The guard against running when flash is disabled isn't perfect and
may lead to calling the row handler anyway. We were crashing due
to mp_hal_delay_us being in flash. So, move it to RAM.
Also move the panic handler to IRAM so we get nice output when this
happens.
Turn off JTAG by default so its pins can be used by code.py.
Fixes#8987
- add tuh_event_hook_cb() in SRAM, required when updated to latest tinyusb
- bump up pico-pio-usb to latest
- bump up tinyusb to latest for new tuh_hid_receive_abort(), and all endpoint abort when
SET_CONFIGURATION
Some ports implement their own protection against this at a low level
but it doesn't hurt to add it here instead.
Based on a patch from @drath42
Closes: #8788
Once the buffer has less that an endpoint's worth, TinyUSB won't
request more from the host. When that happens, ctrl-c will no
longer be sent to the device and TinyUSB won't find the wanted
character.
Fixes#4444
this means that the test for FLAG_CTRL together with FLAG_STRING is
not needed. Instead, the FLAG_STRING | FLAG_CTRL row, when
encountered earlier, will automatically take precedence.
Added the ability to work with the function keys f1-f12, ctrl-left, ctrl-right, ctrl-up, ctrl-down, page down, page up, insert, delete, pause. in the format of command VT 100
This changes storage.mount() to require that a mount point exist
on the parent file system.
A bug in background tasks is also fixed where the function
parameter is cleared on pending callbacks during "reset".
Disk usage is shown on the directory listing and changes based on
the mounted file system. Writable is also loaded per-directory.
Fixes#8108. Fixes#8690. Fixes#8107.
This simplifies allocating outside of the VM because the VM doesn't
take up all remaining memory by default.
On ESP we delegate to the IDF for allocations. For all other ports,
we use TLSF to manage an outer "port" heap. The IDF uses TLSF
internally and we use their fork for the other ports.
This also removes the dynamic C stack sizing. It wasn't often used
and is not possible with a fixed outer heap.
Fixes#8512. Fixes#7334.
This allows you to initialize usb_host.Port once successfully and
then returns the same object as long as you pass the same arguments
in. It does allow you to fix incorrect pins but not switching from
one valid set to another. (It needs a reset for that.)
This also moves hcd cache operations to RAM so that they don't
access the cache when doing maintenance.
This is confined to pure ASCII, but does support Alt Gr. This is enough
to make a French keyboard layout work:
* home row is "qsdfghjklm"
* numerals are all shifted
* keys like {} require Alt Gr
While not tested, this should also support layouts like Colemak with
the necssary keymap file.
Layouts can be produced from Neradoc's keyboard layout modules on the
device & loaded at runtime. Code to do so is at
https://gist.github.com/jepler/597c0a00e0eb014a433e03c0ae363a08
as well as a sketch of how an extended format could support dead keys &
the full Unicode BMP instead of just ASCII.
PicoDVI in CP support 640x480 and 800x480 on Feather DVI, Pico and
Pico W. 1 and 2 bit grayscale are full resolution. 8 and 16 bit
color are half resolution.
Memory layout is modified to give the top most 4k of ram to the
second core. Its MPU is used to prevent flash access after startup.
The port saved word is moved to a watchdog scratch register so that
it doesn't get overwritten by other things in RAM.
Right align status bar and scroll area. This normally gives a few
pixels of padding on the left hand side and improves the odds it is
readable in a case. Fixes#7562
Fixes c stack checking. The length was correct but the top was being
set to the current stack pointer instead of the correct top.
Fixes#7643
This makes Bitmap subscr raise IndexError instead of ValueError
when the index arguments are wrong.
* Enable dcache for OCRAM where the VM heap lives.
* Add CIRCUITPY_SWO_TRACE for pushing program counters out over the
SWO pin via the ITM module in the CPU. Exempt some functions from
instrumentation to reduce traffic and allow inlining.
* Place more functions in ITCM to handle errors using code in RAM-only
and speed up CP.
* Use SET and CLEAR registers for digitalio. The SDK does read, mask
and write.
* Switch to 2MiB reserved for CircuitPython code. Up from 1MiB.
* Run USB interrupts during flash erase and write.
* Allow storage writes from CP if the USB drive is disabled.
* Get perf bench tests running on CircuitPython and increase timeouts
so it works when instrumentation is active.
When the USB serial buffer is full, the Ctrl-C code to send
KeyboardInterrupt can't be sent, which creates a problem if you've
pasted code or otherwise filled the buffer and need to recover.
A similar problem affects advanced UIs that interact with CircuitPython
and may send characters when they're unexpected, such as mu when it
tries to move the cursor based on the user clicking on the screen.
The main way forward seems to be to use some kind of message that can
still reach CircuitPython when its internal serial recieve buffer is full.
RS232 defines a "break" signal, in which the transmitting device holds its
data line in the "space" state for many entire character times. This still
exists in the world of USB serial.
This does work, sort of, except that your host computer software will need
to properly handle blocking serial writes; tio can send a break with
the **ctrl-c b** sequence, but this only works if it hasn't yet written
too much data, so it doesn't actually help in most situations :-/
