The mbuf timestamp is moved to a dynamic field
in order to allow removal of the deprecated static field.
The related mbuf flag is also replaced.
The registration of field and flag is done in both
otx2_nix_dev_start() and otx2_nix_timesync_enable().
The dynamic offset and flag are stored in struct otx2_timesync_info
to favor cache locality.
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: David Marchand <david.marchand@redhat.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
Queue stats are stored in 'struct rte_eth_stats' as array and array size
is defined by 'RTE_ETHDEV_QUEUE_STAT_CNTRS' compile time flag.
As a result of technical board discussion, decided to remove the queue
statistics from 'struct rte_eth_stats' in the long term.
Instead PMDs should represent the queue statistics via xstats, this
gives more flexibility on the number of the queues supported.
Currently queue stats in the xstats are filled by ethdev layer, using
some basic stats, when queue stats removed from basic stats the
responsibility to fill the relevant xstats will be pushed to the PMDs.
During the switch period, temporary 'RTE_ETH_DEV_AUTOFILL_QUEUE_XSTATS'
device flag is created. Initially all PMDs using xstats set this flag.
The PMDs implemented queue stats in the xstats should clear the flag.
When all PMDs switch to the xstats for the queue stats, queue stats
related fields from 'struct rte_eth_stats' will be removed, as well as
'RTE_ETH_DEV_AUTOFILL_QUEUE_XSTATS' flag.
Later 'RTE_ETHDEV_QUEUE_STAT_CNTRS' compile time flag also can be
removed.
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Haiyue Wang <haiyue.wang@intel.com>
Acked-by: Xiao Wang <xiao.w.wang@intel.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
Change eth_dev_stop_t return value from void to int.
Make eth_dev_stop_t implementations across all drivers to return
negative errno values if case of error conditions.
Signed-off-by: Ivan Ilchenko <ivan.ilchenko@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
The glibc free allows free(NULL) as null operation,
so remove this useless null checks.
Coverity issue: 357719
Fixes: da138cd47e06 ("net/octeontx2: handle port reconfigure")
Cc: stable@dpdk.org
Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
The temporary flag RTE_ETH_DEV_CLOSE_REMOVE is removed.
It was introduced in DPDK 18.11 in order to give time for PMDs to migrate.
The old behaviour was to free only queues when closing a port.
The new behaviour is calling rte_eth_dev_release_port() which does
three more tasks:
- trigger event callback
- reset state and few pointers
- free all generic port resources
The private port resources must be released in the .dev_close callback.
The .remove callback should:
- call .dev_close callback
- call rte_eth_dev_release_port()
- free multi-port device shared resources
Despite waiting two years, some drivers have not migrated,
so they may hit issues with the incompatible new behaviour.
After sending emails, adding logs, and announcing the deprecation,
the only last solution is to declare these drivers as unmaintained:
ionic, liquidio, nfp
Below is a summary of what to implement in those drivers.
* The freeing of private port resources must be moved
from the ".remove(device)" function to the ".dev_close(port)" function.
* If a generic resource (.mac_addrs or .hash_mac_addrs) cannot be freed,
it must be set to NULL in ".dev_close" function to protect from
subsequent rte_eth_dev_release_port() freeing.
* Note 1:
The generic resources are freed in rte_eth_dev_release_port(),
after ".dev_close" is called in rte_eth_dev_close(), but not when
calling ".dev_close" directly from the ".remove" PMD function.
That's why rte_eth_dev_release_port() must still be called explicitly
from ".remove(device)" after calling the ".dev_close" PMD function.
* Note 2:
If a device can have multiple ports, the common resources must be freed
only in the ".remove(device)" function.
* Note 3:
The port is supposed to be in a stopped state when it is closed.
If it is not the case, it is free to the PMD implementation
how to react when trying to close a non-stopped port:
either try to stop it automatically or just return an error.
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Reviewed-by: Liron Himi <lironh@marvell.com>
Reviewed-by: Haiyue Wang <haiyue.wang@intel.com>
Acked-by: Jeff Guo <jia.guo@intel.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
The device operation .dev_close was returning void.
This driver interface is changed to return an int.
Note that the API rte_eth_dev_close() is still returning void,
although a deprecation notice is pending to change it as well.
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Reviewed-by: Rosen Xu <rosen.xu@intel.com>
Reviewed-by: Sachin Saxena <sachin.saxena@oss.nxp.com>
Reviewed-by: Liron Himi <lironh@marvell.com>
Reviewed-by: Haiyue Wang <haiyue.wang@intel.com>
Acked-by: Jeff Guo <jia.guo@intel.com>
Reviewed-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
The pointers .device and .intr_handle were already reset by the helper
rte_eth_dev_pci_generic_remove().
It is now made part of rte_eth_dev_release_port().
It makes rte_eth_dev_pci_release() meaningless,
so it is replaced with a call to rte_eth_dev_release_port().
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Reviewed-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Scatter gather mode should get enabled:
- If mbuf size is less than max received packet length.
- MTU is reconfigured greater than mbuf size.
Fixes: 0e2efd02db58 ("net/octeontx2: add MTU set operation")
Cc: stable@dpdk.org
Signed-off-by: Harman Kalra <hkalra@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
This patch is a preparation to hide the 'struct eth_dev_ops' from
applications by moving some device operations from 'struct eth_dev_ops'
to 'struct rte_eth_dev'.
Mentioned ethdev APIs are in the data path and implemented as inline
because of performance reasons.
Exposing 'struct eth_dev_ops' to applications is bad because it is a
contract between ethdev and PMDs, not really needs to be known by
applications, also changes in the struct causing ABI breakages which
shouldn't.
To be able to both keep APIs inline and hide the 'struct eth_dev_ops',
moving device operations used in ethdev inline APIs to 'struct
rte_eth_dev' to the same level with Rx/Tx burst functions.
The list of dev_ops moved:
eth_rx_queue_count_t rx_queue_count;
eth_rx_descriptor_done_t rx_descriptor_done;
eth_rx_descriptor_status_t rx_descriptor_status;
eth_tx_descriptor_status_t tx_descriptor_status;
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Reviewed-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: David Marchand <david.marchand@redhat.com>
Acked-by: Sachin Saxena <sachin.saxena@nxp.com>
Free CQ ring memzone on Rx queue release. This prevents CQ using
incorrect memory size when ring size is reconfigured.
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Add device arguments to lock Rx/Tx contexts.
Application can either choose to lock Rx or Tx contexts by using
'lock_rx_ctx' or 'lock_tx_ctx' respectively per each port.
Example:
-w 0002:02:00.0,lock_rx_ctx=1 -w 0002:03:00.0,lock_tx_ctx=1
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Reviewed-by: Andrzej Ostruszka <aostruszka@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
New cn98xx SOC comes up with two NIX blocks wrt
cn96xx, cn93xx, to achieve higher performance.
Also the no of cores increased to 36 from 24.
Adding support for cn98xx where need a logic to
detect if the LF is attached to NIX0 or NIX1 and
then accordingly use the respective NIX block.
Signed-off-by: Harman Kalra <hkalra@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
The elt_size field in mempool holds the size of one packet buffer.
It can be used to set the lpm_sizem1 field in rq context.
The lpb_sizem1 field in rq context is 12 bit, direct assignment
to it was causing overflow of value. Because of this errors
were observed while trying inline inbound with large packets.
This patch resolves the errors.
Fixes: 094fc8a3a1e2 ("net/octeontx2: add Rx queue setup and release")
Cc: stable@dpdk.org
Signed-off-by: Ankur Dwivedi <adwivedi@marvell.com>
Reviewed-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Reviewed-by: Jerin Jacob <jerinj@marvell.com>
This patch adds SDP packet parsing support with custom L2 header,
adds support to include a field from custom header for flow tag
generation.
Signed-off-by: Satheesh Paul <psatheesh@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
When an application invokes rte_eth_dev_configure consecutively without
setting up Rx/Tx queues, it will incorrectly return error while trying
to restore Rx/Tx queue configuration.
Fix configuration sequence by checking if any Rx/Tx queues are
previously configured before trying to restore them.
Fixes: 548b5839a32b ("net/octeontx2: add device configure operation")
Cc: stable@dpdk.org
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Add Traffic Management capability callbacks to provide
global, level and node capabilities. This patch also
adds documentation on Traffic Management Support.
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Krzysztof Kanas <kkanas@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Add Tx queue ratelimiting support. This support is mutually
exclusive with TM support i.e when TM is configured, tx queue
ratelimiting config is no more valid.
Signed-off-by: Krzysztof Kanas <kkanas@marvell.com>
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Modify resource allocation and freeing logic to support
dynamic topology commit while to traffic is flowing.
This patch also modifies SQ flush to timeout based on minimum shaper
rate configured. SQ flush is further split to pre/post
functions to adhere to HW spec of 96XX C0.
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Krzysztof Kanas <kkanas@marvell.com>
Adding support to configure link attributes like speed,
duplex, negotiation.
Signed-off-by: Harman Kalra <hkalra@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Patch adds routines to set/clear nix lf error & ras interrupt enable
registers. These nix lf error interrupts get triggered if there are
any failures during nix lf configuration. This interrupts are enabled
before any hardware configurations initiated on the allocated nix lf.
Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
Acked-by: Andrzej Ostruszka <aostruszka@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Octeontx2 HW has support for detecting the bad L2/L3/L4 UDP lengths.
Since DPDK does not have specific error flag for this, exposing it
as bad checksum failure in mbuff:ol_flags to leverage this feature.
These errors will be propagated to the ol_flags as follows.
L2 length error ==> (PKT_RX_IP_CKSUM_BAD | PKT_RX_L4_CKSUM_BAD).
Both Outer and Inner L3 length error ==> PKT_RX_IP_CKSUM_BAD.
Outer L4 UDP length/port error ==> PKT_RX_OUTER_L4_CKSUM_BAD.
Inner L4 UDP length/port error ==> PKT_RX_L4_CKSUM_BAD.
Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Currently when application requests for RTE_FC_NONE earlier
than PMD's internal fc mode update, flow control set routine
is returning without updating the flow control state.
Patch updates the PMD's internal fc mode details during
dev_configure to ensure any flow control set requests
issued later are handled properly.
Fixes: 609945f1ce90 ("net/octeontx2: support flow control")
Cc: stable@dpdk.org
Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Added new flag for SECURITY in compiler optimized Tx fastpath
framework. With this, compiler autogenerates functions which
have security enabled.
Signed-off-by: Ankur Dwivedi <adwivedi@marvell.com>
Signed-off-by: Anoob Joseph <anoobj@marvell.com>
Signed-off-by: Archana Muniganti <marchana@marvell.com>
Signed-off-by: Tejasree Kondoj <ktejasree@marvell.com>
Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
Before C0 HW revision, The RSS adder was computed based the following
static formula.
rss_adder<7:0> = flow_tag<7:0> ^ flow_tag<15:8> ^
flow_tag<23:16> ^ flow_tag<31:24>
The above scheme has the following drawbacks:
1) It is not in line with other standard NIC behavior.
2) There can be an SW use case where SW can compute the hash
upfront using Toeplitz function and predict the queue selection
to optimize some packet lookup function. The nonstandard
way of doing XOR makes the consumer to not predict the queue selection.
C0 HW revision onward, The HW can configure the
rss_adder<7:0> as flow_tag<7:0> to align with standard NICs.
This patch adds an option to select legacy RSS adder mode
using tag_as_xor=1 devargs option while keeping the standard NIC
behavior as default.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
If HIGIG mode is enabled on configure, This needs to be disabled
on port stop. Adding support to send mbox message on port stop
to configure the port to default.
Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
octeontx2 PMD does not support both PTP and HIGIG2 together.
Added a check to enforce this and updated the Rx offload capabilities when
Higig2 mode enabled.
Fixes: 602009ee2dfb ("net/octeontx2: support HIGIG2")
Cc: stable@dpdk.org
Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Returning -ENOTSUP only in case loopback mode is enabled and
device is VF or SDP.
Fixes: c2c0aa75cd01 ("net/octeontx2: fix loopback config return for VF")
Cc: stable@dpdk.org
Signed-off-by: Harman Kalra <hkalra@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
loopback mode is not supported for VFs so returning error if
VF is being configured with loopback mode.
Fixes: 920717e4d8ba ("net/octeontx2: add device start operation")
Cc: stable@dpdk.org
Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Enable packet type parsing by default, only disable when
`rte_eth_dev_set_ptypes()` is called with ptype_mask as 0.
This would enable applications that are dependent on packet type parsing
like l3fwd.
Also this patch preserves configuration set by `rte_eth_dev_set_ptypes`
across multiple calls of `rte_eth_dev_configure()`
Fixes: d2706e15e6fb ("net/octeontx2: support reduced set of packet types")
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Add support to set supported ptypes for octeontx2 and
remove devarg scheme to disable ptype parsing support as
application can use rte_eth_dev_set_ptypes() normative API
to enable the same use case.
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Issue has been observed if PTP is already enabled on PF and
later VFs are configured. Since PTP requires mbuf data off
to be shifted by 8 bytes, due to this l3fwd/l2fwd was not
working with VFs.
Also some extra garbage bytes were observed in packet data
when ptp was enabled.
Fixes: b5dc3140448e ("net/octeontx2: support base PTP")
Cc: stable@dpdk.org
Signed-off-by: Harman Kalra <hkalra@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
After otx2_nix_register_cq_irqs() is called and the IRQs are setup,
otx2_nix_unregister_cq_irqs() need to be called in the subsequent error
exit paths.
Fixes: d34db5ccbf30 ("net/octeontx2: fix driver reconfiguration")
Cc: stable@dpdk.org
Signed-off-by: Anoob Joseph <anoobj@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Retrieve burst mode information according to the selected Rx/Tx mode and
offloads.
Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Add DEV_RX_OFFLOAD_RSS_HASH flag for all PMDs that support RSS hash
delivery.
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Reviewed-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
System DPI Packet Interface Unit (SDP) is a co-processor
of OCTEON TX2 which provides PCIe endpoint support for a
remote host to DMA packets into and out of the OCTEON TX2 SoC.
SDP interface comes in to live only when it is connected in
EP mode. It exposes input and output queue pairs to remote host
for instruction input and packet output. It can be used as
a communication channel between remote host and OCTEON TX2.
Host machine needs to use corresponding user/kernel mode
driver to communicate with SDP interface on OCTEON TX2 SoC.
SDP interface support is limited to SDP PF device now.
No SDP VF support.
Signed-off-by: Subrahmanyam Nilla <snilla@marvell.com>
Signed-off-by: Venkateshwarlu Nalla <venkatn@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Adding support to configure specific switch types like high2 and dsa
on a port. When this switch type is configured, it is expected that
all the traffic on that port should be of specific type only.
Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Add support to below TCP segmentation offloads for
96XX A1 onwards and 95xx B0 onwards.
- TCPv4, TCPv6
- VXLAN[v4 | v6][v4 | v6]
- GENEVE[v4 | v6][v4 | v6]
This patch also modifies a fastpath function to be forced
inline due to performance reasons for multi-seg mode.
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Adding support for tx descriptor status dev ops for octeontx2.
Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Update workaround changes for erratas that are fixed on 96xx A1.
This patch also enables cq drop for all the passes for
maintaining performance along with updating a default
Rx ring size in dev_info.
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Patch extends minimum supported max_sqb_count devarg value
such that it can limit the max sqb count to 8 buffers and
also defines NIX_DEF_SQB and uses it to compute the number
of sqe buffers required for the egress traffic.
NIX_DEF_SQB is defined as 16 which is optimal across multiple
octeontx2 platforms to scale up the performance proportional
to the corresponding port/queue to lcore mappings.
Fixes: fb0198b7dc07 ("net/octeontx2: add devargs parsing functions")
Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
From B0 HW revision onwards, HW can drop the Rx and L2 error packets.
Enable this by default if the feature is available.
Since this bit field is used as reserved in old HW revisions,
No need to have additional HW version check.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Acked-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
This patch implements read clock api whose purpose is to return
raw clock ticks. Using this API real time ticks spent in
processing a packet can be known:
<read_clock val at any time> - mbuf->timestamp
Calling mbox for reading raw clock ticks in fastpath is very
expensive so its value is derived from time stamp counter(tsc)
using freq multiplier (ratio of raw clock ticks and tsc) and clock
delta (by how much tsc is lagging from raw clock value).
Signed-off-by: Harman Kalra <hkalra@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
A huge drop in per core MPPS value was observed when PTP stack is
enabled. The reason behind the bottleneck is HW serialises the
transfer of all SQEs, which seeks timestamp capture, on the same
send DMA path. Hence only those packets which requires timestamp
capture should set SETTSTAMP in send mem alg.
With this patch timestamping would be done only for those packets
with PKT_TX_IEEE1588_TMST set.
Fixes: fb3ae0951abd ("net/octeontx2: support Tx")
Fixes: 8980a153006b ("event/octeontx2: support PTP for SSO")
Signed-off-by: Harman Kalra <hkalra@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Earlier implementation for enabling ptp via RX offload flag was
causing segmentation fault as it was getting executed in the
device configuration stage where RX and TX queues were not
configured. As in the ptp enable process rx queues are used for
mbuf setup while tx queues are used for send descriptor setup.
Moving the logic in dev start as all the resources will be
configured.
Fixes: b5dc3140448e ("net/octeontx2: support base PTP")
Signed-off-by: Harman Kalra <hkalra@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
