| Age | Commit message (Collapse) | Author |
|---|
|
The ALC5682I-VD and ALC5682I-VE use the same I2C
codec driver with different calibration settings.
This patch aims to handle their differences.
Signed-off-by: Derek Fang <derek.fang@realtek.com>
Link: https://patch.msgid.link/20241225094307.3678837-1-derek.fang@realtek.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
DTS example in the bindings should be indented with 2- or 4-spaces and
aligned with opening '- |', so correct any differences like 3-spaces or
mixtures 2- and 4-spaces in one binding. While touching the lines do
other non-functional changes: replace raw number with proper define for
GPIO flag and use generic node name.
No functional changes here, but saves some comments during reviews of
new patches built on existing code.
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://patch.msgid.link/20250107125901.227995-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Remove hard-coded strings by using the str_enabled_disabled() helper
function.
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20250107011355.2035-1-thorsten.blum@linux.dev
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
commit f8da001ae7a ("ASoC: audio-graph-card2: Purge absent supplies for
device tree nodes") marks multi/dpcm/c2c nodes as no suppliers. We no
longer need to use post-init-providers property to break fw_devlink cycle
(And no one is using it yet). Let's remove it.
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/87ikrhrfws.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Remove hard-coded strings by using the str_yes_no() helper function.
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Acked-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://patch.msgid.link/20241230085717.785718-2-thorsten.blum@linux.dev
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Currently, patch_sdca_function_type() both patches the function type
for older SDCA revisions, and reports the name of the function. In
general it is cleaner to have a single function only do a single
task, so split these operations into two separate functions.
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20241220173516.907406-5-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
It is not helpful to error out on some SDCA function types, we
might as well report the correct name and let the driver core
simply not bind a driver to those functions for which the code
lacks support. Also given no functions currently have support,
it seems odd to select some as unsupported.
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20241220173516.907406-4-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
SDCA only supports 3-bits for the function address, but the ACPI value
is 64-bits. Update the code that parses this to do a bounds check
and error out on invalid addresses. Currently, an invalid address
would truncate to the bottom 3-bits when used and thus use a likely
incorrect address. With the bounds check, it is also now safe to
shrink the size of the adr member of sdca_function_desc to a u8 and
rearrange the struct members to pack better with the new size of adr.
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20241220173516.907406-3-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
All the error messages in the SDCA code manually print the function
in the output, update these to use dev_fmt instead. Whilst making
the changes tweak a couple of the error messages to make them a
little shorter.
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20241220173516.907406-2-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Several of the SDCA files don't include all the headers they use
locally. These are included by the point of use through other
headers, so it is not currently causing any issues. However, files
should directly include things they directly use, so add the
missing header includes.
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20241220173516.907406-1-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Delete two redundant assignments in cs_dsp_test_bin.c.
Unfortunately none of W=1 or the static analysis tools I ran
flagged these.
Fixes: dd0b6b1f29b9 ("firmware: cs_dsp: Add KUnit testing of bin file download")
Reported-by: Dheeraj Reddy Jonnalagadda <dheeraj.linuxdev@gmail.com>
Closes: https://scan7.scan.coverity.com/#/project-view/52337/11354?selectedIssue=1602511
Closes: https://scan7.scan.coverity.com/#/project-view/52337/11354?selectedIssue=1602490
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20241219155719.84276-1-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Fix sparse warnings:
fsl_asrc_m2m.c:360:45: sparse: warning: incorrect type in argument 1 (different base types)
fsl_asrc_m2m.c:360:45: sparse: expected restricted snd_pcm_format_t [usertype] pcm_forma
fsl_asrc_m2m.c:360:45: sparse: got unsigned int [usertype] format
fsl_asrc_m2m.c:361:41: sparse: warning: incorrect type in assignment (different base types)
fsl_asrc_m2m.c:361:41: sparse: expected restricted snd_pcm_format_t
fsl_asrc_m2m.c:361:41: sparse: got unsigned int [usertype] format
fsl_asrc_m2m.c:365:45: sparse: warning: incorrect type in argument 1 (different base types)
fsl_asrc_m2m.c:365:45: sparse: expected restricted snd_pcm_format_t [usertype] pcm_forma
fsl_asrc_m2m.c:365:45: sparse: got unsigned int [usertype] pcm_format
fsl_asrc_m2m.c:366:42: sparse: warning: incorrect type in assignment (different base types)
fsl_asrc_m2m.c:366:42: sparse: expected restricted snd_pcm_format_t
fsl_asrc_m2m.c:366:42: sparse: got unsigned int [usertype] pcm_format
fsl_asrc_m2m.c:595:54: sparse: warning: incorrect type in assignment (different base types)
fsl_asrc_m2m.c:595:54: sparse: expected unsigned int [usertype] formats
fsl_asrc_m2m.c:595:54: sparse: got restricted snd_pcm_format_t [assigned] [usertype] k
Fixes: 24a01710f627 ("ASoC: fsl_asrc_m2m: Add memory to memory function")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202412180043.PAA4t4sQ-lkp@intel.com/
Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Link: https://patch.msgid.link/20241218024358.3022635-1-shengjiu.wang@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
The variable ret is being assigned a zero value that is never read,
it is being re-assigned a new value from the return value from the
call to snd_soc_dapm_add_routes. The assignment is redundant and can
be removed.
Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Link: https://patch.msgid.link/20241217171151.354550-1-colin.i.king@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
In cs_dsp_mock_wmfw_add_coeff_desc() the value stored in longstring->len
needs a cpu_to_le16() conversion.
Fixes: 5cf1b7b47180 ("firmware: cs_dsp: Add mock wmfw file generator for KUnit testing")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202412170233.8DnsdtY6-lkp@intel.com/
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20241217105624.139479-1-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
The header clearly states that it does not want to be included directly,
only via '<linux/bitmap.h>'. Replace the include accordingly.
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20241217070545.2533-2-wsa+renesas@sang-engineering.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
In cs_dsp_mock_xm_header_drop_from_regmap_cache() for the ADSP2 case read
the big-endian firmware word into a dedicated __be32 variable instead of
using the same u32 for both the big-endian and cpu-endian value.
Fixes: 41e78c0f44f9 ("firmware: cs_dsp: Add mock DSP memory map for KUnit testing")
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20241217113127.186736-1-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Add handling of clock related to secondary MI2S_RX in startup, shutdown
and hw params routines. The handing of MI2S_TX and SEC_MI2S clock is
already there so this requires only placing SECONDARY_MI2S_RX in the
correct switch-case choices.
Signed-off-by: Alexey Klimov <alexey.klimov@linaro.org>
Link: https://patch.msgid.link/20241205023344.2232529-3-alexey.klimov@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Merge series from Bard Liao <yung-chuan.liao@linux.intel.com>:
This series adds TGL and MTL matches for configurations using the
Cirrus Logic CDB35L56-EIGHT-C board.
|
|
Having 1280 bytes of local variables on the stack exceeds the limit
on 32-bit architectures:
drivers/firmware/cirrus/test/cs_dsp_test_bin.c: In function 'bin_patch_mixed_packed_unpacked_random':
drivers/firmware/cirrus/test/cs_dsp_test_bin.c:2097:1: error: the frame size of 1784 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
Use dynamic allocation for the largest two here.
Fixes: dd0b6b1f29b9 ("firmware: cs_dsp: Add KUnit testing of bin file download")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20241216121541.3455880-1-arnd@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
hda_to_sdw() has been unused since it was added in 2020 as part of the
commit d1ede0641b05 ("ASoC: rt715: add RT715 codec driver")
Remove it.
Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Link: https://patch.msgid.link/20241216135110.53426-1-linux@treblig.org
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Original sample-card assumes SND_SOC_CLOCK_IN is used for
snd_soc_dai_set_sysclk(), but someday, Codec uses SND_SOC_CLOCK_IN
and CPU uses SND_SOC_CLOCK_OUT at hw_params(), and dai->clk_direction
is used at simple_init_dai().
There is no uniformity today. Let's use dai->clk_direction for all cases.
Fortunately, almost all DAI doesn't care about "dir"
(= SND_SOC_CLOCK_IN/OUT) in .set_sysclk callback function (which is called
in snd_soc_dai_set_sysclk()), so this patch has no effect in such DAIs.
But this patch might breaks some existing Sound Card. Use
"system-clock-direction-out" property if it needs to use SND_SOC_CLOCK_OUT
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Link: https://patch.msgid.link/87y10lu0gx.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
commit 1f5664351410 ("ASoC: lower "no backend DAIs enabled for ... Port"
log severity") ignores -EINVAL error message on common soc_pcm_ret().
It is used from many functions, ignoring -EINVAL is over-kill.
The reason why -EINVAL was ignored was it really should only be used
upon invalid parameters coming from userspace and in that case we don't
want to log an error since we do not want to give userspace a way to do
a denial-of-service attack on the syslog / diskspace.
So don't use soc_pcm_ret() on .prepare callback is better idea.
Link: https://lore.kernel.org/r/87v7vptzap.wl-kuninori.morimoto.gx@renesas.com
Cc: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Link: https://patch.msgid.link/87bjxg8jju.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Fix two places in kerneldoc where alg_id had been mistyped as alg_ig.
Fixes: 7c052c661529 ("firmware: cs_dsp: Add mock bin file generator for KUnit testing")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202412142205.HHHcousT-lkp@intel.com/
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20241216105520.22135-1-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
commit a22ae72b86a4 ("ASoC: soc-core: disable route checks for legacy
devices") added card->disable_route_checks to disable route checks
for legacy devices at soc_probe_component() and snd_soc_bind_card().
And commit 6974857c2b2c ("ASoC: topology: Do not ignore route checks
when parsing graphs") tidyup soc-topology for same reason.
In snd_soc_bind_card() case, if snd_soc_dapm_add_routes() (A) error,
but has card->disable_route_checks case (B), it will indicate
dev_info() only, and then, next function (C) will be called.
Thus, "ret" will be over written, and it is handled as non-error.
static int snd_soc_bind_card(...)
{
...
(A) ret = snd_soc_dapm_add_routes(...);
if (ret < 0) {
(B) if (card->disable_route_checks) {
dev_info(...);
} else {
...
goto probe_end;
}
}
(C) ret = snd_soc_dapm_add_routes(...);
...
In soc_probe_component() case, if snd_soc_dapm_add_routes() (a)
error, and has card->disable_route_checks case (b), it will indicate
dev_info(). But there is no next function after that, this means ret is
still indicating error, and will not be over written.
So error handline (c) will be handled, and will return error (d)
static int soc_probe_component(...)
{
...
(a) ret = snd_soc_dapm_add_routes(...);
if (ret < 0) {
(b) if (card->disable_route_checks) {
dev_info(...);
} else {
...
goto err_probe;
}
}
/* see for_each_card_components */
list_add(...);
err_probe:
(c) if (ret < 0)
soc_remove_component(...);
(d) return ret;
}
In soc_tplg_dapm_graph_elems_load() case, snd_soc_dapm_add_routes()
is called in for loop (1). if it was error (2), and doesn't have
card->disable_route_checks case flag (3), it will break from loop.
If card has flag, it will indicate dev_info() and handled as non-error.
But ret is still indicating error in this case. If this error happen
in last of loop, if will return error (4).
static int soc_tplg_dapm_graph_elems_load(...)
{
...
(1) for (i = 0; i < count; i++) {
...
(2) ret = snd_soc_dapm_add_routes(...);
if (ret) {
(3) if (!dapm->card->disable_route_checks) {
dev_err(...);
break;
}
dev_info(...);
}
}
(4) return ret;
}
This patch set "ret = 0" for each case.
Cc: Pierre-Louis Bossart <pierre-louis.bossart@linux.dev>
Cc: Cezary Rojewski <cezary.rojewski@intel.com>
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Link: https://patch.msgid.link/87wmg5tzra.wl-kuninori.morimoto.gx@renesas.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
This adds a match entry for using all the amps on a CDB35L56-EIGHT-C board
without the CS42L43 codec. Configuration is:
SDW0: 4x CS35L56 (OUT1, OUT2, OUT3, OUT4)
SDW1: 4x CS35L56 (OUT5, OUT6, OUT7, OUT8)
Speaker playback and amp feedback are aggregated.
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://patch.msgid.link/20241216032721.131227-4-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
This adds a match for the CDB35L56-EIGHT-C board with SmartCodec and
SmartAmp speakers aggregated.
The configuration is:
SDW0: CS35L56 x2 (SmartAmp) using OUT1 and OUT2
SDW1: CS35L56 x2 (SmartAmp) using OUT7 and OUT8
SDW3: CS42L43 (SmartJack, SmartMic, SmartAmp)
CS35L56 and CS42L43 Speaker playback is aggregated across all 3 buses.
The device addresses and reset arrangements of the EIGHT-C board are
quirky hence the use of non-contiguous outputs OUT1,2,7,8.
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://patch.msgid.link/20241216032721.131227-3-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
This adds match entries for the eight CS35L56 amps on the Cirrus Logic
CDB35L56-EIGHT-C board. Speaker playback and amp feedback are aggregated
across all amps on both SoundWire buses.
The mapping of SoundWire addresses to AMPn numbers matches the actual
order of amps on the EIGHT-C board. The SoundWire unique ID is in reverse
order for amps 1..4 on these boards, and the amp resets are paired
1+8, 2+7, 3+6, 4+5.
This then makes the entries from cs35l56_sdw_eight_1_4_fb_adr and
cs35l56_sdw_eight_5_8_fb_adr match the way the amp resets are paired on
the EIGHT-C board.
[0] = 1 + 8
[1] = 2 + 7
[3] = 3 + 6
[4] = 4 + 5
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://patch.msgid.link/20241216032721.131227-2-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Merge series from Shengjiu Wang <shengjiu.wang@nxp.com>:
This function is base on the accelerator implementation
for compress API:
04177158cf98 ("ALSA: compress_offload: introduce accel operation mode")
Audio signal processing also has the requirement for memory to
memory similar as Video.
This asrc memory to memory (memory ->asrc->memory) case is a non
real time use case.
User fills the input buffer to the asrc module, after conversion, then asrc
sends back the output buffer to user. So it is not a traditional ALSA playback
and capture case.
Because we had implemented the "memory -> asrc ->i2s device-> codec"
use case in ALSA. Now the "memory->asrc->memory" needs
to reuse the code in asrc driver, so the patch 1 and patch 2 is for refining
the code to make it can be shared by the "memory->asrc->memory"
driver.
Other change is to add memory to memory support for two kinds of i.MX ASRC
modules.
|
|
Merge series from Richard Fitzgerald <rf@opensource.cirrus.com>:
This series adds KUnit tests for the cs_dsp module.
Most of the functionality in cs_dsp is for downloading firmware to
DSP memory and interacting with "control" words defined in that
memory. This doesn't require any emulation of running firmware,
because it is only reading and writing registers. So the testing can
be done using a dummy regmap. The way this is used to perform testing
is described in more detail in the commit message for each test.
ADSP1 is not tested because this was only used by the WM2200 codec,
a long-obsolete part that was discontinued in 2015.
|
|
Merge series from Peter Ujfalusi <peter.ujfalusi@linux.intel.com>:
A new set of tokens have been added to SOF topology to indicate that the pause
operation is supported or not on the given PCM device.
Pause is an optional feature that depends on pipeline, topology and modules
used by the PCM.
Add a pause_supported flag to snd_sof_pcm_stream and use this flag in Intel
platform code to keep the pause support enabled or to disable it.
|
|
The following definitions have no users: SOF_DAI_STREAM() and SOF_FORMATS,
they can be dropped from the header file.
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Liam Girdwood <liam.r.girdwood@intel.com>
Link: https://patch.msgid.link/20241213131717.24071-1-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Use the SOF_IPC4_MOD_EXT_PARAM_SIZE() macro to set the param size in the
extension part of the IPC message for clarity.
No Functional change as the PARMA_SIZE offset is at 0.
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Liam Girdwood <liam.r.girdwood@intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Link: https://patch.msgid.link/20241213132110.27800-1-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Test that the cs_dsp_client_ops callbacks are called when expected.
pre_run, post_run - when cs_dsp_run() is called.
pre_stop, post_stop - when cs_dsp_stop() is called
control_add - when a WMFW is loaded
control_remove - when cs_dsp_remove() is called
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20241212143725.1381013-13-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Add tests for various types of errors and illegal values in
wmfw files. This covers buffer overflows as well as general
unsupported field values.
There are several sets of test cases to cover various different
versions of the wmfw file format.
V0 format was only used on the earlier ADSP2 devices. It does
not have algorithm blocks.
V1 format is used on all ADSP2 versions. It added algorithm
blocks and firmware coefficient descriptor blocks. Strings
are stored in fixed-length arrays.
V2 format is used on all ADSP2 versions. It is similar to V1
but space for strings is variable-length with either an 8-bit
or 16-bit length field.
V3 format is used on Halo Core DSPs and is mostly identical to
the V3 format.
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20241212143725.1381013-12-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Add tests for various types of errors and illegal values in
bin files. This covers buffer overflows as well as general
unsupported field values.
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20241212143725.1381013-11-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Add KUnit test cases for control read/write.
Tests cases cover general reading and writing of controls:
1) Read/write at offset position in control.
2) Read/write of various lengths less than length of the control.
3) Rejecting illegal arguments.
The test cases are run for ADSP2 with 16-bit registers, ADSP2
with 32-bit registers and Halo Core with 32-bit registers. The
ADSP2 cases are further divided into runs for V1 and V2 format
WMFW files, because there are differences in how V1 and V2
defines controls.
The obsolete V0 format does not have controls, so no testing of
that format is needed.
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20241212143725.1381013-10-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Add KUnit test cases for the caching of control content.
The test cases can be divided into four groups:
1) The cache is correctly initialized when the firmware is first
downloaded.
2) Reads return the correct data.
3) Writes update the registers and cache.
4) If a value has been written to the control it is retained in
the cache and written out to the registers when the firmware
is started.
There are multiple test suites to cover:
- V1 and V2 format files on 16-bit and 32-bit ADSP2.
- V3 format files on Halo Core DSPs.
V1 format files, and some V2 format files, didn't provide access
flags for the controls. There are a couple of test cases for
unspecified flags to ensure backwards compatibility with the
original implementation of these older firmware versions.
The obsolete V0 format does not have controls, so no testing of
that format is needed.
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20241212143725.1381013-9-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Add KUnit test cases for parsing of firmware controls out of the
wmfw. These test cases are only testing that the data in the wmfw
is correctly interpreted and entered into the list of controls.
The test cases can be roughly divided into three types:
1) The correct values are extracted from the wmfw.
2) Variable-length strings are handled correctly.
3) Controls are correctly identified as unique or identical.
There are multiple test suites to cover:
- V1 and V2 format files on 16-bit and 32-bit ADSP2.
- V3 format files on Halo Core DSPs.
V1 format does not have named controls, and the strings in the
coefficient descriptor are fixed-length fields. On V2 and V3 format
the controls are named and all strings are variable-length.
The obsolete V0 format does not have controls, so no testing of
that format is needed.
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20241212143725.1381013-8-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
This adds a KUnit test suite to test downloading wmfw files.
The general technique is
1. Create mock wmfw file content
2. Tell cs_dsp to download the wmfw file
3. Check in the emulated regmap registers that the correct values have
been written to DSP memory
4. Drop the regmap cache for the expected written registers and then do a
regcache_sync() to check for unexpected writes to other registers.
The test covers ADSP2 v1 and v2, and HALO Core DSPs. (ADSP1 is very
obsolete so isn't tested).
There is a large number of test cases and parameterized variants of tests
because of the many different addressing schemes supported by the Cirrus
devices. The DSP has 2 or 3 memory spaces: XM, YM and ZM. The DSP sees
these using its native addressing, which is word-addressed (not
byte-addressed). The host sees these through one of several register
mappings (depending on the DSP type and parent codec family). The
registers have three different addressing schemes: 16-bit registers
addressed by register number, 32-bit registers addressed by register
number, or 32-bit registers addressed by byte (with a stride of 4). In
addition to these multiple addressing schemes, the Halo Core DSPs have a
"packed" register mapping that maps 4 DSP words into 3 registers. In
addition to this there are 4 versions of the wmfw file format to be
tested.
The test cases intentionally have relatively little factoring-out of
similar code. This makes it much easier to visually verify that a test
case is testing correctly, and what exactly it is testing. Factoring out
large amounts of code into helper functions tends to obscure what the
actual test procedure is, so increasing the chance of hidden errors where
test cases don't actually test as intended.
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20241212143725.1381013-7-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
This adds a KUnit test suite to test downloading bin files.
The general technique is
1. Create mock bin file content
2. Tell cs_dsp to download the bin file
3. Check in the emulated regmap registers that the correct values have
been written to DSP memory
4. Drop the regmap cache for the expected written registers and then do a
regcache_sync() to check for unexpected writes to other registers.
The test covers ADSP2 v1 and v2, and HALO Core DSPs. (ADSP1 is very
obsolete so isn't tested).
There is a large number of test cases and parameterized variants of tests
because of the many different addressing schemes supported by the Cirrus
devices. The DSP has 2 or 3 memory spaces: XM, YM and ZM. The DSP sees
these using its native addressing, which is word-addressed (not
byte-addressed). The host sees these through one of several register
mappings (depending on the DSP type and parent codec family). The
registers have three different addressing schemes: 16-bit registers
addressed by register number, 32-bit registers addressed by register
number, or 32-bit registers addressed by byte (with a stride of 4). In
addition to these multiple addressing schemes, the Halo Core DSPs have a
"packed" register mapping that maps 4 DSP words into 3 registers. The bin
file addresses the data blob relative to the base address of an algorithm,
which has to be calculated in both DSP words (for the DSP to access) and
register addresses (for the host).
This results in many different addressing schemes used in parallel, hence
the complexity of the address and size manipulation in the test cases:
word addresses in DSP memory, byte offsets, word offsets, register
addresses (either byte-addressed 32-bit or index-addressed 16-bit), and
packed register addresses.
The test cases intentionally have relatively little factoring-out of
similar code. This makes it much easier to visually verify that a test
case is testing correctly, and what exactly it is testing. Factoring out
large amounts of code into helper functions tends to obscure what the
actual test procedure is, so increasing the chance of hidden errors where
test cases don't actually test as intended.
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20241212143725.1381013-6-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Add a mock firmware file that emulates what the firmware build tools
would normally create. This will be used by KUnit tests to generate a
test bin file.
The data payload in a bin is an opaque blob, so the mock bin only needs
to generate the appropriate file header and description block for each
payload blob.
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20241212143725.1381013-5-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Add a mock firmware file that emulates what the firmware build tools
would normally create. This will be used by KUnit tests to generate a
test wmfw file.
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20241212143725.1381013-4-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Add helper functions to implement an emulation of the DSP memory map.
There are three main groups of functionality:
1. Define a mock cs_dsp_region table.
2. Calculate the addresses of memory and algorithms from the firmware
header in XM.
3. Build a mock XM header in emulated XM.
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20241212143725.1381013-3-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Add a mock regmap implementation to act as a simulated DSP for KUnit
testing. This is built as a utility module so that it could be used by
clients of cs_dsp to create a mock "DSP" for their own testing.
cs_dsp interacts with the DSP only through registers. Most of the
register space of the DSP is RAM. ADSP cores have a small set of control
registers. HALO Core DSPs have a much larger set of control registers but
only a small subset are used.
Most writes are "blind" in the sense that cs_dsp does not expect to
receive any sort of response from the DSP. So there isn't any need to
emulate a "DSP", only a set of registers that can be written and read
back.
The idea of the mock regmap is to use the cache to accumulate writes
which can then be tested against the values that are expected to be in
the registers.
Stray writes can be detected by dropping the cache entries for all
addresses that should have been written and then issuing a regcache_sync().
If this causes bus writes it means there were writes to unexpected
registers.
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20241212143725.1381013-2-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
If the stream's pause_supported flag is false then mask out the PAUSE
support, so user space will be prevented to use it.
Introduce a module parameter to ignore the pause_supported flag, named as
force_pause_support to allow testing of the PAUSE feature.
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Liam Girdwood <liam.r.girdwood@intel.com>
Link: https://patch.msgid.link/20241213101123.27318-3-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
New tokens are added to topology:
1202: SOF_TKN_STREAM_PLAYBACK_PAUSE_SUPPORTED
1203: SOF_TKN_STREAM_CAPTURE_PAUSE_SUPPORTED
The new tokens are used to advertise support for PAUSE/RESUME operation on
a PCM device depending on firmware product, use case, pipeline topology.
The snd_sof_pcm_stream.pause_supported is updated to reflect the advertised
value for the PCM device.
If the token does not exist then the pause_supported is set to false.
Note: it is up to the platform code to use this flag to decide to advertise
the PAUSE support for user space or not.
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Reviewed-by: Liam Girdwood <liam.r.girdwood@intel.com>
Link: https://patch.msgid.link/20241213101123.27318-2-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Register m2m platform device,that user can
use M2M feature.
Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Acked-by: Jaroslav Kysela <perex@perex.cz>
Link: https://patch.msgid.link/20241212074509.3445859-7-shengjiu.wang@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Register m2m platform device, that user can
use M2M feature.
Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Acked-by: Jaroslav Kysela <perex@perex.cz>
Link: https://patch.msgid.link/20241212074509.3445859-6-shengjiu.wang@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
Implement the ASRC memory to memory function using
the compress framework, user can use this function with
compress ioctl interface.
This feature can be shared by ASRC and EASRC drivers
Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Acked-by: Jaroslav Kysela <perex@perex.cz>
Link: https://patch.msgid.link/20241212074509.3445859-5-shengjiu.wang@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
|
ASRC can be used on memory to memory case, define several
functions for m2m usage and export them as function pointer.
Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Acked-by: Jaroslav Kysela <perex@perex.cz>
Link: https://patch.msgid.link/20241212074509.3445859-4-shengjiu.wang@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
|
