Aggregation effects are extremely common with wifi, cellular, and cable
modem link technologies, ACK decimation in middleboxes, and LRO and GRO
in receiving hosts. The aggregation can happen in either direction,
data or ACKs, but in either case the aggregation effect is visible
to the sender in the ACK stream.

Previously BBR's sending was often limited by cwnd under severe ACK
aggregation/decimation because BBR sized the cwnd at 2*BDP. If packets
were acked in bursts after long delays (e.g. one ACK acking 5*BDP after
5*RTT), BBR's sending was halted after sending 2*BDP over 2*RTT, leaving
the bottleneck idle for potentially long periods. Note that loss-based
congestion control does not have this issue because when facing
aggregation it continues increasing cwnd after bursts of ACKs, growing
cwnd until the buffer is full.

To achieve good throughput in the presence of aggregation effects, this
algorithm allows the BBR sender to put extra data in flight to keep the
bottleneck utilized during silences in the ACK stream that it has evidence
to suggest were caused by aggregation.

A summary of the algorithm: when a burst of packets are acked by a
stretched ACK or a burst of ACKs or both, BBR first estimates the expected
amount of data that should have been acked, based on its estimated
bandwidth. Then the surplus ("extra_acked") is recorded in a windowed-max
filter to estimate the recent level of observed ACK aggregation. Then cwnd
is increased by the ACK aggregation estimate. The larger cwnd avoids BBR
being cwnd-limited in the face of ACK silences that recent history suggests
were caused by aggregation. As a sanity check, the ACK aggregation degree
is upper-bounded by the cwnd (at the time of measurement) and a global max
of BW * 100ms. The algorithm is further described by the following
presentation:
https://datatracker.ietf.org/meeting/101/materials/slides-101-iccrg-an-update-on-bbr-work-at-google-00

In our internal testing, we observed a significant increase in BBR
throughput (measured using netperf), in a basic wifi setup.
- Host1 (sender on ethernet) -> AP -> Host2 (receiver on wifi)
- 2.4 GHz -> BBR before: ~73 Mbps; BBR after: ~102 Mbps; CUBIC: ~100 Mbps
- 5.0 GHz -> BBR before: ~362 Mbps; BBR after: ~593 Mbps; CUBIC: ~601 Mbps

Also, this code is running globally on YouTube TCP connections and produced
significant bandwidth increases for YouTube traffic.

This is based on Ian Swett's max_ack_height_ algorithm from the
QUIC BBR implementation.
Signed-off-by: Priyaranjan Jha <priyarjha@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Because bbr_target_cwnd() is really a general-purpose BBR helper for
computing some volume of inflight data as a function of the estimated
BDP, refactor it into following helper functions:
- bbr_bdp()
- bbr_quantization_budget()
- bbr_inflight()
Signed-off-by: Priyaranjan Jha <priyarjha@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Few chip versions use the same sequence to adjust 10M and ALDPS, so
let's factor it out. This patch also fixes a (most likely) typo in
rtl8168g_1_hw_phy_config. There bit 8 in reg 0x14 on page 0x0bcc
was set and not cleared. According to the vendor driver this bit
needs to be cleared in all cases.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Chip versions from RTL8168g onward use the same sequence to disable
ALDPS (Advanced Link-Down Power Saving). So let's factor this out.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

I made a dumb mistake when I summed up the slave stats, obviously slaves
can come and go which would make the master stats unreliable.
Count and export the master stats separately.

Fixes: a258aeac ("bonding: add support for xstats and export 3ad stats")
Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Heiner Kallweit says:

====================
net: phy: improve starting PHY

This patch series improves few aspects of starting the PHY.

v2:
- improve a warning in patch 4
v3:
- extend commit message for patch 2
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Now that we enable the interrupts in phy_start() we don't have to do it
before. Therefore remove enabling interrupts from phy_start_interrupts()
and rename this function to reflect the changed functionality.

v2:
- improve warning to clearly state that we fall back to polling
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Interrupts don't have to be enabled before calling phy_start().
Therefore let's enable them in phy_start(). In a subsequent step
we'll remove enabling interrupts from phy_connect_direct().
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

phy_start() should be called from states PHY_READY or PHY_HALTED only.
Check for this to detect misbehaving drivers. Also the state machine
should be started only when being called from one of the valid states.

Some more background:
For all invalid states phy_start() basically was a no-op. All it did
was triggering a state machine run, but for all "running" states the
poll loop was active anyway. And if called from PHY_DOWN, the state
machine does nothing.

v3:
- extended commit message
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The state machine is a no-op before phy_start() has been called.
Therefore let's enable it in phy_start() only. In phy_start()
let's call phy_start_machine() instead of phy_trigger_machine().
phy_start_machine is an alias for phy_trigger_machine but it makes
clearer that we start the state machine here instead of just
triggering a run.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

In case of error, the function devm_clk_get() returns ERR_PTR() and
never returns NULL. The NULL test in the return value check should be
replaced with IS_ERR().

Fixes: a7c30e62 ("net: stmmac: Add driver for Qualcomm ethqos")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Acked-by: Vinod Koul <vkoul@kernel.org>
Acked-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Two statements are incorrecly indented, fix these by removing a space.
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Claudiu Manoil says:

====================
Introduce ENETC ethernet drivers

ENETC is a multi-port virtualized Ethernet controller supporting GbE
designs and Time-Sensitive Networking (TSN) functionality.
ENETC is operating as an SR-IOV multi-PF capable Root Complex Integrated
Endpoint (RCIE).  As such, it contains multiple physical (PF) and virtual
(VF) PCIe functions, discoverable by standard PCI Express.

The patch series adds basic enablement for these otherwise standard
buffer descriptor (BD) ring based ethernet devices (PCIe PFs and VFs),
currently included in the 64-bit dual ARMv8 processors LS1028A SoC.
The driver is portable to 32-bit designs, and it's independent of CPU
endianness.

Contributors:
Alex Marginean <alexandru.marginean@nxp.com>
Catalin Horghidan <catalin.horghidan@nxp.com>

TODO list:
* IEEE 1588 PTP support;
* TSN support;
* MDIO support and VF link management;
* power management support;
* flow control support;
* TC offloading with h/w MQPRIO;
* interrupt coalescing, configurable BD ring sizes, and other usual
config options if missing.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

A ternary match table is used for RFS. If multiple entries in the table
match, the entry with the lowest numerical values index is chosen as the
matching entry.  Entries in the table are identified using an index
which takes a value from 0 to PRFSCAPR[NUM_RFS]-1 when accessed by the
PSI (PF).
Portions of the RFS table can be assigned to each SI by the PSI (PF)
driver in PSIaRFSCFGR.  Assignments are cumulative, the entries assigned
to SIn start after those assigned to SIn-1.  The total assignments to
all SIs must be equal to or less than the number available to the port
as found in PRFSCAPR.

For RSS, the Toeplitz hash function used requires two inputs, a 40B
random secret key that is supplied through the PRSSKR0-9 registers as well
as the relevant pieces of the packet header (n-tuple).  The 6 LSB bits of
the hash function result will then be used as a pointer to obtain the tag
referenced in the 64 entry indirection table.  The result will provide a
winning group which will be used to help route the received packet.
Signed-off-by: Alex Marginean <alexandru.marginean@nxp.com>
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

VSIs (VFs) may send a message to the PSI (PF) for general notification
or to gain access to hardware resources which requires host inspection.
These messages may vary in size and are handled as a partition copy
between two memory regions owned by the respective participants.
The PSI will respond with fail or success and a 16-bit message code.
The patch implements the vf to pf messaging mechanism above and, as the
first application making use of this support, it enables the VF to
configure its own primary MAC address.
Signed-off-by: Catalin Horghidan <catalin.horghidan@nxp.com>
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This adds most h/w statistics counters: non-privileged SI conters, as
well as privileged Port and MAC counters available only to the PF.
Per ring software stats are also included.
Signed-off-by: Alex Marginean <alexandru.marginean@nxp.com>
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

ENETC is a multi-port virtualized Ethernet controller supporting GbE
designs and Time-Sensitive Networking (TSN) functionality.
ENETC is operating as an SR-IOV multi-PF capable Root Complex Integrated
Endpoint (RCIE).  As such, it contains multiple physical (PF) and
virtual (VF) PCIe functions, discoverable by standard PCI Express.

Introduce basic PF and VF ENETC ethernet drivers.  The PF has access to
the ENETC Port registers and resources and makes the required privileged
configurations for the underlying VF devices.  Common functionality is
controlled through so called System Interface (SI) register blocks, PFs
and VFs own a SI each.  Though SI register blocks are almost identical,
there are a few privileged SI level controls that are accessible only to
PFs, and so the distinction is made between PF SIs (PSI) and VF SIs (VSI).
As such, the bulk of the code, including datapath processing, basic h/w
offload support and generic pci related configuration, is shared between
the 2 drivers and is factored out in common source files (i.e. enetc.c).

Major functionalities included (for both drivers):
MSI-X support for Rx and Tx processing, assignment of Rx/Tx BD ring pairs
to MSI-X entries, multi-queue support, Rx S/G (Rx frame fragmentation) and
jumbo frame (up to 9600B) support, Rx paged allocation and reuse, Tx S/G
support (NETIF_F_SG), Rx and Tx checksum offload, PF MAC filtering and
initial control ring support, VLAN extraction/ insertion, PF Rx VLAN
CTAG filtering, VF mac address config support, VF VLAN isolation support,
etc.
Signed-off-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Soften the memory barrier call of mb() by a sufficient wmb() in the
consumer index update of the event queues.
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

So far member rtl_fw has three states:
- IS_ERR(rtl_fw): firmware not loaded
- !rtl_fw: no firmware available
- other: firmware loaded

This can be made simpler and clearer by adding the firmware name as
member fw_name to struct rtl8169_private. Then:

- !fw_name: no firmware available
- !rtl_fw: firmware not loaded
- rtl_fw: firmware loaded

This change also allows to easily merge rtl_request_uncached_firmware
into rtl_request_firmware.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Huazhong Tan says:

====================
code optimizations & bugfixes for HNS3 driver

This patchset includes bugfixes and code optimizations for the HNS3
ethernet controller driver

Change log:
V1->V2: fixes comment from Eric Dumazet
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

The PFC enabling is based on user priority, currently it is
based on TC, which may cause PFC not setting correctly when pri
to TC mapping is not one to one relation.

This patch adds pfc_en in tm_info to fix it.

Fixes: cacde272 ("net: hns3: Add hclge_dcb module for the support of DCB feature")
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

In the old firmware version, statistics acquisition of
PFC frames and MAC control frames is not supported.
Add command retrieves statistics for PFC frames and
MAC control frames from the firmware.
Signed-off-by: liuzhongzhu <liuzhongzhu@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch sets the TC weight in SSU module according to
info in tm_info.

Also, zero weight of TC weight in SSU ETS module means enabling
strict priority, so do not allow zero weight when in ETS mode.
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

GE MAC does not support PFC, when driver is initializing and MAC
is in GE Mode, ignore the fw not supported error, otherwise
initialization will fail.
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

According to firmware error code definition, the error code of 2
means NOT_SUPPORTED, this patch changes it to NOT_SUPPORTED.
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Param pending_buf and skb may be not NULL when free ring.
This patch clears them when free ring.
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The current code returns the number of all queues that can be used and
the number of queues that have been allocated, which is incorrect.
What should be returned is the number of queues allocated for each enabled
TC and the number of queues that can be allocated.

This patch fixes it.

Fixes: 849e4607 ("net: hns3: add ethtool_ops.get_channels support for VF")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Shaper setting does not change currently, when TC num changes,
which may cause shaper parameter not setting problem.

This patch fixes it by setting the shaper parameter when TC num
changes.

Fixes: cacde272 ("net: hns3: Add hclge_dcb module for the support of DCB feature")
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Currently rss configuration set by user will be lost when setting
channel.

This patch fixes it by not setting rss configuration to default
if user has configured the rss.

Fixes: 09f2af64 ("net: hns3: add support to modify tqps number")
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

In origin codes, there are some statistics item are got from mac, which
also include the packets statistics of VF. It is unreasonable. This
patch fixes it by counting them in the rx/tx processing flow.
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch adds rx multicast packets statistic for each ring.
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

This patch adds calling roce callback function when link status
change.
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Ido Schimmel says:

====================
mlxsw: Add VXLAN support for Spectrum-2

This patchset adds support for VXLAN tunneling on the Spectrum-2 ASIC.
Spectrum-1 and Spectrum-2 are largely backward compatible in this area,
so not too many changes are required.

Patches #1-#2 expose a function and perform small refactoring towards
the actual Spectrum-2 implementation in patches #3-#4.

Patch #3 adds the required initialization steps on Spectrum-2.

Patch #4 finally enables VXLAN on Spectrum-2.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Enable VXLAN on Spectrum-2 as previous patches added the required
functionality.

Note that for now Spectrum-1 and Spectrum-2 use the same function to
determine whether the VXLAN configuration is valid or not. In the
future, when the driver will be extended to support features not present
in Spectrum-1, two different functions will be needed.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Spectrum-1 and Spectrum-2 are largely backward compatible with regards
to VXLAN. One difference - as explained in previous patch - is that an
underlay RIF needs to be specified instead of an underlay VR during NVE
initialization. This is accomplished by calling the relevant function
that returns the index of such a RIF based on the table ID
(RT_TABLE_MAIN) where underlay look up occurs.

The second difference is that VXLAN learning (snooping) is controlled
via a different register (TNPC).
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

The configuration of a VXLAN tunnel in Spectrum-1 and Spectrum-2 is
largely the same. To avoid code duplication, breakout the common parts
to a common function that can be invoked from the ASIC-specific code.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

In Spectrum-2, instead of providing the ID of the virtual router (VR)
where NVE underlay lookups will occur as in Spectrum-1, the ID of a
router interface (RIF) in this VR is required.

Expose functions to create and destroy such a RIF.
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

This patch fixes the following warning:

drivers/net/ethernet/mellanox/mlx4/eq.c: In function ‘mlx4_eq_int’:
drivers/net/ethernet/mellanox/mlx4/mlx4.h:219:5: warning: this statement may fall through [-Wimplicit-fallthrough=]
  if (mlx4_debug_level)      \
     ^
drivers/net/ethernet/mellanox/mlx4/eq.c:558:4: note: in expansion of macro ‘mlx4_dbg’
    mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT. srq_no=0x%x, eq 0x%x\n",
    ^~~~~~~~
drivers/net/ethernet/mellanox/mlx4/eq.c:561:3: note: here
   case MLX4_EVENT_TYPE_SRQ_CATAS_ERROR:
   ^~~~

Warning level 3 was used: -Wimplicit-fallthrough=3

This patch is part of the ongoing efforts to enabling
-Wimplicit-fallthrough.
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

This patch fixes the following warning:

drivers/net/ethernet/qlogic/qed/qed_cxt.c:2126:4: warning: this statement may fall through [-Wimplicit-fallthrough=]

Warning level 3 was used: -Wimplicit-fallthrough=3

This patch is part of the ongoing efforts to enabling
-Wimplicit-fallthrough.
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

This patch fixes the following warnings:

drivers/net/ethernet/brocade/bna/bfa_ioc.c:790:3: warning: this statement may fall through [-Wimplicit-fallthrough=]
drivers/net/ethernet/brocade/bna/bfa_ioc.c:860:3: warning: this statement may fall through [-Wimplicit-fallthrough=]

Warning level 3 was used: -Wimplicit-fallthrough=3

This patch is part of the ongoing efforts to enabling
-Wimplicit-fallthrough
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Sudarsana Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>