net/sfc: support link up/down

Signed-off-by: Artem Andreev <artem.andreev@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
Reviewed-by: Robert Stonehouse <rstonehouse@solarflare.com>

net/sfc: support link speed and duplex settings

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
Reviewed-by: Robert Stonehouse <rstonehouse@solarflare.com>

net/sfc: support MTU change

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
Reviewed-by: Robert Stonehouse <rstonehouse@solarflare.com>

net/sfc: support link status change interrupt

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
Reviewed-by: Robert Stonehouse <rstonehouse@solarflare.com>

net/sfc: support flow control settings

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
Reviewed-by: Robert Stonehouse <rstonehouse@solarflare.com>

net/sfc: support extended statistics

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
Reviewed-by: Robert Stonehouse <rstonehouse@solarflare.com>

net/sfc: add basic statistics

Does not implement any deprecated statistics.
No per-queue statistics yet.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
Reviewed-by: Robert Stonehouse <rstonehouse@solarflare.com>

net/sfc: support parameter to choose performance profile

Supported options are auto (based on NIC firmware variant and
installed licences), throughput, low-latency.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
Reviewed-by: Robert Stonehouse <rstonehouse@solarflare.com>

net/sfc: implement MCDI logging callback

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
Reviewed-by: Robert Stonehouse <rstonehouse@solarflare.com>

net/tap: add TUN/TAP device PMD

The PMD allows for DPDK and the host to communicate using a raw
device interface on the host and in the DPDK application. The device
created is a Tap device with a L2 packet header.

Signed-off-by: Keith Wiles <keith.wiles@intel.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Tested-by: Aws Ismail <aismail@ciena.com>
Tested-by: Vasily Philipov <vasilyf@mellanox.com>

ethdev: remove some VF functions

remove the following API's:

rte_eth_dev_set_vf_rxmode
rte_eth_dev_set_vf_rx
rte_eth_dev_set_vf_tx
rte_eth_dev_set_vf_vlan_filter
rte_eth_dev_set_vf_rate_limit

Increment LIBABIVER in Makefile
Remove deprecation notice for removing rte_eth_dev_set_vf_* API's.

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>

net/ixgbe: remove static set VF functions

remove the following static functions:

ixgbe_set_pool_rx_mode
ixgbe_set_pool_rx
ixgbe_set_pool_tx
ixgbe_set_pool_vlan_filter
ixgbe_set_vf_rate_limit

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>

examples/ethtool: use ixgbe public function

Replace rte_eth_dev_set_vf_rxmode with rte_pmd_ixgbe_set_vf_rx_mode.

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>

app/testpmd: cleanup parameter checking

Parameter checking is done in the rte_pmd_ixgbe_* functions.
Remove parameter checking from before calls to the rte_pmd_ixgbe_*
functions.

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>

app/testpmd: use ixgbe public functions

Use the the following ixgbe public functions:

rte_pmd_ixgbe_set_vf_rate_limit
rte_pmd_ixgbe_set_vf_rx
rte_pmd_ixgbe_set_vf_rxmode
rte_pmd_ixgbe_set_vf_tx
rte_pmd_ixgbe_set_vf_vlan_filter

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>

net/ixgbe: move set VF functions from the ethdev

Move the following functions from eth_dev_ops to the ixgbe PMD and rename:

ixgbe_set_pool_rx_mode
ixgbe_set_pool_rx
ixgbe_set_pool_tx
ixgbe_set_pool_vlan_filter
ixgbe_set_vf_rate_limit

Rename the functions to the following:

rte_pmd_ixgbe_set_vf_rxmode
rte_pmd_ixgbe_set_vf_rx
rte_pmd_ixgbe_set_vf_tx
rte_pmd_ixgbe_set_vf_vlan_filter
rte_pmd_ixgbe_set_vf_rate_limit

Use public function internally

Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>

net/qede: fix resource leak

Current code does not close 'fd' on function exit, leaking resources.

Fixes: 2ea6f76aff40 ("qede: add core driver")

Signed-off-by: Yong Wang <wang.yong19@zte.com.cn>
Acked-by: Harish Patil <harish.patil@qlogic.com>

net/i40e: remove unused macro

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: remove unused macro

remove X722_SUPPORT and I40E_NDIS_SUPPORT MACROs

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: fix byte order

Big Endian platform will accidentally send the wrong
data to the firmware command. This patch fixes the issue.

Fixes: 788fc17b2dec ("i40e/base: support proxy config for X722")
Fixes: 3c89193a36fd ("i40e/base: support WOL config for X722")

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: fix division by zero

For some cases when reading from device are incorrect or image is
incorrect, this part of code causes crash due to division by zero.

Fixes: 8db9e2a1b232 ("i40e: base driver")

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: add broadcast promiscuous control per VLAN

Add a new adminq function that allows driver to configure per-VLAN
broadcast promiscuous mode, similar to how we handle unicast and
multicast promiscuous modes.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: add error state for NVM update state machine

This patch adds I40E_NVMUPD_STATE_ERROR state for NVM update.
Without this patch driver has no possibility to return NVM image write
failure.This state is being set when ARQ rises error.
arq_last_status is also updated every time when ARQ event comes,
not only on error cases.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: remove duplicate definitions

We already define I40E_AQ_PHY_TYPE_EXT_25G* flags in the response adminq
structure above, and do not need to re-define these.

While we are here, replace 0X with 0x as normal style.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: comment that UDP port must be in host order

The firmware expects the Port number to be in Little Endian format, and
the i40e_aq_add_udp_tunnel command clearly expects the udp_port variable
to be in Host order, as it uses CPU_TO_LE16(). It was recently
discovered in the Linux driver that we were passing a Big Endian port
number, which was therefor not enabling the UDP tunnel correctly.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: convert shift values to hex

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: fix NVM access interfering

Acquire NVM lock before reads on all devices.  Previously, locks were
only used for X722 and later.  Fixes an issue where simultaneous X710
NVM accesses were interfering with each other.

Fixes: 8db9e2a1b232 ("i40e: base driver")

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: save link FEC info from link up event

Store the FEC status bits from the link up event into the
hw_link_info structure.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: fix WoL failure on PF reset

By default the device clears all MAC filter information on PF Reset.
However, this will cause Wake-On-LAN to fail because the wake filters
are deleted on transition to D3 power state. To get around this,
firmware is adding functionality to preserve certain MAC filters during
PFR. These bits allow the driver tell the FW which filters to preserve.

Set the datalen field and add I40E_AQ_FLAG_BUF/I40E_AQ_FLAG_RD flags in the
desc struct for the WoL/Proxy AQ descriptors. The WoL/Proxy AQ commands
were failing because these were missing.

Fixes: 3c89193a36fd ("i40e/base: support WOL config for X722")

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: implement VSI full promiscuous mode

This patch implements a function to set a VSI to broadcast, multicast, and
unicast promiscuous mode all at once. This is specifically needed to set
the WoL/Proxy VSI created by FW to full promiscuous mode during power down
for WoL patterns and protocol offloads to function properly.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: implement clear all WoL filters

This patch implements the clear Wake on LAN (WoL) filters admin queue
function which clears out ALL WoL patterns programmed into
the flex filters.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: adjust 25G PHY type values

Define the values for the 25G PHY type bit-fields that match
reported values from firmware. There was a gap in the bit
fields but no corresponding gap i40e_aq_phy_type enum.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: use BIT macro instead of bit fields

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: add FEC bits to PHY capabilities

Add FEC bits to the PHY capabilities AQ command struct. This is required
for 25GbE support. Change the name of the generic mod_type_ext field to
indicate that it is now used for handling FEC.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: remove FPK HyperV VF device ID

Microsoft recently removed the requirement for VFs to use the VMBus.
The Fort Park Windows VF has been changed to use only the hardware
mailbox, so the Hyper-V VF device ID can be removed.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: deprecate unused macro

I40E_MAC_X710 was supposed to be for 10G and I40E_MAC_XL710
was supposed to be for 40G. But i40e_set_mac_type() sets
I40E_MAC_XL710 for all device IDS. I40E_MAC_X710 is not
used at all. Thus deprecating this extra macro.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: replace memcpy

To align with current memcpy use, replace existing legacy memcpy() calls
with i40e_memcpy() calls.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: fix unknown PHYs incorrect identification

The PHY type value for unrecognized PHYs and cables was changed
based on firmware version number. Newer hardware use lower firmware
version numbers and this was causing some PHYs to be identified
as type 0x16 instead of 0xe (unknown).

Without this patch, newer card will incorrectly identify unknown
PHYs and cables.

This change adds hardware type to the check for firmware version
so the PHY type is reported correctly.

Fixes: 8db9e2a1b232 ("i40e: base driver")

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: add protocols when discover capabilities

Add logical_id to I40E_AQ_CAP_ID_MNG_MODE capability starting from major
version 2.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: add bus number info

Currently i40e_bus_info has PCI device and function info only. However
in log messages slot number (i.e hw->bus.device) is being printed
as bus number. Another field should be added to provide bus number
info and preserve existing information.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: add clause22 and clause45 implementation

Some external PHYs require Clause22 and Clause45 method for
accessing registers. Mostly used for X722 support.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: add media type detection for 25G link

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: fix long link down notification time

This patch fixes a problem where it could take a very
long time (>100 msec) to print the link down notification.
This problem is fixed by changing how often we update link
info from fw, when link is down. Without this patch, it can
take over 100msec to notify user link is down.

Fixes: e6691b428eb1 ("i40e/base: fix PHY NVM interaction")

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: group base mode VF offload flags

Group together the minimum set of offload capabilities that are always
supported by VF in base mode. This define would be used by PF to make
sure VF in base mode gets minimum of base capabilities.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: fix bit test mask

Incorrect bit mask was used for testing "get link status" response.
Instead of I40E_AQ_LSE_ENABLE (which is actually 0x03) it should
be I40E_AQ_LSE_IS_ENABLED (which is defined as 0x01).

Fixes: 8db9e2a1b232 ("i40e: base driver")

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: remove unnecessary code

This patch changes some assignments and removing the unnecessary
code to avoid error reported by static analysis tools.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: fix flow control set for 25G

Add phy_type_ext copied from old setting to rpevents 25G PHY
types from being disabled when setting the flow control modes.

Fixes: 51131ae119 ("net/i40e/base: get PHY abilities for 25G")

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/i40e/base: add encap checksum VF offload flag

Add ENCAP_CSUM offload negotiation flag. Currently VF assumes checksum
offload for encapsulated packets is supported by default. Going forward,
this feature needs to be negotiated with PF before advertising to the
stack. Hence, we need a flag to control it.

Signed-off-by: Jingjing Wu <jingjing.wu@intel.com>

net/nfp: document supported features

Signed-off-by: Alejandro Lucero <alejandro.lucero@netronome.com>
Acked-by: John McNamara <john.mcnamara@intel.com>

net/ixgbe: fix typo in comment

Fixes: c03fcee9abbd ("ixgbe: remove CRC size from byte counters")

Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>

net/sfc: restart TxQ in case of exception on event queue

Examples of recoverable exceptions because of Tx error are:
 - Tx descriptor PCI read error
 - invalid Tx option descriptor
 - Tx option descriptor not supported by the firmware variant
 - unexpected Tx option descriptor (e.g. missing FATSO2A before
   FATSO2B, missing FATSO2B after FATSO2A)
 - incomplete packet push (CONT bit set in the latest pushed DMA
   descriptor)

Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
Reviewed-by: Robert Stonehouse <rstonehouse@solarflare.com>

net/sfc: restart RxQ in case of exception on event queue

Examples of recoverable exceptions are:
 - unexpected Rx event (Rx scatter abort with non-zero size,
   too big Rx descriptors batch completed)
 - Rx error due to invalid Rx descriptors push
 - Rx error due to Rx descriptor read error (e.g. unmapped Rx ring
   and denied by IOMMU)

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andrew Lee <alee@solarflare.com>
Reviewed-by: Robert Stonehouse <rstonehouse@solarflare.com>

net/sfc: send bursts of packets

Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: implement transmit path start / stop

Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: set up and release Tx queues

Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: add function to check configured Tx mode

Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: provide basic stubs for Tx subsystem

Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: discard scattered packet on Rx correctly

Since Rx scatter is not supported, all scattered packets are discarded.
It is not always possible to disable scatter on Huntington, so we
should handle scattered packets correctly in any case.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: implement device callback to Rx burst of packets

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: implement Rx queue start and stop operations

These functions should set the queue state in dev->data->rx_queue_state
array.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: validate Rx queue buffers setup

Check that Rx mbuf pool, MTU and Rx scatter config are in sync.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: calculate Rx buffer size which may be used

Take Rx buffer start alignment and end-padding into account.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: implement Rx queue setup release operations

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: check configured Rx mode

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: implement Rx subsystem stubs

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: retrieve link info

Signed-off-by: Artem Andreev <artem.andreev@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: minimum port control sufficient to receive traffic

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: periodic management EVQ polling using alarm

Timers cannot be used to implement periodic polling, since it implies
requirement on application to process timers in the main loop.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: maintain management event queue

The event queue is required for device level events (e.g. link status
change) and flush events.
Provide thread-safe function to poll the event queue since it may be
really done from different contexts.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: implement EVQ dummy exception handling

Right now the code just logs the exception and sets flag to notify
subsequent event handlers and poller that recovery is required.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: support event queue

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: interrupts support sufficient for event queue init

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: estimate available resources

Resources required in accordance with configuration are
allocated only.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: add device start and stop operations

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: add device configuration checks

Manual link speed/duplex configuration is not supported yet.
Loopback is not supported yet.
Flow Director is not supported.
Link status change notification using interrupt is not supported yet.
Receive data notification using interrupts is not supported yet.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: add configure and close stubs

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: add init on attach

The setup and configuration of the PMD is not performance sensitive,
but is not thread safe either. It is possible that the multiple
read/writes during PMD setup and configuration could be corrupted
in a multi-thread environment.  Since this is not performance
sensitive, the developer can choose to add their own layer to provide
thread-safe setup and configuration. It is expected that, in most
applications, the initial configuration of the network ports would be
done by a single thread at startup.

In the case of exception on the event queue, the event queue and
corresponding Rx/Tx queue should be restarted in the Rx/Tx queue
polling context. These operations require access to the device
control which should be serialized. The device level lock will do
the job.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc: build libefx

Implement efsys.h for the PMD.

Signed-off-by: Artem Andreev <artem.andreev@oktetlabs.ru>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import libefx licensing

Provide API to deal with licenses on SFN7xxx and SFN8xxx
family adapters.

EFSYS_OPT_LICENSING should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import bootrom configuration

Provide API to read/write bootrom configuration from/to NVRAM.

EFSYS_OPT_BOOTROM should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import VPD support

Provide API to read/write PCI Vital Product Data.

EFSYS_OPT_VPD should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import NVRAM support

Provide API to work with NIC non-volatile memory. It is used
to update firmware, configure NIC including bootrom parameters,
manage licenses, store PCI Vital Product Data etc.

EFSYS_OPT_NVRAM should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import Rx packed stream mode

In packed stream mode, large buffers are provided to the NIC
into which many packets can be delivered. This reduces the
number of queue refills needed compared to delivering every
packet into a separate buffer.

EFSYS_OPT_RX_PACKED_STREAM should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import monitors access via MCDI

EFSYS_OPT_MON_MCDI should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import monitors statistics

EFSYS_OPT_MON_STATS should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import loopback control

EFSYS_OPT_LOOPBACK should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import RSS support

EFSYS_OPT_RX_SCALE should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import Rx scatter support

EFSYS_OPT_RX_SCATTER should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import event prefetch

EFSYS_OPT_EV_PREFECT allows to enable event prefetching
when event queue is polled.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import MAC statistics

MAC statistics are either periodically (if supported/requested)
or on-demand written to provided DMA-mapped memory.
If periodic update is not supported (e.g. for EF10 virtual
functions), it is the driver responsibility to handle it.

EFSYS_OPT_MAC_STATS should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import PHY LEDs control

EFSYS_OPT_PHY_LED_CONTROL should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import PHY statistics

EFSYS_OPT_PHY_STATS should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import PHY flags control

EFSYS_OPT_PHY_FLAGS should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import software per-queue statistics

EFSYS_OPT_QSTATS should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import built-in selftest

EFSYS_OPT_BIST should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import diagnostics support

EFSYS_OPT_DIAG should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import SFN8xxx family support

SFN8xxx is the second family based on EF10 architecture.

It has few differences from SFN7xxx adapters family.

EFSYS_OPT_MEDFORD should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import SFN7xxx family support

SFN7xxx is the first family based on EF10 architecture.

EFSYS_OPT_HUNTINGTON should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import 5xxx/6xxx family support

EFSYS_OPT_SIENA should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>

net/sfc/base: import MCDI proxy authorization

MCDI proxy authorization may be used if privileged PCI
function (physical function) would like to intercept and
authorize MCDI requests done by unprivileged (e.g. virtual)
PCI function. It may be used to control unprivileged
function Rx mode (e.g. promiscuous, all-multicast), MTU
and default MAC address change requests etc.

Current libefx support is limited to client-side which
is required to work when function requests need to be
authorized.

Server side support required to request and do the
authorization is not implemented yet.

EFSYS_OPT_MCDI_PROXY_AUTH should be enabled to use it.

From Solarflare Communications Inc.

Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>