avoid AltiVec keyword vector

The AltiVec header file is defining "vector", except in C++ build.
The keyword "vector" may conflict easily.
As a rule, it is better to use the alternative keyword "__ve

avoid AltiVec keyword vector

The AltiVec header file is defining "vector", except in C++ build.
The keyword "vector" may conflict easily.
As a rule, it is better to use the alternative keyword "__vector",
so we will be able to #undef vector after including AltiVec header.

Later it may become possible to #undef vector in rte_altivec.h
with a compatibility breakage.

Signed-off-by: Thomas Monjalon <[email protected]>
Reviewed-by: David Christensen <[email protected]>

show more ...

gpu/cuda: unmap GPU memory while freeing

Enable GPU_REGISTERED flag in gpu/cuda driver in the memory list.
If a GPU memory address CPU mapped is freed before being
unmapped, CUDA driver unmaps it be

gpu/cuda: unmap GPU memory while freeing

Enable GPU_REGISTERED flag in gpu/cuda driver in the memory list.
If a GPU memory address CPU mapped is freed before being
unmapped, CUDA driver unmaps it before freeing the memory.

Signed-off-by: Elena Agostini <[email protected]>

show more ...

event/cnxk: flush event queues over multiple pass

If an event queue flush does not complete after a fixed number of tries,
remaining queues are flushed before retrying the one with incomplete
flush.

event/cnxk: flush event queues over multiple pass

If an event queue flush does not complete after a fixed number of tries,
remaining queues are flushed before retrying the one with incomplete
flush.

Signed-off-by: Shijith Thotton <[email protected]>

show more ...

event/cnxk: support setting queue attributes at runtime

Added API to set queue attributes at runtime and API to get weight and
affinity.

Signed-off-by: Shijith Thotton <[email protected]>
Acked-

event/cnxk: support setting queue attributes at runtime

Added API to set queue attributes at runtime and API to get weight and
affinity.

Signed-off-by: Shijith Thotton <[email protected]>
Acked-by: Jerin Jacob <[email protected]>

show more ...

common/cnxk: lock when accessing mbox of SSO

Since mailbox is now accessed from multiple threads, use lock to
synchronize access.

Signed-off-by: Pavan Nikhilesh <[email protected]>
Signed-of

common/cnxk: lock when accessing mbox of SSO

Since mailbox is now accessed from multiple threads, use lock to
synchronize access.

Signed-off-by: Pavan Nikhilesh <[email protected]>
Signed-off-by: Shijith Thotton <[email protected]>

show more ...

event/cnxk: implement event port quiesce function

Implement event port quiesce function to clean up any lcore
resources used.

Signed-off-by: Pavan Nikhilesh <[email protected]>

event/cnxk: move post-processing to separate function

Move event post-processing to a separate function.
Do complete event post-processing in tear-down functions to prevent
incorrect memory free.

S

event/cnxk: move post-processing to separate function

Move event post-processing to a separate function.
Do complete event post-processing in tear-down functions to prevent
incorrect memory free.

Signed-off-by: Pavan Nikhilesh <[email protected]>

show more ...

event/cnxk: add checks in release operation

Add additional checks while performing RTE_EVENT_OP_RELEASE to
ensure that there are no pending SWTAGs and FLUSHEs in flight.

Signed-off-by: Pavan Nikhil

event/cnxk: add checks in release operation

Add additional checks while performing RTE_EVENT_OP_RELEASE to
ensure that there are no pending SWTAGs and FLUSHEs in flight.

Signed-off-by: Pavan Nikhilesh <[email protected]>

show more ...

event/cnxk: fix out of bounds access in test

Fix out of bounds array access reported in coverity scan.

Coverity issue: 375817
Fixes: 2351506401e ("event/cnxk: add SSO selftest and dump")
Cc: stable

event/cnxk: fix out of bounds access in test

Fix out of bounds array access reported in coverity scan.

Coverity issue: 375817
Fixes: 2351506401e ("event/cnxk: add SSO selftest and dump")
Cc: [email protected]

Signed-off-by: Gowrishankar Muthukrishnan <[email protected]>
Acked-by: Jerin Jacob <[email protected]>

show more ...

event/dlb2: allow CQ depths up to 1024

Updated to allow overriding the default CQ depth of 32. Since there are
only 2048 DLB history list entries, increasing the CQ depth decreases
the number of av

event/dlb2: allow CQ depths up to 1024

Updated to allow overriding the default CQ depth of 32. Since there are
only 2048 DLB history list entries, increasing the CQ depth decreases
the number of available LDB ports to 2048/max_cq_depth. Resource query
will take this into account and return the correct maximum number of
LDB ports.

Signed-off-by: Timothy McDaniel <[email protected]>

show more ...

event/cnxk: fix base pointer for SSO head wait

Function roc_sso_hws_head_wait() expects a base as input pointer, and it
will itself get tag_op from the base. By passing tag_op instead of base
pointe

event/cnxk: fix base pointer for SSO head wait

Function roc_sso_hws_head_wait() expects a base as input pointer, and it
will itself get tag_op from the base. By passing tag_op instead of base
pointer to this function will add SSOW_LF_GWS_TAG register offset twice,
which will lead to accessing wrong register.

Fixes: 1f5b3d55c041 ("event/cnxk: store and reuse workslot status")
Cc: [email protected]

Signed-off-by: Volodymyr Fialko <[email protected]>
Acked-by: Jerin Jacob <[email protected]>

show more ...

net/mlx5: support ESP SPI match and RSS hash

In packets with ESP header, the inner IP will be encrypted, and
its fields cannot be used for RSS hashing. So, ESP packets
can be hashed only by the oute

net/mlx5: support ESP SPI match and RSS hash

In packets with ESP header, the inner IP will be encrypted, and
its fields cannot be used for RSS hashing. So, ESP packets
can be hashed only by the outer IP layer.
So, when using RSS on ESP packets, hashing may not be efficient,
because the fields used by the hash functions are only the outer IPs,
causing all traffic belonging to all tunnels between a given
pair of GWs to land on one core.
Adding the SPI hash field can extend the spreading of IPsec packets.

Signed-off-by: Raja Zidane <[email protected]>
Acked-by: Matan Azrad <[email protected]>

show more ...

net/mlx5: fix no-green metering with RSS

When a meter with RSS action being used, there might be several
sub-flows using different sub-policies in the flow splitting stage.
If there's no green actio

net/mlx5: fix no-green metering with RSS

When a meter with RSS action being used, there might be several
sub-flows using different sub-policies in the flow splitting stage.
If there's no green action, there's an error that will always use the
same sub-policy for all sub-flows, some resources will be
overwritten and cannot be released, leading assert during port close.

This patch fixes this issue by checking both green and yellow queue
index during getting a blank sub-policy, to avoid the incorrect
resource overwrite.

Fixes: b38a12272b3a ("net/mlx5: split meter color policy handling")
Cc: [email protected]

Signed-off-by: Shun Hao <[email protected]>
Acked-by: Matan Azrad <[email protected]>

show more ...

net/bnxt: skip wait for link up on port start

Invoking bnxt_link_update_op() with wait_for_completion set would
result in the driver waiting for 10s in case the port link is down to
complete port in

net/bnxt: skip wait for link up on port start

Invoking bnxt_link_update_op() with wait_for_completion set would
result in the driver waiting for 10s in case the port link is down to
complete port initialization (dev_start_op()).
Change it by not waiting for the completion when invoking it in
dev_start_op()

Signed-off-by: Somnath Kotur <[email protected]>
Reviewed-by: Kalesh AP <[email protected]>
Reviewed-by: Ajit Khaparde <[email protected]>

show more ...

net/bnxt: fix freeing VNIC filters

In bnxt_free_all_filters(), all the filters attached to a vnic are removed.
But each of these filters hold a backreference ptr to the vnic and they
need to be rese

net/bnxt: fix freeing VNIC filters

In bnxt_free_all_filters(), all the filters attached to a vnic are removed.
But each of these filters hold a backreference ptr to the vnic and they
need to be reset to NULL now. Otherwise, during a normal testpmd quit, as
part of dev_close_op(), first bnxt_free_all_filters() is invoked in
dev_stop, followed by bnxt_free_filter_mem() from bnxt_uninit_resources(),
which finds a filter with a vnic back reference ptr and now
bnxt_hwrm_clean_up_l2_filter() also tries to remove the filter from the
vnic's filter list which was already done as part of
bnxt_free_all_filters().

Fixes: f0f6b5e6cf94 ("net/bnxt: fix reusing L2 filter")
Cc: [email protected]

Signed-off-by: Somnath Kotur <[email protected]>
Reviewed-by: Kalesh AP <[email protected]>
Reviewed-by: Ajit Khaparde <[email protected]>

show more ...

net/bnxt: recheck FW readiness if in reset process

If Firmware is still in reset process and returns the error
HWRM_ERR_CODE_HOT_RESET_PROGRESS, retry VER_GET command.
We have to do it in bnxt_handl

net/bnxt: recheck FW readiness if in reset process

If Firmware is still in reset process and returns the error
HWRM_ERR_CODE_HOT_RESET_PROGRESS, retry VER_GET command.
We have to do it in bnxt_handle_if_change_status().

Fixes: 0b533591238f ("net/bnxt: inform firmware about IF state changes")
Cc: [email protected]

Signed-off-by: Kalesh AP <[email protected]>
Reviewed-by: Somnath Kotur <[email protected]>
Reviewed-by: Ajit Khaparde <[email protected]>

show more ...

net/bnxt: fix link status when port is stopped

Driver forces link down during port stop. But device is not obliged
link down in certain scenarios, even when forced. In that case,
subsequent link que

net/bnxt: fix link status when port is stopped

Driver forces link down during port stop. But device is not obliged
link down in certain scenarios, even when forced. In that case,
subsequent link queries returns link as up.
Fixed to return link status as down when port is stopped.
Driver is already doing that for VF/NPAR/MH functions.

Fixes: c09f57b49c13 ("net/bnxt: add start/stop/link update operations")
Cc: [email protected]

Signed-off-by: Kalesh AP <[email protected]>
Reviewed-by: Ajit Khaparde <[email protected]>
Reviewed-by: Somnath Kotur <[email protected]>

show more ...

net/bnxt: force PHY update on certain configurations

Device is not obliged link down in certain scenarios, even
when forced. When FW does not allow any user other than the BMC
to shutdown the port,

net/bnxt: force PHY update on certain configurations

Device is not obliged link down in certain scenarios, even
when forced. When FW does not allow any user other than the BMC
to shutdown the port, bnxt_get_hwrm_link_config() call always
returns link up. Force phy update always in that case,
else user configuration for speed/autoneg would not get applied
correctly.

Fixes: 7bc8e9a227cc ("net/bnxt: support async link notification")
Cc: [email protected]

Signed-off-by: Kalesh AP <[email protected]>
Reviewed-by: Ajit Khaparde <[email protected]>
Reviewed-by: Somnath Kotur <[email protected]>

show more ...

net/bnxt: fix speed autonegotiation

The "active_fec_signal_mode" in HWRM_PORT_PHY_QCFG response
does not return correct value till the link is up. Driver cannot
rely on active_fec_signal_mode while

net/bnxt: fix speed autonegotiation

The "active_fec_signal_mode" in HWRM_PORT_PHY_QCFG response
does not return correct value till the link is up. Driver cannot
rely on active_fec_signal_mode while setting autoneg speed.

While setting autoneg speed, driver is currently checking only
"auto_link_speed_mask". Fixed to check "auto_pam4_link_speed_mask"
as well. Also, while setting auto mode and setting speed mask,
driver will have to set both NRZ and PAM4 mask.

Fixes: c23f9ded0391 ("net/bnxt: support 200G PAM4 link")
Cc: [email protected]

Signed-off-by: Kalesh AP <[email protected]>
Reviewed-by: Ajit Khaparde <[email protected]>
Reviewed-by: Somnath Kotur <[email protected]>

show more ...

net/bnxt: avoid unnecessary endianness conversion

The "active_fec_signal_mode" in HWRM_PORT_PHY_QCFG response is uint8_t.
So no need of endianness conversion while parsing response.
Also, signal_mod

net/bnxt: avoid unnecessary endianness conversion

The "active_fec_signal_mode" in HWRM_PORT_PHY_QCFG response is uint8_t.
So no need of endianness conversion while parsing response.
Also, signal_mode is the first 4bits of "active_fec_signal_mode".

Fixes: c23f9ded0391 ("net/bnxt: support 200G PAM4 link")
Cc: [email protected]

Signed-off-by: Kalesh AP <[email protected]>
Reviewed-by: Ajit Khaparde <[email protected]>
Reviewed-by: Somnath Kotur <[email protected]>

show more ...

net/bnxt: handle queue stop during RSS flow create

The programming of the RSS table was not taking into account if
any of the queues in the set were stopped prior to the flow
creation, hence leading

net/bnxt: handle queue stop during RSS flow create

The programming of the RSS table was not taking into account if
any of the queues in the set were stopped prior to the flow
creation, hence leading to a vnic RSS config cmd failure thrown by
the FW.
Fix by programming only the active queues in the RSS action queue
set.

Fixes: 239695f754cb ("net/bnxt: enhance RSS action support")
Cc: [email protected]

Signed-off-by: Somnath Kotur <[email protected]>
Reviewed-by: Ajit Khaparde <[email protected]>
Reviewed-by: Kalesh AP <[email protected]>

show more ...

net/bnxt: check duplicate queue IDs

Currently driver does not have a check for duplicate queue ids.
User must either specify all Rx queues created or no queues in the
flow create command. Repeating

net/bnxt: check duplicate queue IDs

Currently driver does not have a check for duplicate queue ids.
User must either specify all Rx queues created or no queues in the
flow create command. Repeating the queue index is invalid.

Also, moved the check for invalid queue to the beginning of the function.

Fixes: 239695f754cb ("net/bnxt: enhance RSS action support")
Cc: [email protected]

Signed-off-by: Kalesh AP <[email protected]>
Reviewed-by: Ajit Khaparde <[email protected]>
Reviewed-by: Somnath Kotur <[email protected]>

show more ...

net/bnxt: fix ring group on Rx restart

When an Rx queue is stopped and restarted, as part of that workflow,
for cards that have ring groups, we free and reallocate the ring group.
This new ring grou

net/bnxt: fix ring group on Rx restart

When an Rx queue is stopped and restarted, as part of that workflow,
for cards that have ring groups, we free and reallocate the ring group.
This new ring group is not communicated to the VNIC though via
HWRM_VNIC_CFG cmd.
Fix to issue HWRM_VNIC_CFG cmd on all adapters now in this scenario.

Fixes: ed0ae3502fc9 ("net/bnxt: update ring group after ring stop start")
Cc: [email protected]

Signed-off-by: Somnath Kotur <[email protected]>
Reviewed-by: Ajit Khaparde <[email protected]>
Reviewed-by: Kalesh AP <[email protected]>

show more ...

net/bnxt: fix RSS action

Specifying a subset of Rx queues created by the application in
the "flow create" command is invalid.
User must either specify all Rx queues created or no queues.

Also remov

net/bnxt: fix RSS action

Specifying a subset of Rx queues created by the application in
the "flow create" command is invalid.
User must either specify all Rx queues created or no queues.

Also removed a wrong comment as RSS action will not be supported
if user or application specifies MARK or COUNT action.

Fixes: 239695f754cb ("net/bnxt: enhance RSS action support")
Cc: [email protected]

Signed-off-by: Kalesh AP <[email protected]>
Reviewed-by: Somnath Kotur <[email protected]>
Reviewed-by: Ajit Khaparde <[email protected]>

show more ...

net/bnxt: remove count action support

'Count' action was never really implemented in the legacy/AFM model.
But there was some place holder code, remove it so that the user
will see a failure when a

net/bnxt: remove count action support

'Count' action was never really implemented in the legacy/AFM model.
But there was some place holder code, remove it so that the user
will see a failure when a flow with 'count' action is being
created.

Signed-off-by: Somnath Kotur <[email protected]>
Reviewed-by: Kalesh AP <[email protected]>
Reviewed-by: Ajit Khaparde <[email protected]>

show more ...