When the tdm lane mask is computed, the driver currently fills the 1st lane
before moving on to the next. If the stream has less channels than the
lanes can accommodate, slots will be disabled on the last lanes.
Unfortunately, the HW distribute channels in a different way. It distribute
channels in pair on each lanes before moving on the next slots.
This difference leads to problems if a device has an interface with more
than 1 lane and with more than 2 slots per lane.
For example: a playback interface with 2 lanes and 4 slots each (total 8
slots - zero based numbering)
- Playing a 8ch stream:
- All slots activated by the driver
- channel #2 will be played on lane #1 - slot #0 following HW placement
- Playing a 4ch stream:
- Lane #1 disabled by the driver
- channel #2 will be played on lane #0 - slot #2
This behaviour is obviously not desirable.
Change the way slots are activated on the TDM lanes to follow what the HW
does and make sure each channel always get mapped to the same slot/lane.
Fixes: 1a11d88f499c ("ASoC: meson: add tdm formatter base driver")
Signed-off-by: Jerome Brunet <[email protected]>
---
sound/soc/meson/axg-tdm-formatter.c | 42 ++++++++++++++++++-----------
1 file changed, 26 insertions(+), 16 deletions(-)
diff --git a/sound/soc/meson/axg-tdm-formatter.c b/sound/soc/meson/axg-tdm-formatter.c
index 9883dc777f63..63333a2b0a9c 100644
--- a/sound/soc/meson/axg-tdm-formatter.c
+++ b/sound/soc/meson/axg-tdm-formatter.c
@@ -30,27 +30,32 @@ int axg_tdm_formatter_set_channel_masks(struct regmap *map,
struct axg_tdm_stream *ts,
unsigned int offset)
{
- unsigned int val, ch = ts->channels;
- unsigned long mask;
- int i, j;
+ unsigned int ch = ts->channels;
+ u32 val[AXG_TDM_NUM_LANES];
+ int i, j, k;
+
+ /*
+ * We need to mimick the slot distribution used by the HW to keep the
+ * channel placement consistent regardless of the number of channel
+ * in the stream. This is why the odd algorithm below is used.
+ */
+ memset(val, 0, sizeof(*val) * AXG_TDM_NUM_LANES);
/*
* Distribute the channels of the stream over the available slots
- * of each TDM lane
+ * of each TDM lane. We need to go over the 32 slots ...
*/
- for (i = 0; i < AXG_TDM_NUM_LANES; i++) {
- val = 0;
- mask = ts->mask[i];
-
- for (j = find_first_bit(&mask, 32);
- (j < 32) && ch;
- j = find_next_bit(&mask, 32, j + 1)) {
- val |= 1 << j;
- ch -= 1;
+ for (i = 0; (i < 32) && ch; i += 2) {
+ /* ... of all the lanes ... */
+ for (j = 0; j < AXG_TDM_NUM_LANES; j++) {
+ /* ... then distribute the channels in pairs */
+ for (k = 0; k < 2; k++) {
+ if ((BIT(i + k) & ts->mask[j]) && ch) {
+ val[j] |= BIT(i + k);
+ ch -= 1;
+ }
+ }
}
-
- regmap_write(map, offset, val);
- offset += regmap_get_reg_stride(map);
}
/*
@@ -63,6 +68,11 @@ int axg_tdm_formatter_set_channel_masks(struct regmap *map,
return -EINVAL;
}
+ for (i = 0; i < AXG_TDM_NUM_LANES; i++) {
+ regmap_write(map, offset, val[i]);
+ offset += regmap_get_reg_stride(map);
+ }
+
return 0;
}
EXPORT_SYMBOL_GPL(axg_tdm_formatter_set_channel_masks);
--
2.40.1
On Wed, 09 Aug 2023 19:19:31 +0200, Jerome Brunet wrote:
> When the tdm lane mask is computed, the driver currently fills the 1st lane
> before moving on to the next. If the stream has less channels than the
> lanes can accommodate, slots will be disabled on the last lanes.
>
> Unfortunately, the HW distribute channels in a different way. It distribute
> channels in pair on each lanes before moving on the next slots.
>
> [...]
Applied to
https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git for-next
Thanks!
[1/1] ASoC: meson: axg-tdm-formatter: fix channel slot allocation
commit: c1f848f12103920ca165758aedb1c10904e193e1
All being well this means that it will be integrated into the linux-next
tree (usually sometime in the next 24 hours) and sent to Linus during
the next merge window (or sooner if it is a bug fix), however if
problems are discovered then the patch may be dropped or reverted.
You may get further e-mails resulting from automated or manual testing
and review of the tree, please engage with people reporting problems and
send followup patches addressing any issues that are reported if needed.
If any updates are required or you are submitting further changes they
should be sent as incremental updates against current git, existing
patches will not be replaced.
Please add any relevant lists and maintainers to the CCs when replying
to this mail.
Thanks,
Mark