Support prepending data from XDP. We are already always allocating
some headroom because FW may prepend metadata to packets.
xdp_adjust_head() can be supported by making sure that headroom is
big enough for XDP. In case FW had prepended metadata to the packet,
however, we have to move it out of the way before we call XDP.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
XDP may require us to move metadata to make room for pushing
headers. Track meta data location with a pointer and pass
it explicitly to functions.
While at it validate that meta_len from the descriptor is not
bogus.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Rename pkt_off variable to dma_off, it should hold data offset
counting from beginning of DMA mapping. Compute the value only
in XDP context.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
NFP_NET_CFG_RX_OFFSET is 32bit wide, make sure what we read from
there is reasonable for packet headroom. This allows us to store
the rx_offset in a 8bit variable.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of testing if xdp_prog is present store the dma direction
in data path structure.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of passing around sets of rings and their parameters just
store all information in the data path structure.
We will no longer user xchg() on XDP programs when we swap programs
while the traffic is guaranteed not to be flowing. This allows us
to simply assign the entire data path structures instead of copying
field by field.
The optimization to reallocate only the rings on the side (RX/TX)
which has been changed is also removed since it seems like it's not
worth the code complexity.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use xdp_prog member of data path struct to carry the xdp_prog to
alloc/free free functions.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move the mtu member from ring set to data path struct.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use fl_bufsz member of data path struct to carry desired size of
free list entries.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Instead of passing variables around use dp to store number of tx rings
for the stack and number of IRQ vectors.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Make callers of nfp_net_ring_reconfig() pass newly allocated data
path structure. We will gradually make use of that structure
instead of passing parameters around to all the allocation functions.
This commit adds allocation and propagation of new data path struct,
no parameters are converted, yet.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Control BAR pointer is used to unmask interrupts so it should be
in the first cacheline of adapter structure.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Move all data path information into a separate structure. This way
we will be able to allocate new data path with all new rings etc.
and swap it in easily.
No functional changes.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Joao Pinto says:
====================
prepare mac operations for multiple queues
As agreed with David Miller, this patch-set is the first of 3 to enable
multiple queues in stmmac.
This first one concentrates on mac operations adding functionalities as:
a) Configuration through DT
b) RX and TX scheduling algorithms programming
b) TX queues weight programming (essential in weightes algorithms)
c) RX enable as DCB or AVB (preparing for future AVB support)
d) Mapping RX queue to DMA channel
e) IRQ treatment prepared for multiple queues
f) Debug dump prepared for multiple queues
g) CBS configuration
In v3 patch-set version I included a new patch to enable CBS configuration
(Patch 9).
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds the configuration of the AVB Credit-Based Shaper.
Signed-off-by: Joao Pinto <jpinto@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch prepares mac debug dump for multiple queues.
Signed-off-by: Joao Pinto <jpinto@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch prepares mac irq status treatment for multiple queues.
Signed-off-by: Joao Pinto <jpinto@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adapts flow_ctrl function to prepare it for multiple queues.
Signed-off-by: Joao Pinto <jpinto@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds the functionality of RX queue to dma channel mapping
based on configuration.
Signed-off-by: Joao Pinto <jpinto@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch introduces the enabling of RX queues as DCB or as AVB based
on configuration.
Signed-off-by: Joao Pinto <jpinto@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds the RX and TX scheduling algorithms programming.
It introduces the multiple queues configuration function
(stmmac_mtl_configuration) in stmmac_main.
Signed-off-by: Joao Pinto <jpinto@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds the multiple queues configuration in the Device Tree.
It was also created a set of structures to keep the RX and TX queues
configurations to be used in the driver.
Signed-off-by: Joao Pinto <jpinto@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Thierry Reding says:
====================
net: stmmac: Fixes and Tegra186 support
This series of patches start with a few cleanups that I ran across while
adding Tegra186 support to the stmmac driver. It then adds code for FIFO
size parsing from feature registers and finally enables support for the
incarnation of the Synopsys DWC QOS IP found on NVIDIA Tegra186 SoCs.
This is based on next-20170310.
Changes in v2:
- address review comments by Mikko and Joao
- add two additional cleanup patches
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The NVIDIA Tegra186 SoC contains an instance of the Synopsys DWC
ethernet QOS IP core. The binding that it uses is slightly different
from existing ones because of the integration (clocks, resets, ...).
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Split out the binding specific parts of ->probe() and ->remove() to
enable the driver to support variants of the binding. This is useful in
order to keep backwards-compatibility while making it easy for a sub-
driver to deal only with the updated bindings rather than having to add
compatibility quirks all over the place.
Reviewed-by: Mikko Perttunen <mperttunen@nvidia.com>
Reviewed-By: Joao Pinto <jpinto@synopsys.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Program the receive queue size based on the RX FIFO size and enable
hardware flow control for large FIFOs.
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
New version of this core encode the FIFO sizes in one of the feature
registers. Use these sizes as default, but still allow device tree to
override them for backwards compatibility.
Reviewed-by: Mikko Perttunen <mperttunen@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When DMA mapping an SKB fragment, the mapping must be checked for
errors, otherwise the DMA debug code will complain upon unmap.
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
clk_prepare_enable() and clk_disable_unprepare() for this clock aren't
properly balanced, which can trigger a WARN_ON() in the common clock
framework.
Reviewed-By: Joao Pinto <jpinto@synopsys.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If an error occurs while opening the device, make sure to disable the
PTP reference clock.
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If an error occurs while opening the device, make sure that both the TX
timer and the PHY are properly cleaned up.
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
There aren't currently any users of the "clk_ptp_ref", but there are
other references to "ptp_ref", so I'm leaning towards considering that a
typo. Fix it.
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: devicetree@vger.kernel.org
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When sending a L3 miss, the family is set to AF_INET even for IPv6. This
causes userland (eg "ip monitor") to be confused. Ensure we send the
appropriate family in this case. For L2 miss, keep using AF_INET.
Signed-off-by: Vincent Bernat <vincent@bernat.im>
Signed-off-by: David S. Miller <davem@davemloft.net>
There are two duplicated loops codes which used to select right
address in current codes. Now eliminate these codes by creating
one new function in_dev_select_addr.
Signed-off-by: Gao Feng <fgao@ikuai8.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Xin Long says:
====================
sctp: add receiver-side procedures for stream reconf asoc reset and add streams and response
Patch 2/7, 4/7, 5/7, 6/7 are to implement the process of asoc reset request,
add streams requests and all kinds of responses.
Patch 1/7 and 3/7 are ahead of 2/7 and 4/7 to add two event notification
for asoc reset and add streams.
Patch 7/7 is the last patch for implementing rfc6525 sctp stream reconf
to add sysctl and sockopt interface for users to enable sctp stream reconf.
After this patchset, sctp stream reconf will be able to work as rfc6525.
v1->v2:
- put these into a smaller group.
- rename the titles of the commits and improve some changelogs.
- improve sctp_chunk_lookup_strreset_param and reuse it in patch 4/7.
- process addstrm outreq as the ack of in addstrm inreq if strreset_chunk
is not NULL in patch 4/7.
- remove the stream alloc when sending addstrm inreq, and the process in
peer will response it by sending a addstrm out request back in patch 5/7.
- adjust the process of addstrm in resp to fit in the codes that only alloc
streams through addstrm outreq in patch 6/7.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
This patchset is to add SCTP_RECONFIG_SUPPORTED sockopt, it would
set and get asoc reconf_enable value when asoc_id is set, or it
would set and get ep reconf_enalbe value if asoc_id is 0.
It is also to add sysctl interface for users to set the default
value for reconf_enable.
After this patch, stream reconf will work.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch is to implement Receiver-Side Procedures for the
Re-configuration Response Parameter in rfc6525 section 5.2.7.
sctp_process_strreset_resp would process the response for any
kind of reconf request, and the stream reconf is applied only
when the response result is success.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch is to implement Receiver-Side Procedures for the Add Incoming
Streams Request Parameter described in rfc6525 section 5.2.6.
It is also to fix that it shouldn't have add streams when sending addstrm
in request, as the process in peer will handle it by sending a addstrm out
request back.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch is to add Receiver-Side Procedures for the Add Outgoing
Streams Request Parameter described in section 5.2.5.
It is also to improve sctp_chunk_lookup_strreset_param, so that it
can be used for processing addstrm_out request.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch is to add Stream Change Event described in rfc6525
section 6.1.3.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch is to implement Receiver-Side Procedures for the SSN/TSN
Reset Request Parameter described in rfc6525 section 6.2.4.
The process is kind of complicate, it's wonth having some comments
from section 6.2.4 in the codes.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch is to add Association Reset Event described in rfc6525
section 6.1.2.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Optimize DMA in NUMA systems by allocating memory from NUMA node that NIC
is plugged in to; DMA will no longer cross NUMA nodes. If NIC IRQs are
pinned to a local CPU, that CPU's access to the DMA'd data is also
optimized.
Signed-off-by: VSR Burru <veerasenareddy.burru@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: Raghu Vatsavayi <raghu.vatsavayi@cavium.com>
Signed-off-by: Satanand Burla <satananda.burla@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Stephen Hemminger says:
====================
netvsc: fix module removal hangs
A couple of patches are necessary to make netvsc driver module
removable again.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The code in netvsc_device_remove was incorrectly calling napi_disable
repeatedly on the same element. This would cause attempts
to remove netvsc module to hang.
Fixes: 2506b1dc4bbe ("netvsc: implement NAPI")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since rndis_halt_device waits until all outstanding sends and
receives are completed. Netvsc device needs to still schedule
NAPI to see those completions.
Fixes: 2506b1dc4bbe ("netvsc: implement NAPI")
Signed-off-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Madalin Bucur says:
====================
QorIQ DPAA 1 updates
This patch set introduces a series of fixes and features to the DPAA 1
drivers. Besides activating hardware Rx checksum offloading, four traffic
classes are added for Tx traffic prioritisation.
changes from v1: added patch to enable context-A stashing
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
While running a single stream UDPv6 test, we observed that amount
of CPU spent in NET_RX softirq was much greater than UDPv4 for an
equivalent receive rate. The test here was run on an ARM64 based
Android system. On further analysis with perf, we found that UDPv6
was spending significant time in the statistics netfilter targets
which did socket lookup per packet. These statistics rules perform
a lookup when there is no socket associated with the skb. Since
there are multiple instances of these rules based on UID, there
will be equal number of lookups per skb.
By introducing early demux for UDPv6, we avoid the redundant lookups.
This also helped to improve the performance (800Mbps -> 870Mbps) on a
CPU limited system in a single stream UDPv6 receive test with 1450
byte sized datagrams using iperf.
v1->v2: Use IPv6 cookie to validate dst instead of 0 as suggested
by Eric
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The original reason [1] for having hidden qdiscs (potential scalability
issues in qdisc_match_from_root() with single linked list in case of large
amount of qdiscs) has been invalidated by 59cc1f61f0 ("net: sched: convert
qdisc linked list to hashtable").
This allows us for bringing more clarity and determinism into the dump by
making default pfifo qdiscs visible.
We're not turning this on by default though, at it was deemed [2] too
intrusive / unnecessary change of default behavior towards userspace.
Instead, TCA_DUMP_INVISIBLE netlink attribute is introduced, which allows
applications to request complete qdisc hierarchy dump, including the
ones that have always been implicit/invisible.
Singleton noop_qdisc stays invisible, as teaching the whole infrastructure
about singletons would require quite some surgery with very little gain
(seeing no qdisc or seeing noop qdisc in the dump is probably setting
the same user expectation).
[1] http://lkml.kernel.org/r/1460732328.10638.74.camel@edumazet-glaptop3.roam.corp.google.com
[2] http://lkml.kernel.org/r/20161021.105935.1907696543877061916.davem@davemloft.net
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
