any news / progress / estimate when the PR could be reviewed(or rejected) ?

What are the performance implications? How much does the effective baud-rate drop due to the additional handling of configuration? At lower baud-rates there is no impact but I guess that above approx 115Kbps the drop will start. A benchmark is required.

As 9-bit mode is not a very common use case for Serial I would suggest considering a Serial sub-class. Also typical 9-bit mode usage is to signal the start and end of frames. This could be implemented without modifying the current Serial API.

Cheers! Mikael

If this is merged (a pretty big "if"), I would like to suggest a longer, more descriptive define than SERIAL9. Perhaps SERIAL_9BIT_SUPPORT could work?

Any news on this? Multidrop bus is a 9bit uart protocol. I could sure benefit if this branch would ever be merged!

@basprins I admit that I was lazy delivering the requested benchmarks; partially because given the nature of changes, the performance impact cannot be too high: one conditional jump based on register data operation, one IO write per-byte (not bit!). Similar for read.

IMHO worse effect is doubling the rx/tx buffer because of unsigned char to unsigned short change. Can be seen as bad on smaller Arduinos (I use Nanos ;)). Can be probably changed at the expense of some shift/and to use a bitfield for 9th bits - pls. give your opinions on whether you see that as worth the increased complexity.

Also note that if the guard macro is not defined, the change simply will not exist at all, leaving original code as it was - performance impact zero.

@mikaelpatel But now I have two A-Mega boards available, so I can make some measurement. I assume that we need at least to: prove that 16MHz is able to tx / rx 115kbps. That's trivial - but do you have some suggestion to actually measure 'net consumed time' for (say) the write operation ? Sequential write or read operations are limited by UART speed (when it becomes avialable again) - how to measure the really tiny CPU time that one write opreation takes ?
Thanks for the advice.

Re.: API change: good point; the write9 methods can be removed. Thanks, will change.

@PaulStoffregen: good idea; will do on the very next change, the change is going to be further considered for acceptance

CLA assistant check
Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

@svatoun After the latest @CLAassistant notice I revisited this pull request. I believe that if the purpose of 9-bit mode is to allow multi-drop protocols with the 9th bit for indicating address or data this could be done by simply adding a sendAddress(uint8_t addr) function to the HardwareSerial API. This function would set/reset the 9th bit accordingly.