The DevX interface exposes a new feature to the PMD that can allocate a
batch of counters by one FW command. It can improve the flow
transaction rate (with count action).
Add a new counter pools mechanism to manage HW counters in the PMD.
So, for each flow with counter creation the PMD will try to find a free
counter in the PMD pools container and only if there is no a free
counter, it will allocate a new DevX batch counters.
Currently we cannot support batch counter for a group 0 flow, so
create a 2 container types, one which allocates counters one by
one and one which allocates X counters by the batch feature.
The allocated counters objects are never released back to the HW
assuming the flows maximum number will be close to the actual value of
the flows number.
Later, it can be updated, and dynamic release mechanism can be added.
The counters are contained in pools, each pool with 512 counters.
The pools are contained in counter containers according to the
allocation resolution type - single or batch.
The cache memory of the counters statistics is saved as raw data per
pool.
All the raw data memory is allocated for all the container in one
memory allocation and is managed by counter_stats_mem_mng structure
which registers all the raw memory to the HW.
Each pool points to one raw data structure.
The query operation is in pool resolution which updates all the pool
counter raw data by one operation.
Signed-off-by: Matan Azrad <matan@mellanox.com>
Acked-by: Shahaf Shuler <shahafs@mellanox.com>
We need to check devargs pointer before dereference it, if no devargs
specified then this driver just skips the device.
Fixes: 40ef35f4a504 ("net/ifc: detect if VDPA mode is specified")
Cc: stable@dpdk.org
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
In 2.0.1 ENA, there were patches for:
* assigning NUMA node to the IO queue
commit 4217cb0b7d2c ("net/ena: fix assigning NUMA node to IO queue")
* statistics counters (Rx checksum errors and per-queue number of the
Tx packets)
commit ef74b5f7b69b ("net/ena: fix Rx checksum errors statistics")
commit 5673e285a633 ("net/ena: fix Tx statistics")
* SMP support
commit 117ba4a60488 ("net/ena: get device info statically")
* setting Rx checksum support
commit ef538c1a7f56 ("net/ena: fix checksum feature flag")
Signed-off-by: Michal Krawczyk <mk@semihalf.com>
Should allow the outer input set be empty.
Fixes: d76116a4678f ("net/ice: add generic flow API")
Signed-off-by: Qiming Yang <qiming.yang@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
The iavf driver crashes when forwarding packets with TSO
enabled. The reason is that the tx context descriptor
configuration is not transferred to tx-ring. This step is
added in this patch.
Fixes: a2b29a7733ef ("net/avf: enable basic Rx Tx")
Cc: stable@dpdk.org
Signed-off-by: Ting Xu <ting.xu@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Because of the commit mentioned below the default case was changed and
this broke single_iface support. This patch adds a check to fix
single_iface support.
Fixes: a3f5252e5cbd ("net/pcap: enable infinitely Rx a pcap file")
Signed-off-by: Aideen McLoughlin <aideen.mcloughlin@intel.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
In the eth_pcap_tx() and eth_pcap_tx_dumper() functions mbufs were freed
without incrementing num_tx.
This may lead application also try to free or use invalid mbuf.
To fix the issue, the mbuf freeing was removed.
Fixes: 6db141c91e1f ("pcap: support jumbo frames")
Cc: stable@dpdk.org
Signed-off-by: Aideen McLoughlin <aideen.mcloughlin@intel.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
Fix an overrun of the ring group array with BCM5750X-based
adapters by ensuring that the ring group array is not allocated
or accessed for adapters that do not support ring groups.
Fixes: f8168ca0e690 ("net/bnxt: support thor controller")
Signed-off-by: Lance Richardson <lance.richardson@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
The conditional used to determine whether freeing RSS
contexts for thor vs. non-thor controller was reversed.
Fix this, also reset number of active RSS contexts to
zero after release in the thor case.
Fixes: 38412304b50a ("net/bnxt: enable RSS for thor-based controllers")
Signed-off-by: Lance Richardson <lance.richardson@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Layer 2 length must be updated after the prepend to mbuf to keep
the length right to be used by other Tx offloads.
If the packet has tunnel encapsulation, outer_l2_len should be
updated. Otherwise l2_len should be updated.
Fixes: c974021a5949 ("ether: add soft vlan encap/decap")
Cc: stable@dpdk.org
Signed-off-by: Dilshod Urazov <dilshod.urazov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
Don't use RTE_LOGTYPE_PMD as it is too general.
Also, just use 1 log type for all of enic PMD (pmd.net.enic)
Signed-off-by: John Daley <johndale@cisco.com>
Reviewed-by: Hyong Youb Kim <hyonkim@cisco.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
There are some implicit downcast errors in TX offload information
parsing by lgtm tool. This patch is to solve these errors.
Fixes: 64727024d2fd ("net/hinic: add device initialization")
Signed-off-by: Ziyang Xuan <xuanziyang2@huawei.com>
Adding support for flags based extraction in octeontx2 Flow.
Patch supports extracting data greater than 32 bytes using lflags.
When flags based extraction is enabled, lower 4 bits will be
considered (16 flags) for indexing the flags, and will be used
for extraction.
Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
When pattern has ETH, it may contain two kinds of lookup
parameters, MAC and ethertype.
So increasing item number for memory malloc in order
to reserve one more memory slot for ETH which may
consume 2 lookup items.
Fixes: 57c4f2693588 ("net/ice: enable switch filter")
Signed-off-by: Wei Zhao <wei.zhao1@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
If the input set is outer or inner protocol was distinguished by
checking if the item appears once or twice.
But this is not working when the user doesn't configure the outer
input set, this patch fixes the issue.
Fixes: d76116a4678f ("net/ice: add generic flow API")
Signed-off-by: Qiming Yang <qiming.yang@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
The rte_vdev_driver is declared twice.
The first one is not necessary.
Fixes: 3298fa4853b8 ("raw/dpaa2_cmdif: introduce DPAA2 command interface driver")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
The rte_vdev_driver is declared twice.
The first one is not necessary.
Fixes: 61c592a8d035 ("raw/skeleton: introduce skeleton rawdev driver")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
The rte_vdev_driver is declared twice.
The first one is not necessary.
Fixes: 050fe6e9ff97 ("drivers/net: use ethdev allocation helper for vdev")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
The rte_vdev_driver is declared twice.
The first one is not necessary.
Fixes: 740feaf349b1 ("ethdev: remove driver name from device private data")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
The rte_vdev_driver is declared twice.
The first one is not necessary.
Fixes: 050fe6e9ff97 ("drivers/net: use ethdev allocation helper for vdev")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
The rte_vdev_driver is declared twice.
The first one is not necessary.
Fixes: 050fe6e9ff97 ("drivers/net: use ethdev allocation helper for vdev")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
The rte_vdev_driver is declared twice.
The first one is not necessary.
Fixes: 050fe6e9ff97 ("drivers/net: use ethdev allocation helper for vdev")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
The rte_vdev_driver is declared twice.
The first one is not necessary.
Fixes: 050fe6e9ff97 ("drivers/net: use ethdev allocation helper for vdev")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
The rte_vdev_drivers are declared twice.
The first one is not necessary.
Fixes: 740feaf349b1 ("ethdev: remove driver name from device private data")
Fixes: 204d026a3922 ("net/tap: support tun")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Keith Wiles <keith.wiles@intel.com>
Print system error to make easier diagnosis of errors with af_packet.
Signed-off-by: Krzysztof Kanas <kkanas@marvell.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Enabled IP-in-IP tunnel type support on DV/DR flow engine.
This includes the following combination:
- IPv4 over IPv4
- IPv4 over IPv6
- IPv6 over IPv4
- IPv6 over IPv6
MLX5 NIC supports IP-in-IP tunnel via FLEX Parser so
need to make sure fw using FLEX Paser profile 0.
mlxconfig -d <mst device> -y set FLEX_PARSER_PROFILE_ENABLE=0
The example testpmd commands would be:
- Match on IPv4 over IPv4 packets and do inner RSS:
testpmd> flow create 0 ingress pattern eth / ipv4 proto is 0x04 /
ipv4 / udp / end actions rss level 2 queues 0 1 2 3 end / end
- Match on IPv6 over IPv4 packets and do inner RSS:
testpmd> flow create 0 ingress pattern eth / ipv4 proto is 0x29 /
ipv6 / udp / end actions rss level 2 queues 0 1 2 3 end / end
Signed-off-by: Xiaoyu Min <jackmin@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
ice_flow_valid_attr will return zero on success and a negative value
on error.
Current return value check logic is opposite of the expected behavior.
This patch fixes this issue.
Fixes: d76116a4678f ("net/ice: add generic flow API")
Cc: stable@dpdk.org
Signed-off-by: Qiming Yang <qiming.yang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
The phys_addr concept is deprecated in rte_memzone, change it to access
iova member, and use the type 'rte_iova_t'.
Also rename the rx/tx_ring_phys_addr definitions to rx/tx_ring_dma that
matches the IOVA concept design.
Fixes: 50370662b727 ("net/ice: support device and queue ops")
Cc: stable@dpdk.org
Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Procedure xdp_get_channels_info was returning error code -1 in case of
ioctl command SIOCETHTOOL was not supported. This patch sets return
value back to 0 as it is valid case.
Fixes: 339b88c6a91f ("net/af_xdp: support multi-queue")
Signed-off-by: Július Milan <jmilan.dev@gmail.com>
Reviewed-by: Xiaolong Ye <xiaolong.ye@intel.com>
queue= parameter does not exist.
It might have been the previous name of the queue_count parameter, but
anyway, the default value 1 for the number of queues works fine.
Fixes: f1debd77efaf ("net/af_xdp: introduce AF_XDP PMD")
Cc: stable@dpdk.org
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
Support matching on the present bits (C,K,S)
as well as the optional key field.
If the rte_flow_item_gre_key is specified in pattern,
it will set K present match automatically.
Signed-off-by: Xiaoyu Min <jackmin@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
DR engine support matching on GRE protocol field without MPLS supports.
So bypassing the MPLS check when DR is enabled.
Signed-off-by: Xiaoyu Min <jackmin@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
When OS package is not provided driver silently goes into safe mode,
since safe mode is missing most of advanced features, this may confuse
the users.
Instead of going into safe mode silently, add devarg for safe mode
enabling only for users that are asking for it.
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Acked-by: Ray Kinsella <ray.kinsella@intel.com>
Remove devarg "max_queue_pair_num" related code since
it is not complete implemented.
Fixes: f9cf4f864150 ("net/ice: support device initialization")
Cc: stable@dpdk.org
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Using spin lock to protect critical resources
of sending mgmt messages. This will make high
CPU usage for rte_delay_ms when sending mgmt
messages frequently. We can use mutex to protect
the critical resources and usleep to reduce CPU
usage while keep functioning properly.
Signed-off-by: Ziyang Xuan <xuanziyang2@huawei.com>
Adding PF and VF action support for octeontx2 flow driver.
If RTE_FLOW_ACTION_TYPE_PF action is set from VF, then the packet
will be sent to the parent PF.
If RTE_FLOW_ACTION_TYPE_VF action is set and original is specified,
then the packet will be sent to the original VF, otherwise the packet
will be sent to the VF specified in the vf_id.
Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
For SRIOV, fastpath status blocks are not allocated resulting in
segfault. Separate out fastpath DMA allocation/free from rest of
memory allocation/free. It is now done as part of NIC load/unload.
Comment indentation changes in bnx2x_alloc_hsi_mem() and
bnx2x_free_hsi_mem() APIs.
Fixes: f0219d98defd ("net/bnx2x: fix interrupt flood")
Cc: stable@dpdk.org
Signed-off-by: Rasesh Mody <rmody@marvell.com>
We do not need to schedule periodic poll for slowpath link events
for SRIOV. The link events are handled by the PF driver.
Fixes: 6041aa619f9a ("net/bnx2x: fix poll link status")
Cc: stable@dpdk.org
Signed-off-by: Rasesh Mody <rmody@marvell.com>
The logic to read vf_id used by ACQUIRE/TEARDOWN_Q/RELEASE TLVs,
multiplexed return value to convey vf_id value and status of read vf_id
API. This lets to segfault at dev_start() as resources are not properly
cleaned and re-allocated.
Fix read vf_id API to differentiate between vf_id value and return
status. Adjust the status checking accordingly.
Added bnx2x_vf_teardown_queue() API and moved relevant code from
bnx2x_vf_unload() to new API.
Fixes: 540a211084a7 ("bnx2x: driver core")
Cc: stable@dpdk.org
Signed-off-by: Rasesh Mody <rmody@marvell.com>
Replace rte_intr_enable() with rte_intr_ack() API
for acking an interrupt in interrupt handlers and
rx_queue_intr_enable() callbacks of PMD's.
This is inline with original intent of this change in PMDs
to ack interrupts after handling is completed if
device is backed by UIO, IGB_UIO or VFIO(with INTx).
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Acked-by: Shahed Shaikh <shshaikh@marvell.com>
Tested-by: Shahed Shaikh <shshaikh@marvell.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>
Add new ack interrupt API to avoid using
VFIO_IRQ_SET_ACTION_TRIGGER(rte_intr_enable()) for
acking interrupt purpose for VFIO based interrupt handlers.
This implementation is specific to Linux.
Using rte_intr_enable() for acking interrupt has below issues
* Time consuming to do for every interrupt received as it will
free_irq() followed by request_irq() and all other initializations
* A race condition because of a window between free_irq() and
request_irq() with packet reception still on and device still
enabled and would throw warning messages like below.
[158764.159833] do_IRQ: 9.34 No irq handler for vector
In this patch, rte_intr_ack() is a no-op for VFIO_MSIX/VFIO_MSI interrupts
as they are edge triggered and kernel would not mask the interrupt before
delivering the event to userspace and we don't need to ack.
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Tested-by: Shahed Shaikh <shshaikh@marvell.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>
This reverts commit 89aac60e0be9ed95a87b16e3595f102f9faaffb4.
"vfio: fix interrupts race condition"
The above mentioned commit moves the interrupt's eventfd setup
to probe time but only enables one interrupt for all types of
interrupt handles i.e VFIO_MSI, VFIO_LEGACY, VFIO_MSIX, UIO.
It works fine with default case but breaks below cases specifically
for MSIX based interrupt handles.
* Applications like l3fwd-power that request rxq interrupts
while ethdev setup.
* Drivers that need > 1 MSIx interrupts to be configured for
functionality to work.
VFIO PCI for MSIx expects all the possible vectors to be setup up
when using VFIO_IRQ_SET_ACTION_TRIGGER so that they can be
allocated from kernel pci subsystem. Only way to increase the number
of vectors later is first free all by using VFIO_IRQ_SET_DATA_NONE
with action trigger and then enable new vector count.
Above commit changes the behavior of rte_intr_[enable|disable] to
only mask and unmask unlike earlier behavior and thereby
breaking above two scenarios.
Fixes: 89aac60e0be9 ("vfio: fix interrupts race condition")
Cc: stable@dpdk.org
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Tested-by: Stephen Hemminger <stephen@networkplumber.org>
Tested-by: Shahed Shaikh <shshaikh@marvell.com>
Tested-by: Lei Yao <lei.a.yao@intel.com>
Acked-by: David Marchand <david.marchand@redhat.com>
The eth_dev_info was used with content that was obsolete. Added update
of struct content prior to use.
Fixes: 6b7780bfebe4 ("examples/ip_frag: fix use of ethdev internal device array")
Cc: stable@dpdk.org
Signed-off-by: Marcin Zapolski <marcinx.a.zapolski@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Added telemetry to EAL long options so that when
--telemetry is passed as an EAL arg that there is
no unrecognized argument error message printed.
Fixes: 8877ac688b52 ("telemetry: introduce infrastructure")
Cc: stable@dpdk.org
Signed-off-by: Sean Morrissey <sean.morrissey@intel.com>
Tested-by: John OLoughlin <john.oloughlin@intel.com>
Acked-by: Kevin Laatz <kevin.laatz@intel.com>
When bus layer reports the preferred mode as RTE_IOVA_DC then
select the RTE_IOVA_VA mode:
- All drivers work in RTE_IOVA_VA mode, irrespective of physical
address availability.
- By default, a mempool asks for IOVA-contiguous memory using
RTE_MEMZONE_IOVA_CONTIG. This is slow in RTE_IOVA_PA mode and it
may affect the application boot time.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>
In order to align name with other PCI driver flag such as
RTE_PCI_DRV_NEED_MAPPING and to reflect its purpose, change
RTE_PCI_DRV_IOVA_AS_VA flag name as RTE_PCI_DRV_NEED_IOVA_AS_VA.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>
The incriminated commit broke the use of RTE_PCI_DRV_IOVA_AS_VA which
was intended to mean "driver only supports VA" but had been understood
as "driver supports both PA and VA" by most net drivers and used to let
dpdk processes to run as non root (which do not have access to physical
addresses on recent kernels).
The check on physical addresses actually closed the gap for those
drivers. We don't need to mark them with RTE_PCI_DRV_IOVA_AS_VA and this
flag can retain its intended meaning.
Document explicitly its meaning.
We can check that a driver requirement wrt to IOVA mode is fulfilled
before trying to probe a device.
Finally, document the heuristic used to select the IOVA mode and hope
that we won't break it again.
Fixes: 703458e19c16 ("bus/pci: consider only usable devices for IOVA mode")
Signed-off-by: David Marchand <david.marchand@redhat.com>
Reviewed-by: Jerin Jacob <jerinj@marvell.com>
Tested-by: Jerin Jacob <jerinj@marvell.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
This reverts commit 0cb86518db57d35e0abc14d6703fad561a0310e2.
The PCI bus now reports DC when faced with a device bound to an unknown
driver and, in such a case, the IOVA mode is selected against physical
address availability.
As a consequence, there is no reason for this special case for Mellanox
drivers.
Fixes: 703458e19c16 ("bus/pci: consider only usable devices for IOVA mode")
Signed-off-by: David Marchand <david.marchand@redhat.com>
Reviewed-by: Jerin Jacob <jerinj@marvell.com>
fslmc_vfio.c:387:36: note: format string is defined here
DPAA2_BUS_DEBUG("VFIO dmamap 0x%llx:0x%llx, size 0x%llx\n",
format ‘%llx’ expects argument of type ‘long long unsigned int’
argument 6 has type ‘__u64 {aka long unsigned int}’
Fixes: 2b5fa25708cf ("mempool/dpaa2: map external memory with VFIO")
Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
