Turn on the out of band Advanced Congestion Buffering (ACB) mechanism at
the switch level now that we have properly established the queue mapping
between the switch egress queues and the SYSTEMPORT egress queues. This
allows the switch to correctly backpressure the host system when one of
its queue drops below the configured thresholds.

This is also helping achieve so called "lossless" behavior by adapting
the TX interrupt pacing to the actual speed and capacity of the switch
port.
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Establish a queue mapping between the DSA slave network device queues
created that correspond to switch port queues, and the transmit queue
that SYSTEMPORT manages.

We need to configure the SYSTEMPORT transmit queue with the switch port number
and switch port queue number in order for the switch and SYSTEMPORT hardware to
utilize the out of band congestion notification. This hardware mechanism works
by looking at the switch port egress queue and determines whether there is
enough buffers for this queue, with that class of service for a successful
transmission and if not, backpressures the SYSTEMPORT queue that is being used.

For this to work, we implement a notifier which looks at the
DSA_PORT_REGISTER event.  When DSA network devices are registered, the
framework calls the DSA notifiers when that happens, extracts the number
of queues for these devices and their associated port number, remembers
that in the driver private structure and linearly maps those queues to
TX rings/queues that we manage.

This scheme works because DSA slave network deviecs always transmit
through SYSTEMPORT so when DSA slave network devices are
destroyed/brought down, the corresponding SYSTEMPORT queues are no
longer used. Also, by design of the DSA framework, the master network
device (SYSTEMPORT) is registered first.

For faster lookups we use an array of up to DSA_MAX_PORTS * number of
queues per port, and then map pointers to bcm_sysport_tx_ring such that
our ndo_select_queue() implementation can just index into that array to
locate the corresponding ring index.
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

We need to tell the DSA master network device doing the actual
transmission what the desired switch port and queue number is for it to
resolve that to the internal transmit queue it is mapped to.
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In preparation for communicating a given DSA network device's port
number and switch index, create a specialized DSA notifier and two
events: DSA_PORT_REGISTER and DSA_PORT_UNREGISTER that communicate: the
slave network device (slave_dev), port number and switch number in the
tree.

This will be later used for network device drivers like bcmsysport which
needs to cooperate with its DSA network devices to set-up queue mapping
and scheduling.
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This reverts commit df1ec1b9.

It turns out that memory allocated via dma_alloc_coherent is always
aligned to the size of the buffer, so there's no way the RRD and RFD
can ever be in separate 32-bit regions.
Signed-off-by: NTimur Tabi <timur@codeaurora.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Remove three inline helpers that are no longer needed.
Signed-off-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Variable old_flags is being assigned but is never read; it is redundant
and can be removed.

Cleans up clang warning: Value stored to 'old_flags' is never read
Signed-off-by: NColin Ian King <colin.king@canonical.com>
Acked-by: NAlexei Starovoitov <ast@kernel.org>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Tariq Toukan says:

====================
mlx4_en XDP TX improvements

This patchset contains performance improvements
to the XDP_TX use case in the mlx4 Eth driver.

Patch 1 is a simple change in a function parameter type.
Patch 2 replaces a call to a generic function with the
  relevant parts inlined.
Patch 3 moves the write of descriptors' constant values
  from data path to control path.

Series generated against net-next commit:
833e0e2f net: dst: move cpu inside ifdef to avoid compilation warning
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

In XDP_TX, some fields in tx_info and tx_desc are constants across
all entries of the different XDP_TX rings.
Assign values to these fields on ring creation time, rather than in
data-path.

Patchset performance tests:
Tested on ConnectX3Pro, Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
Single queue no-RSS optimization ON.

XDP_TX packet rate:
------------------------------
Before    | After     | Gain |
13.7 Mpps | 14.0 Mpps | %2.2 |
------------------------------
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Function mlx4_en_tx_write_desc() is not optimized to use of XDP xmit.
Use the relevant parts inline instead.
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The struct net_device parameter was passed only to extract
struct mlx4_en_priv out of it.
Here we pass the priv parameter directly.
Signed-off-by: NTariq Toukan <tariqt@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The function ipgre_mpls_encap_hlen is local to the source and
does not need to be in global scope, so make it static.

Cleans up sparse warning:
symbol 'ipgre_mpls_encap_hlen' was not declared. Should it be static?

Fixes: bdc47641 ("ip_tunnel: add mpls over gre support")
Signed-off-by: NColin Ian King <colin.king@canonical.com>
Acked-by: NDavid Ahern <dsahern@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The array sctp_sched_ops  is local to the source and
does not need to be in global scope, so make it static.

Cleans up sparse warning:
symbol 'sctp_sched_ops' was not declared. Should it be static?
Signed-off-by: NColin Ian King <colin.king@canonical.com>
Acked-by: NNeil Horman <nhorman@tuxdriver.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Similar to the previous patch, use the device lookup functions
that bump device refcount and flag this as DOIT_UNLOCKED to avoid
rtnl mutex.
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Instead of relying on rtnl mutex bump device reference count.
After this change, values reported can change in parallel, but thats not
much different from current state, as anyone can change the settings
right after rtnl_unlock (and before userspace processed reply).

While at it, switch to GFP_KERNEL allocation.
Signed-off-by: NFlorian Westphal <fw@strlen.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jiri Pirko says:

====================
net: sched: get rid of cls_flower->egress_dev

Introduction of cls_flower->egress_dev was a workaround. Turned out
to be a bit ugly hack. So replace it with more generic and reusable
infrastructure.

This is a dependency of shared block introduction that will be send as
a follow-up patchsets group.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The helper and the struct field ares no longer used by any code,
so remove them.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The only user of cls_flower->egress_dev is mlx5. So do the conversion
there alongside with the code originating the call in cls_flower
function fl_hw_replace_filter to the newly introduced egress device
callback infrastucture.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Introduce infrastructure that allows drivers to register callbacks that
are called whenever tc would offload inserted rule and specified device
acts as tc action egress device.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Return dev directly, NULL if not possible. That is enough.

Makes no sense to pass struct net * to get_dev op, as there is only one
net possible, the one the action was created in. So just store it in
mirred priv and use directly.

Rename the mirred op callback function.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Subash Abhinov Kasiviswanathan says:

====================
net: qualcomm: rmnet: Rewrite some existing functionality

This series fixes some of the broken rmnet functionality.
Bridge mode is re-written and made useable and the muxed_ep is converted to hlist.

Patches 1-5 are cleanups in preparation for these changes.
Patch 6 does the hlist conversion.
Patch 7 has the implementation of the rmnet bridge mode.

v1->v2: Fix the warning and code style issue in rmnet_rx_handler as
mentioned by David.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add support to bridge two devices which can send multiplexing and
aggregation (MAP) data. This is done only when the data itself is
not going to be consumed in the stack but is being passed on to a
different endpoint. This is mainly used for testing.
Signed-off-by: NSubash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Rather than using a static array, use a hlist to store the muxed
endpoints and use the mux id to query the rmnet_device.
This is useful as usually very few mux ids are used.
Signed-off-by: NSubash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Cc: Dan Williams <dcbw@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The rmnet_devices information is already stored in muxed_ep, so
storing this in rmnet_devices[] again is redundant.
Signed-off-by: NSubash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The end point is set twice in the local_ep as well as the mux_id and
the real_dev in the rmnet private structure. Remove the local_ep.
While these elements are equivalent, rmnet_endpoint will be
used only as part of the rmnet_port for muxed scenarios in VND mode.
Signed-off-by: NSubash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Mode information on the real device makes it easier to route packets
to rmnet device or bridged device based on the configuration.
Signed-off-by: NSubash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Most of these constants were used in the initial patchset where
custom netlink configuration was used and hence are no longer relevant.
Signed-off-by: NSubash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This will be rewritten in the following patches.
Signed-off-by: NSubash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Timur Tabi says:

====================
net: qcom/emac: various minor fixes

A set of patches for 4.15 that clean up some code, apply minors fixes,
and so on.  Some of the code also prepares the driver for a future
version of the EMAC controller.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Some of the error messages that are printed by the interrupt handlers
are poorly written.  For example, many don't include a device prefix,
so there's no indication that they are EMAC errors.

Also use rate limiting for all messages that could be printed from
interrupt context.
Signed-off-by: NTimur Tabi <timur@codeaurora.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The EMAC has a restriction that the upper 32 bits of the base addresses
for the RFD and RRD rings must be the same.  The ensure that restriction,
we allocate twice the space for the RRD and locate it at an appropriate
address.

We also re-arrange the allocations so that invalid addresses are even
less likely.
Signed-off-by: NTimur Tabi <timur@codeaurora.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The EMAC is capable of multiple TX and RX rings, but the driver only
supports one ring for each.  One function had some left-over unused
code that supports multiple rings, but all it did was make the code
harder to read.
Signed-off-by: NTimur Tabi <timur@codeaurora.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The 64/32-bit DMA mask hackery in the EMAC driver is not actually necessary,
and is technically not accurate.  The EMAC hardware is limted to a 45-bit
DMA address.  Although no EMAC-enabled system can have that much DDR,
an IOMMU could possible provide a larger address.  Rather than play games
with the DMA mappings, the driver should provide a correct value and
trust the DMA/IOMMU layers to do the right thing.
Signed-off-by: NTimur Tabi <timur@codeaurora.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Bjorn Andersson says:

====================
net: qrtr: Fixes and support receiving version 2 packets

On the latest Qualcomm platforms remote processors are sending packets with
version 2 of the message header. This series starts off with some fixes and
then refactors the qrtr code to support receiving messages of both version 1
and version 2.

As all remotes are backwards compatible transmitted packets continues to be
send as version 1, but some groundwork has been done to make this a per-link
property.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add the necessary logic for decoding incoming messages of version 2 as
well. Also make sure there's room for the bigger of version 1 and 2
headers in the code allocating skbs for outgoing messages.
Signed-off-by: NBjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Rather than parsing the header of incoming messages throughout the
implementation do it once when we retrieve the message and store the
relevant information in the "cb" member of the sk_buff.

This allows us to, in a later commit, decode version 2 messages into
this same structure.
Signed-off-by: NBjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

As the message header generation is deferred the internal functions for
generating control packets can be simplified.

This patch modifies qrtr_alloc_ctrl_packet() to, in addition to the
sk_buff, return a reference to a struct qrtr_ctrl_pkt, which clarifies
and simplifies the helpers to the point that these functions can be
folded back into the callers.
Signed-off-by: NBjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Defer writing the message header to the skb until its time to enqueue
the packet. As the receive path is reworked to decode the message header
as it's received from the transport and only pass around the payload in
the skb this change means that we do not have to fill out the full
message header just to decode it immediately in qrtr_local_enqueue().

In the future this change also makes it possible to prepend message
headers based on the version of each link.
Signed-off-by: NBjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The QMUX protocol specification defines structure of the special control
packet messages being sent between handlers of the control port.

Add these to the uapi header, as this structure and the associated types
are shared between the kernel and all userspace handlers of control
messages.
Signed-off-by: NBjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The constants are used by both the name server and clients, so clarify
their value and move them to the uapi header.
Signed-off-by: NBjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>