When an IOMMU is in use, the packet split receive path shows a distinct
advantage over the single-buffer path because it minimizes DMA mapping
and unmapping. However, this is not an advantage for systems with no
IOMMU. At init time, check to see if an IOMMU is enabled and enable
packet split receives.

Change-ID: I4f70d2e9c31bbea3dc8fd0c5734959a6e6602210
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Copy setting from ethtool to the HW specific struct to actually
enable prints.  Change print from i40e to i40evf to differentiate
drivers in bare metal scenarios.

Also update the copyright year.

Change-ID: I06fee26247299a08f2e1c70fc811a9ea0931c4dd
Signed-off-by: NAshish Shah <ashish.n.shah@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This patch adds a struct to the VSI struct to keep track of rxnfc
settings done via ethtool.  Without this patch, the device can only
list the options available, not the current settings and this is not
clear to the user.  Without current settings, the available settings
never changing looks like a bug.

Also update the copyright year.

Change-ID: I087bbfdb33b330496a671630a7586773e3b3e589
Signed-off-by: NCarolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Add a requested speed variable to the link_status struct to store the
last speeds we requested from the firmware (the speeds the FW will be
advertising with if autoneg is enabled).

Use the advertised speed settings in get_settings in ethtool now that
we have it.  Also set the requested speed settings in set_settings in
ethtool as they are requested and initialize them in probe based on what
the firmware remembers as the last requested speeds.

To accommodate some longer lines in this new code, and improve
readability I have added two functions i40e_get_settings_link_up
and i40e_get_settings_link_down which get_settings now calls first.
It then does all of the settings that happen regardless of link
state. Some PHY types that supported the same settings were also combined.

Also update the copyright year.

Change-ID: Ica0c5ac81b6069ea6a7406fce7482f7816d4455c
Signed-off-by: NCatherine Sullivan <catherine.sullivan@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The function i40e_debug_aq() prints information helpful in debugging
admin queue commands, but it doesn't do so correctly on big endian machines.
This patch adds the appropriate LExx_TO_CPU wrappers for big endian
architectures.

Also update the copyright year.

Change-ID: I4b2dc229ed5bf6dfe35632a58cddf53c21aff4b0
Signed-off-by: NPaul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Add Byte Queue Limits (BQL) support to via-rhine driver.

[edumazet] tweaked patch and changed TX_RING_SIZE from 16 to 64
Signed-off-by: NTino Reichardt <milky-kernel@mcmilk.de>
Tested-by: NJamie Gloudon <jamie.gloudon@gmail.com>
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The Churn Detection machines detect the situation where a port is operable,
but the Actor and Partner have not attached the link to an Aggregator and
brought the link into operation within a bound time period. Under normal
operation of the LACP, agreement between Actor and Partner should be reached
very rapidly. Continued failure to reach agreement can be symptomatic of
device failure.

Actor-churn-detection state-machine
Reviewed-by: NNikolay Aleksandrov <nikolay@redhat.com>

===================================

BEGIN=True + PortEnable=False
           |
           v
 +------------------------+   ActorPort.Sync=True  +------------------+
 |   ACTOR_CHURN_MONITOR  | ---------------------> |  NO_ACTOR_CHURN  |
 |========================|                        |==================|
 |    ActorChurn=False    |  ActorPort.Sync=False  | ActorChurn=False |
 | ActorChurn.Timer=Start | <--------------------- |                  |
 +------------------------+                        +------------------+
           |                                                ^
           |                                                |
  ActorChurn.Timer=Expired                                  |
           |                                       ActorPort.Sync=True
           |                                                |
           |                +-----------------+             |
           |                |   ACTOR_CHURN   |             |
           |                |=================|             |
           +--------------> | ActorChurn=True | ------------+
                            |                 |
                            +-----------------+

Similar for the Partner-churn-detection.
Signed-off-by: NMahesh Bandewar <maheshb@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The 802.1AX standard states:
"The DA in LACPDUs is the Slow_Protocols_Multicast address."

This patch enforces that and drops LACPDUs with destination MAC
addresses other than Slow_Protocols_Multicast address
Signed-off-by: NMahesh Bandewar <maheshb@google.com>
Reviewed-by: NNikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

bcmgenet_hw_params->bds_cnt and GENET_DEFAULT_BD_CNT are used only in Tx init.
Rename them accordingly:
- bcmgenet_hw_params->bds_cnt => bcmgenet_hw_params->tx_bds_per_q
- GENET_DEFAULT_BD_CNT => GENET_Q16_TX_BD_CNT
Signed-off-by: NPetri Gynther <pgynther@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There is 1-to-1 mapping between TxCBs and TxBDs. Precalculate TxCB->bd_addr
once in bcmgenet_init_dma() instead of doing it over and over needlessly in
bcmgenet_get_txcb().
Signed-off-by: NPetri Gynther <pgynther@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

1. Rename bcmgenet_init_multiq() to bcmgenet_init_tx_queues()
2. Fix bcmgenet_init_tx_queues() function description
3. Move Tx default queue init inside bcmgenet_init_tx_queues()
4. Modify bcmgenet_init_dma() to call bcmgenet_init_tx_queues()
Signed-off-by: NPetri Gynther <pgynther@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

1. Simplify function description
2. Rename function parameter write_ptr to start_ptr to better indicate use
3. Remove unnecessary local variable first_bd
4. Remove out-of-place comment "Unclassified traffic goes to ring 16"
5. Fix TDMA_WRITE_PTR register init
Signed-off-by: NPetri Gynther <pgynther@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Under rare circumstances, after a reset, set_rx_mode might get called
while the watchdog is running, which will cause a deadlock on the
critical section lock. To correct this, add a counter and give up trying
to get the lock after fifty tries. Log a message if this happens but
don't take any other action. Because this happens after a reset, all of
the Rx filters are still in place and the device won't lose
connectivity.

We can also get stuck during shutdown, if the PF has stopped communicating
with us, or if a reset is occurring. If we can't get the lock after a reasonable
amount of time, just error out. Something else bad is happening anyway, so
adding this filter is the least of our concern right now.

Change-ID: I159731e2a82a06b389ee31b34ce336548e05baa0
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

A recent change to the shutdown flow messed up the reset flow. Since
i40evf_down now holds the critical section lock, we cannot call it from
the reset handler, which also holds the lock. To do so causes a deadlock
accompanied by wailing and gnashing of teeth. This is easily triggered
by running an ethtool self-test on the PF device.

Instead, we move the relevant portions of i40evf_down into the reset
handler and bend them to our will. Additionally, we can optimize the
reinit path by not deleting the MAC and VLAN filters and then adding
them back again. Instead, we just set the 'add' flag and let the
watchdog resynchronize the filter list with the PF driver. We also
reword a few messages to make them more consistent with the rest of the
driver.

Change-ID: I03dd92ae736f7719fca3564b12a2cf9b98c6cb18
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

When closing the interface, disable NAPI polling before any other
activities. This fixes an occasional panic during close caused by the
driver trying to delete and clean rings at the same time.

Change-ID: Ib4d427b13d310258ea85b248d535da70ecf0c1e9
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The netdev op that allows the operator to turn MAC/VLAN spoof checking on
and off did not include the flag for VLAN spoof checking.  This patch
fixes that problem.

Change-ID: Ib4c9e639024a854592d97af22706544881ac3fcb
Signed-off-by: NGreg Rose <gregory.v.rose@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Bump i40e to 1.2.8 and i40evf to 1.2.2

Change-ID: I64f47c3367ea8ff2a53068e895d7a1f60726c871
Signed-off-by: NSravanthi Tangeda <sravanthi.tangeda@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

An_enable was never used only set so lets remove it. The function
update_link_info only did two things, call get_link_info and set
an_enabled. Therefore we should also remove update_link_info and
change all references to it to get_link_info.

Change-ID: Ie3022680fa7a94bfd495a4f5fc76a73701d85569
Signed-off-by: NCatherine Sullivan <catherine.sullivan@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

We shouldn't trigger another EMPR when we receive an EMPR event.
This patch handles EMPR event reception with a different state
so that we can do the right thing for NVM.

Change-ID: I9cac70b3658600f016a65beb6fb157e1c1f9adf9
Signed-off-by: NAnjali Singhai Jain <anjali.singhai@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Some registers have been removed so take them out and
stop updating and looking at them.

Change-ID: I33da922c8de993a94dd8b8d8a2ae2146b8ca1a27
Signed-off-by: NAnjali Singhai Jain <anjali.singhai@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Use #defined VSI connection type values instead of using magic numbers.

Change-ID: I2f6cf7bf394d391e1c0fe61779e9e4ad8858154a
Signed-off-by: NNeerav Parikh <neerav.parikh@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Until the time a more robust versioning scheme is needed/implemented all
established virtual channel opcode values should remain consistent between
updates to the opcode enum.

This patch repositions I40E_VIRTCHNL_OP_CONFIG_RSS to the end of the enum. In
its current position this opcode displaces the initial value of
I40E_VIRTCHNL_OP_EVENT and will cause PF/VF compatibility issues.

Going forward the expectation is either:
	a) All future opcode additions will be added as the last element of the
	enum. Once VF drivers start making use of the new commands the virtual
	channel version will need to be incremented and drivers will need to
	implement a simple version check whereby VF drivers can only load on
	PFs with a >= version.
	b) or, if needed, design and implement a more complicated API
	negotiation capability.

In either case PF drivers should always maintain backwards compatibility with
earlier VF driver versions.

Change-ID: Ie245daa09a231b6680ed793d648bdcc76caefe58
Signed-off-by: NNicholas Nunley <nicholas.d.nunley@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Split the receive hot path code into two, one for packet split and one
for single buffer. This improves receive performance since we only need
to check if the ring is in packet split mode once per NAPI poll time,
not several times per packet. The single buffer code is further improved
by the removal of a bunch of code and several variables that are not
needed. On a receive-oriented test this can improve single-threaded
throughput.

Also refactor the packet split receive path to use a fixed buffer for
headers, like ixgbe does. This vastly reduces the number of DMA mappings
and unmappings we need to do, allowing for much better performance in
the presence of an IOMMU.

Lastly, correct packet split descriptor types now that we are actually
using them.

Change-ID: I3a194a93af3d2c31e77ff17644ac7376da6f3e4b
Signed-off-by: NMitch Williams <mitch.a.williams@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Change debugfs command from "clear_stats pf" to "clear_stats port"
to be clearer what the action is.  Also, limit the action to the
base PF, not the NPAR partitions.

Change-ID: I22aa39c0962d83a83a985097b1000ed7f8c66f3f
Signed-off-by: NShannon Nelson <shannon.nelson@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

This change is to refactor the read/write functions to support
future work.

Change-ID: I13150d5e3042f2c617362c0140dc7e6473ebcdee
Signed-off-by: NKamil Krawczyk <kamil.krawczyk@intel.com>
Signed-off-by: NShannon Nelson <shannon.nelson@intel.com>
Tested-by: NJim Young <james.m.young@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Fixed a few cases of when we used msleep() when we should have been
using usleep_range().  Also updated the usage of min/max() to use
min_t/max_t().
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>

Fix the code comments to align with the drivers/net/ commenting style.
Also fix other checkpatch errors such as using tabs where possible and
properly wrap lines to conform to the 80 char limit (unless it is
a string).
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>

i219 is the next-generation LOM that will be available on systems with the
Sunrise Point Platform Controller Hub (PCH) chipset from Intel.  This patch
provides the initial support for the device.
Signed-off-by: NDave Ertman <david.m.ertman@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Tested-by: NCarmen Edwards <carmenx.edwards@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Every time be_setup() is called, the driver will have to wait for the
function/FW to be properly initialized. So, it make sense to move this call
inside be_setup().
Signed-off-by: NSathya Perla <sathya.perla@emulex.com>
Signed-off-by: NKalesh AP <kalesh.purayil@emulex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Most of the resource cleanup sequences performed in be_suspend(),
be_eeh_err_detected() and be_err_detection_task() are same. Moved the
common code to a new routine be_cleanup() to avoid code duplication.
Signed-off-by: NKalesh AP <kalesh.purayil@emulex.com>
Signed-off-by: NSathya Perla <sathya.perla@emulex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Most of the adapter initialisation sequences performed in be_resume(),
be_eeh_resume() and be_err_recover() are same. Renamed be_resume() to
be_pci_resume() and moved the common code to a new routine be_resume() to
avoid code duplication.
Signed-off-by: NKalesh AP <kalesh.purayil@emulex.com>
Signed-off-by: NSathya Perla <sathya.perla@emulex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The steps needed for Lancer's reset/initialization sequence are:
	a) wait for SLIPORT_STAUS RDY bit to be set
	b) set the SLIPORT_CONTROL IP bit
	c) repeat step "a"

The code needed for this sequence is already covered by the be_func_init()
routine (with minor modifications.) So, get rid of the
lancer_test_and_set_rdy_state() and lancer_provisioning_error() routines
that unnecessarily duplicate this code. Also fixed the error recovery
function to take care of these changes
Signed-off-by: NSathya Perla <sathya.perla@emulex.com>
Signed-off-by: NKalesh AP <kalesh.purayil@emulex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently when an error is detected, the queue resources are being cleaned up
in the recovery routine. The resources are better cleaned up in the error
detection routine itself (similar to EEH code.)
So, this patch re-factors error processing logic to follow the following sequence:
	- check if there is an error in adapter
	- if error,
		- cleanup resources
		- attempt recovery

The patch renames lancer_recover_func() to be_err_recover() as this
routine will be used in the future for error recovery on Skyhawk too.
Signed-off-by: NKalesh AP <kalesh.purayil@emulex.com>
Signed-off-by: NSathya Perla <sathya.perla@emulex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Also rename func_recovery_work/task to err_detection_work/task as error
detection is the primary goal of this task while recovery is not guaranteed.
Signed-off-by: NSathya Perla <sathya.perla@emulex.com>
Signed-off-by: NKalesh AP <kalesh.purayil@emulex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Function initialization sequence is executed in be_probe(), be_resume
and be_eeh_resume(). Move this code to a new routine called be_func_init()
to prevent code duplication.
Signed-off-by: NSathya Perla <sathya.perla@emulex.com>
Signed-off-by: NKalesh AP <kalesh.purayil@emulex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Most of the code to fetch the adapter state is in be_setup()->be_get_config().
So, move the code from be_get_initial_config() to be_get_config().
Signed-off-by: NSathya Perla <sathya.perla@emulex.com>
Signed-off-by: NKalesh AP <kalesh.purayil@emulex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The members of be_adapter struct were being allocated in two separate
routines -- be_ctrl_init() and be_stats_init(). Also, some other members
were allocated elsewhere. This patch moves the alloc/free code into
be_drv_init/cleanup() routines. The be_pci_map_bars() routine that was
called from be_ctrl_init() is now called directly from be_probe().
The new routine be_drv_init() will now be the place-holder for allocating
memory for any new be_adapter{} members in the future.
Some routines needed to be moved to provide forward definitions for their
calls.
Signed-off-by: NSathya Perla <sathya.perla@emulex.com>
Signed-off-by: NKalesh AP <kalesh.purayil@emulex.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch updates the BNA driver version to 3.2.25.1 and the firmware version
to 3.2.5.1
Signed-off-by: NRasesh Mody <rasesh.mody@qlogic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Re-brand the BNA driver to QLogic.
Signed-off-by: NRasesh Mody <rasesh.mody@qlogic.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

An error return from __vnet_tx_trigger() sets the TX descriptor to
VIO_DESC_FREE while leaving port->tx_bufs[txi].skb set. This leads
to a BUG_ON() the next time this descriptor is used.

This patch frees the pending skb when getting a trigger error to
match the VIO_DESC_FREE state.
Signed-off-by: NDavid L Stevens <david.stevens@oracle.com>
Acked-by: NSowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>