aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/tools/perf/scripts/python/export-to-postgresql.py (unfollow)
AgeCommit message (Collapse)AuthorFilesLines
2015-07-29ASoC: rcar ctu: Staticise local symbolsLars-Peter Clausen1-1/+1
rsnd_of_parse_ctu() is not used outside this file so it can be static. Fixes the following sparse warning: sound/soc/sh/rcar/ctu.c:72:6: warning: symbol 'rsnd_of_parse_ctu' was not declared. Should it be static? Signed-off-by: Lars-Peter Clausen <lars@metafoo.de> Acked-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-21ASoC: rsnd: tidyup parameter assignment positionKuninori Morimoto1-2/+5
84e95355602c("ASoC: rsnd: show debug message for SSI/SRC/DVC connection") added debug message on rsnd_dai_connect(), but the relationship of parameter check was absurdity. This patch tidyup it. It is reported via Smatch/Dan Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-17ASoC: rsnd: add MIX (Mixer) supportKuninori Morimoto8-13/+333
This patch adds MIX (Mixer) initial support for rsnd driver. It is assuming that this MIX is used via DPCM. This is sample code for playback. CPU0 : [MEM] -> [SRC1] -> [CTU02] -+ | +-> [MIX0] -> [DVC0] -> [SSI0] | CPU1 : [MEM] -> [SRC2] -> [CTU03] -+ sound { compatible = "renesas,rsrc-card"; ... cpu@0 { sound-dai = <&rcar_sound 0>; }; cpu@1 { sound-dai = <&rcar_sound 1>; }; codec { ... }; }; rcar_sound { ... rcar_sound,dai { dai0 { playback = <&src1 &ctu02 &mix0 &dvc0 &ssi0>; }; dai1 { playback = <&src2 &ctu03 &mix0 &dvc0 &ssi0>; }; }; }; Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-17ASoC: rsnd: add CTU (Channel Transfer Unit) prototype supportKuninori Morimoto8-6/+236
This patch adds CTU (Channel Transfer Unit) support for rsnd driver. But, it does nothing to data at this point, but is required for MIX support. CTU design is a little different from other IPs (CTU0 is including CTU00 - CTU03, and CTU1 is including CTU10 - CTU13, these have different register mapping) We need to care about it on this driver. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-17ASoC: rsnd: update Audio DMA path search methodKuninori Morimoto1-35/+53
Current rsnd driver is assuming Audio DMAC / Audio DMAC peri peri are used from SSI/SSIU/SRC/DVC. But we will add CTU/MIX to this driver. Then, current DMA path searching method is not understandable, and good enough for this purpose. This patch update DMA path search method, more simply. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: tidyup SRC position on each codeKuninori Morimoto3-24/+24
This is cleanup for CTU/MIX support Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: add rsnd_io_to_mod()Kuninori Morimoto1-3/+4
Sometimes we would like to get each module directly, especially data path searching. this patch adds rsnd_io_to_mod() macro, and existing rsnd_io_to_mod_xxx() use it. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: dma: add DMA name on .opsKuninori Morimoto1-1/+11
Current rsnd driver is using Audio DMAC (via DMAEngine) and Audio DMAC peri peri (via original method), and usage of these DMAC are different. Indicates its naming is useful for debugging. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: check the Gen1 at the beginning of DVC probeKuninori Morimoto1-6/+6
DVC doesn't support Gen1, check it beginning of probe Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: tidyup rsnd_dma_ops definition placeKuninori Morimoto2-7/+8
rsnd_dma_ops is used only from dma.c, rsnd.h doesn't need it. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: show debug message for SSI/SRC/DVC connectionKuninori Morimoto1-0/+7
It can help for connection debug Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: tidyup data align positionKuninori Morimoto4-15/+45
Sound L/R order of SSI is different from Linux sound data order. So current rsnd driver is using DALIGN (= data align) to exchange data align on SSIU. OTOH, CMD/SRC/SSIU have DALIGN register. Now inverted sound volume will be exchanged if user used volume control on DVC. Because SSIU which exchanges data align is located after DVC. MEM -> SRC -> DVC -> SSI This patch exchanges data align SRC if possible Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: add rsnd_get_adinr_chan()Kuninori Morimoto2-0/+23
Current rsnd driver has rsnd_get_adinr_bit() to get bit settings for ADINR (= Audio Information Register) of SSIU/SRC/DVC. This patch adds rsnd_get_adinr_chan() to get channel settings for ADINR (= Audio Information Register) of CTU/MIX. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: tidyup ADINR function nameKuninori Morimoto4-6/+6
Renesas sound IP (= SSIU/SRC/CTU/MIX/DVC) have ADINR (= Audio Information Register), but some of them (= SSIU/SRC/DVC) are for audio data bits, some of them (= CTU/MIX) are for audio data channels. Current rsnd driver is supporting SSIU/SRC/DVC, and these ADINR were for bits. This patch rename rsnd_get_adinr() to rsnd_get_adinr_bit(), and we will have rsnd_get_adinr_chan() for CTU/MIX. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: add rsnd_src_initialize_lock/unlock()Kuninori Morimoto1-11/+11
Renesas SCU (Sampling Rate Convert Unit) includes SRC/CTU/MIX/DVC, and these have similar register. xxxIR (Initialization Register) is one of them. These xxxIR need be set to 1 during initialization. Current rsnd driver has src.c / dvc.c, and we will have mix.c. It is readable if these have same named function. This patch adds rsnd_src_initialize_lock/unlock() and make sure it Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: add rsnd_dvc_initialize_lock/unlock()Kuninori Morimoto1-4/+11
Renesas SCU (Sampling Rate Convert Unit) includes SRC/CTU/MIX/DVC, and these have similar register. xxxIR (Initialization Register) is one of them. These xxxIR need be set to 1 during initialization. Current rsnd driver has src.c / dvc.c, and we will have mix.c. It is readable if these have same named function. This patch adds rsnd_dvc_initialize_lock/unlock() and make sure it Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: add rsnd_path_parse() for CTU/MIX/DVC route settingKuninori Morimoto3-31/+33
Current sound data route settings is done in dvc.c, and it doesn't care about CTU/MIX at this poinnt, but we need to care about these. OTOH, rsnd driver already has rsnd_path_xxx() functions for data path which are good match for CTU/MIX/DVC path selectio. This patch adds new rsnd_path_parse() to select sound data route which will care about CTU/MIX/DVC path. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: rename rsnd_path_parse/break() into add/removeKuninori Morimoto1-7/+7
parse/break is a little ambiguous/confusable name for rsnd module path. Especially for CTU/MIX support. It was renamed to add/remove Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: enable module multi connectionKuninori Morimoto1-10/+0
'8a4e379b54f8("ASoC: rsnd: remove io from rsnd_mod")' removed mod/io relationship. rsnd_dai_connect() mod/io check is no longer needed Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: src: make sure SRC soft resetKuninori Morimoto1-4/+8
Renesas SCU (Sampling Rate Convert Unit) includes SRC/CTU/MIX/DVC, and these have similar register. xxxRSR (Software reset Register) is one of them. These xxxRSR need be set to 1 to 0 when software reset. Current rsnd driver has src.c / dvc.c, and we will have mix.c. It is readable if these have same named function. This patch adds rsnd_src_soft_reset() and make sure it Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: dvc: make sure DVC soft resetKuninori Morimoto1-3/+8
Renesas SCU (Sampling Rate Convert Unit) includes SRC/CTU/MIX/DVC, and these have similar register. xxxRSR (Software reset Register) is one of them. These xxxRSR need be set to 1 to 0 when software reset. Current rsnd driver has src.c / dvc.c, and we will have mix.c. It is readable if these have same named function. This patch adds rsnd_dvc_soft_reset() and make sure it Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: move SRC specific macro into src.cKuninori Morimoto2-2/+1
rsnd_src_nr() is used only from src.c Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: move DVC specific macro into dvc.cKuninori Morimoto2-3/+1
rsnd_dvc_nr() is used only from dvc.c Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: rsnd_mod_id() return -1 if mod was NULLKuninori Morimoto1-1/+1
enabling to use same method for exception case is useful. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: add workaround for SRC sync convert + DVCKuninori Morimoto1-11/+32
We couldn't use SRC sync convert mode together with DVC, but we can use workaround for it. This patch adds workaround and can use SRC sync convert + DVC Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: fixup each module counter on __rsnd_mod_call()Kuninori Morimoto1-2/+2
'5451ea443b ("ASoC: rsnd: count each mod (SSI/SRC/DVC)")' counts each module's callback status, but counts 1st callback only. This patch fixup it. Otherwise, multi-called function will be trouble Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: rename INT_ENABLE to SSI_INT_ENABLEKuninori Morimoto3-7/+6
based on datasheet Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: rename BUSIF_DALIGN to SSI_BUSIF_DALIGNKuninori Morimoto3-3/+3
based on datasheet Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: remove unnecessary 'out of memory' message from DVCKuninori Morimoto1-3/+1
Current checkpatch.pl indicates 'out of memory' message is unnecessary. Let's remove it Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: remove unnecessary 'out of memory' message from SRCKuninori Morimoto1-3/+1
Current checkpatch.pl indicates 'out of memory' message is unnecessary. Let's remove it Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsnd: remove unnecessary 'out of memory' message from SSIKuninori Morimoto1-3/+1
Current checkpatch.pl indicates 'out of memory' message is unnecessary. Let's remove it Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: rsrc-card: use snd_soc_of_parse_audio_route/prefix for routingKuninori Morimoto2-4/+25
using common audio routing path method makes sense. Let's use snd_soc_of_parse_audio_route/prefix. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-16ASoC: core: add snd_soc_of_parse_audio_prefix()Kuninori Morimoto2-0/+24
Current ASoC can add name_prefix for DAPM, and it is necessary for route settings. This patch adds snd_soc_of_parse_audio_prefix() for this purpose. It will be used with snd_soc_of_parse_audio_routing(). Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Tested-by: Keita Kobayashi <keita.kobayashi.ym@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-10ASoC: rsnd: gen: add rsnd_force_write()Kuninori Morimoto2-0/+20
rsnd_force_write() is similar to rsnd_write(), but rsnd_force_write() write data to register even though it is same value. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-10regmap: add regmap_fields_force_write()Kuninori Morimoto2-0/+14
regmap_fields_force_write() is similar to regmap_fields_write(), but regmap_fields_force_write() write data to register even though it is same value. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-10regmap: add regmap_write_bits()Kuninori Morimoto2-0/+32
regmap_write_bits() is similar to regmap_update_bits(), but regmap_write_bits() write data to register even though it is same value. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-10regmap: add force_write option on _regmap_update_bits()Kuninori Morimoto1-8/+8
Sometimes we want to write data even though it doesn't change value. Then, force_write option on _regmap_update_bits() helps this purpose. Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Signed-off-by: Mark Brown <broonie@kernel.org>
2015-07-05Linux 4.2-rc1Linus Torvalds1-2/+2
2015-07-04bluetooth: fix list handlingLinus Torvalds2-2/+3
Commit 835a6a2f8603 ("Bluetooth: Stop sabotaging list poisoning") thought that the code was sabotaging the list poisoning when NULL'ing out the list pointers and removed it. But what was going on was that the bluetooth code was using NULL pointers for the list as a way to mark it empty, and that commit just broke it (and replaced the test with NULL with a "list_empty()" test on a uninitialized list instead, breaking things even further). So fix it all up to use the regular and real list_empty() handling (which does not use NULL, but a pointer to itself), also making sure to initialize the list properly (the previous NULL case was initialized implicitly by the session being allocated with kzalloc()) This is a combination of patches by Marcel Holtmann and Tedd Ho-Jeong An. [ I would normally expect to get this through the bt tree, but I'm going to release -rc1, so I'm just committing this directly - Linus ] Reported-and-tested-by: Jörg Otte <jrg.otte@gmail.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Original-by: Tedd Ho-Jeong An <tedd.an@intel.com> Original-by: Marcel Holtmann <marcel@holtmann.org>: Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-07-049p: cope with bogus responses from server in p9_client_{read,write}Al Viro1-0/+8
if server claims to have written/read more than we'd told it to, warn and cap the claimed byte count to avoid advancing more than we are ready to.
2015-07-04p9_client_write(): avoid double p9_free_req()Al Viro1-0/+1
Braino in "9p: switch p9_client_write() to passing it struct iov_iter *"; if response is impossible to parse and we discard the request, get the out of the loop right there. Cc: stable@vger.kernel.org Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2015-07-049p: forgetting to cancel request on interrupted zero-copy RPCAl Viro1-1/+2
If we'd already sent a request and decide to abort it, we *must* issue TFLUSH properly and not just blindly reuse the tag, or we'll get seriously screwed when response eventually arrives and we confuse it for response to later request that had reused the same tag. Cc: stable@vger.kernel.org # v3.2 and later Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2015-07-04dax: bdev_direct_access() may sleepMatthew Wilcox1-0/+6
The brd driver is the only in-tree driver that may sleep currently. After some discussion on linux-fsdevel, we decided that any driver may choose to sleep in its ->direct_access method. To ensure that all callers of bdev_direct_access() are prepared for this, add a call to might_sleep(). Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2015-07-04block: Add support for DAX reads/writes to block devicesMatthew Wilcox2-2/+8
If a block device supports the ->direct_access methods, bypass the normal DIO path and use DAX to go straight to memcpy() instead of allocating a DIO and a BIO. Includes support for the DIO_SKIP_DIO_COUNT flag in DAX, as is done in do_blockdev_direct_IO(). Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2015-07-04dax: Use copy_from_iter_nocacheMatthew Wilcox1-1/+1
When userspace does a write, there's no need for the written data to pollute the CPU cache. This matches the original XIP code. Signed-off-by: Matthew Wilcox <willy@linux.intel.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2015-07-04dax: Add block size note to documentationMatthew Wilcox1-2/+4
For block devices which are small enough, mkfs will default to creating a filesystem with block sizes smaller than page size. Signed-off-by: Matthew Wilcox <willy@linux.intel.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2015-07-04NTB: Add split BAR output for debugfs statsDave Jiang1-15/+68
When split BAR is enabled, the driver needs to dump out the split BAR registers rather than the original 64bit BAR registers. Signed-off-by: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Jon Mason <jdmason@kudzu.us>
2015-07-04NTB: Change WARN_ON_ONCE to pr_warn_once on unsafeDave Jiang1-8/+16
The unsafe doorbell and scratchpad access should display reason when WARN is called. Otherwise we get a stack dump without any explanation. Signed-off-by: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Jon Mason <jdmason@kudzu.us>
2015-07-04NTB: Print driver name and version in module initDave Jiang2-0/+6
Printouts driver name and version to indicate what is being loaded. Signed-off-by: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Jon Mason <jdmason@kudzu.us>
2015-07-04NTB: Increase transport MTU to 64k from 16kDave Jiang1-1/+1
Benchmarking showed a significant performance increase with the MTU size to 64k instead of 16k. Change the driver default to 64k. Signed-off-by: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Jon Mason <jdmason@kudzu.us>
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.