The template is updated to support additional combinations
of NAT actions.
Fixes: 2951f7f311 ("net/bnxt: support NAT action items")
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>
When a packet is looped back from VF to VFR, it is marked to identify
the VFR interface. However, this mark_id shouldn't be percolated up to
the OVS as it is internal to pmd.
This patch fixes it by skipping mark injection into mbuf if the packet
is received on VFR interface.
Fixes: 6dc83230b4 ("net/bnxt: support port representor data path")
Signed-off-by: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com>
Signed-off-by: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Added TruFlow hash API for common hash uses across TruFlow
core functions.
Signed-off-by: Mike Baucom <michael.baucom@broadcom.com>
Reviewed-by: Farah Smith <farah.smith@broadcom.com>
Reviewed-by: Kishore Padmanabha <kishore.padmanabha@broadcom.com>
Modified ulp mapper to use the new tf_search_tcam_entry API.
When search before allocation is requested, mapper calls
tc_search_tcam_entry with the alloc flag.
- On HIT, the result and tcam index is returned.
- On MISS, the tcam index is returned but the result is
created and the tcam entry is set.
- On REJECT, the flow request is rejected.
Signed-off-by: Mike Baucom <michael.baucom@broadcom.com>
Reviewed-by: Kishore Padmanabha <kishore.padmanabha@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
PARIF is handler to a partition of the physical port.
For the offload miss rules, the parif miss path needs to be
considered. The higher parif are reserved for handling this.
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>
Add support to enable or disable the NAT global registers.
The NAT feature is enabled in hardware during initialization
and disabled at deinitialization of the application.
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>
- Add TCAM shadow tables for searching
- Add Search API to allow reuse of TCAM entries
Signed-off-by: Mike Baucom <michael.baucom@broadcom.com>
Reviewed-by: Randy Schacher <stuart.schacher@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
RXQ interrupts under Linux are based on the epoll mechanism. An
expected order of operations is as follows:
1. Call rte_eth_dev_rx_intr_enable(), to arm the CQ for receiving events
on data input.
2. Block on rte_epoll_wait() with an array of file descriptors
representing the CQ events. Upon data arrival the kernel will signal an
input event on the corresponding CQ fd.
3. Call rte_eth_dev_rx_intr_disable() after the event was received and
continue in polling mode. The mlx4 implementation of
rte_eth_dev_rx_intr_disable() is to get the CQ event and ack it.
In practice applications may wake up from rte_epoll_wait() due to
timeout with no event to ack but still call
rte_eth_dev_rx_intr_disable() unconditionally. In such cases the call
should return EAGAIN (since the file descriptors are non-blocked), as
opposed to EINVAL which indicates a real failure. In case of EAGAIN the
PMD should not warn on "unable to disable interrupt on rx queue".
Signed-off-by: Ophir Munk <ophirmu@mellanox.com>
Acked-by: Raslan Darawsheh <rasland@mellanox.com>
The function rte_zmalloc() could return NULL, the return
value need to be checked.
Fixes: f4ca3fd54c ("net/hinic: create and destroy flow director filter")
Cc: stable@dpdk.org
Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Replace gettimeofday() with clock_gettime(CLOCK_MONOTONIC_RAW, &now),
the reason is same with
commit d08d304508 ("eal/linux: make alarm not affected by system time
jump")
Fixes: 81d53291a4 ("net/hinic/base: add various headers")
Cc: stable@dpdk.org
Signed-off-by: Xiaoyun Wang <cloud.wangxiaoyun@huawei.com>
For ovs offload scenario, when fw processes the virtio header,
there is no need to offset; and for standard card scenarios,
fw does not care about the vhd_type parameter, so in order to
be compatible with these two scenarios, use 0 offset instead.
Signed-off-by: Xiaoyun Wang <cloud.wangxiaoyun@huawei.com>
For x86 platform, the rq cqe without cache aligned, which can
improve performance for some gateway scenarios.
Fixes: 361a9ccf81 ("net/hinic: optimize Rx performance")
Cc: stable@dpdk.org
Signed-off-by: Xiaoyun Wang <cloud.wangxiaoyun@huawei.com>
Recent patch added creation of Rx CQ using DevX API.
The reading of events from DevX channel was not done correctly.
This patch fixes the event reading, using the correct data structure.
Cleanup after CQ creation, in case of error, is also updated.
Fixes: 08d1838f64 ("net/mlx5: implement CQ for Rx using DevX API")
Signed-off-by: Dekel Peled <dekelp@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
An invalid rule should not be validated successfully. If the rule is not
in the supporting list, just return failure to application.
Fixes: 5ad3db8d4b ("net/ice: enable advanced RSS")
Cc: stable@dpdk.org
Signed-off-by: Jeff Guo <jia.guo@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
We don't support SCTP in PPPoE RSS, remove it.
Fixes: d117de4600 ("net/ice: fix GTPU/PPPoE packets with no hash value")
Fixes: 0b952714e9 ("net/ice: refactor PF hash flow")
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Tested-by: Nannan Lu <nannan.lu@intel.com>
Acked-by: Jeff Guo <jia.guo@intel.com>
A new symmetric RSS rule may force another asymmetric rule to be
symmetric, vice versa. The reason is due to the flow engine will
try to reuse the existing profile if the input set matches with the
new rule. The fix is to disable this optimization for RSS since we
are not at the situation as profile shortage.
Fixes: ddae044035 ("net/ice/base: enable symmetric hash for RSS")
Cc: stable@dpdk.org
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Tested-by: Nannan Lu <nannan.lu@intel.com>
Acked-by: Jeff Guo <jia.guo@intel.com>
This patch enable i40e outer vlan strip on and off in QinQ
mode with mask bit of DEV_RX_OFFLOAD_QINQ_STRIP, users can
use "vlan set qinq_strip on 0" to enable or "vlan set
qinq_strip off 0" to disable i40e outer vlan strip when
try with testpmd app.
Fixes: 4861cde461 ("i40e: new poll mode driver")
Cc: stable@dpdk.org
Signed-off-by: Wei Zhao <wei.zhao1@intel.com>
Reviewed-by: Qiming Yang <qiming.yang@intel.com>
Other PMDs may be using the mempool, so don't free it when destroying the
UMEM.
Fixes: d8a210774e ("net/af_xdp: support unaligned umem chunks")
Cc: stable@dpdk.org
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
The ConnectX NICs can transfer data from the host memory with two
approaches: provide the pointer to the data buffer, or do data inline
- copy the data to the transmit descriptor (WQE) entirely or only the
part of data. In some configurations the NIC hardware requires the
minimal data to be inline in the descriptor to operate correctly. And
there is the special dynamic flag to hint PMD not to inline the data
(for example, if buffer is located on some other device - storage or
GPU) on per packet basis.
If there was a packet with length shorter than the minimal inline data
length requested by the NIC hardware and the no-inline hint was set
the PMD tried to inline the packet with minimal required length
instead of actual packet's one. This patch adds the missed length
check into no-inline hint handling branch.
Fixes: cacb44a099 ("net/mlx5: add no-inline Tx flag")
Cc: stable@dpdk.org
Signed-off-by: Gregory Etelson <getelson@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
There was the typo introducing the bug, affected the mlx5 vectorized
rx_burst on ARM architectures in case if CQE compression was enabled.
Fixes: 6c55b622a9 ("net/mlx5: set dynamic flow metadata in Rx queues")
Cc: stable@dpdk.org
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
The User Access Region is a special mechanism to provide direct
access to the hardware registers, and is the part of PCI address
space that is mapped to CPU virtual address. The mapping can be
performed with the type "Write-Combining" or "Non-Cached", and
these ones might be supported or not on different setups.
To prevent device probing failure the UAR allocation attempt
with alternative mapping type is performed. The datapath
takes the actual UAR mapping into account on queue creation.
There was another issue with NULL UAR base address.
OFED 5.0.x and Upstream rdma_core before v29 returned the NULL as
UAR base address if UAR was not the first object in the UAR page.
It caused the PMD failure and we should try to get another UAR
till we get the first one with non-NULL base address returned.
Fixes: fc4d4f732b ("net/mlx5: introduce shared UAR resource")
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Ori Kam <orika@mellanox.com>
The hash look up table (LUT) is managed by global register but it is not
initialized when RSS is disabled. Once user wants to enable RSS during
runtime, the LUT will not be initialized.
This patch fixes the issue by initializing the LUT whatever RSS enabled
or not.
Fixes: feaae285b3 ("net/i40e: support hash configuration in RSS flow")
Cc: stable@dpdk.org
Signed-off-by: Shougang Wang <shougangx.wang@intel.com>
Tested-by: Xi Zhang <xix.zhang@intel.com>
Acked-by: Jeff Guo <jia.guo@intel.com>
The combined hash type should be bound with prefix protocol when
configure it, so delete some useless and unsupported part for
rss types mapping.
Fixes: 7be10c3004 ("net/iavf: add RSS configuration for VF")
Cc: stable@dpdk.org
Signed-off-by: Jeff Guo <jia.guo@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
FDIR allocating msix resource is not strictly necessary, if no
resource left, jump the error.
Fixes: 4861cde461 ("i40e: new poll mode driver")
Cc: stable@dpdk.org
Signed-off-by: Mao Jiang <maox.jiang@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
The value of vsi->nb_msix shouldn't`t be zero, otherwise, all of
interrupts will be bind to vector 0.
Fixes: 4861cde461 ("i40e: new poll mode driver")
Cc: stable@dpdk.org
Signed-off-by: Mao Jiang <maox.jiang@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
'port_id' storage size should be 'uint16_t', the API
'rte_pmd_dpaa_set_tx_loopback()' has it as 'uint8_t' but fixing it is an
ABI breakage, that is why planning the fix in v20.11 release where ABI
breakage is allowed.
Signed-off-by: Sachin Saxena <sachin.saxena@nxp.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Acked-by: Zhiyong Yang <zhiyong.yang@intel.com>
When trying to set MAC address of an ethernet device and if it was
a representor, PMD sets the MAC over the corresponding VF instead.
For the case of HPF (Host PF representor on BlueField), PMD shouldn't
attempt to set it, since it doesn't have any corresponding VF and fails.
This will fix the issue by setting the MAC on the dev directly.
Fixes: 0d1d731708 ("net/mlx5: set VF MAC address from host")
Cc: stable@dpdk.org
Signed-off-by: Raslan Darawsheh <rasland@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
There was an optimization work to prefetch all the CQEs before
their invalidation. It allowed us to speed up the mini-CQE
decompression process by preheating the cache in the vectorized
Rx routine.
Prefetching of the next mini-CQE, on the other hand, showed
no difference in the performance on x86 platform. So, that was
removed. Unfortunately this caused the performance drop on ARM.
Prefetch the mini-CQE as well as all the soon to be
invalidated CQEs to get both CQE and mini-CQE on the hot path.
Fixes: 28a4b96321 ("net/mlx5: prefetch CQEs for a faster decompression")
Cc: stable@dpdk.org
Signed-off-by: Alexander Kozyrev <akozyrev@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Function simple_xor for AVF RSS is not required currently, thus we
just return rte_flow error when the command line has item simple_xor.
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
The device configuration struct is not small enough to be used as
function argument by value.
Call spawn function with device configuration by reference.
Signed-off-by: Michael Baum <michaelba@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
The flow_dv_convert_action_mark function defines an array of
field_modify_info structures and initializes the first entity.
In the first entity id field, it initializes to 0, even though its type
is an enum that has no value of 0.
In fact, the function does not use this id field before assigning the
appropriate register id into it, so the initialization is unnecessary.
Moreover, this initialization is int into enum, and it would be better
not to create a type conflict for no reason.
Wait for the first entity initialization until the appropriate register
id is already known.
Fixes: 55deee1715 ("net/mlx5: extend flow mark support")
Cc: stable@dpdk.org
Signed-off-by: Michael Baum <michaelba@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
When PMD releases shared IB device context, It locks the
mlx5_ibv_list_mutex lock throughout the function so that it does not
happen while removing a device from the list, another process will try
to insert another device into it.
On the other hand, having removed the device from the list even if it
has not yet released all of its resources, it should not care about
other processes and can release the lock.
However, the PMD does not release the lock even though it can, and
performs a number of operations, some of which include sleep and may be
long.
To improve this, shorten the lock time to the minimum necessary.
Signed-off-by: Michael Baum <michaelba@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
In mlx5_sysfs_switch_info function, the driver gets switch information
associated with network interface.
The driver writes the port name into buffer and translates it.
However, when it writes the name, it does not limit writing to the
buffer size.
Limit writing to the size of the buffer.
Fixes: 1256805dd5 ("net/mlx5: move Linux-specific functions")
Cc: stable@dpdk.org
Signed-off-by: Michael Baum <michaelba@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
The mlx4_pci_probe function sets a pointer to the mlx4_priv structure,
and during that function fills its fields one by one with relevant
values.
It wants to put a value in the intr_handle field that has all its fields
zero except 2. To do so, it initializes a local struct rte_intr_handle
type variable and updates it only 2 fields and assigns it into the
appropriate field. However, it initializes a very large structure on the
stack while not at all certain that this place exists and in any case it
is very wasteful.
Reset all fields directly to the pointer by memset, then format the 2
fields to the relevant values.
Fixes: 63c2f23c85 ("net/mlx4: use a single interrupt handle")
Cc: stable@dpdk.org
Signed-off-by: Michael Baum <michaelba@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
The flow_hairpin_split function defines a pointer called addr that
points to the list of items.
When the function wants to progress in the list, it adds the size of an
item to the pointer.
At the end of the function, it precedes the pointer one more time even
though it is not used afterwards. In fact, this line is unaffected and
the operation of the function would have been no different without it.
Remove the line where the pointer is preceded unnecessarily.
Fixes: d85c7b5ea5 ("net/mlx5: split hairpin flows")
Cc: stable@dpdk.org
Signed-off-by: Michael Baum <michaelba@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
The flow_dv_translate_item_nvgre function add NVGRE item to matcher and
to the value.
It defines a pointer named nvrge_m that receives the item's mask into
it, and then copies some of it to the matcher.
Before copying, it checks for mask validation, and in case the mask is
NULL the function gives it a pointer to rte_flow_item_nvgre_mask.
However, the function calls from the vni mask's field before the check,
and if there is no mask, it actually does dereference to the NULL
pointer and indeed the program crashes with segfault.
Move the call from the vni field to post-validation.
Fixes: cd18e1b72f ("net/mlx5: fix build on Arm")
Cc: stable@dpdk.org
Signed-off-by: Michael Baum <michaelba@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
The mlx5_flow_action_copy_mreg structure contains a field called src
type enum modify_reg, similarly the mlx5_rte_flow_item_tag field
contains a field called id type enum modify_reg.
The enum modify_reg variable represents different registers in the
system and it also has a field called REG_NONE whose value is 0 which
means that the register does not exist.
The flow_mreg_add_copy_action function sets a variable of struct
mlx5_flow_action_copy_mreg type, and initializes the src field to be 0.
Similarly the flow_create_split_metadata function sets a variable of
struct mlx5_rte_flow_item_tag type and initializes the id field to be 0.
In both functions, they initialize a enum modify_reg type variable with
an int type value while modify_reg has an appropriate field for that
value (REG_NONE).
Replace assigning 0 with REG_NONE in both functions.
Fixes: dd3c774f6f ("net/mlx5: add metadata register copy table")
Fixes: 71e254bc02 ("net/mlx5: split Rx flows to provide metadata copy")
Cc: stable@dpdk.org
Signed-off-by: Michael Baum <michaelba@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Currently, the counter query requires the counter ID should start
with 4 aligned. In none-batch mode, the counter pool might have the
chance to get the counter ID not 4 aligned. In this case, the counter
should be skipped, or the query will be failed.
Skip the counter with ID not 4 aligned as the first counter in the
none-batch count pool to avoid invalid counter query. Once having
new min_dcs ID in the poll less than the skipped counters, the
skipped counters will be returned to the pool free list to use.
Fixes: 5382d28c21 ("net/mlx5: accelerate DV flow counter transactions")
Cc: stable@dpdk.org
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Currently, when allocate the counter or counter based age from group 0,
counter and age may share the same counter dcs ID range. Both age and
pure counter need to sync up with each other's container to check if
the ID range exists and update the min_dcs.
It comes two disadvantages:
1. If the ID range is shared, this counter range will be queried twice
both from age and pure counter container in 1s.
2. The same range counter check between the two container makes the
counter allocate sync min_dcs time to time with extra min_dcs
updating.
This patch avoid the same ID range to be shared when allocate the new
pool. If the same ID range exists in other container, just add the
counter to the other container until get new range which saves the
min_dcs sync up time to time.
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
When Rx/Tx queue was being created with DevX the allocated
doorbell record size was only uint64_t. That was definitely
less than size of CPU cacheline and it might have happened the
doorbell records attached to different queues handled by
different cores were allocated within same cacheline. It might
have caused the contention on doorbell record writing.
This patch extends the allocated memory size for doorbell
record to cacheline size.
Fixes: 21cae8580f ("net/mlx5: allocate door-bells via DevX")
Cc: stable@dpdk.org
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
flow_dv_get_item_len returns the actual header size of
an rte_flow item.
Changing any of the structs for rte_flow items by adding
or removing some extra fields will break this function.
This fixes the behavior by returning the actual header size
of each item.
Fixes: 34d41b7aa3 ("net/mlx5: add VXLAN encap action to Direct Verbs")
Cc: stable@dpdk.org
Signed-off-by: Raslan Darawsheh <rasland@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
RXQ interrupts under Linux are based on the epoll mechanism. An expected
order of operations is as follows:
1. Call rte_eth_dev_rx_intr_enable(), to arm the CQ for receiving events
on data input.
2. Block on rte_epoll_wait() with an array of file descriptors
representing the CQ events. Upon data arrival the kernel will signal
an input event on the corresponding CQ fd.
3. Call rte_eth_dev_rx_intr_disable() after the event was received and
continue in polling mode. The mlx5 implementation of
rte_eth_dev_rx_intr_disable() is to get the CQ event and ack it.
In practice applications may wake up from rte_epoll_wait() due to
timeout with no event to ack but still call
rte_eth_dev_rx_intr_disable() unconditionally. In such cases the call
should return EAGAIN (since the file descriptors are non-blocked), as
opposed to EINVAL which indicates a real failure. In case of EAGAIN the
PMD should not warn on "Unable to disable interrupt on Rx queue".
This commit fixes a earlier commit where the returned value 0 from
function devx_get_event() - was considered an error.
Fixes: 08d1838f64 ("net/mlx5: implement CQ for Rx using DevX API")
Signed-off-by: Ophir Munk <ophirmu@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Raslan Darawsheh <rasland@mellanox.com>
This patch fixed the issue that rx/tx bytes overflowed
on 40 bit limitation by enlarging the limitation.
Fixes: a37bde5631 ("net/ice: support statistics")
Cc: stable@dpdk.org
Signed-off-by: Junyu Jiang <junyux.jiang@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Following the new RegEx class.
There is a need to create a dedicated test application in order to
validate this class and PMD.
Unlike net device this application loads data from a file.
This commit introduces the new RegEx test app.
The basic app flow:
1. Configure the RegEx device to use one queue, and set the rule
database, using precompiled file.
2. Allocate mbufs based on the requested number of jobs, each job will
i get one mbuf.
3. Enqueue as much as possible jobs.
4. Dequeue jobs.
5. if the number of dequeue jobs < requested number of jobs job to step
Signed-off-by: Ori Kam <orika@mellanox.com>
Signed-off-by: Yuval Avnery <yuvalav@mellanox.com>
When enqueueing a buffer the PMD check if there is room
in its send queue (SQ).
The current implementation did not take into account that
queue indices are wrapping around, which may result in
consumer index (sq->ci) can have bigger value than than
the producer index (sq->pi).
Fixes: 4d4e245ad6 ("regex/mlx5: support enqueue")
Signed-off-by: Yuval Avnery <yuvalav@mellanox.com>
Acked-by: Ori Kam <orika@mellanox.com>
rte_smp_mb() uses the same locked ADD as the in-kernel vmbus driver,
and it has slightly performance improvement over rte_mb().
Signed-off-by: Long Li <longli@microsoft.com>
