Forum | Documentation | Website | Blog

Skip to content
Snippets Groups Projects
Select Git revision
0 results
Search by author
  • Any Author
0 authors
  1. Dec 26, 2023
  3. Dec 22, 2023
  5. Dec 21, 2023
    • Damien George's avatar
      lib/micropython-lib: Update submodule to latest. · 0b2676db
      Damien George authored 
      
Signed-off-by: default avatarDamien George <damien@micropython.org>
      0b2676db
    • Nicko van Someren's avatar
      rp2/rp2_dma: Introduce a new rp2.DMA class for control over DMA xfers. · cfc212b1
      Nicko van Someren authored 
      
This commit implements fairly complete support for the DMA controller in
the rp2 series of microcontrollers.  It provides a class for accessing the
DMA channels through a high-level, Pythonic interface, and functions for
setting and manipulating the DMA channel configurations.

Creating an instance of the rp2.DMA class claims one of the processor's DMA
channels.  A sensible, per-channel default value for the ctrl register can
be fetched from the DMA.pack_ctrl() function, and the components of this
register can be set via keyword arguments to pack_ctrl().

The read, write, count and ctrl attributes of the DMA class provide
read/write access to the respective registers of the DMA controller.  The
config() method allows any or all of these values to be set simultaneously
and adds a trigger keyword argument to allow the setup to immediately be
triggered.  The read and write attributes (or keywords in config()) accept
either actual addresses or any object that supports the buffer interface.
The active() method provides read/write control of the channel's activity,
allowing the user to start and stop the channel and test if it is running.

Standard MicroPython interrupt handlers are supported through the irq()
method and the channel can be released either by deleting it and allowing
it to be garbage-collected or with the explicit close() method.

Direct, unfettered access to the DMA controllers registers is provided
through a proxy memoryview() object returned by the DMA.registers attribute
that maps directly onto the memory-mapped registers.  This is necessary for
more fine-grained control and is helpful for allowing chaining of DMA
channels.

As a simple example, using DMA to do a fast memory copy just needs:

    src = bytearray(32*1024)
    dest = bytearray(32*1024)
    dma = rp2.DMA()
    dma.config(read=src, write=dest, count=len(src) // 4,
        ctrl=dma.pack_ctrl(), trigger=True)

    # Wait for completion
    while dma.active():
        pass

This API aims to strike a balance between simplicity and comprehensiveness.

Signed-off-by: default avatarNicko van Someren <nicko@nicko.org>
Signed-off-by: default avatarDamien George <damien@micropython.org>
      cfc212b1
    • Sebastian Romero's avatar
      nrf/main: Add /flash and /flash/lib to sys.path. · e4d3ab33
      Sebastian Romero authored 
      
This allows to follow good practice and have libraries live in the lib
folder which means they will be found by the runtime without adding this
path manually at runtime.

Signed-off-by: default avatarSebastian Romero <s.romero@arduino.cc>
      e4d3ab33
    • Peter Züger's avatar
      py/mkrules.mk: Fix dependency file generation for compiler wrappers. · d69e69ad
      Peter Züger authored 
      When compiling with distcc, it does not understand the -MD flag on its own.
This fixes the interaction by explicitly adding the -MF option.

The error in distcc is described here under "Problems with gcc -MD":
https://www.distcc.org/faq.html



Signed-off-by: default avatarPeter Züger <zueger.peter@icloud.com>
      d69e69ad
    • Peter Züger's avatar
      extmod/vfs_lfs: Fix lfs cache_size calculation. · ce42c9ee
      Peter Züger authored 
      
The calculation of the lfs2 cache_size was incorrect, the maximum allowed
size is block_size.

The cache size must be: "a multiple of the read and program sizes, and a
factor of the block size".

Signed-off-by: default avatarPeter Züger <zueger.peter@icloud.com>
      ce42c9ee
    • Maarten van der Schrieck's avatar
      ports: Fix sys.stdout.buffer.write() return value. · 3bca93b2
      Maarten van der Schrieck authored 
      
MicroPython code may rely on the return value of sys.stdout.buffer.write()
to reflect the number of bytes actually written. While in most scenarios a
write() operation is successful, there are cases where it fails, leading to
data loss. This problem arises because, currently, write() merely returns
the number of bytes it was supposed to write, without indication of
failure.

One scenario where write() might fail, is where USB is used and the
receiving end doesn't read quickly enough to empty the receive buffer. In
that case, write() on the MicroPython side can timeout, resulting in the
loss of data without any indication, a behavior observed notably in
communication between a Pi Pico as a client and a Linux host using the ACM
driver.

A complex issue arises with mp_hal_stdout_tx_strn() when it involves
multiple outputs, such as USB, dupterm and hardware UART. The challenge is
in handling cases where writing to one output is successful, but another
fails, either fully or partially. This patch implements the following
solution:

mp_hal_stdout_tx_strn() attempts to write len bytes to all of the possible
destinations for that data, and returns the minimum successful write
length.

The implementation of this is complicated by several factors:
- multiple outputs may be enabled or disabled at compiled time
- multiple outputs may be enabled or disabled at runtime
- mp_os_dupterm_tx_strn() is one such output, optionally containing
  multiple additional outputs
- each of these outputs may or may not be able to report success
- each of these outputs may or may not be able to report partial writes

As a result, there's no single strategy that fits all ports, necessitating
unique logic for each instance of mp_hal_stdout_tx_strn().

Note that addressing sys.stdout.write() is more complex due to its data
modification process ("cooked" output), and it remains unchanged in this
patch. Developers who are concerned about accurate return values from
write operations should use sys.stdout.buffer.write().

This patch might disrupt some existing code, but it's also expected to
resolve issues, considering that the peculiar return value behavior of
sys.stdout.buffer.write() is not well-documented and likely not widely
known. Therefore, it's improbable that much existing code relies on the
previous behavior.

Signed-off-by: default avatarMaarten van der Schrieck <maarten@thingsconnected.nl>
      3bca93b2
    • Maarten van der Schrieck's avatar
      extmod/os_dupterm: Let mp_os_dupterm_tx_strn() return num bytes written. · 91ee8ac8
      Maarten van der Schrieck authored 
      
In case of multiple outputs, the minimum successful write length is
returned.  In line with this, in case any output has a write error, zero is
returned.

In case of no outputs, -1 is returned.

The return value can be used to assess whether writes were attempted, and
if so, whether they succeeded.

Signed-off-by: default avatarMaarten van der Schrieck <maarten@thingsconnected.nl>
      91ee8ac8
  7. Dec 20, 2023
  9. Dec 19, 2023
  11. Dec 18, 2023
  13. Dec 17, 2023
  15. Dec 15, 2023
  17. Dec 14, 2023
  19. Dec 13, 2023
  21. Dec 12, 2023

Open hardware computers for makers, educators and professionals