On Wed 18 Dec 2019 at 18:50, Mark Brown <broonie@xxxxxxxxxx> wrote: > On Wed, Dec 18, 2019 at 06:24:18PM +0100, Jerome Brunet wrote: > >> Add a new property with the depth of the fifo in bytes. This is useful >> since some instance of the fifo, even on the same SoC, may have different >> depth. The depth is useful is set some parameters of the fifo. > > Can't we figure this out from the compatible strings? They look SoC > specific (which is good). That means we don't need to add new > properties for each quirk that separates the variants. I don't think it would be appropriate in this case: If I take the example of TODDR fifos on the SM1 SoC; All the TODDR fifo on this SoC are compatible with the same driver and use: compatible = "amlogic,sm1-toddr", "amlogic,axg-toddr"; However instance A on this SoC has a 8192B fifo while instance B, C and D have 256B fifo. Same goes for the other SoC and also FRDDR fifos. To store this difference using compatible I would have to add 1 compatible string for each "A" instance of each FRDDR and TODDR of each SoC. At the moment this would be 6 more compatible string for something that is really a parameter ... This also shows that fifo depth is something the HW manufacturer can tweak easily for each instances. It would not scale which is why I went for a property. _______________________________________________ Alsa-devel mailing list Alsa-devel@xxxxxxxxxxxxxxxx https://mailman.alsa-project.org/mailman/listinfo/alsa-devel
