ports/rp2: Bluetooth HCI fixes. #11234
Conversation
|
This will conflict with #10739. |
Why would it ? Seems unrelated |
|
Ah I see the |
6575c2c to
094c7f
8000
a
Compare
|
@dpgeorge Note I found a maybe minor issue with the HCI UART config, the baudrate was set as a positional arg, when it actually should be a keyword arg. Also related note both EDIT: Actually might be easier to just implement |
451e660 to
7d2a238
Compare
bd98355 to
15c4531
Compare
|
@dpgeorge @robert-hh Can we get these fixes merged especially the critical mpbthciport timer fix ? The other PR seems stalled and I would like to rebase some other work on those fixes. |
|
@iabdalkader What can I do in this respect? I can re-run the tests. The code changes are well known to me and look fine. Did the test coverage increase with these changes? |
I didn't do any more testing since last time, will revisit after this is merged. Just wanted to let you know these fixes are still pending here since you're adding WiFi/BT for another port, might want to rebase on this. |
|
Two notes:
|
Yes, this one and #10233. But I will add WiFi first. I'm still not overly happy with the BLE test coverage using the NINA module & software. |
Yeah me neither but it seems that it's not an issue in the Nina module/driver/firmware. I have another board based on Renesas chip/port and an ESP32 module, the firmware is based on IDF 5.x and I added a nimble port, and the tests results are bad too: Note the firmware is an official firmware from espressif |
15c4531 to
0a8b597
Compare
|
@dpgeorge Rebased. |
Signed-off-by: iabdalkader <i.abdalkader@gmail.com>
Fixes are: - The baudrate argument is a keyword arg, it was passed before as a positional arg. - Use the port and baudrate arguments passed from higher level code instead of the hard-coded port ID and baudrate, which would allow HCI drivers to change baudrates. - Increase UART char timeout and RX buffer size. Signed-off-by: iabdalkader <i.abdalkader@gmail.com>
Bluetooth code runs in the scheduler, so no locking/mutex is required. Signed-off-by: iabdalkader <i.abdalkader@gmail.com>
Fixes are: - Reset the module first before changing GPIO1 direction. - Skip spurious bytes received after reset. - Use HCI UART ID and baudrate when reinitializing UART. - Disable all printf output which causes unit-tests to fail. Signed-off-by: iabdalkader <i.abdalkader@gmail.com>
Signed-off-by: iabdalkader <i.abdalkader@gmail.com>
0a8b597 to
5473200
Compare
No description provided.