Allocate the FIFO across the hardware Rx queues based on the priority
of the queues.  Giving more FIFO resources to queues with a higher
priority.  If PFC is active but not enabled for a queue, then less
resources can allocated to the queue.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently, the Rx and Tx fifos are evenly allocated between the hardware
queues of the device.  As more queues are instantiated, the fifo memory
needs to be able to be allocated based on queue priority. This allows for
higher priority queues to have more fifo memory than lower priority
queues. Prepare for this by modifying the current fifo calculation to
assign the fifo queue allocation in an array that is then used to program
the hardware.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fix the length value used for the PCS register dump so that the full
value can be displayed.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Fix to return error code -ENODEV from the DMA is not supported error
handling case instead of 0, as done elsewhere in this function.
Signed-off-by: NWei Yongjun <weiyongjun1@huawei.com>
Acked-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Somehow, I missed a healthy number of ethernet drivers in the last pass.
Most of these drivers either were in need of an updated max_mtu to make
jumbo frames possible to enable again. In a few cases, also setting a
different min_mtu to match previous lower bounds. There are also a few
drivers that had no upper bounds checking, so they're getting a brand new
ETH_MAX_MTU that is identical to IP_MAX_MTU, but accessible by includes
all ethernet and ethernet-like drivers all have already.

acenic:
- min_mtu = 0, max_mtu = 9000

amazon/ena:
- min_mtu = 128, max_mtu = adapter->max_mtu

amd/xgbe:
- min_mtu = 0, max_mtu = 9000

sb1250:
- min_mtu = 0, max_mtu = 1518

cxgb3:
- min_mtu = 81, max_mtu = 65535

cxgb4:
- min_mtu = 81, max_mtu = 9600

cxgb4vf:
- min_mtu = 81, max_mtu = 65535

benet:
- min_mtu = 256, max_mtu = 9000

ibmveth:
- min_mtu = 68, max_mtu = 65535

ibmvnic:
- min_mtu = adapter->min_mtu, max_mtu = adapter->max_mtu
- remove now redundant ibmvnic_change_mtu

jme:
- min_mtu = 1280, max_mtu = 9202

mv643xx_eth:
- min_mtu = 64, max_mtu = 9500

mlxsw:
- min_mtu = 0, max_mtu = 65535
- Basically bypassing the core checks, and instead relying on dynamic
  checks in the respective switch drivers' ndo_change_mtu functions

ns83820:
- min_mtu = 0
- remove redundant ns83820_change_mtu, only checked for mtu > 1500

netxen:
- min_mtu = 0, max_mtu = 8000 (P2), max_mtu = 9600 (P3)

qlge:
- min_mtu = 1500, max_mtu = 9000
- driver only supports setting mtu to 1500 or 9000, so the core check only
  rules out < 1500 and > 9000, qlge_change_mtu still needs to check that
  the value is 1500 or 9000

qualcomm/emac:
- min_mtu = 46, max_mtu = 9194

xilinx_axienet:
- min_mtu = 64, max_mtu = 9000

Fixes: 61e84623 ("net: centralize net_device min/max MTU checking")
CC: netdev@vger.kernel.org
CC: Jes Sorensen <jes@trained-monkey.org>
CC: Netanel Belgazal <netanel@annapurnalabs.com>
CC: Tom Lendacky <thomas.lendacky@amd.com>
CC: Santosh Raspatur <santosh@chelsio.com>
CC: Hariprasad S <hariprasad@chelsio.com>
CC: Sathya Perla <sathya.perla@broadcom.com>
CC: Ajit Khaparde <ajit.khaparde@broadcom.com>
CC: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
CC: Somnath Kotur <somnath.kotur@broadcom.com>
CC: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
CC: John Allen <jallen@linux.vnet.ibm.com>
CC: Guo-Fu Tseng <cooldavid@cooldavid.org>
CC: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
CC: Jiri Pirko <jiri@mellanox.com>
CC: Ido Schimmel <idosch@mellanox.com>
CC: Manish Chopra <manish.chopra@qlogic.com>
CC: Sony Chacko <sony.chacko@qlogic.com>
CC: Rajesh Borundia <rajesh.borundia@qlogic.com>
CC: Timur Tabi <timur@codeaurora.org>
CC: Anirudha Sarangi <anirudh@xilinx.com>
CC: John Linn <John.Linn@xilinx.com>
Signed-off-by: NJarod Wilson <jarod@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Casting away const is bad practice. Since this is ARM specific driver
don't have hardware actually test this.

Having getter functions for ops is really unnecessary code bloat, but
not going to touch that.
Signed-off-by: NStephen Hemminger <stephen@networkplumber.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

After resume from hibernate on arm64, any amd-xgbe devices that were
running when we hibernated are reported as down, even when it is not.

Re-plugging the cables does not cause the interface to come back, the
link must be marked as down then up via 'ip set link' using the serial
console.

This happens because the device has been power-cycled and possibly
re-initialised by firmware, whereas the driver's memory structures have
been restored from the hibernate image and the two do not agree.

Schedule a restart of the device after powerup in case the world changed
while we were asleep.
Signed-off-by: NJames Morse <james.morse@arm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

i has been defined as unsigned int.
So use %u for output.
Signed-off-by: NHeinrich Schuchardt <xypron.glpk@gmx.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

I added this check in setup_tc to multiple drivers,

 if (handle != TC_H_ROOT || tc->type != TC_SETUP_MQPRIO)

Unfortunately restricting to TC_H_ROOT like this breaks the old
instantiation of mqprio to setup a hardware qdisc. This patch
relaxes the test to only check the type to make it equivalent
to the check before I broke it. With this the old instantiation
continues to work.

A good smoke test is to setup mqprio with,

# tc qdisc add dev eth4 root mqprio num_tc 8 \
  map 0 1 2 3 4 5 6 7 \
  queues 0@0 1@1 2@2 3@3 4@4 5@5 6@6 7@7

Fixes: e4c6734e ("net: rework ndo tc op to consume additional qdisc handle paramete")
Reported-by: NSingh Krishneil <krishneil.k.singh@intel.com>
Reported-by: NJake Keller <jacob.e.keller@intel.com>
CC: Murali Karicheri <m-karicheri2@ti.com>
CC: Shradha Shah <sshah@solarflare.com>
CC: Or Gerlitz <ogerlitz@mellanox.com>
CC: Ariel Elior <ariel.elior@qlogic.com>
CC: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
CC: Bruce Allan <bruce.w.allan@intel.com>
CC: Jesse Brandeburg <jesse.brandeburg@intel.com>
CC: Don Skidmore <donald.c.skidmore@intel.com>
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently the auto-negotiation interrupt handling disables the irq
instead of masking off the interrupts. This was done because the phy
library was originally used to read and write the PCS registers, which
could not be performed in interrupt context. Now that the phy library is
no longer used to read and write the PCS registers the interrupts can be
masked off in the interrupt service routine eliminating the need to call
disable_irq/enable_irq. This also requires changing the protection mutex
to a spinlock.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Check to be sure that the Rx queue fifos are empty before stopping the
Rx DMA channels.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently the netdev traffic class setup is only performed when invoked
through the ndo_setup_tc interface. However, the same setup should be
performed when the dcbnl interface (ieee_setets) is invoked. Rework the
netdev traffic class setup to be invokable through either interface and
also provide the priority to traffic class mapping if available.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The driver is checking the pfc_en field of the ieee_pfc structure to
determine whether to associate a priority with a traffic class. This is
incorrect since the pfc_en field is for determining if PFC is enabled
for a traffic class.

The association of priority to traffic class does not depend on whether
the traffic class is enabled for PFC, so remove that check. Also, the
mapping of priorities to traffic classes should be done when configuring
the traffic classes and not the PFC support so move the priority to traffic
class association from xgbe_config_dcb_pfc to xgbe_config_dcb_tc.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently the PFC flow control is enabled on all traffic classes if
one or more traffic classes request it. The PFC enable setting of the
traffic class should be used to determine whether to enable or disable
flow control for the traffic class.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When using ethtool to set the speed for the device, verify that the
specified speed is valid within the active speedset.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Change from calling __napi_schedule to __napi_schedule_irqoff when running
in interrupt context or when called by netpoll with interrupts already
disabled. The Tx timer function will continue to use __napi_schedule.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Change from using napi_complete to napi_complete_done to allow for the
use of gro_flush_timeout in tuning network processing.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When the hardware is placed in promiscuous mode it will still perform
VLAN filtering and therefore may not pass all packets to the driver.

Disable all VLAN filtering when entering promiscuous mode and restore
VLAN filtering upon exit from promiscuous mode. In order to avoid adding
forward declarations, move the VLAN related functions earlier in the
file.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch updates setup_tc so we can pass additional parameters into
the ndo op in a generic way. To do this we provide structured union
and type flag.

This lets each classifier and qdisc provide its own set of attributes
without having to add new ndo ops or grow the signature of the
callback.
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The ndo_setup_tc() op was added to support drivers offloading tx
qdiscs however only support for mqprio was ever added. So we
only ever added support for passing the number of traffic classes
to the driver.

This patch generalizes the ndo_setup_tc op so that a handle can
be provided to indicate if the offload is for ingress or egress
or potentially even child qdiscs.

CC: Murali Karicheri <m-karicheri2@ti.com>
CC: Shradha Shah <sshah@solarflare.com>
CC: Or Gerlitz <ogerlitz@mellanox.com>
CC: Ariel Elior <ariel.elior@qlogic.com>
CC: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
CC: Bruce Allan <bruce.w.allan@intel.com>
CC: Jesse Brandeburg <jesse.brandeburg@intel.com>
CC: Don Skidmore <donald.c.skidmore@intel.com>
Signed-off-by: NJohn Fastabend <john.r.fastabend@intel.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

At the end of the loop we test "if (!count)" but because "count--" is
a post-op then the loop will end with count set to -1.  I have fixed
this by changing it to --count.

Fixes: c5aa9e3b ('amd-xgbe: Initial AMD 10GbE platform driver')
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We would like to automatically provide busy polling support
to all NAPI drivers, without them having to implement anything.

skb_mark_napi_id() can be called from napi_gro_receive() and
napi_get_frags().

Few drivers are still calling skb_mark_napi_id() because
they use netif_receive_skb(). They should eventually call
napi_gro_receive() instead. I will leave this to drivers
maintainers.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Now that we have the new DMA attribute APIs, we can replace the older
acpi_check_dma() and device_dma_is_coherent().
Signed-off-by: NSuravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>
Acked-by: NBjorn Helgaas <bhelgaas@google.com>
Reviewed-by: NHanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

During Tx cleanup it's still possible for the descriptor data to be
read ahead of the descriptor index. A memory barrier is required between
the read of the descriptor index and the start of the Tx cleanup loop.
This allows a change to a lighter-weight barrier in the Tx transmit
routine just before updating the current descriptor index.

Since the memory barrier does result in extra overhead on arm64, keep
the previous change to not chase the current descriptor value. This
prevents the execution of the barrier for each loop performed.
Suggested-by: NAlexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The code currently uses the lightweight dma_wmb barrier before updating
the current descriptor count. Under heavy load, the Tx cleanup routine
was seeing the updated current descriptor count before the updated
descriptor information. As a result, the Tx descriptor was being cleaned
up before it was used because it was not "owned" by the hardware yet,
resulting in a Tx queue hang.

Using the wmb barrier insures that the descriptor is updated before the
descriptor counter preventing the Tx queue hang. For extra insurance,
the Tx cleanup routine is changed to grab the current decriptor count on
entry and uses that initial value in the processing loop rather than
trying to chase the current value.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Tested-by: NChristoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Many drivers initialize uselessly n_priv_flags, n_stats, testinfo_len,
eedump_len & regdump_len fields in their .get_drvinfo() ethtool op.
It's not necessary as these fields is filled in ethtool_get_drvinfo().

v2: removed unused variable
v3: removed another unused variable
Signed-off-by: NIvan Vecera <ivecera@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

A previous patch switched from using the system workqueue to the device
workqueue for various operations. During a device restart the device
workqueue is flushed so the restart cannot use this workqueue or else
a deadlock results.  Move the device restart back to using the system
workqueue.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The kasprintf function can return NULL if the allocation fails. Check for
successful allocation before attempting to use the returned buffer.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The XGBE_LINK bit is used just to determine whether to call the
netif_carrier_on/off functions. Rather than define and use this bit,
just call the functions. The netif_carrier_ok function can be used in
place of checking the XGBE_LINK bit in the future.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The driver creates, flushes and destroys a device workqueue but queues
work to the system workqueue. Switch from using the system workqueue to
the device workqueue.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add a statistic that tracks how many times an interrupt is generated for
a receive buffer not being available to the hardware which prevents the
hardware from being able to DMA the received data.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The calculation of the Tx and Rx fifo sizes can be calculated rather
than hardcoded in a switch statement. Additionally, the per-queue fifo
sizes can be calculated rather than hardcoded using if/else if statements
that can possibly underutilize the available fifo area.

Change the code to calculate the fifo sizes and the per-queue fifo sizes
to simplify the code and make best use of the available fifo.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add error and dynamic debug messages to various ethtool functions in
the driver while also removing the DBGPR debug print calls. Also, change
the message level for some error messages from alert to err.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Provide the ethtool functions to support getting and setting the
msglevel for the driver.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Device tree presence takes precedence over ACPI in the device_* APIs.
The amd-xgbe driver should follow the same precedence. Update the check
on whether to use DT / ACPI to follow this.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Remove an unneeded semicolon at the end of a switch statement block.
Reported-by: Nkbuild test robot <fengguang.wu@intel.com>
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Added kfree() to avoid the memory leak when debugfs_create_dir() fails.
Signed-off-by: NGeliang Tang <geliangtang@163.com>
Acked-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Looks like the word "contiguous" is often mistyped.
Signed-off-by: NMasahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: NJiri Kosina <jkosina@suse.com>

When running a kernel configured with CONFIG_DMA_API_DEBUG=y a warning
is issued:
  DMA-API: device driver tries to sync DMA memory it has not allocated

This warning is the result of mapping the full range of the Rx buffer
pages allocated and then performing a dma_sync_single_for_cpu against
a calculated DMA address. The proper thing to do is to use the
dma_sync_single_range_for_cpu with a base DMA address and an offset.
Reported-by: NKim Phillips <kim.phillips@arm.com>
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Tested-by: NKim Phillips <kim.phillips@arm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When allocating Rx related buffers, alloc_pages is called using an order
number that is decreased until successful. A system under stress can
experience failures during this allocation process resulting in a warning
being issued. This message can be of concern to end users even though the
failure is not fatal. Since the failure is not fatal and can occur
multiple times, the driver should include the __GFP_NOWARN flag to
suppress the warning message from being issued.
Signed-off-by: NTom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>