The mlx5 PMD supports send scheduling feature, it allows
to send packets at specified moment of time, to do that
PMD pushes special wait descriptor (WQE) to the hardware
queue and then pushes descriptor for packet data as usual.
If queue is close to be full or there is no enough elts
buffers to store mbufs being sent the data descriptors might
be not pushed and the orphan wait WQE (not followed by the
data) might reside in queue on tx_burst routine exit.
To avoid orphan wait WQEs there was the check for enough
free space in the queue WQE buffer and enough amount of the
free elts in queue mbuf storage. This check was incomplete
and did not cover all the cases for Enhanced Multi-Packet
Write descriptors.
Fixes: 2f827f5ea6 ("net/mlx5: support scheduling on send routine template")
Cc: stable@dpdk.org
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
ESP is one of IPSec protocols over both IPv4 and IPv6 and is considered
a tunnel layer that cannot be followed by any other layer. Taking that
into consideration, ESP is considered as a 4 layer.
Not defining ESP's priority will make it match with the same priority as
its prior IP layer, which has a layer 3 priority. This will lead to
issues in matching and will match the packet with the first matching
rule even if it doesn't have an esp layer in its pattern, disregarding
any following rules that could have an esp item and can be actually
a more accurate match since it will have a longer matching criterion.
This is fixed by defining the priority for the ESP item to have a
layer 4 priority, making the match be for the rule with the more
accurate and longer matching criteria.
Fixes: 18ca4a4ec7 ("net/mlx5: support ESP SPI match and RSS hash")
Cc: stable@dpdk.org
Signed-off-by: Bassam Zaid AlKilani <bzalkilani@nvidia.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
Acked-by: Raslan Darawsheh <rasland@nvidia.com>
One of the conditions to allow LRO offload is the DV configuration.
The function incorrectly checks the DV configuration before initializing
it by the user devarg; hence, LRO cannot be allowed.
This patch moves this check to mlx5_shared_dev_ctx_args_config, where DV
configuration is initialized.
Fixes: c4b8620135 ("net/mlx5: refactor to detect operation by DevX")
Cc: stable@dpdk.org
Signed-off-by: Michael Baum <michaelba@nvidia.com>
Reported-by: Gal Shalom <galshalom@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Current PMD logs all DevX errors at error level.
DevX interface can fail queue counters allocation on some hardware
types. That is a known issue.
PMD fallbacks to Verbs API to allocate queue counters
when it detects the fault.
That DevX failure should not be logged as PMD error.
The patch provides DevX with flexible API that selects log level.
Signed-off-by: Gregory Etelson <getelson@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
FDs passed from rte_mp_msg are duplicated to the secondary process and
need to be closed.
Fixes: 9a8ab29b84 ("net/mlx5: replace IPC socket with EAL API")
Cc: stable@dpdk.org
Signed-off-by: Long Li <longli@microsoft.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
FDs passed from rte_mp_msg are duplicated to the secondary process and
need to be closed.
Fixes: 0203d33a10 ("net/mlx4: support secondary process")
Cc: stable@dpdk.org
Signed-off-by: Long Li <longli@microsoft.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
In case of higher order (greater than 99) logical cores, name was
truncated (length is restricted to 16 characters, including the
terminating null byte ('\0')) and it makes hard to follow threads.
Before this fix, this issue can be reproduced using following arguments:
--lcores=0,10@1,100@2
Then we had:
lcore-worker-10
lcore-worker-10
Signed-off-by: Abdullah Ömer Yamaç <omer.yamac@ceng.metu.edu.tr>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Checking a const pointer for alignment would emit a warning about the
const qualifier being discarded.
No need to calculate the aligned pointer; just check the last bits of the
pointer.
Signed-off-by: Morten Brørup <mb@smartsharesystems.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
The rte_mov256 function was missing for AVX2.
Fixes: 9144d6bcde ("eal/x86: optimize memcpy for SSE and AVX")
Signed-off-by: Morten Brørup <mb@smartsharesystems.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
In async_enqueue_pkts(), the failed pkts will
be freed before return, but, the failed pkts may be
retried later, it will cause use after free. So,
we free the failed pkts after retry.
Fixes: 1907ce4bae ("examples/vhost: fix retry logic on Rx path")
Cc: stable@dpdk.org
Signed-off-by: Wenwu Ma <wenwux.ma@intel.com>
Tested-by: Wei Ling <weix.ling@intel.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
If an application does not request IOMMU support, we can avoid
allocating a IOMMU pool.
This saves 112kB (IOTLB_CACHE_SIZE * sizeof(struct vhost_iotlb_entry))
per vq.
Signed-off-by: David Marchand <david.marchand@redhat.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
Currently in function vhost_user_msg_handler, variable ret is used to
store both vhost msg result code and function call return value.
After this patch, variable ret is used only to store function call
return value, a new dedicated variable msg_result is used to
store vhost msg result. This can improve readability.
Signed-off-by: Andy Pei <andy.pei@intel.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
When first attempt to configure a device with RX interrupt enabled fails
for some reason (e.g. because "Multiple intr vector not supported"),
second attempt to configure the device with RX interrupt disabled and
feature set unchanged will succeed but will leave virtio queues not
allocated. Accessing the queues will cause a segfault.
First attempt:
- virtio_dev_configure()
- virtio_init_device() is called to reinit the device because
"dev->data->dev_conf.intr_conf.rxq" is "1"
- virtio_configure_intr() fails and returns an error
- virtio_free_queues() frees previously allocated virtio queues
- virtio_init_device() fails and returns an error
- virtio_dev_configure() fails and returns an error
Second attempt:
- virtio_dev_configure()
- This time virtio_init_device() is not called, virtio queues
are not allocated
With this fix, reinit the device during configuration if virtio queues
are not allocated.
Fixes: 2b38151f74 ("net/virtio: fix queue memory leak on error")
Cc: stable@dpdk.org
Signed-off-by: Alexander Chernavin <achernavin@netgate.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
Those helpers have been marked as deprecated for a long time and have
documented equivalent helpers.
Signed-off-by: David Marchand <david.marchand@redhat.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
This patch is to enable scalar path inner and outer Tx checksum offload
for tunnel packet by configure ol_flags.
Signed-off-by: Peng Zhang <peng1x.zhang@intel.com>
Signed-off-by: Zhichao Zeng <zhichaox.zeng@intel.com>
Tested-by: Ke Xu <ke1.xu@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
When receiving tunneled packets, the testpmd output log shows 'ol_flags'
value always as 'RTE_MBUF_F_RX_OUTER_L4_CKSUM_UNKNOWN', but expected value
should be 'RX_OUTER_L4_CKSUM_GOOD' or 'RX_OUTER_L4_CKSUM_BAD'.
Adding 'RX_OUTER_L4_CKSUM_GOOD' and 'RX_OUTER_L4_CKSUM_BAD' to 'flags' for
normal path, 'l3_l4_flags_shuf' for AVX2 and AVX512 vector path and
'cksum_flags' for SSE vector path to ensure that the 'ol_flags'
can match correct flags.
Fixes: b8b4c54ef9 ("net/iavf: support flexible Rx descriptor in normal path")
Fixes: 1162f5a0ef ("net/iavf: support flexible Rx descriptor in SSE path")
Fixes: 5b6e885908 ("net/iavf: support flexible Rx descriptor in AVX path")
Fixes: 9c9aa00403 ("net/iavf: add offload path for Rx AVX512 flex descriptor")
Cc: stable@dpdk.org
Signed-off-by: Zhichao Zeng <zhichaox.zeng@intel.com>
Tested-by: Ke Xu <ke1.xu@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Add a known issue: configuring VLAN filters from VF is unsupported
for i40e driver 2.17.15.
Signed-off-by: Steve Yang <stevex.yang@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
The SSE RX path does not process the vlan tci correctly when it's stored
in L2TAG2, so the vlan tci could not be extracted from descriptor,
then would not be put into mbuf either.
Add processing when vlan tci is stored in L2TAG2.
Fixes: 1162f5a0ef ("net/iavf: support flexible Rx descriptor in SSE path")
Cc: stable@dpdk.org
Signed-off-by: Zhichao Zeng <zhichaox.zeng@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Because of base code update, "ice_ptp_init_phc" API for E810/E822 depends
on PHY configuration, not whether the device is E810 based. So before this
API is called, assign specific value to phy cfg.
Fixes: 646dcbe6c7 ("net/ice: support IEEE 1588 PTP")
Cc: stable@dpdk.org
Signed-off-by: Simei Su <simei.su@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Move all VF related limitation or known issues from i40e.rst to
intel_vf.rst, as i40evf has been removed from i40e, i40e.rst should only
cover PF's information.
The patch also fix couple typos and refine the words to be more accurate.
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
Updated copyright to 2022 and update base code version.
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Exposed ice_aq_move_sched_elems to support sched element moving
by AQ command.
Signed-off-by: Ben Shelton <benjamin.h.shelton@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
PTP HW semaphore can be held for ~50 ms in worst case.
SW should wait longer and check more frequently if
the HW lock is held.
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Added GTP tunnel type and also re-order the code to align with
kernel driver.
Signed-off-by: Marcin Szycik <marcin.szycik@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Remove unnecessary fields in data structure for 1588 and QoS
func capabilities.
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Use bitfields in 1588 structs so they don't waste too much space.
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
ICE_SW_LKUP_DFLT is handled in ice_update_vsi_list_rule and
ice_aq_alloc_free_vsi_list.
Signed-off-by: Lukasz Kupczak <lukasz.kupczak@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
LLDP MIB Change Event (opcode 0x0A01) already contains MIB, which
has been changed. Add ice_dcb_process_lldp_set_mib_change() function,
which will set local/remote DCBX config from LLDP MIB Change Event's
buffer.
This function will be used in a base driver handler for LLDP MIB
Change Event.
Signed-off-by: Anatolii Gerasymenko <anatolii.gerasymenko@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
The bit that is overloaded is bit 11 in the flex descriptor,
updating the comment to have the right one reflected.
Signed-off-by: Alice Michael <alice.michael@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Admin queue command for shutdown AQ contains flag to indicate
driver unload. However the flag is always set in driver, even
for the resets. It causes Firmware to consider driver as unloaded
once the PF reset is triggered on all ports of device. Firmware then
restores default configuration of some features like Tx Balancing,
which is not expected behavior.
This patch added an additional function parameter to indicate
driver unload.
Signed-off-by: Piotr Gardocki <piotrx.gardocki@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
For GTPoGRE, When setting the prot_id of prot, it should be
set to second inner.
Fixes: 34a0e7c44f ("net/ice/base: improve flow director masking")
Cc: stable@dpdk.org
Signed-off-by: Kevin Liu <kevinx.liu@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Added new tunnel type to support NvGRE
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Add L2TPv2 (include PPP over L2TPv2) support for FDIR.
And add support PPPoL2TPv2oUDP with inner IPV4/IPV6/UDP/TCP for
FDIR.
The supported L2TPv2 packets are defined as below:
ICE_FLTR_PTYPE_NONF_IPV4_L2TPV2_CONTROL
ICE_FLTR_PTYPE_NONF_IPV4_L2TPV2
ICE_FLTR_PTYPE_NONF_IPV4_L2TPV2_PPP
ICE_FLTR_PTYPE_NONF_IPV4_L2TPV2_PPP_IPV4
ICE_FLTR_PTYPE_NONF_IPV4_L2TPV2_PPP_IPV4_UDP
ICE_FLTR_PTYPE_NONF_IPV4_L2TPV2_PPP_IPV4_TCP
ICE_FLTR_PTYPE_NONF_IPV4_L2TPV2_PPP_IPV6
ICE_FLTR_PTYPE_NONF_IPV4_L2TPV2_PPP_IPV6_UDP
ICE_FLTR_PTYPE_NONF_IPV4_L2TPV2_PPP_IPV6_TCP
ICE_FLTR_PTYPE_NONF_IPV6_L2TPV2_CONTROL
ICE_FLTR_PTYPE_NONF_IPV6_L2TPV2
ICE_FLTR_PTYPE_NONF_IPV6_L2TPV2_PPP
ICE_FLTR_PTYPE_NONF_IPV6_L2TPV2_PPP_IPV4
ICE_FLTR_PTYPE_NONF_IPV6_L2TPV2_PPP_IPV4_UDP
ICE_FLTR_PTYPE_NONF_IPV6_L2TPV2_PPP_IPV4_TCP
ICE_FLTR_PTYPE_NONF_IPV6_L2TPV2_PPP_IPV6
ICE_FLTR_PTYPE_NONF_IPV6_L2TPV2_PPP_IPV6_UDP
ICE_FLTR_PTYPE_NONF_IPV6_L2TPV2_PPP_IPV6_TCP
Signed-off-by: Jie Wang <jie1x.wang@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Add L2TPv2 session ID field support for RSS.
Enable L2TPv2 non-tunneled packet types for UDP protocol header
bitmaps.
Signed-off-by: Jie Wang <jie1x.wang@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Define new type id ICE_MAC_GENERIC_3k in ice_mac_type enum, to
distinguish devices which use RSA-3K/SHA-384 segment signature type.
Use 3k signing type for E824S device.
Signed-off-by: Grzegorz Nitka <grzegorz.nitka@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
There are few custom Westport Channel (WPC) and Logan Beach (LGB)
network interface cards (NICs) - add their subdevice IDs to be
able to distinguish them.
Signed-off-by: Michal Michalik <michal.michalik@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Clean the main timer command register after use to avoid residual
command execution, such as re-initialization of the main timer.
Signed-off-by: Sergey Temerkhanov <sergey.temerkhanov@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
ICE_PHY_TYPE_HIGH_MAX_INDEX should be the maximum index value and
not the length/number of ICE_PHY_TYPE_HIGH.
Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
The default Link Establishment State Machine (LESM) behavior does
not allow the use of FEC disable mode if the media does not support
FEC disabled. However users may want to override this behavior.
Add support for setting Auto FEC with FEC disabled.
Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
The add rule functionality works fine with a NULL lookups parameter.
However when running the undefined behavior sanitizer it noticed that
the function could trigger a memcpy from a NULL target.
Fix the code to handle NULL lkups and a zero lkups_cnt variable more
explicitly, and clean up the test to just directly pass a NULL value
instead of allocating a stack variable assigned to NULL and passing
that as a pointer.
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Ignore ERR_ALREADY_EXISTS error when setting promiscuous mode.
This fix is needed because the driver could set promiscuous mode
when it still has not cleared properly.
Promiscuous mode could be set only once, so setting it second
time will be rejected.
Fixes: 60ff6f5ce2 ("net/ice/base: consolidate VF promiscuous mode")
Cc: stable@dpdk.org
Signed-off-by: Grzegorz Siwik <grzegorz.siwik@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
The ice_switch.h and ice_fdir.h headers include ice_common.h. They
are both themselves included in ice_common.h. This causes a circular
dependency ordering.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Because the macros of L2TPv2 packet type value were changed in
ice_ppp-o-l2tpv2-o-udp-1.3.4.0.pkg. So update the macros of L2TPv2
packet type value and the bitmaps of packet types for relevant
protocol header to match the new DDP package.
Signed-off-by: Jie Wang <jie1x.wang@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Add defines for Queue Mng and Full CSR Space in debug
dump internal data. This defines are used in Lanconf for
debug dump. Added QV_SUPPORT macro in ifdef for ACL.
Signed-off-by: Dawid Zielinski <dawid.zielinski@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Add module ID and struct necessary to read and save Tx Scheduler
Topology Tree User Selection data from PFA TLV.
Signed-off-by: Lukasz Czapnik <lukasz.czapnik@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Move function ice_ptp_set_vernier_wl and ice_ptp_src_cmd to align with
kernel driver.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Avoid enabling or disabling vlan 0 when trying to set promiscuous
vlan mode if double vlan mode is enabled. This fix is needed
because the driver tries to add the vlan 0 filter twice (once for
inner and once for outer) when double VLAN mode is enabled. The
filter program is rejected by the firmware when double vlan is
enabled, because the promiscuous filter only needs to be set once.
This issue was missed in the initial implementation of double vlan
mode.
Fixes: 60ff6f5ce2 ("net/ice/base: consolidate VF promiscuous mode")
Cc: stable@dpdk.org
Signed-off-by: Grzegorz Siwik <grzegorz.siwik@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
