CN10K platform supports different stats for HW bandwidth profiles.
Implement RoC API to get index for given stats type.
Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
To maintain chain of bandwidth profiles, they needs to be
connected. Implement RoC API to connect two bandwidth profiles
at different levels.
Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
For initial coloring of input packet, CN10K platform maintains
precolor table for VLAN, DSCP and Generic. Implement RoC
interface to setup pre color table.
Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Implement RoC API to dump bandwidth profile on CN10K
platform.
Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Implement RoC API to enable or disable HW bandwidth profiles
on CN10K platform.
Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Implement RoC API to configure HW bandwidth profile for
CN10K platform.
Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Implement RoC interface to free HW bandwidth profiles on
CN10K platform.
Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Implement RoC API to allocate HW resources i.e. bandwidth
profiles for policer processing on CN10K platform.
Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Implement interface to get available profile count for given
NIXLF.
Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
CN10K platform supports policer up to 3 level of hierarchy.
Implement RoC API to get corresponding index for given level.
Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
To support ingress policer on CN10K, MBOX interfaces and HW
definitions updated.
Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Acked-by: Ray Kinsella <mdr@ashroe.eu>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Using fast metadata and userdata flags instead of
driver callbacks for set_pkt_metadata and
get_userdata in inline IPsec.
Signed-off-by: Tejasree Kondoj <ktejasree@marvell.com>
Acked-by: Anoob Joseph <anoobj@marvell.com>
The RSS expansion algorithm is using a graph to find the possible
expansion paths. The current implementation does not differentiate
between standard (L2) VXLAN and L3 VXLAN. As result the flow is expanded
with all possible paths.
For example:
testpmd> flow create... / vxlan / end actions rss level 2 / end
It is currently expanded to the following paths:
ETH IPV4 UDP VXLAN END
ETH IPV4 UDP VXLAN ETH IPV4 END
ETH IPV4 UDP VXLAN ETH IPV6 END
ETH IPV4 UDP VXLAN IPV4 END
ETH IPV4 UDP VXLAN IPV6 END
The fix is to adjust the expansion according to the outer UDP destination
port. In case flow pattern defines a match on the standard udp port, 4789,
or does not define a match on the destination port, which also implies
setting the standard one, the expansion for the above example will be:
ETH IPV4 UDP VXLAN END
ETH IPV4 UDP VXLAN ETH IPV4 END
ETH IPV4 UDP VXLAN ETH IPV6 END
Otherwise, the expansion will be:
ETH IPV4 UDP VXLAN END
ETH IPV4 UDP VXLAN IPV4 END
ETH IPV4 UDP VXLAN IPV6 END
Fixes: f4f06e3615 ("net/mlx5: add flow VXLAN item")
Cc: stable@dpdk.org
Signed-off-by: Lior Margalit <lmargalit@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Rx descriptor is 16B/32B in size. If the DD bit is set, it indicates
that the rest of the descriptor words have valid values. Hence, the
word containing DD bit must be read first before reading the rest of
the descriptor words.
In NEON vector PMD, vector load loads two contiguous 8B of
descriptor data into vector register. Given vector load ensures no
16B atomicity, read of the word that includes DD field could be
reordered after read of other words. In this case, some words could
contain invalid data.
Read barrier is added after read of qword1 that includes DD field.
And qword0 is reloaded to update vector register. This ensures
that the fetched data is correct.
Testpmd single core test on N1SDP/ThunderX2 showed no performance drop.
Fixes: ae0eb310f2 ("net/i40e: implement vector PMD for ARM")
Cc: stable@dpdk.org
Signed-off-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
To keep flow format uniform with ice, this patch adds support for
this RSS rule:
flow create 0 ingress pattern eth / ipv6 / ipv6_frag_ext / end \
actions rss types ipv6-frag end queues end queues end / end
Fixes: ef4c16fd91 ("net/i40e: refactor RSS flow")
Cc: stable@dpdk.org
Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
The common header file for vectorization is included in multiple files,
and so must use macros for the current compilation unit, rather than the
compiler-capability flag set for the whole driver. With the current,
incorrect, macro, the AVX512 or AVX2 flags may be set when compiling up
SSE code, leading to compilation errors. Changing from "CC_AVX*_SUPPORT"
to the compiler-defined "__AVX*__" macros fixes this issue. In addition,
splitting AVX-specific code into the new ice_rxtx_common_avx.h header
file to avoid such bugs.
Bugzilla ID: 788
Fixes: a4e480de26 ("net/ice: optimize Tx by using AVX512")
Fixes: 20daa1c978 ("net/ice: fix crash in AVX512")
Cc: stable@dpdk.org
Signed-off-by: Leyi Rong <leyi.rong@intel.com>
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
The common header file for vectorization is included in multiple files,
and so must use macros for the current compilation unit, rather than the
compiler-capability flag set for the whole driver. With the current,
incorrect, macro, the AVX512 or AVX2 flags may be set when compiling up
SSE code, leading to compilation errors. Changing from "CC_AVX*_SUPPORT"
to the compiler-defined "__AVX*__" macros fixes this issue. In addition,
splitting AVX-specific code into the new i40e_rxtx_common_avx.h header
file to avoid such bugs.
Bugzilla ID: 788
Fixes: 0604b1f220 ("net/i40e: fix crash in AVX512")
Cc: stable@dpdk.org
Signed-off-by: Leyi Rong <leyi.rong@intel.com>
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
After the meter policies are created, they are not freed on device
close.
This patch fixes it.
Fixes: 5f0d54f372 ("ethdev: add pre-defined meter policy API")
Cc: stable@dpdk.org
Signed-off-by: Dapeng Yu <dapengx.yu@intel.com>
Acked-by: Jasvinder Singh <jasvinder.singh@intel.com>
This version update contains:
* Fix for verification of the offload capabilities (especially for
IPv6 packets).
* Support for Tx and Rx free threshold values.
* Fixes for per-queue offload capabilities.
* Announce support of the scattered Rx offload.
* NUMA aware allocations.
* Check for the missing Tx completions.
Signed-off-by: Michal Krawczyk <mk@semihalf.com>
In some cases Tx descriptors may be uncompleted by the HW and as a
result they will never be released.
This patch adds checking for the missing Tx completions to the ENA timer
service, so in order to use this feature, the application must call the
function rte_timer_manage().
Missing Tx completion reset threshold is determined dynamically, by
taking into consideration ring size and the default value.
Tx cleanup is associated with the Tx burst function. As DPDK
applications can call Tx burst function dynamically, time when last
cleanup was called must be traced to avoid false detection of the
missing Tx completion.
Signed-off-by: Michal Krawczyk <mk@semihalf.com>
Reviewed-by: Igor Chauskin <igorch@amazon.com>
Reviewed-by: Shai Brandes <shaibran@amazon.com>
Only the IO rings memory was allocated with taking the socket ID into
the respect, while the other structures was allocated using the regular
rte_zmalloc() API.
Ring specific structures are now being allocated using the ring's
socket ID.
Signed-off-by: Michal Krawczyk <mk@semihalf.com>
Reviewed-by: Igor Chauskin <igorch@amazon.com>
Reviewed-by: Shai Brandes <shaibran@amazon.com>
ENA can't be forced to always pass single descriptor for the Rx packet.
Even if the passed buffer size is big enough to hold the data, we can't
make assumption that the HW won't use extra descriptor because of
internal optimizations. This assumption may be true, but only for some
of the FW revisions, which may differ depending on the used AWS instance
type.
As the scattered Rx support on the Rx path already exists, the driver
just needs to announce DEV_RX_OFFLOAD_SCATTER capability by turning on
the rte_eth_dev_data::scattered_rx option.
Fixes: 1173fca25a ("ena: add polling-mode driver")
Cc: stable@dpdk.org
Signed-off-by: Michal Krawczyk <mk@semihalf.com>
Reviewed-by: Igor Chauskin <igorch@amazon.com>
Reviewed-by: Shai Brandes <shaibran@amazon.com>
As ENA currently doesn't support offloads which could be configured
per-queue, only per-port flags should be set.
In addition, to make the code cleaner, parsing appropriate offload
flags is encapsulated into helper functions, in a similar matter it's
done by the other PMDs.
[1] https://doc.dpdk.org/guides/prog_guide/
poll_mode_drv.html?highlight=offloads#hardware-offload
Fixes: 7369f88f88 ("net/ena: convert to new Rx offloads API")
Fixes: 56b8b9b7e5 ("net/ena: convert to new Tx offloads API")
Cc: stable@dpdk.org
Signed-off-by: Michal Krawczyk <mk@semihalf.com>
Reviewed-by: Igor Chauskin <igorch@amazon.com>
Reviewed-by: Shai Brandes <shaibran@amazon.com>
The caller can pass Tx or Rx free threshold value to the configuration
structure for each ring. It determines when the Tx/Rx function should
start cleaning up/refilling the descriptors. ENA was ignoring this value
and doing it's own calculations.
Now the user can configure ENA's behavior using this parameter and if
this variable won't be set, the ENA will continue with the old behavior
and will use it's own threshold value.
The default value is not provided by the ENA in the ena_infos_get(), as
it's being determined dynamically, depending on the requested ring size.
Note that NULL check for Tx conf was removed from the function
ena_tx_queue_setup(), as at this place the configuration will be
either provided by the user or the default config will be used and it's
handled by the upper (rte_ethdev) layer.
Tx threshold shouldn't be used for the Tx cleanup budget as it can be
inadequate to the used burst. Now the PMD tries to release mbufs for the
ring until it will be depleted.
Signed-off-by: Michal Krawczyk <mk@semihalf.com>
Reviewed-by: Igor Chauskin <igorch@amazon.com>
Reviewed-by: Shai Brandes <shaibran@amazon.com>
ENA PMD has multiple checksum offload flags, which are more discrete
than the DPDK offload capabilities flags.
As the driver wasn't storing it's internal checksum offload capabilities
and was relying only on the DPDK capabilities, not all scenarios could
be properly covered (like when to prepare pseudo header checksum and
when not).
Moreover, the user could request offload capability, which isn't
supported by the HW and the PMD would quietly ignore the issue.
This commit reworks eth_ena_prep_pkts() function to perform additional
checks and to properly reflect the HW requirements. With the
RTE_LIBRTE_ETHDEV_DEBUG enabled, the function will do even more
verifications, to help the user find any issues with the mbuf
configuration.
Fixes: b3fc5a1ae1 ("net/ena: add Tx preparation")
Cc: stable@dpdk.org
Signed-off-by: Michal Krawczyk <mk@semihalf.com>
Reviewed-by: Igor Chauskin <igorch@amazon.com>
Reviewed-by: Shai Brandes <shaibran@amazon.com>
In sfc, MAE admin serves as a transfer proxy. In order to track which
ethdev is privileged, augment every independent switch port structure
with information about its MAE privilege.
Signed-off-by: Viacheslav Galaktionov <viacheslav.galaktionov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Reviewed-by: Andy Moreton <amoreton@xilinx.com>
Register unprivileged ports in the switch domain registry in order to
allow redirecting traffic to them.
Differentiate between different levels of MAE support, update all MAE
status checks.
Signed-off-by: Viacheslav Galaktionov <viacheslav.galaktionov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Reviewed-by: Andy Moreton <amoreton@xilinx.com>
In order to differentiate between privileged and unprivileged MAE clients,
add a separate boolean flag to represent a NIC's MAE privilege level.
Allow initializing unprivileged MAE clients by avoiding calls to functions
that can only be called by the admin NIC.
Signed-off-by: Viacheslav Galaktionov <viacheslav.galaktionov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Reviewed-by: Andy Moreton <amoreton@xilinx.com>
Removing 'DEV_RX_OFFLOAD_JUMBO_FRAME' offload flag.
Instead of drivers announce this capability, application can deduct the
capability by checking reported 'dev_info.max_mtu' or
'dev_info.max_rx_pktlen'.
And instead of application setting this flag explicitly to enable jumbo
frames, this can be deduced by driver by comparing requested 'mtu' to
'RTE_ETHER_MTU'.
Removing this additional configuration for simplification.
Suggested-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Reviewed-by: Rosen Xu <rosen.xu@intel.com>
Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Huisong Li <lihuisong@huawei.com>
Acked-by: Hyong Youb Kim <hyonkim@cisco.com>
Acked-by: Michal Krawczyk <mk@semihalf.com>
Move requested MTU value check to the API to prevent the duplicated
code.
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Reviewed-by: Rosen Xu <rosen.xu@intel.com>
Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Setting MTU bigger than RTE_ETHER_MTU requires the jumbo frame support,
and application should enable the jumbo frame offload support for it.
When jumbo frame offload is not enabled by application, but MTU bigger
than RTE_ETHER_MTU is requested there are two options, either fail or
enable jumbo frame offload implicitly.
Enabling jumbo frame offload implicitly is selected by many drivers
since setting a big MTU value already implies it, and this increases
usability.
This patch moves this logic from drivers to the library, both to reduce
the duplicated code in the drivers and to make behaviour more visible.
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Reviewed-by: Rosen Xu <rosen.xu@intel.com>
Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Huisong Li <lihuisong@huawei.com>
There is a confusion on setting max Rx packet length, this patch aims to
clarify it.
'rte_eth_dev_configure()' API accepts max Rx packet size via
'uint32_t max_rx_pkt_len' field of the config struct 'struct
rte_eth_conf'.
Also 'rte_eth_dev_set_mtu()' API can be used to set the MTU, and result
stored into '(struct rte_eth_dev)->data->mtu'.
These two APIs are related but they work in a disconnected way, they
store the set values in different variables which makes hard to figure
out which one to use, also having two different method for a related
functionality is confusing for the users.
Other issues causing confusion is:
* maximum transmission unit (MTU) is payload of the Ethernet frame. And
'max_rx_pkt_len' is the size of the Ethernet frame. Difference is
Ethernet frame overhead, and this overhead may be different from
device to device based on what device supports, like VLAN and QinQ.
* 'max_rx_pkt_len' is only valid when application requested jumbo frame,
which adds additional confusion and some APIs and PMDs already
discards this documented behavior.
* For the jumbo frame enabled case, 'max_rx_pkt_len' is an mandatory
field, this adds configuration complexity for application.
As solution, both APIs gets MTU as parameter, and both saves the result
in same variable '(struct rte_eth_dev)->data->mtu'. For this
'max_rx_pkt_len' updated as 'mtu', and it is always valid independent
from jumbo frame.
For 'rte_eth_dev_configure()', 'dev->data->dev_conf.rxmode.mtu' is user
request and it should be used only within configure function and result
should be stored to '(struct rte_eth_dev)->data->mtu'. After that point
both application and PMD uses MTU from this variable.
When application doesn't provide an MTU during 'rte_eth_dev_configure()'
default 'RTE_ETHER_MTU' value is used.
Additional clarification done on scattered Rx configuration, in
relation to MTU and Rx buffer size.
MTU is used to configure the device for physical Rx/Tx size limitation,
Rx buffer is where to store Rx packets, many PMDs use mbuf data buffer
size as Rx buffer size.
PMDs compare MTU against Rx buffer size to decide enabling scattered Rx
or not. If scattered Rx is not supported by device, MTU bigger than Rx
buffer size should fail.
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Acked-by: Somnath Kotur <somnath.kotur@broadcom.com>
Acked-by: Huisong Li <lihuisong@huawei.com>
Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Rosen Xu <rosen.xu@intel.com>
Acked-by: Hyong Youb Kim <hyonkim@cisco.com>
Build error:
../drivers/net/enic/enic_fm_flow.c: In function 'enic_fm_flow_parse':
../drivers/net/enic/enic_fm_flow.c:1467:24:
error: 'dev' may be used uninitialized in this function
[-Werror=maybe-uninitialized]
struct rte_eth_dev *dev;
^~~
../drivers/net/enic/enic_fm_flow.c:1580:24:
error: 'dev' may be used uninitialized in this function
[-Werror=maybe-uninitialized]
struct rte_eth_dev *dev;
^~~
../drivers/net/enic/enic_fm_flow.c:1599:24:
error: 'dev' may be used uninitialized in this function
[-Werror=maybe-uninitialized]
struct rte_eth_dev *dev;
^~~
Build error looks like false positive, but to silence the compiler
initializing the pointer with NULL.
Bugzilla ID: 812
Fixes: 54bd4ebe8b ("net/enic: support meta flow actions to overrule destinations")
Reported-by: David Marchand <david.marchand@redhat.com>
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Reviewed-by: David Marchand <david.marchand@redhat.com>
Since AARCH32 extension is not implemented on octeontx2 family, only
enable build for 64bit.
Due to Linux kernel AF(Admin Function) driver dependency, only enable
build for 64-bit Linux.
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Since AARCH32 extension is not implemented on octeontx family, only
enable build for 64bit.
Due to Linux kernel AF(Admin function) driver dependency, only enable
build for 64-bit Linux.
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Since AARCH32 extension is not implemented on thunderx family, only
enable build for 64bit.
Due to Linux kernel AF(Admin function) driver dependency, only enable
build for Linux.
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
When release Tx queue, Rx queue data got freed because wrong Tx queue
data located.
This patch fixes the wrong Tx queue data location.
Fixes: 7483341ae5 ("ethdev: change queue release callback")
Signed-off-by: Xueming Li <xuemingl@nvidia.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Fate actions are different per domain.
When all the domains, ingress, egress and FDB (transfer),
can support all the policy actions, i.e. [SET_TAG],
the policy prepares resources for all the domains and
failure happens if one of the domains misses its fate action
in the policy action list.
Remove the domains missing their fate action
from the meter policy preparation.
Now, the policy will prepare a domain only when the domain supports
all the actions and when one of the domain fate actions is on the list.
Fixes: afb4aa4f12 ("net/mlx5: support meter policy operations")
Cc: stable@dpdk.org
Signed-off-by: Li Zhang <lizh@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
This patch fixes coverity issue by avoiding use of null pointer
in taking false branch.
Coverity issue: 373360
Fixes: 437dbd2fd4 ("net/ice: support 1PPS")
Signed-off-by: Simei Su <simei.su@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
In function ice_dcf_stop_queues(), RX queues and TX queues are actually
not freed, so their pointers shall not be set to NULL when queues are
stopped.
This patch adds function call to free queues on DCF device close,
which also set the RX and TX queues' pointers to NULL on freeing
queues, and avoids referring to the released resource when device is
started again.
Fixes: 1a86f4dbdf ("net/ice: support DCF device reset")
Cc: stable@dpdk.org
Signed-off-by: Dapeng Yu <dapengx.yu@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
If flow redirect failed, the spinlock will not be unlocked.
This patch fixes it.
Fixes: bc9201388d ("net/ice: support flow redirect")
Cc: stable@dpdk.org
Signed-off-by: Dapeng Yu <dapengx.yu@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
The Timestamp Overlay feature is available only in 32B Flex Descriptors.
This patch adds compile option when in 16B Flex Descriptors.
Fixes: 953e74e6b7 ("net/ice: enable Rx timestamp on flex descriptor")
Fixes: 646dcbe6c7 ("net/ice: support IEEE 1588 PTP")
Signed-off-by: Simei Su <simei.su@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Null-checking "p" suggests that it may be null, but it has already
been dereferenced on all paths leading to the check. Thus correct
the code lines and remove the redundant line.
Fixes: c84f8aa210 ("net/ice/base: add parser runtime skeleton")
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Firmware 8.4+ will return I40E_AQ_RC_ENOENT when try to delete
non-existent MAC/VLAN addresses from the HW filtering, this should
not be considered as an Admin Queue error. But in i40e_asq_send_command,
it will return I40E_ERR_ADMIN_QUEUE_ERROR if the return value of Admin
Queue command processed by Firmware is not I40E_AQ_RC_OK or
I40E_AQ_RC_EBUSY.
Use i40e_aq_remove_macvlan_v2 instead so that we can get the
corresponding Admin Queue status, and not report as an error in DPDK
when Firmware return I40E_AQ_RC_ENOENT, and this also not break with an
old firmware.
Signed-off-by: Robin Zhang <robinx.zhang@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Adjust the code line order of the parser runtime reset, since the
struct rt->psr is used in function _rt_flag_set before assignment.
Fixes: c84f8aa210 ("net/ice/base: add parser runtime skeleton")
Cc: stable@dpdk.org
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Some drivers do not provide per-queue statistics. So, there is no point
to have these misleading zeros in xstats.
Fixes: f30e69b41f ("ethdev: add device flag to bypass auto-filled queue xstats")
Cc: stable@dpdk.org
Signed-off-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Parse inner L2 length to set correct packet type, and ensure that
hardware can compute the checksum successfully.
Fixes: b950203be7 ("net/txgbe: support VXLAN-GPE")
Cc: stable@dpdk.org
Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Setting exact link speed makes sense if auto-negotiation is
disabled. Fixed flag is required to disable auto-negotiation.
Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
It's necessary to set 1 on TXGBE_PX_INTA register to get interrupts
normally, when legacy interrupt mode is used.
Fixes: 2fc745e6b6 ("net/txgbe: add interrupt operation")
Cc: stable@dpdk.org
Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Update immediate value/pointer source operand support
for modify field RTE Flow action:
- source operand data can be presented by byte buffer
(instead of former uint64_t) or by pointer
- no host byte ordering is assumed anymore for immediate
data buffer (not uint64_t anymore)
- no immediate value offset is expected (the source
subfield is located at the same offset as in destination)
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
Setting 'RTE_LIBRTE_BNXT_TRUFLOW_DEBUG' macro cause build error,
removing it.
Also with meson build system compile time debug macros should be
documented in driver documentation, since there is no other way to
figure out their existence.
Fixes: ad9eed0248 ("net/bnxt: support flow template for Thor")
Cc: stable@dpdk.org
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reported by "gcc (GCC) 12.0.0 20211003 (experimental)":
./drivers/net/softnic/rte_eth_softnic_cli.c:
In function ‘tmgr_hierarchy_default’:
./drivers/net/softnic/rte_eth_softnic_cli.c:634:73:
error: the comparison will always evaluate as ‘true’ for the
address of ‘tc_valid’ will never be NULL [-Werror=address]
634 | (¶ms->shared_shaper_id.tc_valid[0]) ? 1 : 0,
| ^
Fixing it by removing useless check.
Fixes: 1af2dc5111 ("net/softnic: add command for default tmgr hierarchy")
Fixes: 5eb676d74f ("net/softnic: add config flexibility to TM")
Cc: stable@dpdk.org
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Jasvinder Singh <jasvinder.singh@intel.com>
Add support for item PORT_REPRESENTOR which should
be used instead of ambiguous item PORT_ID.
Signed-off-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Action PORT_ID implementation assumes ingress only. Its semantics
suggests that support for equal action PORT_REPRESENTOR be added.
Signed-off-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Semantics of the existing support for action PORT_ID suggests
that support for equal action REPRESENTED_PORT be implemented.
Helper functions keep port_id suffix since action
MLX5_FLOW_ACTION_PORT_ID is still used internally.
Signed-off-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Add support for actions PORT_REPRESENTOR and REPRESENTED_PORT
based on the existing support for action PORT_ID.
Signed-off-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Acked-by: Hyong Youb Kim <hyonkim@cisco.com>
Add support for actions PORT_REPRESENTOR and REPRESENTED_PORT
based on the existing support for action PORT_ID.
Signed-off-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Add support for items PORT_REPRESENTOR and REPRESENTED_PORT
based on the existing support for item PORT_ID.
The use of item PORT_ID depends on the specified direction attribute.
Items PORT_REPRESENTOR and REPRESENTED_PORT, in turn, define traffic
direction themselves. The former matches traffic from the driver's
vNIC. The latter matches packets from either a v-port (network) or
a VF's vNIC (if the driver's port is a VF representor).
Signed-off-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Move rte_eth_dev, rte_eth_dev_data, rte_eth_rxtx_callback and related
data into private header (ethdev_driver.h).
Few minor changes to keep DPDK building after that.
Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Tested-by: Feifei Wang <feifei.wang2@arm.com>
Currently majority of fast-path ethdev ops take pointers to internal
queue data structures as an input parameter.
While eth_rx_queue_count() takes a pointer to rte_eth_dev and queue
index.
For future work to hide rte_eth_devices[] and friends it would be
plausible to unify parameters list of all fast-path ethdev ops.
This patch changes eth_rx_queue_count() to accept pointer to internal
queue data as input parameter.
While this change is transparent to user, it still counts as an ABI change,
as eth_rx_queue_count_t is used by ethdev public inline function
rte_eth_rx_queue_count().
Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Acked-by: Hyong Youb Kim <hyonkim@cisco.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Tested-by: Feifei Wang <feifei.wang2@arm.com>
By design, in a GROUP flow, outer match criteria go to "ENC" fields
of the action rule match specification. The current HW/FW hasn't
got support for these fields (except the VXLAN VNI) yet.
As a workaround, start parsing the pattern from the tunnel item.
Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Such a counter will only report the number of hits, which is actually
a sum of two contributions (the JUMP rule's own counter + indirect
increments issued by counters of the associated GROUP rules.
Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
By design, JUMP flows should be represented solely by the outer rules. But
the HW/FW hasn't got support for setting Rx mark from RECIRC_ID on outer
rule lookup yet. Neither does it support outer rule counters. As a
workaround, an action rule of lower priority is used to do the job.
Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
The current HW/FW doesn't allow to match on MAC addresses in outer rules.
One day this will change for sure, but right now a workaround is needed.
Match on VLAN presence in outer rules is also unsupported. Ignore it.
Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Support generic callbacks which callers will invoke to get
PMD-specific actions and items used to produce JUMP and
GROUP flows and to detect tunnel information.
Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
GROUP is an in-house term for so-called "tunnel_match" flows.
On parsing, they are detected by virtue of PMD-internal item
MARK. It associates a given flow with its tunnel context.
Such a flow is represented by a MAE action rule which is
chained with the corresponding JUMP rule's outer rule
by virtue of matching on its recirculation ID.
GROUP flows do narrower match than JUMP flows do and
decapsulate matching packets (full offload).
Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Currently, there is an API for setting recirculation ID in
outer rules. Add an API to let action rules match on it.
Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
JUMP is an in-house term for so-called "tunnel_set" flows. On parsing,
they are identified by virtue of actions MARK (PMD-internal) and JUMP.
The action MARK associates a given flow with its tunnel context.
Such a flow is represented by a MAE outer rule (OR) which has its
recirculation ID set. This ID is also associated with the tunnel
context. The OR is supposed to set this ID in 8 high bits of
Rx mark in matching packets. It also counts the packets.
Packets that hit the OR but miss in action rule (AR) table,
should go to MAE admin PF (that is, to DPDK) by default.
Support for the use of action COUNT in JUMP
flows will be introduced by later patches.
Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
When an outer rule is hit, it can pass recirculation ID down
to action rule lookup, and action rules can match on this ID
instead of matching on the outer rule allocation handle.
By default, recirculation ID is assumed to be zero.
Add an API to set recirculation ID in outer rules.
Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Acked-by: Ray Kinsella <mdr@ashroe.eu>
Later patches add support for tunnel offload on Riverhead (EF100).
A board can host at most 254 tunnels. Partially offloaded (missed)
tunnel packets are identified by virtue of 8 high bits in Rx mark.
Add basic definitions of the upcoming tunnel offload support and
take care of the dedicated bits in Rx mark across the driver.
Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Reviewed-by: Andy Moreton <amoreton@xilinx.com>
vnic_dev_capable_filter_mode() currently fails when
CMD_CAPABILITY(CMD_ADD_FILTER) returns ERR_EPERM. In turn, this
failure causes the driver initialization to fail.
But, firmware may legitimately return ERR_EPERM. For example, VF vNIC
returns ERR_EPERM when it does not support filtering at all. So, treat
ERR_EPERM as "no filtering available" instead of an unexpected error.
Fixes: 322b355f21 ("net/enic/base: bring NIC interface functions up to date")
Cc: stable@dpdk.org
Signed-off-by: Hyong Youb Kim <hyonkim@cisco.com>
Reviewed-by: John Daley <johndale@cisco.com>
The intr_handle->intr_vec is allocated by rte_zmalloc(), but freed by
free(), this patch fixes it.
Fixes: 02a7b55657 ("net/hns3: support Rx interrupt")
Cc: stable@dpdk.org
Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Detect the flag in Rx prefix and pass it to users.
Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Reviewed-by: Andy Moreton <amoreton@xilinx.com>
Add an RxQ flag to request support for user flag field of Rx
prefix. The feature is supported only on EF100 and EF10 ESSB.
Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Reviewed-by: Andy Moreton <amoreton@xilinx.com>
MAE counter engine gets generation counts by virtue of the mark,
so the code to extract the field is already in place, but flow
action MARK doesn't benefit from it. Support this use case, too.
Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Reviewed-by: Andy Moreton <amoreton@xilinx.com>
Initial support for the method. Later patches will extend it to
make FLAG and MARK delivery available on EF100 native datapath.
Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Reviewed-by: Andy Moreton <amoreton@xilinx.com>
Enhance support for RSS action in the non-TruFlow path.
This will allow the user or application to update the RSS settings
using RTE_FLOW API.
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Lance Richardson <lance.richardson@broadcom.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Fix Rx queue state on device start.
The state of Rx queues could be incorrect in some cases
because instead of updating the state for all the Rx queues,
we are updating it for queues in a VNIC.
Fixes: 0105ea1296 ("net/bnxt: support runtime queue setup")
Cc: stable@dpdk.org
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Lance Richardson <lance.richardson@broadcom.com>
Aggregation rings are needed when PMD needs to support jumbo frames, LRO.
Currently we are creating the aggregation rings whether jumbo frames or
LRO has been enabled or disabled. This causes unnecessary allocation of
mbufs needing larger mbuf pool which is not used at all.
This patch modifies the code to create aggregation rings only when
needed.
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Lance Richardson <lance.richardson@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Support of the keep-CRC offloading by checking
the relevant FW capability (scatter_fcs) for NIC support.
Supported offload:
DEV_RX_OFFLOAD_KEEP_CRC
Signed-off-by: Tal Shnaiderman <talshn@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Tested-by: Idan Hackmon <idanhac@nvidia.com>
mlx5 in Windows needs the hca capability scatter_fcs
to query the NIC support for the CRC keeping offload.
Added the capability as part of the capabilities
queried by the PMD using DevX.
Signed-off-by: Tal Shnaiderman <talshn@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Tested-by: Idan Hackmon <idanhac@nvidia.com>
Support of the VLAN stripping offloading by checking
the relevant FW capability (vlan_cap) for NIC support.
Supported offload:
DEV_RX_OFFLOAD_VLAN_STRIP
Signed-off-by: Tal Shnaiderman <talshn@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Tested-by: Idan Hackmon <idanhac@nvidia.com>
mlx5 in Windows needs the hca capability vlan_cap
to query the NIC for VLAN stripping support
Added the capability as part of the capabilities
queried by the PMD using DevX.
Signed-off-by: Tal Shnaiderman <talshn@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Tested-by: Idan Hackmon <idanhac@nvidia.com>
Support of the TSO offloading by checking
the relevant FW capability for NIC support.
Supported offloads:
DEV_TX_OFFLOAD_TCP_TSO
DEV_TX_OFFLOAD_VXLAN_TNL_TSO
DEV_TX_OFFLOAD_GRE_TNL_TSO
DEV_TX_OFFLOAD_GENEVE_TNL_TSO
Signed-off-by: Tal Shnaiderman <talshn@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Tested-by: Idan Hackmon <idanhac@nvidia.com>
mlx5 in Windows needs the hca capability max_lso_cap
to query the NIC for TSO offloading support.
Added the capability as part of the capabilities
queried by the PMD using DevX.
Signed-off-by: Tal Shnaiderman <talshn@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Tested-by: Idan Hackmon <idanhac@nvidia.com>
Query tunneling supported on the NIC.
Save the offloads values in a config parameter.
This is needed for the following TSO support:
DEV_TX_OFFLOAD_VXLAN_TNL_TSO
DEV_TX_OFFLOAD_GRE_TNL_TSO
DEV_TX_OFFLOAD_GENEVE_TNL_TSO
Signed-off-by: Tal Shnaiderman <talshn@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Tested-by: Idan Hackmon <idanhac@nvidia.com>
mlx5 in Windows needs the tunneling hca capabilities
to query the NIC for Inner TSO offloading support.
Added the capability as part of the capabilities
queried by the PMD using DevX.
Signed-off-by: Tal Shnaiderman <talshn@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Tested-by: Idan Hackmon <idanhac@nvidia.com>
Currently, the PMD decides if the tunneling offload
can enable VXLAN/GRE/GENEVE tunneled TSO support by checking
config->tunnel_en (single bit) and config->tso.
This is incorrect, the right way is to check the following
flags returned by the mlx5dv_query_device function:
MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_VXLAN - if supported the offload
DEV_TX_OFFLOAD_VXLAN_TNL_TSO can be enabled.
MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_GRE - if supported the offload
DEV_TX_OFFLOAD_GRE_TNL_TSO can be enabled.
MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_GENEVE - if supported the offload
DEV_TX_OFFLOAD_GENEVE_TNL_TSO can be enabled.
The fix enables the offloads according to the correct
flags returned by the kernel.
Fixes: dbccb4cddc ("net/mlx5: convert to new Tx offloads API")
Cc: stable@dpdk.org
Signed-off-by: Tal Shnaiderman <talshn@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Tested-by: Idan Hackmon <idanhac@nvidia.com>
Query software parsing supported on the NIC.
Save the offloads values in a config parameter.
This is needed for the outer IPv4 checksum and
IP and UDP tunneled packet TSO support.
Signed-off-by: Tal Shnaiderman <talshn@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Tested-by: Idan Hackmon <idanhac@nvidia.com>
mlx5 in Windows needs the software parsing hca capabilities
to query the NIC for TSO and Checksum offloading support.
Added the capability as part of the capabilities
queried by the PMD using DevX.
Signed-off-by: Tal Shnaiderman <talshn@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Tested-by: Idan Hackmon <idanhac@nvidia.com>
Currently, the PMD decides if the software parsing
offload can enable outer IPv4 checksum and tunneled
TSO support by checking config->hw_csum and config->tso
respectively.
This is incorrect, the right way is to check the following
flags returned by the mlx5dv_query_device function:
MLX5DV_SW_PARSING - check general swp support.
MLX5DV_SW_PARSING_CSUM - check swp checksum support.
MLX5DV_SW_PARSING_LSO - check swp LSO/TSO support.
The fix enables the offloads according to the correct
flags returned by the kernel.
Fixes: e46821e9fc ("net/mlx5: separate generic tunnel TSO from the standard one")
Cc: stable@dpdk.org
Signed-off-by: Tal Shnaiderman <talshn@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Tested-by: Idan Hackmon <idanhac@nvidia.com>
Add helper functions that allow one to check platform
ROC is running on. Platform type is retrieved from device
tree attribute runplatform which is updated by EBF accordingly.
Signed-off-by: Tomasz Duszynski <tduszynski@marvell.com>
Reviewed-by: Jerin Jacob <jerinj@marvell.com>
Maximum interrupt number function used direct access to
structure field while ROC helper exists and serves the
same purpose.
Signed-off-by: Jakub Palider <jpalider@marvell.com>
Reviewed-by: Jerin Jacob <jerinj@marvell.com>
One sends commands and receive responses by enqueuing or dequeuing
custom messages. In order to simplify this scheme simple wrappers
were added which take care of all the heavy lifting.
Signed-off-by: Tomasz Duszynski <tduszynski@marvell.com>
Reviewed-by: Jakub Palider <jpalider@marvell.com>
Reviewed-by: Jerin Jacob <jerinj@marvell.com>
When the iavf_adapter instance is not initialized completely in the
primary process, the secondary process accesses its "rte_eth_dev"
member, it causes secondary process crash.
This patch replaces eth_dev with eth_dev_data in iavf_adapter.
Fixes: f978c1c9b3 ("net/iavf: add RSS hash parsing in AVX path")
Fixes: 9c9aa00403 ("net/iavf: add offload path for Rx AVX512 flex descriptor")
Fixes: 63660ea3ee ("net/iavf: add RSS hash parsing in SSE path")
Cc: stable@dpdk.org
Signed-off-by: Dapeng Yu <dapengx.yu@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
This patch adds some defines related to DDP Track ID.
Signed-off-by: Artur Tyminski <arturx.tyminski@intel.com>
Signed-off-by: Robin Zhang <robinx.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
Update FVL FW API version to 1.15
Signed-off-by: Maciej Paczkowski <maciej.paczkowski@intel.com>
Signed-off-by: Robin Zhang <robinx.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
Add raw format for i40e_32byte_rx_desc, right now this only be used
by kernel driver, the commit is just to sync with kernel driver.
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Robin Zhang <robinx.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
