micropython/ports/minimal/uart_core.c

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

50 lines
1.1 KiB
C
Raw Permalink Normal View History

#include <unistd.h>
#include "py/mpconfig.h"
/*
* Core UART functions to implement for a port
*/
#if MICROPY_MIN_USE_STM32_MCU
typedef struct {
volatile uint32_t SR;
volatile uint32_t DR;
} periph_uart_t;
#define USART1 ((periph_uart_t *)0x40011000)
#endif
// Receive single character
int mp_hal_stdin_rx_chr(void) {
unsigned char c = 0;
#if MICROPY_MIN_USE_STDOUT
int r = read(STDIN_FILENO, &c, 1);
(void)r;
#elif MICROPY_MIN_USE_STM32_MCU
// wait for RXNE
while ((USART1->SR & (1 << 5)) == 0) {
}
c = USART1->DR;
#endif
return c;
}
// Send string of given length
ports: Fix sys.stdout.buffer.write() return value. 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>
2023-06-18 10:46:25 +01:00
mp_uint_t mp_hal_stdout_tx_strn(const char *str, mp_uint_t len) {
mp_uint_t ret = len;
#if MICROPY_MIN_USE_STDOUT
int r = write(STDOUT_FILENO, str, len);
ports: Fix sys.stdout.buffer.write() return value. 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>
2023-06-18 10:46:25 +01:00
if (r >= 0) {
// in case of an error in the syscall, report no bytes written
ret = 0;
}
#elif MICROPY_MIN_USE_STM32_MCU
while (len--) {
// wait for TXE
while ((USART1->SR & (1 << 7)) == 0) {
}
USART1->DR = *str++;
}
#endif
ports: Fix sys.stdout.buffer.write() return value. 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>
2023-06-18 10:46:25 +01:00
return ret;
}