With these changes IPv6 works on the rp2 port (and possibly others that use
the lwIP socket implementation).
Things that have been tested and work:
- Neighbour solicitation for v6 link local address.
- Ping of v6 link-local address.
- Receiving a SLAAC address via router advertisement.
- Ping a v6 address allocated via SLAAC.
- Perform an outgoing connection to a routed v6-address (via default
gateway).
- Create a listening IPv6 wildcard socked bound to ::, and trying to access
it via link-local, SLAAC, and IPv4 (to ensure the dual-stack binding
works).
Things that could be improved:
- socket.socket().getaddrinfo only returns the v4 address. It could also
return v6 addresses (getaddrinfo is actively programmed to only return a
single address, and this is the v4-address by default, with fallback to
the v6 address if both are enabled).
Signed-off-by: Felix Dörre <felix@dogcraft.de>
The Python BLE IRQ handler will most likely run on the NimBLE task, so its
C stack must be large enough to accommodate reasonably complicated Python
code (eg a few call depths). So increase this stack size.
Also increase the headroom from 1024 to 2048 bytes. This is needed because
(1) the esp32 architecture uses a fair amount of stack in general; and (2)
by the time execution gets to setting the Python stack top via
`mp_stack_set_top()` in this interlock code, about 600 bytes of stack are
already used, which reduces the amount available for Python.
Fixes issue #12349.
Signed-off-by: Damien George <damien@micropython.org>
Similar to the previous commit but for MP_BLUETOOTH_IRQ_GATTC_READ_DONE:
the pending_value_handle needs to be reset before calling
mp_bluetooth_gattc_on_read_write_status(), which will call the Python IRQ
handler, which may in turn call back into BTstack to perform an action like
a write. In that case the pending_value_handle will need to be available
for the write/read/etc to proceed.
Fixes issue #13634.
Signed-off-by: Damien George <damien@micropython.org>
The pending_value_handle needs to be freed and reset before calling
mp_bluetooth_gattc_on_read_write_status(), which will call the Python IRQ
handler, which may in turn call back into BTstack to perform an action like
a write. In that case the pending_value_handle will need to be available
for the write/read/etc to proceed.
Fixes issue #13611.
Signed-off-by: Damien George <damien@micropython.org>
The current `ssl` module has quite a few differences to the CPython
implementation. This change moves the MicroPython variant to a new `tls`
module and provides a wrapper module for `ssl` (in micropython-lib).
Users who only rely on implemented comparible behavior can continue to use
`ssl`, while users that rely on non-compatible behavior should switch to
`tls`. Then we can make the facade in `ssl` more strictly adhere to
CPython.
Signed-off-by: Felix Dörre <felix@dogcraft.de>
Changes include:
- Some mbedtls source files renamed or deprecated.
- Our `mbedtls_config.h` files are renamed to `mbedtls_config_port.h`, so
they don't clash with mbedtls's new default configuration file named
`mbedtls_config.h`.
- MBEDTLS_TLS_DEFAULT_ALLOW_SHA1_IN_KEY_EXCHANGE is deprecated.
- MBEDTLS_HAVE_TIME now requires an `mbedtls_ms_time` function to be
defined but it's only used for TLSv1.3 (currently not enabled in
MicroPython so there is a lazy implementation, i.e. seconds * 1000).
- `tests/multi_net/ssl_data.py` is removed (due to deprecation of
MBEDTLS_TLS_DEFAULT_ALLOW_SHA1_IN_KEY_EXCHANGE), there are the existing
`ssl_cert_rsa.py` and `sslcontext_server_client.py` tests which do very
similar, simple SSL data transfer.
- Tests now use an EC key by default (they are smaller and faster), and the
RSA key has been regenerated due to the old PKCS encoding used by openssl
rsa command, see
https://stackoverflow.com/questions/40822328/openssl-rsa-key-pem-and-der-conversion-does-not-match
(and `tests/README.md` has been updated accordingly).
Signed-off-by: Carlos Gil <carlosgilglez@gmail.com>
Prior to this commit it would skip every second cipher returned from
mbedtls.
The corresponding test is also updated and now passes on esp32, rp2, stm32
and unix.
Signed-off-by: Damien George <damien@micropython.org>
Adds support to asyncio.gather() for the case that one or more (or all)
sub-tasks finish and/or raise an exception before the gather starts.
Signed-off-by: Damien George <damien@micropython.org>
Instead, configure the default once at compile-time. This means the GAP
name will no longer be set to default after re-initializing Bluetooth.
Signed-off-by: Daniël van de Giessen <daniel@dvdgiessen.nl>
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: Peter Züger <zueger.peter@icloud.com>
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: Maarten van der Schrieck <maarten@thingsconnected.nl>
The poll_obj_t instances have their pollfd field point into this
allocation. So if re-allocating results in a move, we need to update the
existing poll_obj_t's.
Update the test to cover this case.
Fixes issue #12887.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
It looks like these never worked and there are no tests for this
functionality. Furthermore, CPython doesn't support this.
Fixes#12995.
Signed-off-by: Damien George <damien@micropython.org>
esp8266 doesn't need ets task because the notify is now scheduled (see
commits 7d57037906 and
c60caf1995 for relevant history).
Signed-off-by: Damien George <damien@micropython.org>
This adds asyncio ssl support with SSLContext and the corresponding
tests in `tests/net_inet` and `tests/multi_net`.
Note that not doing the handshake on connect will delegate the handshake to
the following `mbedtls_ssl_read/write` calls. However if the handshake
fails when a client certificate is required and not presented by the peer,
it needs to be notified of this handshake error (otherwise it will hang
until timeout if any). Finally at MicroPython side raise the proper
mbedtls error code and message.
Signed-off-by: Carlos Gil <carlosgilglez@gmail.com>
Fixes two issues:
- None should not be allowed in the list, otherwise the corresponding entry
in ciphersuites[i] will have an undefined value.
- The terminating 0 needs to be put in ciphersuites[len].
Signed-off-by: Damien George <damien@micropython.org>
And only enable this method when the relevant feature is available in
mbedtls. Otherwise, if mbedtls doesn't support getting the peer
certificate, this method always returns None and it's confusing why it does
that. It's better to remove the method altogether, so the error trying to
use it is more obvious.
Signed-off-by: Damien George <damien@micropython.org>
This commit adds:
1) Methods to SSLContext class that match CPython signature:
- `SSLContext.load_cert_chain(certfile, keyfile)`
- `SSLContext.load_verify_locations(cafile=, cadata=)`
- `SSLContext.get_ciphers()` --> ["CIPHERSUITE"]
- `SSLContext.set_ciphers(["CIPHERSUITE"])`
2) `sslsocket.cipher()` to get current ciphersuite and protocol
version.
3) `ssl.MBEDTLS_VERSION` string constant.
4) Certificate verification errors info instead of
`MBEDTLS_ERR_X509_CERT_VERIFY_FAILED`.
5) Tests in `net_inet` and `multi_net` to test these new methods.
`SSLContext.load_cert_chain` method allows loading key and cert from disk
passing a filepath in `certfile` or `keyfile` options.
`SSLContext.load_verify_locations`'s `cafile` option enables the same
functionality for ca files.
Signed-off-by: Carlos Gil <carlosgilglez@gmail.com>
So that ports don't need to specify each of these files, they can simply
refer to the appropriate make/cmake variable.
Signed-off-by: Damien George <damien@micropython.org>
See previous commit for details of these functions. As of this commit,
these still call the old hook macros on all ports.
This work was funded through GitHub Sponsors.
Signed-off-by: Angus Gratton <angus@redyak.com.au>
This patch simplifies the connection and sockets polling code, by switching
to a soft-timer to schedule polling code, and by using one node for
scheduling. This also fixes any issues that could result from using a heap
allocated machine_timer, and includes better handling of the sockets poll
list.
Signed-off-by: iabdalkader <i.abdalkader@gmail.com>
This is usually called on soft-reboot, a NIC can implement this to do any
necessary cleaning up (such as invalidating root pointers).
Signed-off-by: iabdalkader <i.abdalkader@gmail.com>
All ports using this common configuration already enable time/date
validation, so this commit is a no-op change.
Signed-off-by: Damien George <damien@micropython.org>
The os.dupterm() function has changed on this port, it now matches the
semantics used by all other ports (except it's restricted to accept only
machine.UART objects).
Signed-off-by: Damien George <damien@micropython.org>
The ports esp32, mimxrt, rp2 and samd all shared exactly the same
implementation of machine.disable_irq() and machine.enable_irq(),
implemented in terms of MICROPY_{BEGIN,END}_ATOMIC_SECTION. This commit
factors these implementations into extmod/modmachine.c.
The cc3200, esp8266, nrf, renesas-ra and stm32 ports do not yet use this
common implementation.
Signed-off-by: Damien George <damien@micropython.org>
Minor changes for consistency are:
- nrf gains: unique_id(), freq() [they do nothing]
- samd: deepsleep() now resets after calling lightsleep()
- esp32: lightsleep()/deepsleep() no longer take kw arg "sleep", instead
it's positional to match others. also, passing 0 here will now do a 0ms
sleep instead of acting like nothing was passed.
reset_cause() no longer takes any args (before it would just ignore them)
- mimxrt: freq() with an argument and lightsleep() both raise
NotImplementedError
Signed-off-by: Damien George <damien@micropython.org>
And use it in all ports. The ports are unchanged, except esp8266 which now
just returns None from this function instead of the time elapsed (to match
other ports), and qemu-arm which gains this function.
Signed-off-by: Damien George <damien@micropython.org>
This is a code factoring to have the dict for the machine module in one
location, and all the ports use that same dict. The machine.soft_reset()
function implementation is also factored because it's the same for all
ports that did already implement it. Eventually more functions/bindings
can be factored.
All ports remain functionally the same, except:
- cc3200 port: gains soft_reset, mem8, mem16, mem32, Signal; loses POWER_ON
(which was a legacy constant, replaced long ago by PWRON_RESET)
- nrf port: gains Signal
- qemu-arm port: gains soft_reset
- unix port: gains soft_reset
- zephyr port: gains soft_reset, mem8, mem16, mem32
Signed-off-by: Damien George <damien@micropython.org>
Fixes undefined behavior when calling vfs_posix_file_ioctl with
MP_STREAM_CLOSE as request because that casts away the constness and
assigns -1 to the object's fd member.
Fixes issue #12670.
Signed-off-by: stijn <stijn@ignitron.net>
Similar to 3883f29485 where this change was
implemented for threads: when the Bluetooth IRQ handler is called the
thread state is not not zero-initialized and thus we need to manually set
this to NULL.
Fixes issue #12239.
Signed-off-by: Daniël van de Giessen <daniel@dvdgiessen.nl>
This is a code factoring to have the Python bindings in one location, and
all the ports use those same bindings. At this stage only esp32 implements
this class, so the code for the bindings comes from that port.
The documentation is also updated to reflect the esp32's behaviour of
ADCBlock.connect().
Signed-off-by: Damien George <damien@micropython.org>
This fixes the case where e.g.
struct foo_t {
mp_obj_t x;
uint16_t y;
char buf[];
};
will have `sizeof(struct foo_t)==8`, but `offsetof(struct foo_t, buf)==6`.
When computing the size to allocate for `m_new_obj_var` we need to use
offsetof to avoid over-allocating. This is important especially when it
might cause it to spill over into another GC block.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
The flags returned from `select()` were misinterpreted to mean an error had
occurred for the socket, when it's actually just an exceptional condition
for the socket, such as OOB data.
Signed-off-by: iabdalkader <i.abdalkader@gmail.com>
The contents of machine_mem.h, machine_i2c.h and machine_spi.h have been
moved into extmod/modmachine.h.
Signed-off-by: Damien George <damien@micropython.org>
The contents of machine_bitstream.h, machine_pinbase.h, machine_pulse.h and
machine_signal.h have been moved into extmod/modmachine.h.
Signed-off-by: Damien George <damien@micropython.org>
The machine_i2c_type, machine_spi_type and machine_timer_type symbols are
already declared in extmod/modmachine.h and should not be declared anywhere
else.
Also move declarations of machine_pin_type and machine_rtc_type to the
common header in extmod.
Signed-off-by: Damien George <damien@micropython.org>
This is a code factoring to have the Python bindings in one location, and
all the ports use those same bindings. For all ports except the two listed
below there is no functional change.
The nrf port has UART.sendbreak() removed, but this method previously did
nothing.
The zephyr port has the following methods added:
- UART.init(): supports setting timeout and timeout_char.
- UART.deinit(): does nothing, just returns None.
- UART.flush(): raises OSError(EINVAL) because it's not implemented.
- UART.any() and UART.txdone(): raise NotImplementedError.
Signed-off-by: Damien George <damien@micropython.org>
No functional change, just code factoring to have the Python bindings in
one location, and all the ports use those same bindings.
Signed-off-by: Damien George <damien@micropython.org>
This factors the basic top-level I2S class code from the ports into
extmod/machine_i2s.c:
- I2S class definition and method table.
- The init and deinit method wrappers.
- The make_new code.
Further factoring will follow.
Signed-off-by: Damien George <damien@micropython.org>
With public declarations moved to extmod/modmachine.h. It's now mandatory
for a port to define MICROPY_PY_MACHINE_PWM_INCLUDEFILE if it enables
MICROPY_PY_MACHINE_PWM. This follows how extmod/machine_wdt.c works.
All ports have been updated to work with this modified scheme.
Signed-off-by: Damien George <damien@micropython.org>
There are currently 7 ports that implement machine.WDT and a lot of code is
duplicated across these implementations. This commit factors the common
parts of all these implementations to a single location in
extmod/machine_wdt.c. This common code provides the top-level Python
bindings (class and method wrappers), and then each port implements the
back end specific to that port.
With this refactor the ports remain functionally the same except for:
- The esp8266 WDT constructor now takes keyword arguments, and accepts the
"timeout" argument but raises an exception if it's not the default value
(this port doesn't support changing the timeout).
- The mimxrt and samd ports now interpret the argument to WDT.timeout_ms()
as signed and if it's negative truncate it to the minimum timeout (rather
than it being unsigned and a negative value truncating to the maximum
timeout).
Signed-off-by: Damien George <damien@micropython.org>
The unwritten API contract expected of a VFS.getcwd() by mp_vfs_getcwd()
is that its return value should be either "" or "/" when the CWD is at
the root of the VFS and otherwise start with a slash and not end with a
slash. This was not correctly implemented in VfsPosix for instances with
a non-empty root - the required leading slash, if any, was cut off
because the root length includes a trailing slash. This would result in
missing slashes in the middle of the return value of os.getcwd() or in
uninitialized garbage from beyond a string's null terminator when the
CWD was at the VFS root.
Signed-off-by: Christian Walther <cwalther@gmx.ch>
The unwritten API contract expected of a VFS by mp_vfs_lookup_path() is
that paths passed in are relative to the root of the VFS if they start
with '/' and relative to the current directory of the VFS otherwise.
This was not correctly implemented in VfsPosix for instances with a
non-empty root - all paths were interpreted relative to the root. Fix
that. Since VfsPosix tracks its CWD using the "external" CWD of the Unix
process, the correct handling for relative paths is to pass them through
unmodified.
Also, when concatenating absolute paths, fix an off-by-one resulting in
a harmless double slash (the root path already has a trailing slash).
Signed-off-by: Christian Walther <cwalther@gmx.ch>
A VfsPosix created with a relative root path would get confused when
chdir() was called on it and become unable to properly resolve absolute
paths, because changing directories effectively shifted its root. The
simplest fix for that would be to say "don't do that", but since the
unit tests themselves do it, fix it by making a relative path absolute
before storing it.
Signed-off-by: Christian Walther <cwalther@gmx.ch>
This wasn't correctly accounting for the bits-per-pixel and was returning a
bufinfo struct with the incorrect length. Instead, just forward directly
to the underlying buffer object.
Fixes issue #12563.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This ensures that the buffer is large enough for the specified width,
height, bits-per-pixel, and stride.
Also makes the legacy FrameBuffer1 constructor re-use the FrameBuffer
make_new to save some code size.
Fixes issue #12562.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Sometimes these are different file descriptors, not to mention the Unix
port, so use stderr to distinguish these error messages.
CPython prints to stdout, but it does it via a call to the logging module.
We don't want to introduce a dependency on logging, so printing to stderr
is a good alternative. One can override default_exception_handler() if
needed.
If a non-string buffer was passed to execfile, then it would be passed
as a non-null-terminated char* to mp_lexer_new_from_file.
This changes mp_lexer_new_from_file to take a qstr instead (as in almost
all cases a qstr will be created from this input anyway to set the
`__file__` attribute on the module).
This now makes execfile require a string (not generic buffer) argument,
which is probably a good fix to make anyway.
Fixes issue #12522.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Flushing console output in msvc builds always fails because that
output is not buffered so don't propagate that as an error (in a
simlar way as was done in 1c047742 for macOS).
Signed-off-by: stijn <stijn@ignitron.net>
This removes the duplicate code in cyw43, esp32, esp8266 that implements
the same logic as network.hostname.
Renames the `mod_network_hostname` (where we store the hostname value in
`.data`) to `mod_network_hostname_data` to make way for calling the shared
function `mod_network_hostname`.
And uses memcpy for mod_network_hostname_data, because the length of source
is already known and removes reliance on string data being null-terminated.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This changes from the previous limit of 15 characters. Although DHCP and
mDNS allow for up to 63, ESP32 and ESP8266 only allow 32, so this seems
like a reasonable limit to enforce across all ports (and avoids wasting the
additional memory).
Also clarifies that `MICROPY_PY_NETWORK_HOSTNAME_MAX_LEN` does not include
the null terminator (which was unclear before).
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
The following code:
server = await asyncio.start_server(...)
async with server:
... code that raises ...
would lose the original exception because the server's task would not have
had a chance to be scheduled yet, and so awaiting the task in wait_closed
would raise the cancellation instead of the original exception.
Additionally, ensures that explicitly cancelling the parent task delivers
the cancellation correctly (previously was masked by the server loop), now
this only happens if the server was closed, not when the task was
cancelled.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Prior to this commit, BTstack would only be notified of sent UART data when
the mp_bluetooth_hci_poll() function was called for some other reason, eg
because of incoming data over UART. This is highly suboptimal.
With this commit, BTstack is now notified immediately after UART data has
been sent out. This improves the multi_bluetooth/perf_gatt_char_write.py
performance test by about a factor of 10x for write-without-response, and
about 4x for write-with-response (tested on LEGO_HUB_NO6 as instance1).
Signed-off-by: Damien George <damien@micropython.org>
iobase_ioctl expects that an ioctl method must return an integer, and will
raise otherwise.
This was tripping up aioble on Unix, where the new hybrid modselect.c
implementation will attempt to extract a file descriptor from the pollable
via ioctl(MP_STREAM_GET_FILENO).
However, ThreadSafeFlag's ioctl only supported MP_STREAM_POLL, and returned
None otherwise.
This makes it return `-1` (to match tests/extmod/select_poll_custom.py). It
should probably be `-22` (corresponding to MP_EINVAL), but the value is
never checked, and MP_EINVAL can be a different value on different ports.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This is a host driver for ESP32 chips running the esp-hosted firmware,
which turns ESP32s into a WLAN/BT co-processor.
Signed-off-by: iabdalkader <i.abdalkader@gmail.com>
It appears a new session ticket being issued by the server right after
completed handshake is not uncommon and shouldn't be treated as fatal.
mbedtls itself states "This error code is experimental and may be changed
or removed without notice."
Signed-off-by: Mirko Vogt <mirko-dev|mpy@nanl.de>
Whenever the PSA interface is used (if MBEDTLS_PSA_CRYPTO is defined),
psa_crypto_init() needs to be called to initialise the global PSA data
struct, before any PSA related operations.
TLSv1.3 depends on the PSA interface, TLSv1.2 only uses the PSA stack if
MBEDTLS_USE_PSA_CRYPTO is defined.
Without psa_crypto_init() every PSA related call will result in
-0x6C00/-27648 which translates to "SSL - Internal error (eg, unexpected
failure in lower-level module)".
The error is misleading, especially since mbedtls in its docs itself
advices "to return #PSA_ERROR_BAD_STATE or some other applicable error.".
Signed-off-by: Mirko Vogt <mirko-dev|mpy@nanl.de>
Add the buffer attribute to sys.stdin, sys.stdout and sys.stderr. This
provides raw access to underlying stdio streams for the unix port (and
others that use VfsPosix).
Signed-off-by: stephanelsmith <stephane.smith@titansensor.com>
On macOS, if running micropython from subprocess.check_output, then a
stdout.flush() raises error 45.
Here's a test case. This will run fine on linux, but crashes on macOS with
error 45.
import sys
import subprocess
import tempfile
with tempfile.NamedTemporaryFile('w') as fp:
fp.write('''
import sys
sys.stdout.write('hello world')
sys.stdout.flush()
print('')
''')
fp.flush()
print('py3')
o = subprocess.check_output(f'python3 {fp.name}'.split())
print(o)
print('upy')
o = subprocess.check_output(f'micropython {fp.name}'.split())
print(o)
On macOS:
py3
b'hello world\n'
upy
Traceback (most recent call last):
File "...", line 4, in <module>
OSError: 45
On unix:
py3
b'hello world\n'
upy
b'hello world\n'
Signed-off-by: stephanelsmith <stephane.smith@titansensor.com>
The primary purpose of this commit is to make decompress default to
wbits=15 when the format is gzip (or auto format with gzip detected). The
idea is that someone decompressing a gzip stream should be able to use the
default `deflate.DeflateIO(f)` and it will "just work" for any input
stream, even though it uses a lot of memory.
This is done by making uzlib report gzip files as having wbits set to 15
in their header (where it previously only set the wbits out parameter for
zlib files), and then fixing up the logic in `deflateio_init_read`.
Updates the documentation to match.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Otherwise if/when the finaliser runs for this newly created SSLSocket the
mbedtls state will be freed again.
Signed-off-by: Damien George <damien@micropython.org>
This is difficult to implement on cmake-based ports, and having the list
of variants in mpconfigboard.{cmake,mk} duplicates information that's
already in board.json.
This removes the existing query-variants make target from stm32 & rp2
and the definition of BOARD_VARIANTS from the various board files.
Also renames the cmake variable to MICROPY_BOARD_VARIANT to match other
variables such as MICROPY_BOARD. The make variable stays as
BOARD_VARIANT.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
An SSL stream can only handle CLOSE and POLL ioctls. Other ones do not
make sense, or at least it doesn't make sense to pass the ioctl request
directly down to the underlying stream.
In particular MP_STREAM_GET_FILENO should not be passed to the underlying
stream because the SSL stream is not directly related to a file descriptor,
and the SSL stream must handle the polling itself.
Signed-off-by: Damien George <damien@micropython.org>
The signature of this method was poller.poll(timeout=-1, flags=0, /) but
the flags argument was not documented and is not CPython compatible. So
it's removed in this commit.
(The optional flags remains for the ipoll() method, which is documented.)
Signed-off-by: Damien George <damien@micropython.org>
A previous commit removed the unix-specific select module implementation
and made unix use the common one.
This commit adds an optimisation so that the system poll function is used
when polling objects that have a file descriptor. With this optimisation
enabled, if code registers both file-descriptor-based objects, and non-
file-descriptor-based objects with select.poll() then the following occurs:
- the system poll is called for all file-descriptor-based objects with a
timeout of 1ms
- then the bare-metal polling implementation is used for remaining objects,
which calls into their ioctl method (which can be in C or Python)
In the case where all objects have file descriptors, the system poll is
called with the full timeout requested by the caller. That makes it as
efficient as possible in the case everything has a file descriptor.
Benefits of this approach:
- all ports use the same select module implementation
- the unix port now supports polling of all objects and matches bare metal
implementations
- it's still efficient for existing cases where only files and sockets are
polled (on unix)
- the bare metal implementation does not change
- polling of SSL objects will now work on unix by calling in to the ioctl
method on SSL objects (this is required for asyncio ssl support)
Note that extmod/vfs_posix_file.c has poll disable when the optimisation is
enabled, because the code is not reachable when the optimisation is used.
Signed-off-by: Damien George <damien@micropython.org>
This provides similar functionality to the former zlib.DecompIO and
especially CPython's gzip.GzipFile for both compression and decompression.
This class can be used directly, and also can be used from Python to
implement (via io.BytesIO) zlib.decompress and zlib.compress, as well as
gzip.GzipFile.
Enable/disable this on all ports/boards that zlib was previously configured
for.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
There are enough places that implement __exit__ by forwarding directly to
mp_stream_close that this saves code size.
For the cases where __exit__ is a no-op, additionally make their
MP_STREAM_CLOSE ioctl handled as a no-op.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This will be replaced with a new deflate module providing the same
functionality, with an optional frozen Python wrapper providing a
replacement zlib module.
binascii.crc32 is temporarily disabled.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This commit adds the SSLContext class to the ssl module, and retains the
existing ssl.wrap_socket() function to maintain backwards compatibility.
CPython deprecated the ssl.wrap_socket() function since CPython 3.7 and
instead one should use ssl.SSLContext().wrap_socket(). This commit makes
that possible.
For the axtls implementation:
- ssl.SSLContext is added, although it doesn't hold much state because
axtls requires calling ssl_ctx_new() for each new socket
- ssl.SSLContext.wrap_socket() is added
- ssl.PROTOCOL_TLS_CLIENT and ssl.PROTOCOL_TLS_SERVER are added
For the mbedtls implementation:
- ssl.SSLContext is added, and holds most of the mbedtls state
- ssl.verify_mode is added (getter and setter)
- ssl.SSLContext.wrap_socket() is added
- ssl.PROTOCOL_TLS_CLIENT and ssl.PROTOCOL_TLS_SERVER are added
The signatures match CPython:
- SSLContext(protocol)
- SSLContext.wrap_socket(sock, *, server_side=False,
do_handshake_on_connect=True, server_hostname=None)
The existing ssl.wrap_socket() functions retain their existing signature.
Signed-off-by: Damien George <damien@micropython.org>
The mod_binascii_a2b_base64() function allocates a buffer which may be
too small. It needs to be no less than three-quarters of the input
length, but is calculated as (<length> / 4) * 3 + 1, which may be less
due to integer division. Changed to (<length> * 3) / 4 + 1.
Signed-off-by: Duncan Lowther <Duncan.Lowther@glasgow.ac.uk>
This allows existing code that does `import uasyncio` or
`import uasyncio as asyncio` to continue working.
It uses the same lazy-loading as asyncio to prevent loading of unused
features.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
The asyncio module now has much better CPython compatibility and
deserves to be just called "asyncio".
This will avoid people having to write `from uasyncio import asyncio`.
Renames all files, and updates port manifests to use the new path. Also
renames the built-in _uasyncio to _asyncio.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This is a MicroPython-specific module that existed to support the old
version of uasyncio. It's undocumented and not enabled on all ports and
takes up code size unnecessarily.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Applies to drivers/examples/extmod/port-modules/tools.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Updates any includes, and references from Makefiles/CMake.
This essentially reverts what was done long ago in commit
136b5cbd76
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This renames the builtin-modules, such that help('modules') and printing
the module object will show "module" rather than "umodule".
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
To be consistent with MP_UNARY_OP_INT_FLOAT and MP_UNARY_OP_INT_COMPLEX,
and allow int() to first check if a type supports __int__ before trying
other things (as per CPython).
Signed-off-by: Damien George <damien@micropython.org>
Avoiding code duplication. To enable it, set MICROPY_PY_UOS_SYNC in the
port's mpconfigport.h. It is operational only for FAT file system. For
other filesystems it's a no-op.
Signed-off-by: robert-hh <robert@hammelrath.com>
All ports that enable MICROPY_PY_MACHINE_PWM now enable these two
sub-options, so remove these sub-options altogether to force consistency in
new ports that implement machine.PWM.
Signed-off-by: Damien George <damien@micropython.org>
This fixes:
- type-comparison (E721): do not compare types, use isinstance().
- string-dot-format-missing-arguments (F524): .format call is missing
argument(s) for placeholder(s): {message}.
- f-string-missing-placeholders (F541).
- is-literal (F632): Use != to compare constant literals.
The last one is fixed by just comparing for truthfulness of `state`.
Based on extmod/utime_mphal.c, with:
- a globals dict added
- time.localtime wrapper added
- time.time wrapper added
- time.time_ns function added
New configuration options are added for this module:
- MICROPY_PY_UTIME (enabled at basic features level)
- MICROPY_PY_UTIME_GMTIME_LOCALTIME_MKTIME
- MICROPY_PY_UTIME_TIME_TIME_NS
Signed-off-by: Damien George <damien@micropython.org>
- Use HCI_TRACE macro consistently.
- Use the same colour formatting.
- Add a tool to convert to .pcap for Wireshark.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
The att_flags for descriptors does not use the same bitfield as for
characteristics. This was leading to NimBLE descriptors getting the wrong
flags set.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This allows gatts_write(..., send_update=True) to work, which will send
notifications/indications to subscribed clients.
btstack already created the CCCD but writes to it were ignored.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
There was no event handler for central-initiated MTU exchange.
Fix truncation of notify/indicate to match NimBLE.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This replaces the previous pending operation queue (that used to also be
shared with pending server notify/indicate ops) with a single pending
operation per connection. This allows the value handle to be correctly
passed to the Python-level events.
Also re-structure GATT client event handling to simplify the packet handler
functions.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This adds a mechanism to track a pending notify/indicate operation that
is deferred due to the send buffer being full. This uses a tracked alloc
that is passed as the content arg to the callback.
This replaces the previous mechanism that did this via the global pending
op queue, shared with client read/write ops.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Makes gatts_notify and gatts_indicate work in the same way: by default they
send the DB value, but you can manually override the payload.
In other words, makes gatts_indicate work the same as gatts_notify.
Note: This removes support for queuing notifications and indications on
btstack when the ACL buffer is full. This functionality will be
reimplemented in a future commit.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This enables the use of WLAN(0).status('rssi') to get current RSSI of the
AP that the STA is connected to.
Signed-off-by: Damien George <damien@micropython.org>
The NINA socket types have the same values as modnetwork, but that may
change in the future. So check the socket types passed to socket() and
convert them (if needed) to their respective Nina socket types.
Also remove the unnecessary socket type check code from bind(), as pointed
out by @robert-hh.
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>
This removes the previous WiFi driver from drivers/cyw43 (but leaves behind
the BT driver), and makes the stm32 port (i.e. PYBD and Portenta) use the
new "lib/cyw43-driver" open-source driver already in use by the rp2 port.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This allows for a port (e.g. esp8266/esp32) to use extmod/modnetwork.c
and provide the globals dict, rather than just a list of interfaces.
When this is used, the default implementation of `network.route` and the
NIC list is not enabled.
Also splits out the LWIP-specific helpers from modnetwork.c into
network_lwip.c.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This provides a standard interface to setting the global networking config
for all interfaces and interface types.
For ports that already use either a static hostname (mimxrt, rp2) they will
now use the configured value. The default is configured by the port
(or optionally the board).
For interfaces that previously supported .config(hostname), this is still
supported but now implemented using the global network.hostname.
Similarly, pyb.country and rp2.country are now deprecated, but the methods
still exist (and forward to network.hostname).
Because ESP32/ESP8266 do not use extmod/modnetwork.c they are not affected
by this commit.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Since commit d6d8722558, modbtree.c is
included unconditionally in the build (if SRC_EXTMOD_C is used). So guard
the includes of system headers files in case a target doesn't have them.
Signed-off-by: Damien George <damien@micropython.org>
MicroPython overrides the axTLS port configuration file, but fails to
include <arpa/inet.h> (needed for htonl) and <sys/time.h> (needed for
gettimeofday). This results in build failures with compilers which do not
support implicit function declarations (which were removed from C in 1999).
This commit adds back the needed headers that were removed in this commit:
bd08017309
Signed-off-by: Damien George <damien@micropython.org>
Prior to this commit, the default security=-1 would be passed directly
through to the cyw43 driver to auto-detect the security type, but that
driver did not correctly handle the case of open security.
The cyw43 driver has now been changed to no longer support auto-detection,
rather it is up to the caller to always select the security type. The
defaults are now implemented in the Python bindings and are:
- if no key is given then it selects open security
- if a key is given then it selects WPA2_MIXED_PSK
Calling `wlan.connect(<ssid>)` will now connect to an open network, on
both rp2 and stm32 ports. The form `wlan.connect(<ssid>, <key>)` will
connect to a WPA2 network.
Fixes issue #9016.
Signed-off-by: Damien George <damien@micropython.org>
During the initial handshake or subsequent renegotiation, the protocol
might need to read in order to write (or conversely to write in order
to read). It might be blocked from doing so by the state of the
underlying socket (i.e. there is no data to read, or there is no space
to write).
The library indicates this condition by returning one of the errors
`MBEDTLS_ERR_SSL_WANT_READ` or `MBEDTLS_ERR_SSL_WANT_WRITE`. When that
happens, we need to enforce that the next poll operation only considers
the direction that the library indicated.
In addition, mbedtls does its own read buffering that we need to take
into account while polling, and we need to save the last error between
read()/write() and ioctl().
This was previously implemented by adding additional members to the
mp_obj_type_t defined for each NIC, which is difficult to do cleanly with
the new object type slots mechanism. The way this works is also not
supported on GCC 8.x and below.
Instead replace it with the type protocol, which is a much simpler way of
achieving the same thing.
This affects the WizNet (in non-LWIP mode) and Nina NIC drivers.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
The compiler is not picky right now, but these are actually all syntax
errors:
- await is only valid in an async function
- async functions that use yield are actually async generators (a construct
not supported by the compiler right now)
`_WIN64` is defined for all 64-bit targets, including Arm, so it doesn't
work for detecting `x86_64`. We can use `_M_X64` instead.
Signed-off-by: David Lechner <david@pybricks.com>
Since _M_IX86 is already being checked in the x86 case, it will never
be true in the xtensa case and can be removed.
Signed-off-by: David Lechner <david@pybricks.com>
Instead of defining `MICROPY_PY_BTREE` in `mpconfigport.h` we can define
it via CMake similar to how other ports that use Makefiles define it in
`mpconfigport.mk`.
Signed-off-by: David Lechner <david@pybricks.com>
Before this patch, WiFi connection was blocking, and could raise exceptions
if the connection failed for any reason (including timeouts). This doesn't
match the behavior of other WiFi modules, which connect asynchronously, and
requires handling of exceptions on connect. This change makes `connect()`
work asynchronously by scheduling code to poll connection status, and
handle reconnects (if needed), and return immediately without blocking.
If a board defines MICROPY_BLUETOOTH_BTSTACK_CONFIG_FILE as the path to a
header file, then that file will be used for the BTstack config.
Signed-off-by: Damien George <damien@micropython.org>
The actual underlying error number raised from the lwIP subsystem when
attempting to listen on a socket is swallowed and replaced with an
out-of-memory error which is confusing.
This commit passes the underlying error message from the lwIP subsystem to
the appropriate OSError exception.
They are much slower than NIST (SECP) curves and shouldn't be needed.
Reduces rp2 PICO_W firmware by 1328 bytes.
Thanks to @Carglglz for the information.
Signed-off-by: Damien George <damien@micropython.org>
Curve25519 arithmetic is supported in mbedtls, but it's not used for TLS.
So there's no need to have this option enabled.
Reduces rp2 PICO_W firmware by 2440 bytes.
Thanks to @Carglglz for the information.
Signed-off-by: Damien George <damien@micropython.org>
This is necessary to access sites that only support these protocols.
The rp2 port already has ECDH enabled, so this just adds ECDSA there. The
other ports now gain both ECDH and ECDSA. The code size increase is:
- rp2 (PICO_W): +2916 bytes flash, +24 bytes BSS
- stm32 (PYBD_SF6): +20480 bytes flash, +32 bytes data, +48 bytes BSS
- mimxrt (TEENSY41): +20708 bytes flash, +32 bytes data, +48 bytes BSS
- unix (standard x86-64): +39344 executable, +1744 bytes data, +96 BSS
This is obviously a large increase in code size. But there doesn't seem to
be any other option because without elliptic curve cryptography devices are
partially cut off from the internet. For use cases that require small
firmware size, they'll need to build custom firmware with a custom mbedtls
config.
Signed-off-by: Damien George <damien@micropython.org>
The following multi-tests pass (eg with PYBD_SF6+LEGO_HUB_NO6):
ble_gap_advertise.py
ble_gap_connect.py
ble_gap_device_name.py
ble_gattc_discover_services.py
ble_gatt_data_transfer.py
perf_gatt_char_write.py
perf_gatt_notify.py
stress_log_filesystem.py
These are the same tests that passed prior to this BTstack update.
Also tested on the unix port using H4 transport.
Signed-off-by: Damien George <damien@micropython.org>
This makes it so that all a port needs to do is set the relevant variables
and "include extmod.mk" and doesn't need to worry about adding anything to
OBJ, CFLAGS, SRC_QSTR, etc.
Make all extmod variables (src, flags, etc) private to extmod.mk.
Also move common/shared, extmod-related fragments (e.g. wiznet, cyw43,
bluetooth) into extmod.mk.
Now that SRC_MOD, CFLAGS_MOD, CXXFLAGS_MOD are unused by both extmod.mk
(and user-C-modules in a previous commit), remove all uses of them from
port makefiles.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This applies to nimble, btstack, axtls, mbedtls, lwip.
Rather than having the ports individually manage GIT_SUBMODULES for these
components, make extmod.mk append them when the relevant feature is
enabled.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
The call to invoke_irq_handler_run() always needs to run in a protected NLR
context, to catch exceptions from the Python handler, and the m_new's (and
also mp_local_alloc when PYSTACK is enabled). With
MICROPY_PY_BLUETOOTH_USE_SYNC_EVENTS_WITH_INTERLOCK enabled there was
already an explicit nlr_push, and that is now used in all cases.
Without this change, on stm32 (for example), the callbacks from the BLE
stack to invoke_irq_handler() were made via static scheduled nodes which do
not have any NLR protection, and hence would lead to a hard fault (uncaught
NLR) if an exception was raised in the Python BLE IRQ handler. This was a
regression introduced by 8045ac07f5, which is
fixed by this commit.
Signed-off-by: Damien George <damien@micropython.org>
The calls to m_new and m_del require an exclusive uPy (really a GC)
context. In particular these functions cannot be called directly from a
FreeRTOS task on esp32.
Fixes issue #9369.
Signed-off-by: Damien George <damien@micropython.org>
Prevent handle leaks when file objects aren't closed explicitly and
fix some MICROPY_CPYTHON_COMPAT issues: this wasn't properly adhered
to because #ifdef was used so it was always on, and closing files
multiple times should be avoided unconditionally.
Instead of being an explicit field, it's now a slot like all the other
methods.
This is a marginal code size improvement because most types have a make_new
(100/138 on PYBV11), however it improves consistency in how types are
declared, removing the special case for make_new.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
The goal here is to remove a slot (making way to turn make_new into a slot)
as well as reduce code size by the ~40 references to mp_identity_getiter
and mp_stream_unbuffered_iter.
This introduces two new type flags:
- MP_TYPE_FLAG_ITER_IS_ITERNEXT: This means that the "iter" slot in the
type is "iternext", and should use the identity getiter.
- MP_TYPE_FLAG_ITER_IS_CUSTOM: This means that the "iter" slot is a pointer
to a mp_getiter_iternext_custom_t instance, which then defines both
getiter and iternext.
And a third flag that is the OR of both, MP_TYPE_FLAG_ITER_IS_STREAM: This
means that the type should use the identity getiter, and
mp_stream_unbuffered_iter as iternext.
Finally, MP_TYPE_FLAG_ITER_IS_GETITER is defined as a no-op flag to give
the default case where "iter" is "getiter".
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This will always have the maximum/minimum size of a mp_obj_type_t
representation and can be used as a member in other structs.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
The buffer protocol type only has a single member, and this existing layout
creates problems for the upcoming split/slot-index mp_obj_type_t layout
optimisations.
If we need to make the buffer protocol more sophisticated in the future
either we can rely on the mp_obj_type_t optimisations to just add
additional slots to mp_obj_type_t or re-visit the buffer protocol then.
This change is a no-op in terms of generated code.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
When iterating over filesystem/folders with os.iterdir(), an open file
(directory) handle is used internally. Currently this file handle is only
closed once the iterator is completely drained, eg. once all entries have
been looped over / converted into list etc.
If a program opens an iterdir but does not loop over it, or starts to loop
over the iterator but breaks out of the loop, then the handle never gets
closed. In this state, when the iter object is cleaned up by the garbage
collector this open handle can cause corruption of the filesystem.
Fixes issues #6568 and #8506.
This is technically a breaking change, but:
a) We need the end handle to do descriptor discovery properly.
b) We have no possible use for the existing definition handle in the
characteristic result IRQ. None of the methods can use it, and therefore
no existing code should be using it in a way that changing it to a
different integer value should break.
Unfortunately NimBLE doesn't make it easy to get the end handle, so also
implement a mechanism to use the following characteristic to calculate
the previous characteristic's end handle.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
