aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/tools/perf/scripts/python/export-to-postgresql.py (unfollow)
AgeCommit message (Collapse)AuthorFilesLines
2024-12-18ASoC: fsl_asrc_m2m: force cast for snd_pcm_format_t typeShengjiu Wang1-5/+5
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>
2024-12-17ASoC: soc-core: remove redundant assignment to variable retColin Ian King1-1/+0
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>
2024-12-17firmware: cs_dsp: Fix endianness conversion in cs_dsp_mock_wmfw.cRichard Fitzgerald1-1/+1
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>
2024-12-17ASoC: cs42l43: don't include '<linux/find.h>' directlyWolfram Sang1-1/+1
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>
2024-12-17firmware: cs_dsp: Avoid using a u32 as a __be32 in cs_dsp_mock_mem_maps.cRichard Fitzgerald1-3/+4
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>
2024-12-16ASoC: qcom: sdm845: add handling of secondary MI2S clockAlexey Klimov1-2/+3
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>
2024-12-16firmware: cs_dsp: avoid large local variablesArnd Bergmann1-14/+19
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>
2024-12-16ASoC: rt715: Remove unused hda_to_sdwDr. David Alan Gilbert2-44/+0
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>
2024-12-16ASoC: simple-card-utils: Unify clock direction by clk_directionKuninori Morimoto1-6/+6
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>
2024-12-16ASoC: soc-pcm: don't use soc_pcm_ret() on .prepare callbackKuninori Morimoto1-4/+28
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>
2024-12-16firmware: cs_dsp: Fix kerneldoc typos in cs_dsp_mock_bin.cRichard Fitzgerald1-2/+2
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>
2024-12-16ASoC: soc-core: tidyup ret handling for card->disable_route_checksKuninori Morimoto2-3/+7
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>
2024-12-16ASoC: Intel: mtl-match: Add CDB35L56-EIGHT-C 8x CS35L56 without CS42L43Richard Fitzgerald1-0/+134
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>
2024-12-16ASoC: Intel: mtl-match: Add CDB35L56-EIGHT-C with aggregated speakersRichard Fitzgerald1-0/+79
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>
2024-12-16ASoC: Intel: tgl-match: Add entries for CS35L56 on CDB35L56-EIGHT-CRichard Fitzgerald1-0/+194
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>
2024-12-13ASoC: SOF: sof-priv: Remove unused SOF_DAI_STREAM() and SOF_FORMATSPeter Ujfalusi1-8/+0
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>
2024-12-13ASoC: SOF: ipc4-topology: Use macro to set the EXT_PARAM_SIZE in widget setupPeter Ujfalusi1-1/+1
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>
2024-12-13firmware: cs_dsp: Add KUnit testing of client callbacksRichard Fitzgerald2-0/+689
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>
2024-12-13firmware: cs_dsp: Add KUnit testing of wmfw error casesRichard Fitzgerald2-0/+1348
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>
2024-12-13firmware: cs_dsp: Add KUnit testing of bin error casesRichard Fitzgerald2-0/+601
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>
2024-12-13firmware: cs_dsp: Add KUnit testing of control read/writeRichard Fitzgerald2-0/+2670
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>
2024-12-13firmware: cs_dsp: Add KUnit testing of control cacheRichard Fitzgerald2-0/+3283
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>
2024-12-13firmware: cs_dsp: Add KUnit testing of control parsingRichard Fitzgerald2-0/+1852
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>
2024-12-13firmware: cs_dsp: Add KUnit testing of wmfw downloadRichard Fitzgerald2-0/+2212
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>
2024-12-13firmware: cs_dsp: Add KUnit testing of bin file downloadRichard Fitzgerald4-0/+2590
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>
2024-12-13firmware: cs_dsp: Add mock bin file generator for KUnit testingRichard Fitzgerald3-0/+218
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>
2024-12-13firmware: cs_dsp: Add mock wmfw file generator for KUnit testingRichard Fitzgerald3-1/+508
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>
2024-12-13firmware: cs_dsp: Add mock DSP memory map for KUnit testingRichard Fitzgerald3-0/+815
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>
2024-12-13firmware: cs_dsp: Add mock regmap for KUnit testingRichard Fitzgerald7-2/+444
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>
2024-12-13ASoC: SOF: Intel: hda-pcm: Follow the pause_supported flag to drop PAUSE supportPeter Ujfalusi1-0/+15
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>
2024-12-13ASoC: SOF: Add support for pause supported tokens from topologyPeter Ujfalusi3-0/+7
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>
2024-12-13ASoC: fsl_easrc: register m2m platform deviceShengjiu Wang1-2/+31
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>
2024-12-13ASoC: fsl_asrc: register m2m platform deviceShengjiu Wang1-4/+33
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>
2024-12-13ASoC: fsl_asrc_m2m: Add memory to memory functionShengjiu Wang4-1/+739
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>
2024-12-13ASoC: fsl_easrc: define functions for memory to memory usageShengjiu Wang2-0/+232
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>
2024-12-13ASoC: fsl_asrc: define functions for memory to memory usageShengjiu Wang3-0/+205
ASRC can be used on memory to memory case, define several functions for m2m usage. m2m_prepare: prepare for the start step m2m_start: the start step m2m_unprepare: unprepare for stop step, optional m2m_stop: stop step m2m_check_format: check format is supported or not m2m_calc_out_len: calculate output length according to input length m2m_get_maxburst: burst size for dma m2m_pair_suspend: suspend function of pair, optional. m2m_pair_resume: resume function of pair get_output_fifo_size: get remaining data size in FIFO Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com> Acked-by: Jaroslav Kysela <perex@perex.cz> Link: https://patch.msgid.link/20241212074509.3445859-3-shengjiu.wang@nxp.com Signed-off-by: Mark Brown <broonie@kernel.org>
2024-12-13ALSA: compress: Add output rate and output format supportShengjiu Wang1-2/+21
Add 'pcm_format' for struct snd_codec, add 'pcm_formats' for struct snd_codec_desc, these are used for accelerator usage. Current accelerator example is sample rate converter (SRC). Define struct snd_codec_desc_src for descript minmum and maxmum sample rates. And add 'src_d' in union snd_codec_options structure. These are mainly used for capbility query. Signed-off-by: Jaroslav Kysela <perex@perex.cz> Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com> Acked-by: Jaroslav Kysela <perex@perex.cz> Acked-by: Vinod Koul <vkoul@kernel.org> Link: https://patch.msgid.link/20241212074509.3445859-2-shengjiu.wang@nxp.com Signed-off-by: Mark Brown <broonie@kernel.org>
2024-12-11ASoC: dt-bindings: convert rt5682.txt to dt-schemaNeil Armstrong2-98/+156
Convert the text bindings for the Realtek rt5682 and rt5682i codecs to dt-schema. Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org> Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> Link: https://patch.msgid.link/20241211-topic-misc-rt5682-convert-v2-1-9e1dd4ff7093@linaro.org Signed-off-by: Mark Brown <broonie@kernel.org>
2024-12-11ASoC: dt-bindings: renesas,rz-ssi: Document the Renesas RZ/G3S SoCClaudiu Beznea1-0/+1
The SSI IP variant present on the Renesas RZ/G3S SoC is similar to the one found on the Renesas RZ/G2{UL, L, LC} SoCs. Add documentation for it. Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com> Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Link: https://patch.msgid.link/20241210170953.2936724-20-claudiu.beznea.uj@bp.renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
2024-12-11ASoC: dt-bindings: renesas,rz-ssi: Remove DMA descriptionClaudiu Beznea1-18/+0
Remove the DMA description, as it duplicates content from ../dma/renesas,rz-dma.yaml. Additionally, remove the MID/RID examples mentioned in the dropped description (this information is already documented in the hardware manual). Suggested-by: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com> Link: https://patch.msgid.link/20241210170953.2936724-19-claudiu.beznea.uj@bp.renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
2024-12-11ASoC: renesas: rz-ssi: Add suspend to RAM supportClaudiu Beznea1-2/+44
The SSIF-2 IP is available on the Renesas RZ/G3S SoC. The Renesas RZ/G3S SoC supports a power-saving mode where power to most of the SoC components is turned off. Add suspend/resume support to the SSIF-2 driver to support this power-saving mode. On SNDRV_PCM_TRIGGER_SUSPEND trigger the SSI is stopped (the stream user pointer is left untouched to avoid breaking user space and the dma buffer pointer is set to zero), on SNDRV_PCM_TRIGGER_RESUME software reset is issued for the SSIF-2 IP and the clocks are re-configured. Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com> Link: https://patch.msgid.link/20241210170953.2936724-18-claudiu.beznea.uj@bp.renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
2024-12-11ASoC: renesas: rz-ssi: Issue software reset in hw_params APIClaudiu Beznea1-8/+14
The code initially issued software reset on SNDRV_PCM_TRIGGER_START action only before starting the first stream. This can be easily moved to hw_params() as the action is similar to setting the clocks. Moreover, according to the hardware manual (Table 35.7 Bits Initialized by Software Reset of the SSIFCR.SSIRST Bit) the software reset action acts also on the clock dividers bits. Due to this issue the software reset in hw_params() before configuring the clock dividers. This also simplifies the code in trigger API. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com> Link: https://patch.msgid.link/20241210170953.2936724-17-claudiu.beznea.uj@bp.renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
2024-12-11ASoC: renesas: rz-ssi: Add runtime PM supportClaudiu Beznea1-5/+21
Add runtime PM support to the ssi driver. This assert/de-assert the reset lines on runtime suspend/resume. Along with it the de-assertion of the reset line from probe function was removed as it is not necessary anymore. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com> Link: https://patch.msgid.link/20241210170953.2936724-16-claudiu.beznea.uj@bp.renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
2024-12-11ASoC: renesas: rz-ssi: Enable runtime PM autosuspend supportClaudiu Beznea1-0/+3
Enable runtime PM autosuspend support. The chosen autosuspend delay is zero for immediate autosuspend. In case there are users that need a different autosuspend delay, it can be adjusted through sysfs. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com> Link: https://patch.msgid.link/20241210170953.2936724-15-claudiu.beznea.uj@bp.renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
2024-12-11ASoC: renesas: rz-ssi: Rely on the ASoC subsystem to runtime resume/suspend the SSIClaudiu Beznea1-11/+5
The ASoC subsystem takes care of runtime resume/suspend the audio devices when needed. Just enable the runtime PM on the SSI driver and let the subsystem runtime resume/suspend it. While at it use directly the devm_pm_runtime_enable(). Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com> Link: https://patch.msgid.link/20241210170953.2936724-14-claudiu.beznea.uj@bp.renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
2024-12-11ASoC: renesas: rz-ssi: Use goto label names that specify their actionsClaudiu Beznea1-8/+8
Use goto label names that specify their action. In this way we can have a better understanding of what is the action associated with the label by just reading the label name. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com> Link: https://patch.msgid.link/20241210170953.2936724-13-claudiu.beznea.uj@bp.renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
2024-12-11ASoC: renesas: rz-ssi: Use temporary variable for struct deviceClaudiu Beznea1-31/+31
Use a temporary variable for the struct device pointers to avoid dereferencing. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com> Link: https://patch.msgid.link/20241210170953.2936724-12-claudiu.beznea.uj@bp.renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
2024-12-11ASoC: renesas: rz-ssi: Use readl_poll_timeout_atomic()Claudiu Beznea1-10/+6
Use readl_poll_timeout_atomic() instead of hardcoding something similar. While at it replace dev_info() with dev_warn_ratelimited() as the rz_ssi_set_idle() can also be called from IRQ context and if the SSI idle is not properly set this is at least a warning for user. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com> Link: https://patch.msgid.link/20241210170953.2936724-11-claudiu.beznea.uj@bp.renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
2024-12-11ASoC: renesas: rz-ssi: Remove the first argument of rz_ssi_stream_is_play()Claudiu Beznea1-5/+4
The first argument of the rz_ssi_stream_is_play() is not used. Remove it. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com> Link: https://patch.msgid.link/20241210170953.2936724-10-claudiu.beznea.uj@bp.renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
2024-12-11ASoC: renesas: rz-ssi: Remove the rz_ssi_get_dai() functionClaudiu Beznea1-12/+5
Remove the rz_ssi_get_dai() function and use directly the snd_soc_rtd_to_cpu() where needed or the struct device pointer embedded in the struct rz_ssi_priv objects. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com> Link: https://patch.msgid.link/20241210170953.2936724-9-claudiu.beznea.uj@bp.renesas.com Signed-off-by: Mark Brown <broonie@kernel.org>
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.