[Bug 1161] [dpdk-23.03]virtio_user_as_exceptional_path/vhost_exception_path_with_virtio_user: launch testpmd as virtio-user failed

[Bug 1161] [dpdk-23.03]virtio_user_as_exceptional_path/vhost_exception_path_with_virtio_user: launch testpmd as virtio-user failed

[bugzilla]

[-- Attachment #1: Type: text/plain, Size: 6696 bytes --]

https://bugs.dpdk.org/show_bug.cgi?id=1161

            Bug ID: 1161
           Summary: [dpdk-23.03]virtio_user_as_exceptional_path/vhost_exce
                    ption_path_with_virtio_user: launch testpmd as
                    virtio-user failed
           Product: DPDK
           Version: 22.03
          Hardware: x86
                OS: Linux
            Status: UNCONFIRMED
          Severity: normal
          Priority: Normal
         Component: vhost/virtio
          Assignee: dev@dpdk.org
          Reporter: weix.ling@intel.com
  Target Milestone: ---

[Environment]

DPDK version: Use make showversion or for a non-released version: git remote -v
&& git show-ref --heads
DPDK-23.03.0-rc0
Other software versions: N/A
OS: Ubuntu 22.04.1 LTS/Linux 5.15.45-051545-generic
Compiler: gcc version 11.3.0 (Ubuntu 11.3.0-1ubuntu1~22.04)
Hardware platform: Intel(R) Xeon(R) Platinum 8380 CPU @ 2.30GHz
NIC hardware: Intel Ethernet Controller XL710 for 40GbE QSFP+ 1583
Driver/NIC firmware: i40e-2.22.8/firmware-version: 9.10 0x8000d01e 1.3295.0

[Test Setup]

Steps to reproduce
List the steps to reproduce the issue.

1. Build DPDK:

rm -fr x86_64-native-linuxapp-gcc
CC=gcc meson --werror -Denable_kmods=True -Dlibdir=lib -Dexamples=all
--default-library=static x86_64-native-linuxapp-gcc
ninja -C x86_64-native-linuxapp-gcc

2. Bind 1 NIC port to vfio-pci:

dpdk-devbind.py --bind=vfio-pci 0000:31:00.0

3. Start testpmd as virito-user:

x86_64-native-linuxapp-gcc/app/dpdk-testpmd  -l 5-6 -n 8 -a 0000:31:00.0 
--file-prefix=dpdk_1925052_20230217094416    
--vdev=virtio_user0,mac=52:54:00:00:00:01,path=/dev/vhost-net,queue_size=1024
-- -i --rxd=1024 --txd=1024

[Show the output from the previous commands.]

# Start testpmd as virtio-user failed:

root@dut245:~/dpdk# x86_64-native-linuxapp-gcc/app/dpdk-testpmd  -l 5-6 -n 8 -a
0000:31:00.0  --file-prefix=dpdk_1925052_20230217094416    
--vdev=virtio_user0,mac=52:54:00:00:00:01,path=/dev/vhost-net,queue_size=1024
-- -i --rxd=1024 --txd=1024
EAL: Detected CPU lcores: 128
EAL: Detected NUMA nodes: 2
EAL: Detected static linkage of DPDK
EAL: Multi-process socket /var/run/dpdk/dpdk_1925052_20230217094416/mp_socket
EAL: Selected IOVA mode 'VA'
EAL: 4096 hugepages of size 2097152 reserved, but no mounted hugetlbfs found
for that size
EAL: VFIO support initialized
EAL: Using IOMMU type 1 (Type 1)
EAL: Ignore mapping IO port bar(1)
EAL: Ignore mapping IO port bar(4)
EAL: Probe PCI driver: net_i40e (8086:1583) device: 0000:31:00.0 (socket 0)
i40e_GLQF_reg_init(): i40e device 0000:31:00.0 changed global register
[0x002689a0]. original: 0x00000021, new: 0x00000029
vhost_kernel_ioctl(): Vhost-kernel ioctl 2148052736 failed (Bad file
descriptor)
vhost_kernel_get_features(): Failed to get features
virtio_user_dev_init(): (/dev/vhost-net) Failed to get device features
virtio_user_pmd_probe(): virtio_user_dev_init fails
vdev_probe(): failed to initialize virtio_user0 device
EAL: Bus (vdev) probe failed.
Interactive-mode selected
testpmd: create a new mbuf pool <mb_pool_0>: n=155456, size=2176, socket=0
testpmd: preferred mempool ops selected: ring_mp_mcWarning!
port-topology=paired and odd forward ports number, the last port will pair with
itself.Configuring Port 0 (socket 0)
Port 0: 00:00:00:00:01:00
Checking link statuses...
Done
testpmd>
Port 0: link state change eventtestpmd> show port summary all
Number of available ports: 1
Port MAC Address       Name         Driver         Status   Link
0    00:00:00:00:01:00 0000:31:00.0 net_i40e       up       40 Gbps
testpmd>

[Expected Result]

Explain what is the expected result in text or as an example output:

# Start testpmd as virtio-user sucessed:

root@dut245:~/dpdk# x86_64-native-linuxapp-gcc/app/dpdk-testpmd  -l 5-6 -n 8 -a
0000:31:00.0  --file-prefix=dpdk_1925052_20230217094416    
--vdev=virtio_user0,mac=52:54:00:00:00:01,path=/dev/vhost-net,queue_size=1024
-- -i --rxd=1024 --txd=1024
EAL: Detected CPU lcores: 128
EAL: Detected NUMA nodes: 2
EAL: Detected static linkage of DPDK
EAL: Multi-process socket /var/run/dpdk/dpdk_1925052_20230217094416/mp_socket
EAL: Selected IOVA mode 'VA'
EAL: 4096 hugepages of size 2097152 reserved, but no mounted hugetlbfs found
for that size
EAL: VFIO support initialized
EAL: Using IOMMU type 1 (Type 1)
EAL: Ignore mapping IO port bar(1)
EAL: Ignore mapping IO port bar(4)
EAL: Probe PCI driver: net_i40e (8086:1583) device: 0000:31:00.0 (socket 0)
Interactive-mode selected
Warning: NUMA should be configured manually by using --port-numa-config and
--ring-numa-config parameters along with --numa.
testpmd: create a new mbuf pool <mb_pool_0>: n=155456, size=2176, socket=0
testpmd: preferred mempool ops selected: ring_mp_mc
Configuring Port 0 (socket 0)
i40e_set_mac_max_frame(): Set max frame size at port level not applicable on
link down
Port 0: 00:00:00:00:01:00
Configuring Port 1 (socket 0)
Port 1: 52:54:00:00:00:01
Checking link statuses...
Done
Error during enabling promiscuous mode for port 1: Operation not supported -
ignore
testpmd>
Port 0: link state change eventtestpmd> show port summary all
Number of available ports: 2
Port MAC Address       Name         Driver         Status   Link
0    00:00:00:00:01:00 0000:31:00.0 net_i40e       up       40 Gbps
1    52:54:00:00:00:01 virtio_user0 net_virtio_user up       Unknown
testpmd> 

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

Version the regression was introduced: Specify git id if known.

7be724856315a0dab9645c20a617fba276607294 is the first bad commit
commit 7be724856315a0dab9645c20a617fba276607294
Author: Maxime Coquelin <maxime.coquelin@redhat.com>
Date:   Thu Feb 9 10:17:04 2023 +0100



    net/virtio-user: get max number of queue pairs from device



    When supported by the backend (only vDPA for now), this
    patch gets the maximum number of queue pairs supported by
    the device by querying it in its config space.



    This is required for adding backend control queue support,
    as is index equals the maximum number of queues supported
    by the device as described by the Virtio specification.



    Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
    Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
    Acked-by: Eugenio Pérez <eperezma@redhat.com>



drivers/net/virtio/virtio_user/virtio_user_dev.c | 93 ++++++++++++++++++------
drivers/net/virtio/virtio_user_ethdev.c          |  7 –
2 files changed, 71 insertions, 29 deletions

-- 
You are receiving this mail because:
You are the assignee for the bug.

[-- Attachment #2: Type: text/html, Size: 8885 bytes --]

[Bug 1161] [dpdk-23.03]virtio_user_as_exceptional_path/vhost_exception_path_with_virtio_user: launch testpmd as virtio-user failed

[bugzilla]

[-- Attachment #1: Type: text/plain, Size: 1658 bytes --]

https://bugs.dpdk.org/show_bug.cgi?id=1161

lingwei (weix.ling@intel.com) changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|IN_PROGRESS                 |RESOLVED
         Resolution|---                         |FIXED

--- Comment #3 from lingwei (weix.ling@intel.com) ---
Patch have merged into the DPDK main branch.

Verified PASSED.

OS: Ubuntu 22.04.1 LTS/Linux 5.15.45-051545-generic

NIC hardware: Intel Ethernet Controller XL710 for 40GbE QSFP+ 1583

Driver/NIC firmware: i40e-2.22.8/firmware-version: 9.10 0x8000d01e 1.3295.0

commit be26e898ffb3a1719c88bf025d45a847d3a60ffc
Author: Maxime Coquelin <maxime.coquelin@redhat.com>
Date:   Fri Feb 17 13:31:19 2023 +0100

    net/virtio-user: fix vhost-kernel initialization

    This patch fixes a regression causing devices with
    Vhost-kernel backends initialization to fail.

    Indeed, Vhost-kernel backend init expects
    dev->max_queue_pairs to be set at setup time, while its
    assignment was moved after backend setup when adding
    control queue support for Vhost-vdpa backends.

    It is safe to set dev->max_queue_pairs early for
    Vhost-kernel backends as if the backend does not support
    multiqueue, its setup will fail.

    Bugzilla ID: 1161
    Fixes: 7be724856315 ("net/virtio-user: get max number of queue pairs from
device")

    Reported-by: Wei Ling <weix.ling@intel.com>
    Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>

-- 
You are receiving this mail because:
You are the assignee for the bug.

[-- Attachment #2: Type: text/html, Size: 4054 bytes --]