Since the 20.08 release deprecated rte_cio_*mb APIs because these APIs
provide the same functionality as rte_io_*mb APIs on all platforms, so
remove them and use rte_io_*mb instead.
Signed-off-by: Phil Yang <phil.yang@arm.com> Signed-off-by: Joyce Kong <joyce.kong@arm.com> Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com> Acked-by: David Marchand <david.marchand@redhat.com>
Feifei Wang [Sun, 20 Sep 2020 11:48:56 +0000 (06:48 -0500)]
test/ring: enhance debug info in failure cases
Add more parameters into the macro TEST_RING_VERIFY and expand the scope
of application for it. Then replace all ring APIs check with
TEST_RING_VERIFY to facilitate debugging.
Furthermore, correct a spelling mistakes of the macro
TEST_RING_FULL_EMTPY_ITER.
Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com> Signed-off-by: Feifei Wang <feifei.wang2@arm.com> Reviewed-by: Phil Yang <phil.yang@arm.com> Reviewed-by: Dharmik Thakkar <dharmik.thakkar@arm.com> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Feifei Wang [Sun, 20 Sep 2020 11:48:55 +0000 (06:48 -0500)]
test/ring: factorize object checks
Do code clean up by moving repeated code inside 'test_ring_mem_cmp'
function to validate data and print information of enqueue/dequeue
elements if validation fails.
Signed-off-by: Feifei Wang <feifei.wang2@arm.com> Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com> Reviewed-by: Phil Yang <phil.yang@arm.com> Reviewed-by: Dharmik Thakkar <dharmik.thakkar@arm.com> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Feifei Wang [Sun, 20 Sep 2020 11:48:54 +0000 (06:48 -0500)]
test/ring: validate single element enqueue/dequeue
Validate the return value of single element enqueue/dequeue operation in
the test.
Suggested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com> Signed-off-by: Feifei Wang <feifei.wang2@arm.com> Reviewed-by: Phil Yang <phil.yang@arm.com> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Feifei Wang [Sun, 20 Sep 2020 11:48:53 +0000 (06:48 -0500)]
test/ring: check dequeued object for single element
Add check in test_ring_basic_ex and test_ring_with_exact_size for single
element enqueue and dequeue operations to validate the dequeued objects.
Signed-off-by: Feifei Wang <feifei.wang2@arm.com> Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com> Reviewed-by: Phil Yang <phil.yang@arm.com> Reviewed-by: Dharmik Thakkar <dharmik.thakkar@arm.com> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Feifei Wang [Sun, 20 Sep 2020 11:48:51 +0000 (06:48 -0500)]
test/ring: fix number of single element enqueue/dequeue
The ring capacity is (RING_SIZE - 1), thus only (RING_SIZE - 1) number of
elements can be enqueued into the ring.
Fixes: af75078fece3 ("first public release") Cc: stable@dpdk.org Signed-off-by: Feifei Wang <feifei.wang2@arm.com> Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com> Reviewed-by: Phil Yang <phil.yang@arm.com> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Feifei Wang [Sun, 20 Sep 2020 11:48:50 +0000 (06:48 -0500)]
test/ring: fix object reference for single element enqueue
When enqueue one element to ring in the performance test, a pointer
should be passed to rte_ring_[sp|mp]enqueue APIs, not the pointer
to a table of void *pointers.
Fixes: a9fe152363e2 ("test/ring: add custom element size functional tests") Cc: stable@dpdk.org Signed-off-by: Feifei Wang <feifei.wang2@arm.com> Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com> Reviewed-by: Phil Yang <phil.yang@arm.com> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
net/enic: support VXLAN decap action combined with VLAN pop
Flow Manager (flowman) provides DECAP_STRIP operation which
decapsulates VXLAN header and then removes VLAN header from the inner
packet. Use this operation to support vxlan_decap followed by
of_pop_vlan.
Signed-off-by: Hyong Youb Kim <hyonkim@cisco.com> Reviewed-by: John Daley <johndale@cisco.com>
net/enic: generate VXLAN src port if it is zero in template
When VXLAN source port in the template is zero, the adapter is
expected to generate a value based on the inner packet flow, when it
performs encapsulation. Flow Manager in the VIC adapter currently
lacks such ability. So, generate a random port when creating a flow if
the port is zero, to avoid transmitting packets with source port 0.
Fixes: ea7768b5bba8 ("net/enic: add flow implementation based on Flow Manager API") Cc: stable@dpdk.org Signed-off-by: Hyong Youb Kim <hyonkim@cisco.com> Reviewed-by: John Daley <johndale@cisco.com>
When a VLAN pattern is present, the flow handler always copies its
inner_type to the match buffer regardless of its value (i.e. HW
matches inner_type against packet's inner ethertype). When inner_type
spec and mask are both 0, adding it to the match buffer is usually
harmless but breaks the following pattern used in some applications
like OVS-DPDK.
flow create 0 ingress ... pattern eth ... type is 0x0800 /
vlan tci spec 0x2 tci mask 0xefff / ipv4 / end actions count /
of_pop_vlan / ...
The VLAN pattern's inner_type is 0. And the outer eth pattern's type
actually specifies the inner ethertype. The outer ethertype (0x0800)
is first copied to the match buffer. Then, the driver copies
inner_type (0) to the match buffer, which overwrites the existing
0x0800 with 0 and breaks the app usage above.
Simply ignore inner_type when it is 0, which is the correct
behavior. As a byproduct, the driver can support the usage like the
above.
Fixes: ea7768b5bba8 ("net/enic: add flow implementation based on Flow Manager API") Cc: stable@dpdk.org Signed-off-by: Hyong Youb Kim <hyonkim@cisco.com> Reviewed-by: John Daley <johndale@cisco.com>
Use Flow Manager (flowman) to support egress PORT_ID action. It can
steer egress packets from PFs and VFs to any uplink port as long as
they are all on the same VIC adapter. It can also steer packets
between ports on the same VIC adapter (i.e. loopback).
Signed-off-by: Hyong Youb Kim <hyonkim@cisco.com> Reviewed-by: John Daley <johndale@cisco.com>
Use Flow Manager (flowman) to support flow API for
representors. Representor's flow handlers simply invoke PF handlers
and pass the representor's flowman structure. The PF flowman handlers
are aware of representors and perform appropriate devcmds to create
flows on the NIC.
Also use flowman to create internal flows for implicit VF-representor
path. With that, representor Tx/Rx is now functional.
Signed-off-by: Hyong Youb Kim <hyonkim@cisco.com> Reviewed-by: John Daley <johndale@cisco.com>
net/enic: extend flow handler to support VF representors
VF representor ports can create flows on VFs through the PF flowman
(Flow Manager) instance in the firmware. These flows match packets
egressing from VFs and apply flowman actions.
1. Make flow handler aware of VF representors
When a representor port invokes flow APIs, use the PF port's flowman
instance to perform flowman devcmd. If the port ID refers to a
representor, use VF handle instead of PF handle.
2. Serialize flow API calls
Multiple application thread may invoke flow APIs through PF and VF
representor ports simultaneously. This leads to races, as ports all
share the same PF flowman instance. Use a lock to serialize API
calls. Lock is used only when representors exist.
3. Add functions to create flows for implicit representor paths
There is an implicit path between VF and its representor. The
functions below create flow rules to implement that path.
- enic_fm_add_rep2vf_flow()
- enic_fm_add_vf2rep_flow()
The flows created for representor paths are marked as internal. These
are not visible to application, and the flush API does not destroy
them. They are automatically deleted when the representor port stops
(enic_fm_destroy).
Signed-off-by: Hyong Youb Kim <hyonkim@cisco.com> Reviewed-by: John Daley <johndale@cisco.com>
Enable the minimal VF representor without Tx/Rx and flow API support.
1. Enable the standard devarg 'representor'
When the devarg is specified, create VF representor ports.
2. Initialize flowman early during PF probe
Representors require the flowman API from the firmware. Initialize it
before creating VF representors, so probe can detect the flowman
support and fail if not available.
3. Add enic_fm_allocate_switch_domain() to allocate switch domain ID
PFs and VFs on the same VIC adapter can forward packets to each other,
so the switch domain is the physical adapter.
4. Create a vnic_dev lock to serialize concurrent devcmd calls
PF and VF representor ports may invoke devcmd (e.g. dump stats)
simultaneously. As they all share a single PF devcmd instance in the
firmware, use a lock to serialize devcmd calls.
Signed-off-by: Hyong Youb Kim <hyonkim@cisco.com> Reviewed-by: John Daley <johndale@cisco.com>
VF representors need to proxy devcmd through the PF vnic_dev
instance. Extend vnic_dev to accommodate them as follows.
1. Add vnic_vf_rep_register()
A VF representor creates its own vnic_dev instance via this function
and saves VF ID. When performing devcmd, vnic_dev uses the saved VF ID
to proxy devcmd through the PF vnic_dev instance.
2. Add vnic_register_lock()
As PF and VF representors appear as independent ports to the
application, its threads may invoke APIs on them simultaneously,
leading to race conditions on the PF vnic_dev. For example, thread A
can query stats on PF port, while thread B queries stats on a VF
representor.
The PF port invokes this function to provide a lock to vnic_dev. This
lock is used to serialize devcmd calls from PF and VF representors.
3. Add utility functions to assist VF representor settings
vnic_dev_mtu() and vnic_dev_uif() retrieve vnic MTU and UIF number
(uplink index), respectively.
Signed-off-by: Hyong Youb Kim <hyonkim@cisco.com> Reviewed-by: John Daley <johndale@cisco.com>
Phil Yang [Fri, 11 Sep 2020 05:38:19 +0000 (13:38 +0800)]
net/memif: relax barrier for zero copy path
Using 'rte_mb' to synchronize the shared ring head/tail between producer
and consumer will stall the pipeline and damage performance on the weak
memory model platforms, such like aarch64.
Relax the expensive barrier with c11 atomic with explicit memory
ordering can improve 3.6% performance on throughput.
Signed-off-by: Phil Yang <phil.yang@arm.com> Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com> Reviewed-by: Jakub Grajciar <jgrajcia@cisco.com>
net/hns3: fix crash when Tx multiple buffer packets
Currently, there is a possibility that segment faults occur when sending
packets whose payloads are stored in multiple buffers based on hns3
network engine. The related core dump information as follows:
Program terminated with signal 11, Segmentation fault.
0 hns3_reassemble_tx_pkts
2512 temp = temp->next;
Missing separate debuginfos, use:
(gdb) bt
0 hns3_reassemble_tx_pkts
1 0x0000000000969c60 in hns3_check_non_tso_pkt
2 0x000000000096adbc in hns3_xmit_pkts
3 0x000000000050d4d0 in rte_eth_tx_burst
4 0x000000000050fca4 in pkt_burst_transmit
5 0x00000000004ca6b8 in run_pkt_fwd_on_lcore
6 0x00000000004ca7fc in start_pkt_forward_on_core
7 0x00000000006975a4 in eal_thread_loop
8 0x0000ffffa6f7fc48 in start_thread
9 0x0000ffffa6ed1600 in thread_start
The root cause is that hns3 PMD driver invokes the rte_pktmbuf_free_seg
API function to release the same rte_mbuf multiple times. The rte_mbuf
pointer is not set to NULL in the internal function
hns3_rx_queue_release_mbufs which is invoked during queue setup, stop
and close. As a result the rte_mbuf in Rx queues will be repeatedly
released when the user application setup queues or stop/start the dev
for multiple times.
Probably for performance reasons, DPDK mempool lib does not check for
the repeated rte_mbuf releases. The Address of released rte_mbuf are
directly stored into the per lcore cache of the mempool. This makes the
rte_mbufs obtained from mempool by calling rte_mempool_get_bulk API
function repetitively. ultimately, it causes to access to a NULL
pointer in PMD driver.
This patch fixes this problem by setting released mbuf pointer to NULL
in the internal function named hns3_rx_queue_release_mbuf. And the other
internal function named hns3_reassemble_tx_pkts is optimized to avoid a
similar problem.
Fixes: bba636698316 ("net/hns3: support Rx/Tx and related operations") Cc: stable@dpdk.org Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com> Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
When Rx of scattered packets is off, we have some possibility of using
vector Rx process function or simple Rx functions in hns3 PMD driver.
If the input MTU is increased and the maximum length of received packets
is greater than the length of a buffer for Rx packets, the hardware
network engine needs to use multiple BDs and buffers to store these
packets. This will cause problems when still using vector Rx process
function or simple Rx function to receiving packets. So, when Rx of
scattered packets is off and device is started, it is not permitted to
increase MTU so that the maximum length of Rx packets is greater than Rx
buffer length.
Signed-off-by: Chengwen Feng <fengchengwen@huawei.com> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
This patch adds simple Tx process function. When multiple segment
packets are not needed, Which means that DEV_TX_OFFLOAD_MBUF_FAST_FREE
offload is not set, we can simple Tx process.
Signed-off-by: Huisong Li <lihuisong@huawei.com> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com> Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
This patch adds the internal function named hns3_write_reg_opt to avoid
performance loss from address calculation during register access in the
'.rx_pkt_burst' ops implementation function named hns3_recv_pkts.
In addition, because hardware always access register in little-endian
mode based on hns3 network engine, so driver should also call
rte_cpu_to_le_32 to convert data in little-endian mode before writing
register and call rte_le_to_cpu_32 to convert data after reading from
register. Here the driver encapsulates the data conversion operation in
the register read/write operation function as below:
hns3_write_reg
hns3_write_reg_opt
hns3_read_reg
Therefore, when calling these functions, conversion is not required
again.
Signed-off-by: Chengwen Feng <fengchengwen@huawei.com> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
This patch reports .rx_free_thresh value in the .dev_infos_get ops
implementation function named hns3_dev_infos_get and
hns3vf_dev_infos_get.
In addition, the name of the member variable of struct hns3_rx_queue is
modified and comments are added to improve code readability.
Signed-off-by: Chengwen Feng <fengchengwen@huawei.com> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Ivan Dyukov [Tue, 15 Sep 2020 19:06:57 +0000 (22:06 +0300)]
ethdev: format link status text
There is new link_speed value introduced. It's INT_MAX value which
means that speed is unknown. To simplify processing of the value
in application, new function is added which convert link_speed to
string. Also dpdk examples have many duplicated code which format
entire link status structure to text.
This commit adds two functions:
* rte_eth_link_speed_to_str - format link_speed to string
* rte_eth_link_to_str - convert link status structure to string
The kernel expects the start address of the UMEM to be page size
aligned.
Since the mempool is not guaranteed to have such alignment, we have been
aligning the address to the start of the page the mempool is on. However
when passing the 'size' of the UMEM during it's creation we did not take
this into account.
This commit adds the amount by which the address was aligned to the size
of the UMEM.
net/virtio: fix variable assignment in helper macro
Inside Macro ASSIGN_UNLESS_EQUAL(var, val), assignment to var is always
failing as assignment done using var_ having local scope only.
This leads to TX packets not going out and found broken due to cleanup
malfunctioning. This patch fixes the wrong variable assignment.
Fixes: 57f90f894588 ("net/virtio: reuse packed ring functions") Cc: stable@dpdk.org Signed-off-by: Vipul Ashri <vipul.ashri@oracle.com> Acked-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
The CQ polling is done in order to notify the guest about new traffic
bursts and to release FW resources for the next bursts management.
When HW is faster than SW, it may be that all the FW resources are busy
in SW due to late polling.
In this case, due to wrong WQE counter masking, the fullness
calculation of the completions number is 0 while the queue is full.
Change the WQE counter masking to 16-bit wideness instead of the CQ
size mask as defined by the CQE format.
The CQ configuration enables the collapse feature in HW what cause HW to
write all the completions in the first CQE.
When this feature is enabled the HW doesn't switch the owner bit when it
starts a new cycle of the CQ, not like working without the collapse
feature.
The current SW CQ polling wrongly added an assertion to validate the
owner bit switch what causes a panic in debug mode.
Control thread (which handles iotlb msg) and forwarding thread
both use iotlb to translate address. The former may modify the
same entry of mempool and may cause a loop in iotlb_pending_entries
list.
Xueming Li [Tue, 25 Aug 2020 09:17:28 +0000 (09:17 +0000)]
vdpa/mlx5: fix event channel setup
During vDPA device setup, if some error happens, event channel
release stucks at polling event channel.
Event channel fd is set to non-blocking in cqe setup, so if any
error happens before this function and after event channel created,
the pooling before releasing resources will stuck.
This patch moves event channel to non-blocking mode right after
creation.
Fixes: 8395927cdfaf ("vdpa/mlx5: prepare HW queues") Cc: stable@dpdk.org Signed-off-by: Xueming Li <xuemingl@nvidia.com> Acked-by: Matan Azrad <matan@nvidia.com> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Adrian Moreno [Wed, 5 Aug 2020 14:45:17 +0000 (16:45 +0200)]
net/virtio-user: enable feature checking
virtio 1.0 introduced a mechanism for the driver to verify that the
feature bits it sets are accepted by the device. This mechanism consists
in setting the VIRTIO_STATUS_FEATURE_OK status bit and re-reading it,
which gives a chance for the device to clear it if the features
were not accepted.
This is currently being done only in modern virtio-pci devices but since
the appropriate vhost-user messages have been added, it can also be done
in virtio-user (vhost-user only).
This patch activates this mechanism on virtio-user.
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com> Signed-off-by: Adrian Moreno <amorenoz@redhat.com>
Chelsio T6 NIC can support up to 8 priority channels to manage
congestion. So, increase to 8 congestion channels for T6. Also,
add Rxq state to avoid unnecessarily ringing doorbell and polling
the hardware for more traffic when the Rxq is stopped.
Firmware returns the max queues that can be allocated on the entire
PF. The driver evenly distributes them across all the ports belonging
to the PF. However, some ports may need more queues than others and
this equal distribution scheme prevents accessing these other ports
unused queues. So, remove the equal distribution scheme and allow the
ports to allocate as many queues as they need.
Also remove the hardcoded 64 max limit on queue allocation. Instead,
use the max limit given by firmware.
net/cxgbe: release port resources during port close
Enable RTE_ETH_DEV_CLOSE_REMOVE during PCI probe for all ports
enumerated under the PF. Free up the underlying port Virtual
Identifier (VI) and associated resources during port close.
Once all the ports under the PF are closed, free up the PF-wide
shared resources. Invoke port close function of all ports under
the PF, in PCI remove too.
net/cxgbe: fix queue DMA ring leaks during port close
Free up the DMA memzones properly for all the port's queues during
port close. So, rework DMA ring allocation/free logic to use
rte_eth_dma_zone_reserve()/rte_eth_dma_zone_free() helper functions
for allocating/freeing the memzones.
The firmware event queue doesn't have an associated freelist queue.
So, remove check that tries to give memzone name for a non-existent
freelist queue.
Also, add a missing free for the control queue mempools.
Igor Romanov [Tue, 8 Sep 2020 09:20:22 +0000 (10:20 +0100)]
net/sfc/base: fix tunnel configuration
Tunnel configuration may fail because of insufficient access rights
on a virtual function. Ignore the failure if a tunnel configuration
with empty UDP ports is requested.
Fixes: 17551f6dffcc ("net/sfc/base: add API to control UDP tunnel ports") Cc: stable@dpdk.org Signed-off-by: Igor Romanov <igor.romanov@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Adding support to set RSS level from ethdev config.
level-default will requests the default behavior.
level-outer will requests RSS to be performed on the outermost packet
encapsulation level.
level-inner will request RSS to be performed on the specified inner
packet encapsulation level, from outermost to innermost.
Signed-off-by: Kiran Kumar K <kirankumark@marvell.com> Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
ethdev: support encapsulation level for RSS offload
This patch reserves 2 bits as input selection to select inner and outer
encapsulation level for RSS computation. It is combined with existing
ETH_RSS_* to choose inner or outer layers.
This functionality already exists in rte_flow through level parameter in
RSS action configuration rte_flow_action_rss.
Signed-off-by: Kiran Kumar K <kirankumark@marvell.com> Acked-by: Andrew Rybchenko <arybchenko@solarflare.com> Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Heinrich Kuhn [Thu, 3 Sep 2020 11:23:51 +0000 (13:23 +0200)]
doc: improve multiport PF in nfp guide
The Agilio CX family of smartNIC's generally have a 1:many mapping of PF
to physical ports. Elaborate on this mapping in the PF multiport section
of the NFP PMD documentation.
Fixes: d625beafc8be ("doc: update NFP with PF support information") Cc: stable@dpdk.org Signed-off-by: Heinrich Kuhn <heinrich.kuhn@netronome.com> Signed-off-by: Simon Horman <simon.horman@netronome.com>
Yi Yang [Thu, 17 Sep 2020 02:12:49 +0000 (10:12 +0800)]
gso: fix payload unit size for UDP
Fragment offset of IPv4 header is measured in units of
8 bytes. Fragment offset of UDP fragments will be wrong
after GSO if pyld_unit_size isn't multiple of 8. Say
pyld_unit_size is 1500, fragment offset of the second
UDP fragment will be 187 (i.e. 1500 / 8), which means 1496,
and it will result in 4-byte data loss (1500 - 1496 = 4).
So UDP GRO will reassemble out a wrong packet.
Fixes: b166d4f30b66 ("gso: support UDP/IPv4 fragmentation") Cc: stable@dpdk.org Signed-off-by: Yi Yang <yangyi01@inspur.com> Acked-by: Jiayu Hu <jiayu.hu@intel.com>
def_cp_lock was added to sync race between dev_configure and
int_handler. It should not be used to synchronize scheduling of FW
health check between dev_start and async event handler as well,
use a separate mutex for the same.
Fixes: a73b8e939f10 ("net/bnxt: fix race between start and interrupt handler") Cc: stable@dpdk.org Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com> Reviewed-by: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com> Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com> Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Add a couple of NULL pointer checks in bnxt_free_all_filters()
and bnxt_free_vnics() respectively to guard against certain error
injection/recovery scenarios where it was found that the application
was crashing with the bp->vnic_info pointer being NULL.
Fixes: 51fafb89a9a0 ("net/bnxt: get rid of ff pools and use VNIC info array") Cc: stable@dpdk.org Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com> Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
1.Representor Rx ring producer index was not getting reset in
the ring full case. Fix it by incrementing only in
success case.
2.Instead of calling the mbuf specific routine to free the mbuf when
representor ring is full rte_free was being called leading to
'invalid memory' errors being logged.
3. Do not account the pkt meant for the representor in the parent
Rx ring's array that is returned to the application.
Fixes: 6dc83230b43b ("net/bnxt: support port representor data path") Cc: stable@dpdk.org Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com> Reviewed-by: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com> Reviewed-by: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com> Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
net/bnxt: provide switch info if VFR are configured
Some applications need switch_info of the device to be returned
as a part of eth_dev_info_get(). The offload logic in such
applications could use this info. Pass this info to the when VF
representors are configured.
Added support for performing L3 or L4 rewrite for VLAN tagged
flows. The outer most DMAC, SMAC and VLAN are used to overwrite
when NAT operations are performed.
Add code to support vxlan ipv6 tunnel encapsulation. The
ipv6 flow traffic class and flow label wild card match
can be ignored to support offload on some applications.
Randy Schacher [Fri, 11 Sep 2020 01:55:52 +0000 (18:55 -0700)]
net/bnxt: use direct HWRM message for interface table
Change interface tables to use direct or non-tunneled HWRM messaging
instead of tunneled messaging. Update HWRM API to a new version to
allow this change.
If VF-rep port add fails for some reason, code was rolling back
all ports added so far. With some applications, there is no need
to do that. Just log failure message for the VF rep port add and
continue.
Also include RTE_MAX_ETH_PORTS value in the bounds check as one port
will be taken by the uplink port anyway
Fixes: 6dc83230b43b ("net/bnxt: support port representor data path") Cc: stable@dpdk.org Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com> Reviewed-by: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com> Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Instead of bounds checking against max possible rings while selecting
queue index for the VF representor, do it against the number of rings
configured.
Fixes: 6dc83230b43b ("net/bnxt: support port representor data path") Cc: stable@dpdk.org Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com> Reviewed-by: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com>
When parent VF or PF ports are cleaned up, the child VF representor
ports also need to be cleaned up. If not cleaned up, then deleting
the parent VF shall result in not cleaning up the hardware rules and
updating the firmware of VFR removal. The issue can occur even when
application is exited without deleting VFR ports.
Change default flow rule to use 8-byte encap.
The VFR conduit uses VLAN encap to send packets. So the encap record
is changed from 16B to 8B. That frees up 8B of encap records.
net/bnxt: fix coexistence of IPv4 and IPv6 ingress rules
The ingress rule to match on ipv4 and ipv6 is now two rules to
make sure both rules can coexist at the same time. Added count
action only for ingress flows.
Fixes: fe82f3e02701 ("net/bnxt: support exact match templates") Cc: stable@dpdk.org Signed-off-by: Kishore Padmanabha <kishore.padmanabha@broadcom.com> Reviewed-by: Mike Baucom <michael.baucom@broadcom.com> Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
net/bnxt: fix port stop process and cleanup resources
The port deinitialization now cleans up all the resources
properly. If all the ports are stopped then ULP context is
freed.
Added fix to update the correct tfp pointer in the ULP context
with the changes to support multi control channels.
The ptype mask for flexible descriptor in Rx function ice_recv_pkts_vec
has a reversed order, which leads to an incorrect value of the final
ptype. This patch fix the mask to parse the correct ptype of RX packets.
Fixes: c68a52b8b38c ("net/ice: support vector SSE in Rx") Cc: stable@dpdk.org Signed-off-by: Ting Xu <ting.xu@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Guinan Sun [Tue, 15 Sep 2020 06:52:25 +0000 (06:52 +0000)]
net/i40e: fix recreating flexible flow director rule
This patch fixes the failure of recreate flexible fdir rule.
The root cause is that the flex_mask_flag is not reset during
flow destroy and flow flush.
Fixes: 6ced3dd72f5f ("net/i40e: support flexible payload parsing for FDIR") Cc: stable@dpdk.org Signed-off-by: Guinan Sun <guinanx.sun@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Guinan Sun [Wed, 16 Sep 2020 03:10:02 +0000 (03:10 +0000)]
net/ice: remove devargs for flow mark
Currently, all data paths already support flow mark, so remove devargs
"flow-mark-support". FDIR matched ID will display in verbose
when packets match the created rule.
Signed-off-by: Guinan Sun <guinanx.sun@intel.com> Acked-by: Leyi Rong <leyi.rong@intel.com>
This patch supports RxDID #22 by the following changes:
- add structure and macro definition for RxDID #22.
- support RxDID #22 format in normal path.
- change RSS hash parsing from RxDID #22 in AVX/SSE data path.
Signed-off-by: Junyu Jiang <junyux.jiang@intel.com> Acked-by: Leyi Rong <leyi.rong@intel.com>
Michael Baum [Sun, 13 Sep 2020 19:05:21 +0000 (19:05 +0000)]
net/mlx5: fix Rx objects creator selection
There are 2 creators for Rx objects, DevX and Verbs.
There are supported DR versions when a DevX destination TIR flow action
creation cannot be supported, using this versions the TIR object should
be created by Verbs, what forces all the Rx objects to be created by
Verbs.
The selection of the Rx objects creator, wrongly, didn't take into
account the destination TIR action support what caused a failure in the
Rx flows creation.
Select Verbs creator when destination TIR action creation is not
supported by the DR version.
Fixes: 6deb19e1b2d2 ("net/mlx5: separate Rx queue object creations") Signed-off-by: Michael Baum <michaelba@nvidia.com> Acked-by: Matan Azrad <matan@nvidia.com>
Currently, offload capabilities are only enabled for all Rx/Tx queues in
hns3 PF/VF PMD driver, and offload capability only applied in a Rx/Tx
queue is not supported.
So this patch moves 'DEV_TX_OFFLOAD_MBUF_FAST_FREE' from
tx_queue_offload_capa to tx_offload_capa.
Fixes: 1f5ca0b460cd ("net/hns3: support some device operations") Fixes: a5475d61fa34 ("net/hns3: support VF") Cc: stable@dpdk.org Signed-off-by: Huisong Li <lihuisong@huawei.com> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
git.droids-corp.org / dpdk.git / log