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: Maarten van der Schrieck <maarten@thingsconnected.nl>
See the commit a00c9d56db for a detailed description of the problem, a
regression introduced in 26d503298.
Same approach here as the linked fix for rp2 (applied unconditionally here
as this port only supports USB-CDC for stdin/stdout).
Signed-off-by: Angus Gratton <angus@redyak.com.au>
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>
It turned out that the result of calling ticks_us() was always either odd
or even, depending on some internal state during boot. So the us-counter
was set to a 2 MHz input and the result shifted by 1. The counting period
is still long enough, since internally a (now) 63 bit value is used for us.
If USB CDC is connected and the board sends data, but the host does not
receive the data, the device locks up. This is fixed in this commit by
having a timeout of 500ms, after which time the transmission is skipped.
This removes the difference in the time.ticks_us() range between SAMD21 and
SAMD51.
The function mp_hal_ticks_us_64() is added and used for:
- SAMD51's mp_hal_ticks_us and mp_hal_delay_us().
For SAMD21, keep the previous methods, which are faster.
- mp_hal_ticks_ms() and mp_hal_tick_ms_64(), which saves some bytes
and removes a potential race condition every 50 days.
Also set the us-counter for SAMD51 to 16 MHz for a faster reading of the
microsecond value.
Note: With SAMD51, mp_hal_ticks_us_64() has a 60 bit range only, which is
still a long time (~36000 years).
Porting PR #8040 by @hoihu to SAMD, following the commit
5873390226.
One small addition: before executing keyboard interrupt, the input buffer
is cleared.
Features are:
- 3 to 5 different frequency groups.
- Freq range of 1Hz - 24 MHz.
- Duty rate stays stable on freq change.
Keyword options to the PWM constructor:
- device=n Select a specific PWM device. If no device is specified, a free
device is chosen, if available at that pin.
- freq=nnnn
- duty_u16=nnnn
- duty_ns=nnnn
- invert=True/False Allowing two outputs on the same device/channel to have
complementary signals.
If both freq and duty are provided, PWM output will start immediately.
Pins at the same device have the same frequency. If the PWM output number
exceeds the number of channels at the PWM device, the effctive channel_no
is output_no % channel_count. So with a channel count of 4, output 7 is
assigned to channel 3. Pins at a certain channel have the same frequency
and duty rate, but may be seperately inverted.
The changes in this commit are:
- Add an interface for pin open-drain mode.
- Improve ticks_us() by using the us-counter.
- Improve ticks_cpu() by using the CPU's SysTick.
- Makefile: update to use new ASF4 files, support frozen manifest, and
include source files in upcoming commits
- boards/manifest.py: add files to freeze
- boards/samd51p19a.ld: add linker script for this MCU
- help.c: add custom help text
- main.c: execute _boot.py, boot.py and main.py on start-up
- modules/_boot.py: startup file to freeze
- modutime.c: add gmtime, localtime, mktime, time functions
- mpconfigport.h: enabled more features for sys and io and modules
- mphalport.h: add mp_hal_pin_xxx macros
- mphalport.c: add mp_hal_stdio_poll
This is a more logical place to clear the KeyboardInterrupt traceback,
right before it is set as a pending exception. The clearing is also
optimised from a function call to a simple store of NULL.
This function is tightly coupled to the state and behaviour of the
scheduler, and is a core part of the runtime: to schedule a pending
exception. So move it there.