In the latest revision of the hardware, if a packet is spanning
across multiple BDs then only VLD bit and current data size info
is valid in each BD, and rest of the information is only valid
in the last BD of the packet. In such case we should make sure
we are fetching RX packet size from the first descriptor and
information like VLAN should be fetched from last BD.
Signed-off-by: NPeng Li <lipeng321@huawei.com>
Reviewed-by: NYisen Zhuang <yisen.zhuang@huawei.com>
Signed-off-by: NSalil Mehta <salil.mehta@huawei.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Manage dwmac-4.20a version from synopsys
Signed-off-by: NChristophe Roullier <christophe.roullier@st.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Glue codes to support stm32mp157c device and stay
compatible with stm32 mcu familly
Signed-off-by: NChristophe Roullier <christophe.roullier@st.com>
Acked-by: NAlexandre TORGUE <alexandre.torgue@st.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Global variable gfar_phc_index was used to get and store
phc index through gianfar_ptp driver. However gianfar_ptp
had been renamed as ptp_qoriq for QorIQ common PTP driver.
This gfar_phc_index doesn't work any more, and the phc index
is stored in drvdata now. This patch is to support getting
phc index through ptp_qoriq drvdata.
Signed-off-by: NYangbo Lu <yangbo.lu@nxp.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

gianfar_ptp was the PTP clock driver for 1588 timer
module of Freescale QorIQ eTSEC (Enhanced Three-Speed
Ethernet Controllers) platforms. Actually QorIQ DPAA
(Data Path Acceleration Architecture) platforms is
also using the same 1588 timer module in hardware.

This patch is to rework gianfar_ptp as QorIQ common
PTP driver to support both DPAA and eTSEC. Moved
gianfar_ptp.c to drivers/ptp/, renamed it as
ptp_qoriq.c, and renamed many variables. There were
not any function changes.
Signed-off-by: NYangbo Lu <yangbo.lu@nxp.com>
Acked-by: NRichard Cochran <richardcochran@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Some drivers, such as DWC EQOS on Tegra, need to perform operations that
can sleep under this lock (clk_set_rate() in tegra_eqos_fix_speed()) for
proper operation. Since there is no need for this lock to be a spinlock,
convert it to a mutex instead.

Fixes: e6ea2d16 ("net: stmmac: dwc-qos: Add Tegra186 support")
Reported-by: NJon Hunter <jonathanh@nvidia.com>
Signed-off-by: NThierry Reding <treding@nvidia.com>
Tested-by: NBhadram Varka <vbhadram@nvidia.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Tx-timeout mostly happens due to some issue in the device. In such cases,
debug dump would be helpful for identifying the cause of the issue.
This patch adds support to spill debug data during the Tx timeout. Here
bnx2x_panic_dump() API is used instead of bnx2x_panic(), since we still
want to allow the Tx-timeout recovery a chance to succeed.

Changes from previous version:
-------------------------------
v2: Fixed a coding error.

Please consider applying this to "net-next".
Signed-off-by: NSudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The call to free_netdev() in __rtl8139_cleanup_dev() clears the network device
napi list, and explicit calls to netif_napi_del() are unnecessary.
Signed-off-by: NBo Chen <chenbo@pdx.edu>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In its current state, the driver will handle backing device
login in a loop for a certain number of retries while the
device returns a partial success, indicating that the driver
may need to try again using a smaller number of resources.

The variable it checks to continue retrying may change
over the course of operations, resulting in reallocation
of resources but exits without sending the login attempt.
Guard against this by introducing a boolean variable that
will retain the state indicating that the driver needs to
reattempt login with backing device firmware.
Signed-off-by: NThomas Falcon <tlfalcon@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

With this patch, User can configure for the supported
flows to be dropped. Added a stat "gft_filter_drop"
as well to be populated in ethtool for the dropped flows.

For example -

ethtool -N p5p1 flow-type udp4 dst-port 8000 action -1
ethtool -N p5p1 flow-type tcp4 scr-ip 192.168.8.1 action -1
Signed-off-by: NManish Chopra <manish.chopra@cavium.com>
Signed-off-by: NShahed Shaikh <shahed.shaikh@cavium.com>
Signed-off-by: NAriel Elior <ariel.elior@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

With the supported classification modes [4 tuples based,
udp port based, src-ip based], flows can be classified
to the VFs as well. With this patch, flows can be re-directed
to the requested VF provided in "action" field of command.

Please note that driver doesn't really care about the queue bits
in "action" field for the VFs. Since queue will be still chosen
by FW using RSS hash. [I.e., the classification would be done
according to vport-only]

For examples -

ethtool -N p5p1 flow-type udp4 dst-port 8000 action 0x100000000
ethtool -N p5p1 flow-type tcp4 src-ip 192.16.6.10 action 0x200000000
ethtool -U p5p1 flow-type tcp4 src-ip 192.168.40.100 dst-ip \
	192.168.40.200 src-port 6660 dst-port 5550 \
	action 0x100000000
Signed-off-by: NManish Chopra <manish.chopra@cavium.com>
Signed-off-by: NShahed Shaikh <shahed.shaikh@cavium.com>
Signed-off-by: NAriel Elior <ariel.elior@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Currently, driver supports flow classification to PF
receive queues based on TCP/UDP 4 tuples [src_ip, dst_ip,
src_port, dst_port] only.

This patch enables to configure different flow profiles
[For example - only UDP dest port or src_ip based] on the
adapter so that classification can be done according to
just those fields as well. Although, at a time just one
type of flow configuration is supported due to limited
number of flow profiles available on the device.

For example -

ethtool -N enp7s0f0 flow-type udp4 dst-port 45762 action 2
ethtool -N enp7s0f0 flow-type tcp4 src-ip 192.16.4.10 action 1
ethtool -N enp7s0f0 flow-type udp6 dst-port 45762 action 3
Signed-off-by: NManish Chopra <manish.chopra@cavium.com>
Signed-off-by: NShahed Shaikh <shahed.shaikh@cavium.com>
Signed-off-by: NAriel Elior <ariel.elior@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Validate and prevent some of the configurations for
unsupported [by firmware] inputs [for example - mac ext,
vlans, masks/prefix, tos/tclass] via ethtool -N/-U.
Signed-off-by: NManish Chopra <manish.chopra@cavium.com>
Signed-off-by: NShahed Shaikh <shahed.shaikh@cavium.com>
Signed-off-by: NAriel Elior <ariel.elior@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch simplifies the ethtool rx flow configuration
[via ethtool -U/-N] flow code base by dividing it logically
into various APIs based on given protocols. It also separates
various validations and calculations done along the flow
in their own APIs.
Signed-off-by: NManish Chopra <manish.chopra@cavium.com>
Signed-off-by: NShahed Shaikh <shahed.shaikh@cavium.com>
Signed-off-by: NAriel Elior <ariel.elior@cavium.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We have a confusion of two different abstractions in the Common
Code:  Physical Link (Port) and Logical Network Interface (Virtual
Interface), and we haven't been properly managing the state of the
intersection of those two abstractions.
On the one hand we have the Physical state of the Link -- up or down --
and on the other we have the logical state of the VI, enabled or not.
{ethN} refers to both the Physical and Logical State. In this case,
ifconfig only affects/interrogates the Logical State of a VI,
and ethtool only deals with the Physical State. And these are different.

So, just because we disable the VI, we don't really want to change the
Physical Link Up/Down state.  Thus, the previous hack to set
"lc->link_ok = 0" when we disable a VI is completely incorrect.

Where we get into trouble is where the Physical Link State and the
Logical VI State cross swords.  And that happens in
t4_handle_get_port_info() where we need to manage/safe the Physical
Link State, but we also need to know when the Logical VI State has
changed and pass that back up to the OS-dependent Driver routine
t4_os_link_changed() which is concerned about the Logical Interface.

So we enable a VI and that causes Firmware to send us a new Port
Information message, but if none of the Physical Link State
particulars have changed, we don't call t4_os_link_changed().

This fix uses the existing OS Contract APIs for the Common Code to
inform the OS-dependent portion of the Host Driver when the "Link" (really
Logical Network Interface) is "up" or "down". A new API
t4_enable_pi_params() is added which calls t4_enable_vi_params() and,
if that is successful, then calls back to the OS Contract API
t4_os_link_changed() notifying the OS-dependent layer of the
potential Link State change.

Original Work by : Casey Leedom <leedom@chelsio.com>
Signed-off-by: NSantosh Rastapur <santosh@chelsio.com>
Signed-off-by: NArjun Vynipadath <arjun@chelsio.com>
Signed-off-by: NGanesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

clean up init_one and use chip_ver consistently throughout
init_one() for chip version.
Signed-off-by: NCasey Leedom <leedom@chelsio.com>
Signed-off-by: NGanesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

newer SFPs like SFP28 and QSFP28 Transceiver Modules present
several new possibilities which we haven't faced before. Fix the
assumptions in the code reflecting the more limited capabilities
of previous Transceiver Module systems

Original work by Casey Leedom <leedom@chelsio.com>
Signed-off-by: NGanesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This comment is outdated as fec_ptp_ioctl has been replaced by fec_ptp_set/fec_ptp_get
since commit 1d5244d0 ("fec: Implement the SIOCGHWTSTAMP ioctl")
Signed-off-by: NYueHaibing <yuehaibing@huawei.com>
Acked-by: NFugang Duan <fugang.duan@nxp.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

efx_enqueue_skb() can push new buffers for the xmit_more functionality.
We must stops the TX queue before this or else the TX queue does not get
restarted and we get a netdev watchdog.

In the error handling we may now need to unwind more than 1 packet, and
we may need to push the new buffers onto the partner queue.

v2: In the error leg also push this queue if xmit_more is set

Fixes: e9117e50 ("sfc: Firmware-Assisted TSO version 2")
Reported-by: NJarod Wilson <jarod@redhat.com>
Tested-by: NJarod Wilson <jarod@redhat.com>
Signed-off-by: NMartin Habets <mhabets@solarflare.com>
Acked-by: NEdward Cree <ecree@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When a system is under memory presure (high usage with fragments),
the original 256KB ICM chunk allocations will likely trigger kernel
memory management to enter slow path doing memory compact/migration
ops in order to complete high order memory allocations.

When that happens, user processes calling uverb APIs may get stuck
for more than 120s easily even though there are a lot of free pages
in smaller chunks available in the system.

Syslog:
...
Dec 10 09:04:51 slcc03db02 kernel: [397078.572732] INFO: task
oracle_205573_e:205573 blocked for more than 120 seconds.
...

With 4KB ICM chunk size on x86_64 arch, the above issue is fixed.

However in order to support smaller ICM chunk size, we need to fix
another issue in large size kcalloc allocations.

E.g.
Setting log_num_mtt=30 requires 1G mtt entries. With the 4KB ICM chunk
size, each ICM chunk can only hold 512 mtt entries (8 bytes for each mtt
entry). So we need a 16MB allocation for a table->icm pointer array to
hold 2M pointers which can easily cause kcalloc to fail.

The solution is to use kvzalloc to replace kcalloc which will fall back
to vmalloc automatically if kmalloc fails.
Signed-off-by: NQing Huang <qing.huang@oracle.com>
Acked-by: NDaniel Jurgens <danielj@mellanox.com>
Reviewed-by: NZhu Yanjun <yanjun.zhu@oracle.com>
Reviewed-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If the egress device of an offloaded rule is a LAG port, then encode the
output port to the NFP with a LAG identifier and the offloaded group ID.

A prelag action is also offloaded which must be the first action of the
series (although may appear after other pre-actions - e.g. tunnels). This
causes the FW to check that it has the necessary information to output to
the requested LAG port. If it does not, the packet is sent to the kernel
before any other actions are applied to it.
Signed-off-by: NJohn Hurley <john.hurley@netronome.com>
Reviewed-by: NPieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Adds the control message handler to synchronize offloaded group config
with that of the kernel. Such messages are sent from fw to driver and
feature the following 3 flags:

- Data: an attached cmsg could not be processed - store for retransmission
- Xon: FW can accept new messages - retransmit any stored cmsgs
- Sync: full sync requested so retransmit all kernel LAG group info
Signed-off-by: NJohn Hurley <john.hurley@netronome.com>
Reviewed-by: NPieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Monitor LAG events via the NETDEV_CHANGEUPPER/NETDEV_CHANGELOWERSTATE
notifiers to maintain a list of offloadable groups. Sync these groups with
HW via a delayed workqueue to prevent excessive re-configuration. When the
workqueue is triggered it may generate multiple control messages for
different groups. These messages are linked via a batch ID and flags to
indicate a new batch and the end of a batch.

Update private data in each repr to track their LAG lower state flags. The
state of a repr is used to determine the active netdevs that can be
offloaded. For example, in active-backup mode, we only offload the netdev
currently active.
Signed-off-by: NJohn Hurley <john.hurley@netronome.com>
Reviewed-by: NPieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add a bitmap to each flower repr to track its state if it is enslaved by a
bond. This LAG state may be different to the port state - for example, the
port may be up but LAG state may be down due to the selection in an
active/backup bond.
Signed-off-by: NJohn Hurley <john.hurley@netronome.com>
Reviewed-by: NPieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Check if the fw contains the _abi_flower_balance_sync_enable symbol. If it
does then write a 1 to this indicating that the driver is willing to
receive NIC to kernel LAG related control messages.

If the write is successful, update the list of extra features supported by
the fw and add a stub to accept LAG cmsgs.
Signed-off-by: NJohn Hurley <john.hurley@netronome.com>
Reviewed-by: NPieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add an rtsym API function that combines the lookup of a symbol and the
writing of a value to it. Values can be written as unsigned 32 or 64 bits.
Signed-off-by: NJohn Hurley <john.hurley@netronome.com>
Reviewed-by: NPieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Adding a netdev to a bond requires that its mac address can be modified.
The default eth_mac_addr is sufficient to satisfy this requirement.
Signed-off-by: NJohn Hurley <john.hurley@netronome.com>
Reviewed-by: NPieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In commit 624dbf55 ("driver/net: enic: Try DMA 64 first, then
failover to DMA") DMA mask was changed from 40 bits to 64 bits.
Hardware actually supports only 47 bits.

Fixes: 624dbf55 ("driver/net: enic: Try DMA 64 first, then failover to DMA")
Signed-off-by: NGovindarajulu Varadarajan <gvaradar@cisco.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Introduce a recovery hard reset to handle reset failure as a result of
change of device context following a transport event, such as a
backing device failover or partition migration. These operations reset
the device context to its initial state. If this occurs during a reset,
any initialization commands are likely to fail with an invalid state
error as backing device firmware requests reinitialization.

When this happens, make one more attempt by performing a hard reset,
which frees any resources currently allocated and performs device
initialization. If a transport event occurs during a device reset, a
flag is set which will trigger a new hard reset following the
completionof the current reset event.
Signed-off-by: NThomas Falcon <tlfalcon@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Set device resetting state at the earliest possible point: as soon as a
reset is successfully scheduled. The reset state is toggled off when
all resets have been processed to completion.
Signed-off-by: NThomas Falcon <tlfalcon@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Instead of having one initialization routine for all cases, create
a separate, simpler function for standard initialization, such as during
device probe. Use the original initialization function to handle
device reset scenarios. The goal of this patch is to avoid having
a single, cluttered init function to handle all possible
scenarios.
Signed-off-by: NThomas Falcon <tlfalcon@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If setting the link state is not successful, print a warning
with the resulting return code and return it to be handled
by the caller.
Signed-off-by: NThomas Falcon <tlfalcon@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

If device init is interrupted by a failover, set the init return
code so that it can be checked and handled appropriately by the
init routine.
Signed-off-by: NThomas Falcon <tlfalcon@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Check whether CRQ command is successful before awaiting a response
from the management partition. If the command was not successful, the
driver may hang waiting for a response that will never come.
Signed-off-by: NThomas Falcon <tlfalcon@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Introduce an "active" state for a IBM vNIC Command-Response Queue. A CRQ
is considered active once it has initialized or linked with its partner by
sending an initialization request and getting a successful response back
from the management partition.  Until this has happened, do not allow CRQ
commands to be sent other than the initialization request.

This change will avoid a protocol error in case of a device transport
event occurring during a initialization. When the driver receives a
transport event notification indicating that the backing hardware
has changed and needs reinitialization, any further commands other
than the initialization handshake with the VIOS management partition
will result in an invalid state error. Instead of sending a command
that will be returned with an error, print a warning and return an
error that will be handled by the caller.
Signed-off-by: NThomas Falcon <tlfalcon@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Set adapter NAPI state as disabled if they are removed. This will allow
them to be enabled again if reallocated in case of a hard reset.
Signed-off-by: NThomas Falcon <tlfalcon@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

t4_prep_fw doesn't check for card_fw pointer before store the read data,
which could lead to a NULL pointer dereference if kvzalloc failed.
Signed-off-by: NYueHaibing <yuehaibing@huawei.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch change the API for ndo_xdp_xmit to support bulking
xdp_frames.

When kernel is compiled with CONFIG_RETPOLINE, XDP sees a huge slowdown.
Most of the slowdown is caused by DMA API indirect function calls, but
also the net_device->ndo_xdp_xmit() call.

Benchmarked patch with CONFIG_RETPOLINE, using xdp_redirect_map with
single flow/core test (CPU E5-1650 v4 @ 3.60GHz), showed
performance improved:
 for driver ixgbe: 6,042,682 pps -> 6,853,768 pps = +811,086 pps
 for driver i40e : 6,187,169 pps -> 6,724,519 pps = +537,350 pps

With frames avail as a bulk inside the driver ndo_xdp_xmit call,
further optimizations are possible, like bulk DMA-mapping for TX.

Testing without CONFIG_RETPOLINE show the same performance for
physical NIC drivers.

The virtual NIC driver tun sees a huge performance boost, as it can
avoid doing per frame producer locking, but instead amortize the
locking cost over the bulk.

V2: Fix compile errors reported by kbuild test robot <lkp@intel.com>
V4: Isolated ndo, driver changes and callers.
Signed-off-by: NJesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>

Sandbox QP Commands are retired in the order they are sent. Outstanding
commands are stored in a linked-list in the order they appear. Once a
response is received and the callback gets called, we pull the first
element off the pending list, assuming they correspond.

Sending a message and adding it to the pending list is not done atomically,
hence there is an opportunity for a race between concurrent requests.

Bind both send and add under a critical section.

Fixes: bebb23e6 ("net/mlx5: Accel, Add IPSec acceleration interface")
Signed-off-by: NYossi Kuperman <yossiku@mellanox.com>
Signed-off-by: NAdi Nissim <adin@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>

When RXFCS feature is enabled, the HW do not strip the FCS data,
however it is not present in the checksum calculated by the HW.

Fix that by manually calculating the FCS checksum and adding it to the SKB
checksum field.

Add helper function to find the FCS data for all SKB forms (linear,
one fragment or more).

Fixes: 102722fc ("net/mlx5e: Add support for RXFCS feature flag")
Signed-off-by: NEran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: NSaeed Mahameed <saeedm@mellanox.com>