Rearrangement of WQ and CQ creation for Verbs Rx queue:
1. Rename the allocation function.
2. Reduce the number of arguments that the creation functions receive.
Signed-off-by: Michael Baum <michaelba@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Rearrangement of RQ and CQ resource handling for DevX Rx queue:
1. Rename the allocation function so that it is understood that it
allocates all resources and not just the CQ or RQ.
2. Move the allocation and release of the doorbell into creation and
release functions.
3. Reduce the number of arguments that the creation functions receive.
Signed-off-by: Michael Baum <michaelba@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Move Rx object similar resources allocations and debug logs from DevX
and Verbs modules to a shared location.
Signed-off-by: Michael Baum <michaelba@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Separate interrupt event handler into both Verbs and DevX modules.
Signed-off-by: Michael Baum <michaelba@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
As an arrangement to Windows OS support, the Verbs operations should be
separated to another file.
By this way, the build can easily cut the unsupported Verbs APIs from
the compilation process.
Define operation structure and DevX module in addition to the existing
linux Verbs module.
Separate Rx object creation into the Verbs/DevX modules and update the
operation structure according to the OS support and the user
configuration.
Signed-off-by: Michael Baum <michaelba@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
The Rx queue structures manage 2 different reference counter per queue:
rxq_ctrl reference counter and rxq_obj reference counter.
There is no real need to use two different counters, it just complicates
the release functions.
Remove the rxq_obj counter and use only the rxq_ctrl counter.
Signed-off-by: Michael Baum <michaelba@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Rx HW objects can be created by both Verbs and DevX operations.
The management of the 2 types of operations are done directly in the
main flow of the object’s creations.
Some arrangements and validations were wrongly done to the irrelevant
type:
1. LRO related validations were done for Verbs type where LRO is not
supported at all.
2. Verbs allocation arrangements were done for DevX operations where it
is not needed.
3. Doorbell destroy was considered for Verbs types where it is
irrelevant.
Adjust the aforementioned points only for the relevant types.
Fixes: e79c9be915 ("net/mlx5: support Rx hairpin queues")
Fixes: 08d1838f64 ("net/mlx5: implement CQ for Rx using DevX API")
Fixes: 17ed314c6c ("net/mlx5: allow LRO per Rx queue")
Fixes: dc9ceff73c ("net/mlx5: create advanced RxQ via DevX")
Cc: stable@dpdk.org
Signed-off-by: Michael Baum <michaelba@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
In order to support DevX Rx queue stop and start operations, the state
of the queue should be updated in FW.
The state update PRM command requires to set both the current state and
the new requested state.
The current state and the new requested state fields setting were
wrongly switched.
Switch them back to the correct setting.
Fixes: 161d103b23 ("net/mlx5: add queue start and stop")
Cc: stable@dpdk.org
Signed-off-by: Michael Baum <michaelba@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
The mlx5_hrxq_new function allocates several resources and if one of the
allocations fails, the function jumps to an error label where it
releases all the allocated resources.
When the TIR action creation fails, the hrxq memory is not released what
can cause a resource leak.
Add an appropriate release to the hrxq pointer in the error flow.
Fixes: 772dc0eb83 ("net/mlx5: convert hrxq to indexed")
Fixes: dc9ceff73c ("net/mlx5: create advanced RxQ via DevX")
Cc: stable@dpdk.org
Signed-off-by: Michael Baum <michaelba@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Replace behavior with RTE_LIBRTE_ARK_MIN_TX_PKTLEN
with a default value of 0.
Update documentation as needed.
Signed-off-by: Ed Czeck <ed.czeck@atomicrules.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Use ARK_PMD_LOG in place of PMD_DRV_LOG, PMD_DEBUG_LOG, PMD_FUNC_LOG,
PMD_STATS_LOG, PMD_RX_LOG, and PMD_TX_LOG.
Review and adjust log levels and messages as needed.
Signed-off-by: Ed Czeck <ed.czeck@atomicrules.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
When loading the OS default package and the pipeline mode is enabled
by the "pipeline-mode-support=1" operation. In this case, the wrong
parser is selected for processing and it will cause the unsupported
patterns(pppoes/pfcp/l2tpv3/esp/ah) to be validated successfully.
This patch corrects the parser selection issue.
Fixes: 47d460d632 ("net/ice: rework switch filter")
Cc: stable@dpdk.org
Signed-off-by: Guinan Sun <guinanx.sun@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Current RSS implementation is not easy to scale and maintain.
The patch refactor the code base on below design:
1. iavf_pattern_match_item->input_set_mask is the superset of
ETH_RSS_xxx.
2. iavf_pattern_match_item->meta is the virtchnl_proto_hdrs template.
3. iavf_hash_parse_pattern will generate pattern hint.
4. iavf_hash_parse_action will refine the virtchnl_proto_hdrs base on
pattern hint and ETH_RSS_xxx.
5. The refine process include
1) refine field selector of l2, l3, l4.
2) insert gtpu proto_hdr at the beginning base on pattern hint.
3) refine field selector for gtpu header.
The patch reduce the code from 4000+ line to less than 1000.
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Jeff Guo <jia.guo@intel.com>
ptype 264, 265, 266, 267, 275 should not be set
in ice_ptypes_ipv6_ofos_all.
Fixes: 88824213be ("net/ice/base: enable RSS for PFCP/L2TP/ESP/AH")
Cc: stable@dpdk.org
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Jeff Guo <jia.guo@intel.com>
With fmlib (FMCLESS) mode now RSS can be modified on runtime.
This patch add support for RSS update functions
Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Signed-off-by: Sachin Saxena <sachin.saxena@nxp.com>
FMC tool generates and saves the setup in a file.
This patch help Parse the /tmp/fmc.bin generated by FMC to
setup RXQs for each port on FMC mode.
The parser gets the fqids and vspids from fmc.bin
Signed-off-by: Jun Yang <jun.yang@nxp.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
This patch adds support for Virtual Storage profile (VSP) feature.
With VSP support when memory pool is created, the hw buffer pool id
i.e. bpid is not allocated; the bpid is identified by dpaa flow
create API.
The memory pool of RX queue is attached to specific BMan pool
according to the VSP ID when RX queue is setup.
For fmlib based hash queue, VSP base ID is assigned to each queue.
Signed-off-by: Jun Yang <jun.yang@nxp.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
A shared MAC interface is an interface which can be used
by both kernel and userspace based on classification configuration
It is defined in dts with the compatible string
"fsl,dpa-ethernet-shared" which bpool will be seeded by the dpdk
partition and configured as a netdev by the dpaa Linux eth driver.
User space buffers from the bpool will be kmapped by the kernel.
Signed-off-by: Radu Bulie <radu-andrei.bulie@nxp.com>
Signed-off-by: Jun Yang <jun.yang@nxp.com>
Signed-off-by: Nipun Gupta <nipun.gupta@nxp.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
This patch uses fmlib to configure the FMAN HW for flow
and distribution configuration, thus avoiding the need
for static FMC tool execution optionally.
Signed-off-by: Sachin Saxena <sachin.saxena@nxp.com>
Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
This patch adds support for VSP (Virtual Storage Profile)
in fmlib routines.
VSP allow a network interface to be divided into physical
and virtual instance(s).
The concept is very similar to SRIOV.
Signed-off-by: Jun Yang <jun.yang@nxp.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
DPAA platorm MAC interface is known as FMAN i.e. Frame Manager.
There are two ways to control it.
1. Statically configure the queues and classification rules before the
start of the application using FMC tool.
2. Dynamically configure it within application by making API calls of
fmlib.
The fmlib or Frame Manager library provides an API on top of the
Frame Manager driver ioctl calls, that provides a user space application
with a simple way to configure driver parameters and PCD
(parse - classify - distribute) rules.
This patch integrates the base fmlib so that various queue config, RSS
and classification related features can be supported on DPAA platform.
Signed-off-by: Sachin Saxena <sachin.saxena@nxp.com>
Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
This patch fixes (out-of-bounds access) coverity issue.
Coverity issue: 349932
Fixes: 7d7f9f80bb ("net/hns3: support MAC address related operations")
Cc: stable@dpdk.org
Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Reviewed-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
When receiving the unsupported AQ messages, it's taken as an
error. It's not appropriate and triggers too much unnecessary print.
Fixes: 22b123a36d ("net/avf: initialize PMD")
Cc: stable@dpdk.org
Signed-off-by: Steve Yang <stevex.yang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
When setting the MAC address, the ethdev layer copies the new mac
address in dev->data->mac_addrs[0] before calling the dev_ops.
Therefore, is_same_ether_addr(mac_addr, dev->data->mac_addrs) was
always true, and the MAC was never set. Remove this test to fix the
issue.
Fixes: 538da7a1ca ("net: add rte prefix to ether functions")
Cc: stable@dpdk.org
Signed-off-by: Steve Yang <stevex.yang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
If configuring VF promiscuous mode is not supported,
return -ENOTSUP error code in .promiscuous_enable/disable dev_ops.
This is to fix the port start during configuration restore,
where if .promiscuous_enable/disable dev_ops exists
and return any value other than -ENOTSUP, start will fail.
Same is done for .allmulticast_enable/disable dev_ops.
Fixes: ca041cd44f ("ethdev: change allmulticast callbacks to return status")
Fixes: 9039c81257 ("ethdev: change promiscuous callbacks to return status")
Cc: stable@dpdk.org
Signed-off-by: Steve Yang <stevex.yang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
No need to add additional vlan tag size for max packet size,
the queue's Rx Max Frame Size (rxq->max_pkt_len) already
includes the vlan header size in iavf.
Fixes: 69dd4c3d08 ("net/avf: enable queue and device")
Cc: stable@dpdk.org
Signed-off-by: Steve Yang <stevex.yang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
If the PF driver supports the new speed reporting capabilities
then use link_event_adv instead of link_event to get the speed.
Fixes: 2a73125b70 ("i40evf: fix link info update")
Cc: stable@dpdk.org
Signed-off-by: Guinan Sun <guinanx.sun@intel.com>
Acked-by: Jeff Guo <jia.guo@intel.com>
Tested-by: Jiaqi Min <jiaqix.min@intel.com>
rte_ethdev has declared new NUM_UNKNOWN speed which
could be used in case when no speed information is available and
link is up. NUM_NONE should be returned, if link is down.
Signed-off-by: Ivan Dyukov <i.dyukov@samsung.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
rte_ethdev has declared new NUM_UNKNOWN speed which
could be used in case when no speed information is available and
link is up. NUM_NONE should be returned, if link is down.
Signed-off-by: Ivan Dyukov <i.dyukov@samsung.com>
Acked-by: Jeff Guo <jia.guo@intel.com>
rte_ethdev has declared new NUM_UNKNOWN speed which
could be used in case when no speed information is available
Signed-off-by: Ivan Dyukov <i.dyukov@samsung.com>
Reviewed-by: Wei Zhao <wei.zhao1@intel.com>
When querying the link information, the link status is
a mandatory major information.
Other boolean values are supposed to be accurate:
- duplex mode (half/full)
- negotiation (auto/fixed)
This API update is making explicit that the link speed information
is optional.
The value ETH_SPEED_NUM_NONE (0) was already part of the API.
The value ETH_SPEED_NUM_UNKNOWN (infinite) is added to cover
two different cases:
- speed is not known by the driver
- device is virtual
Suggested-by: Morten Brørup <mb@smartsharesystems.com>
Suggested-by: Benoit Ganne <bganne@cisco.com>
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
The descriptor of the command between firmware and driver consists of
8-byte header and 24-byte data field. The contents sent to firmware are
packaged into a command structure as the data field of command
descriptor.
There are some command structures in hns3_dcb.h file that are less than
24 byte. So this patch fixes these incomplete command structures.
Fixes: 62e3ccc2b9 ("net/hns3: support flow control")
Cc: stable@dpdk.org
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Currently, default MAC address obtained from firmware in PF driver is
directly used by .mac_addr_set ops implementation function when the
rte_eth_dev_start API function is executed. At this moment, if the
default MAC addr isn't an unicast address, it will fail to set default
MAC addr to hardware.
So this patch adds the validity check of default MAC addr in PF driver.
We will use a random unicast address, if the default MAC address
obtained from firmware is not a valid unicast address.
In addition, this patch also adjusts the location of processing default
MAC addr in VF driver so as to increase relevance and readability of the
code.
Fixes: eab2177671 ("net/hns3: support setting VF MAC address by PF driver")
Fixes: d51867db65 ("net/hns3: add initialization")
Cc: stable@dpdk.org
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Signed-off-by: Chengchang Tang <tangchengchang@huawei.com>
This patch uses RTE_MAX function in DPDK lib to replace the private
macro named max_t in driver.
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
The FDIR counter was used to count the number of FDIR hit, the maximum
number of the counter is 128 based on kunpeng 920, and it was 256 based
on kunpeng 930.
The firmware is responsible to allocate counters for different PF
devices, so the available counter number of one PF may be bigger than
128.
Currently, there are two places using the counter in driver:
1. Configure the counter. Driver uses the command whose opcode is
HNS3_OPC_FD_AD_OP, now we extend one bit to hold the high bit of
counter-id in the command format.
2. Query the statistic information of the counter. Driver uses the
command whose opcode is HNS3_OPC_FD_COUNTER_OP, now the command
already support 16-bit counter-id.
Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
The new firmware adds the hardware error types reported by MSI-x mode.
These errors are defined as RAS errors in hardware and belong to a
different type from the MSI-x errors processed by the driver.
When hardware detects an error which must be handled by the driver for
device to run properly it reports the error information through the
MSI-x interrupt. After receiving the interrupt reported by the hardware,
the driver queries the error information and identifies the error level,
then rectifies the error. All errors will be logged.
In addition, the hardware may be reset at the function or global level
based on the error level. After the reset is complete, the hardware will
recover to the normal status.
Signed-off-by: Hongbo Zheng <zhenghongbo3@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
There are difference about padding ultra-short frame in Tx procession
for different versions of hardware network engine.
If packet length is less than minimum packet length supported by
hardware in Tx direction, driver need to pad it to avoid error. The
minimum packet length in Tx direction is 33 based on kunpeng 920, and 9
based on kunpeng 930.
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Signed-off-by: Chengchang Tang <tangchengchang@huawei.com>
There are difference about queue's interrupt configurations for
different versions of hardware network engine, such as queue's interrupt
mapping mode, coalesce configuration, etc.
The following uses the configuration differences of the interrupt
mapping mode as an example.
1) For some versions of hardware network engine, such as kunpeng 920,
because of the hardware constraint, we need implement unmmapping
relationship configurations by binding all queues to the last
interrupt vector and reserving the last interrupt vector. This
results in a decrease of the maximum queues when upper applications
call the rte_eth_dev_configure API function to enable Rx interrupt.
2) And for another versions, such as kunpeng 930, hns3 PMD driver can
map/unmmap all interrupt vectors with queues when Rx interrupt is
enabled.
This patch resolves configuration differences about Rx interrupts based
on kunpeng 920 and kunpeng 930.
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
This patch adds getting device capabilities from firmware, so driver can
supply different capabilities and specifications to upper level
applications base on different versions of hardware network engine.
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
The "command mismatch" warning shouldn't be triggered by
VIRTCHNL_OP_EVENT opcode, because the VIRTCHNL_OP_EVENT
opcode is used by PF notifies status change events to VF.
This patch fixed the issue.
Fixes: 837c2ed86e ("net/iavf: return error if opcode is mismatched")
Cc: stable@dpdk.org
Signed-off-by: Junyu Jiang <junyux.jiang@intel.com>
Reviewed-by: Qiming Yang <qiming.yang@intel.com>
When PF event VIRTCHNL_EVENT_LINK_CHANGE received, i40evf need update
the link status and issue RTE_ETH_EVENT_INTR_LSC via rte ether device
callback function.
Signed-off-by: Steve Yang <stevex.yang@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
On BCM957508-N2100 adapters, FW will not allow any user other
than BMC to shutdown the port. As a result, bnxt_get_hwrm_link_config()
always returns link up.
Because of this, driver will not update the new port configurations
such as speed, autoneg during a port start.
Fixed the condition to invoke bnxt_set_hwrm_link_config() in
bnxt_init_chip().
Fixes: 7bc8e9a227 ("net/bnxt: support async link notification")
Cc: stable@dpdk.org
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
DPDK does not support RoCE and XDP. The driver should set the
bit 5:4 of the flag to 1 and set bit 6 of the flag in the
HWRM_CFA_L2_FILTER_ALLOC command to disable RoCE and XDP features.
This change will greatly reduce the CFA resource consumption.
Fixes: f92735db1e ("net/bnxt: add L2 filter alloc/init/free")
Cc: stable@dpdk.org
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
rte_pktmbuf_prefree_seg() can return NULL if the mbuf still
has remaining references on it.
Adding a NULL check to prevent segfault.
Fixes: bc4a000f2f ("net/bnxt: implement SSE vector mode")
Fixes: 3983583414 ("net/bnxt: support NEON")
Cc: stable@dpdk.org
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Lance Richardson <lance.richardson@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
During port start if bnxt_alloc_all_hwrm_stat_ctxs() fails,
in the cleanup path we do see errors like below:
bnxt_hwrm_ring_free(): hwrm_ring_free cp failed. rc:2
bnxt_hwrm_ring_free(): hwrm_ring_free rx failed. rc:2
The reason for this is in bnxt_free_all_hwrm_rings(), the check
is made against "ring->fw_ring_id != INVALID_HW_RING_ID" which
always return true as ring->fw_ring_id is not set to INVALID_HW_RING_ID
while initialising the ring structs.
Fixes: 6eb3cc2294 ("net/bnxt: add initial Tx code")
Fixes: 2eb53b134a ("net/bnxt: add initial Rx code")
Cc: stable@dpdk.org
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Lance Richardson <lance.richardson@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
The maximum number of TCP segments that can be aggregated & the
maximum number of aggregations the VNIC supports are configured
incorrectly during LRO configuration.
This patch fixes these values.
Fixes: b150a7e7ee ("net/bnxt: support LRO on Thor adapters")
Cc: stable@dpdk.org
Signed-off-by: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Use "req.tunnel_dst_port_val" in bnxt_hwrm_tunnel_dst_port_alloc()
as big endian since hwrm spec mandates this field in network byte order.
Also, fixed the endianness while parsing the command output.
Fixes: 10d074b202 ("net/bnxt: support tunneling")
Cc: stable@dpdk.org
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
