc99_4_gb8ad35697

[Test Setup]
Steps to reproduce
1. ssh root at dpdk-yingya-spr2  

2.bind NIC port to vfio-pci,  
./usertools/dpdk-devbind.py -b vfio-pci 45:00.0

3. Launch vhost by below command:: 
./x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 1-2 -n 4 --file-prefix=vhost
--vdev 'net_vhost0,iface=./vhost-net,queues=1' -- -i --rxq=1 --txq=1

4. Launch virtio with l3fwd-power::      
 ./x86_64-native-linuxapp-gcc/examples/dpdk-l3fwd-power -l 3-4 -n 4 --no-pci
--file-prefix=l3fwd-power --vdev=virtio_user0,path=./vhost-net
--log-level='user1,7' -- -p 1 --config="(0,0,4)" --parse-ptype
--pmd-mgmt=monitor

[Show the output from the previous commands]
EAL: Detected CPU lcores: 128
EAL: Detected NUMA nodes: 2
EAL: Detected static linkage of DPDK
EAL: Multi-process socket /var/run/dpdk/l3fwd-power/mp_socket
EAL: Selected IOVA mode 'VA'
EAL: VFIO support initialized
virtio_user_dev_init_mac(): (./vhost-net) No valid MAC in devargs or device,
use random
soft parse-ptype is enabled
PMD power mgmt mode is enabled
L3FWD_POWER: Selected operation mode: pmd mgmt
Initializing port 0 ... Creating queues: nb_rxq=1 nb_txq=1... Port 0 modified
RSS hash function based on hardware support,requested:0x20820 configured:0
 Address:06:8F:52:89:DE:C0, Allocated mbuf pool on socket 0
LPM: Adding route 0x01010100 / 24 (0)
LPM: Adding route 0x02010100 / 24 (1)
LPM: Adding route 0x03010100 / 24 (2)
LPM: Adding route 0x04010100 / 24 (3)
LPM: Adding route 0x05010100 / 24 (4)
LPM: Adding route 0x06010100 / 24 (5)
LPM: Adding route 0x07010100 / 24 (6)
LPM: Adding route 0x08010100 / 24 (7)
txq=3,0,0

Initializing rx queues on lcore 3 ...
Initializing rx queues on lcore 4 ... rxq=0,0,0 Port 0: softly parse packet
type info

Checking link statusdone
Port 0 Link up at Unknown FDX Autoneg
L3FWD_POWER: entering main telemetry loop on lcore 4
L3FWD_POWER:  -- lcoreid=4 portid=0 rxqueueid=0
L3FWD_POWER: lcore 3 has nothing to do
Segmentation fault (core dumped)

[Expected Result]
Launch dpdk-l3fwd-power normal.

Regression
Is this issue a regression: (Y/N) Y

First bad commit 60943c04f3bcd0ed32a9844993d1182c917b978b 

Author: Tyler Retzlaff <roretzla at linux.microsoft.com>
Date:   Fri Aug 11 12:20:47 2023 -0700


    eal/x86: use intrinsics for power management


    Inline assembly is not supported for MSVC x64 instead use _umonitor,
    _umwait and _tpause intrinsics.


    Signed-off-by: Tyler Retzlaff <roretzla at linux.microsoft.com>
    Acked-by: Morten Brørup <mb at smartsharesystems.com>
    Acked-by: Konstantin Ananyev <konstantin.v.ananyev at yandex.ru>


test on SPR only
The bad commit 60943c04f3 will build failed, fixed commit ac1d4db91e (eal/x86:
fix build on systems with WAITPKG)

-- 
You are receiving this mail because:
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mails.dpdk.org/archives/dev/attachments/20231109/b1f3a964/attachment.htm>


More information about the dev mailing list