Tom Herbert says:
====================
net: Remote checksum offload for VXLAN
This patch set adds support for remote checksum offload in VXLAN.
The remote checksum offload is generalized by creating a common
function (remcsum_adjust) that does the work of modifying the
checksum in remote checksum offload. This function can be called
from normal or GRO path. GUE was modified to use this function.
To support RCO is VXLAN we use the 9th bit in the reserved
flags to indicated remote checksum offload. The start and offset
values are encoded n a compressed form in the low order (reserved)
byte of the vni field.
Remote checksum offload is described in
https://tools.ietf.org/html/draft-herbert-remotecsumoffload-01
Changes in v2:
- Add udp_offload_callbacks which has GRO functions that take a
udp_offload pointer argument. This argument can be used to retrieve
a per port structure of the encapsulation for use in gro processing
(mostly by doing container_of on the structure).
- Use the 10th bit in VXLAN flags for RCO which does not seem to
conflict with other proposals at this time (ie. VXLAN-GPE and
VXLAN-GPB)
- Require that RCO must be explicitly enabled on the receiver
as well as the sender.
Tested by running 200 TCP_STREAM connections with VXLAN (over IPv4).
With UDP checksums and Remote Checksum Offload
IPv4
Client
11.84% CPU utilization
Server
12.96% CPU utilization
9197 Mbps
IPv6
Client
12.46% CPU utilization
Server
14.48% CPU utilization
8963 Mbps
With UDP checksums, no remote checksum offload
IPv4
Client
15.67% CPU utilization
Server
14.83% CPU utilization
9094 Mbps
IPv6
Client
16.21% CPU utilization
Server
14.32% CPU utilization
9058 Mbps
No UDP checksums
IPv4
Client
15.03% CPU utilization
Server
23.09% CPU utilization
9089 Mbps
IPv6
Client
16.18% CPU utilization
Server
26.57% CPU utilization
8954 Mbps
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Add support for remote checksum offload in VXLAN. This uses a
reserved bit to indicate that RCO is being done, and uses the low order
reserved eight bits of the VNI to hold the start and offset values in a
compressed manner.
Start is encoded in the low order seven bits of VNI. This is start >> 1
so that the checksum start offset is 0-254 using even values only.
Checksum offset (transport checksum field) is indicated in the high
order bit in the low order byte of the VNI. If the bit is set, the
checksum field is for UDP (so offset = start + 6), else checksum
field is for TCP (so offset = start + 16). Only TCP and UDP are
supported in this implementation.
Remote checksum offload for VXLAN is described in:
https://tools.ietf.org/html/draft-herbert-vxlan-rco-00
Tested by running 200 TCP_STREAM connections with VXLAN (over IPv4).
With UDP checksums and Remote Checksum Offload
IPv4
Client
11.84% CPU utilization
Server
12.96% CPU utilization
9197 Mbps
IPv6
Client
12.46% CPU utilization
Server
14.48% CPU utilization
8963 Mbps
With UDP checksums, no remote checksum offload
IPv4
Client
15.67% CPU utilization
Server
14.83% CPU utilization
9094 Mbps
IPv6
Client
16.21% CPU utilization
Server
14.32% CPU utilization
9058 Mbps
No UDP checksums
IPv4
Client
15.03% CPU utilization
Server
23.09% CPU utilization
9089 Mbps
IPv6
Client
16.18% CPU utilization
Server
26.57% CPU utilization
8954 Mbps
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch introduces udp_offload_callbacks which has the same
GRO functions (but not a GSO function) as offload_callbacks,
except there is an argument to a udp_offload struct passed to
gro_receive and gro_complete functions. This additional argument
can be used to retrieve the per port structure of the encapsulation
for use in gro processing (mostly by doing container_of on the
structure).
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When IPV4 support is disabled, we cannot call arp_send from
the bridge code, which would result in a kernel link error:
net/built-in.o: In function `br_handle_frame_finish':
:(.text+0x59914): undefined reference to `arp_send'
:(.text+0x59a50): undefined reference to `arp_tbl'
This makes the newly added proxy ARP support in the bridge
code depend on the CONFIG_INET symbol and lets the compiler
optimize the code out to avoid the link error.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Fixes: 958501163d ("bridge: Add support for IEEE 802.11 Proxy ARP")
Cc: Kyeyoon Park <kyeyoonp@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Replace tasklet with NAPI.
Add rx_queue to queue the remaining rx packets if the number of the
rx packets is more than the request from poll().
Signed-off-by: Hayes Wang <hayeswang@realtek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Vinod Koul <vinod.koul@intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Adam Thomson <Adam.Thomson.Opensource@diasemi.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
The codec field of the snd_soc_widget struct is eventually going to be
removed, use snd_soc_dapm_to_codec(w->dapm) instead.
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
This patch adds clock provider (currently only for DT platforms) for
the CODECLKO (CDCLK) gate, RCLKSRC mux and RCLK pre-scaler divider
divider clock. Those all tree clock are only available in the IIS
Multi Audio Interface (I2S0), the regular IIS Bus Interface has only
CDCLK gate clock.
The motivation behind this patch is to expose the I2S internal clocks
which are currently controlled through set_sysclk() through the clk
API, so dedicated sound machine driver per each board can be avoided.
The intention is also to fix the CDCLK gating issue reported by
Daniel Drake:
http://mailman.alsa-project.org/pipermail/alsa-devel/2014-September/081753.html
This patch also reverts commit b97c60abf9
("ASoC: samsung-i2s: Maintain CDCLK settings across i2s_{shutdown/
startup}") The problem that commit attempted to solve only affects
the Odroid X2/U3, which doesn't configure the CDCLK clock in
struct snd_soc_dai_ops hw_params callback and the issue should be
now resolved by using clk API, i.e. having the codec enabling/
disabling the CDCLK clock as required.
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The new DT properties required for the I2S device node to be referred
as a clock provider and corresponding clock indices definition is added.
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
In order to support old DTs we check the codec device node if it
contains "clocks" property and only if it doesn't (which indicates
an old DT) we proceed with enabling the CDCLK clock by means of
the set_sysclk() callback. For new DTs which use the common clock
bindings for CDCLK that clock is supposed to be handled outside
the sound machine driver.
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Ensure the I2SMOD, I2SPSR registers, which are also exposed through
clk API are only accessed with the i2s->spinlock spinlock held.
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
It seems this driver hasn't been updated for SMP, as local_irq_save/
local_irq_restore don't provide proper protection of read/modify/write
of the device's registers on such systems. Introduce a spinlock
serializing access to the register region, it will be helpful later
when I2SMOD, I2SPSR registers are made also accessible through the
clk API.
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The usage of this goto seems unjustified, use if/else statement instead.
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The code to get pointer to the other DAI is repeated multiple
times. Add a helper function and use it instead.
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The clk_prepare_enable() call on the "iis" clock is moved to happen earlier
in the DAI platform device driver's probe() callback, so the I2S registers
can be safely accessed through the clk API, after the clk supplier is
registered in the platform device probe().
After this patch the "iis" clock is kept enabled since the (primary) I2S
platform device probe() and until the platform device driver remove() call.
This is similar to gating the clock in the snd_soc_dai probe() and remove()
callbacks.
Normally, in addition to that we should mark the device as PM runtime active,
so if runtime PM is enabled it can idle the device by turning off the clock.
Correcting this issue is left for a separate patch series, as we need to
ensure the BUSCLK clock is always enabled when required.
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Acquire the I2S interface clock in driver probe() callback
as it's a per-device not a per-DAI clock. While at it switch
to the resource managed clk_get().
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
The memory mapped registers region is common for both DAIs so request
it in the I2S platform device driver's probe for the platform device
corresponding to the primary DAI, rather than in the ASoC DAI's probe
callback. While at it switch to devm_ioremap_resource(). This also
drops the hard coded (0x100) register region size in the driver.
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
These functions may fail so let's properly report any errors.
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
