GitLab

This is a follow up to d263438a, which
solved one problem (reset on disconnect) but introduced a second one (hang
in bootloader).

To solve both probles, False/False is needed for DTR/RTS for ESPxx, but
that would then block stm32 and others.  Any unconditional combination of
DTR/RTS ends up blocking normal operation on some type of board or another.

A simple overview (for windows only):

  DTR          CTS            ESP8266/ESP32          STM32/SAMD51/RP2040
  unspecified  unspecified    Reset on disconnect    OK
  True         False          Hang in bootloader     OK
  False        False          OK                     No Repl
  True         True           Reset on disconnect    No Repl
  False        True           Reset on disconnect    No Repl

  serial.manufacturer:        wch.cn/Silicon Labs    Microsoft

  serial.description:         USB-SERIAL CH340 /     USB Serial Device
                              CP210x USB to UART
                              Bridge

The updated logic will only set the DTR/RTS signals for boards that do not
use standard Microsoft drivers (based on the manufacturer).  It would also
be possible to check against a list of known driver manufactures (like
wch.cn or Silicon Labs) but this would require a list of known drivers for
all ports.
Signed-off-by: Jos Verlinde <jos_verlinde@hotmail.com>

Signed-off-by: Damien George <damien@micropython.org>

Following other vfs_fat tests, so the test works on ports like stm32 that
only support 512-byte block size.
Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: David Lechner <david@pybricks.com>

This is a best-effort implementation of write polling.  It's difficult to
do correctly because if there are multiple output streams (eg UART and USB
CDC) then some may not be writeable while others are.  A full solution
should also have a return value from mp_hal_stdout_tx_strn(), returning the
number of bytes written to the stream(s).  That's also hard to define.

The renesas-ra and stm32 ports already implement a similar best-effort
mechanism for write polling.

Fixes issue #11026.
Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: Damien George <damien@micropython.org>

If a multitest calls `multitest.output_metric(...)` then that output will
be collected separately, not considered as part of the test verification
output, and instead be printed at the end.  This is useful for tests that
want to output performance/timing metrics that may change from one run to
the next.
Signed-off-by: Damien George <damien@micropython.org>

But leave these disabled.
Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: Damien George <damien@micropython.org>

Prior to this change, setting of UART parameters like parity, stop bits or
data bits did not work correctly.  As suggested by @iabdalkader, adding
__DSB() fixes the problem, making sure that changes to the UART LCR_H
register are seen by the peripheral.

Note: the FIFO is already enabled in the call to uart_init(), so the call
to uart_set_fifo_enabled() is not required, but kept for visibility.

Fixes issue #10976.

This was broken by 5327cd10Signed-off-by: Damien George <damien@micropython.org>

This is intended to be used by the very outer caller of the VM/runtime.  It
allows setting a top-level NLR handler that can be jumped to directly, in
order to forcefully abort the VM/runtime.

Enable using:

    #define MICROPY_ENABLE_VM_ABORT (1)

Set up the handler at the top level using:

    nlr_buf_t nlr;
    nlr.ret_val = NULL;
    if (nlr_push(&nlr) == 0) {
        nlr_set_abort(&nlr);
        // call into the VM/runtime
        ...
        nlr_pop();
    } else {
        if (nlr.ret_val == NULL) {
            // handle abort
            ...
        } else {
            // handle other exception that propagated to the top level
            ...
        }
    }
    nlr_set_abort(NULL);

Schedule an abort, eg from an interrupt handler, using:

    mp_sched_vm_abort();
Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: Damien George <damien@micropython.org>

When iterating over os.ilistdir(), the special directories '.' and '..'
are filtered from the results.  But the code inadvertently also filtered
any file/directory which happened to match '..*'.  This change fixes the
filter.

Fixes issue #11032.
Signed-off-by: Jeremy Rand <jeremy@rand-family.com>

The following have been tested and are working:
- 550MHz CPU frequency
- UART REPL via ST-Link
- USB REPL and mass storage
- 3x LEDs and 1x user button
- Ethernet
Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: Damien George <damien@micropython.org>

For builds with DEBUG=1 and MICROPY_HW_ENABLE_UART_REPL=1, calling
stdio_init_all() in main() detaches the UART input from REPL.  This change
suppresses calling stdio_init_all() then.

Previously, setting MICROPY_HW_ENABLE_USBDEV to 0 caused build errors.  The
change affects the nrf and samd ports as well, so MICROPY_HW_ENABLE_USBDEV
had to be explicitly enabled there.

The configuration options MICROPY_HW_ENABLE_USBDEV and
MICROPY_HW_ENABLE_UART_REPL are independent, and can be enabled or disabled
by a board.
Signed-off-by: Damien George <damien@micropython.org>

Mostly for compatibility.  Effective values are 100000, 250000 and 400000.
The supplied values are mapped to these.

Calling MICROPY_EVENT_POLL_HOOK.  That allows Ctrl-C to break loops with
idle().

Suggested by @ricksorensen after testing.  These match better the hardware
of the NRF52xx.

Changes in this commit:
- Add the timeout and timeout_char keyword options.
- Make uart.read() non-blocking.
- Add uart.any().
- Add ioctl MP_STREAM_POLL handling.
- Change uart.write() into non-busy waiting. uart.write() still waits until
  all data has been sent, but calls MICROPY_EVENT_POLL_HOOK while waiting.
  uart.write() uses DMA for transfer.  One option would be to add a small
  local buffer, such that transfers up to the size of the buffer could be
  done without waiting.
- As a side effect to the change of uart.write(), uart.txdone() and ioctl
  flush now report/wait correctly for the end of transmission.
- Change machine_hard_uart_buf_t in machine_hard_uart_obj_t to an instance
  of that struct, rather than a pointer to one.

Signed-off-by: Damien George <damien@micropython.org>

Example code should use mp_obj_malloc() as well since people will
likely copy this code.
Signed-off-by: David Lechner <david@pybricks.com>

As the comment in py/obj.h says:

> Implementing this as a call rather than inline saves 8 bytes per usage.

So in order to get this savings, we need to tell the compiler to never
inline the function.
Signed-off-by: David Lechner <david@pybricks.com>

Even if boards do not have a clock crystal.  In that case, the clock
quality will be very poor.

Always having machine.RTC means that the date/time can be set in a way that
is consistent with other ports.

This commit also removes the special code in modutime.c for devices without
the RTC class.
Signed-off-by: Damien George <damien@micropython.org>

Update arguments to mp_raw_code_load_mem so that the embed port can build
when MICROPY_PERSISTENT_CODE_LOAD is enabled.

Moving forward, tags in this repository will always have three components.
Signed-off-by: Damien George <damien@micropython.org>

These are basic PEP8 recommendations.

Without this, building the unix port variants gives:
ports/unix/main.c:667: undefined reference to `mp_obj_is_package',
when MICROPY_ENABLE_EXTERNAL_IMPORT is 0.
Signed-off-by: Laurens Valk <laurens@pybricks.com>

The C-level printf is usually used for internal debugging prints, and a
port/board may want to redirect this somewhere other than stdout.
Signed-off-by: Damien George <damien@micropython.org>

So that callers can redirect the output if needed.
Signed-off-by: Damien George <damien@micropython.org>

Signed-off-by: Damien George <damien@micropython.org>