qmk_firmware/quantum/debounce/eager_pk.c
Purdea Andrei 6c2c3c13e9
Various fixes to how timer differences are calculated (#8585)
* tmk_core/common: Fixing TIMER_DIFF macro to calculate difference correctly after the timer wraps.

Let's go through an example, using the following macro:

If the first timer read is 0xe4 and the second one is 0x32, the timer wrapped.
If the timer would have had more bits, it's new value would have been 0x132,
and the correct difference in time is 0x132 - 0xe4 = 0x4e

old code TIMER_DIFF_8(0x32, 0xe4) = 0xff - 0xe4 + 0x32 = 0x4d, which is wrong.
new code TIMER_DIFF_8(0x32, 0xe4) = 0xff + 1 - 0xe4 + 0x32 = 0x4e, which is correct.

This also gives a chance for a smart compiler to optimize the code using normal
integer overflow.

For example on AVR, the following C code:
uint8_t __attribute__ ((noinline)) test(uint8_t current_timer, uint8_t start_timer)
{
    return TIMER_DIFF_8(current_timer, start_timer);
}
With the original code, it gets translated to the following list of instructions:
00004c6e <test>:
    4c6e:       98 2f           mov     r25, r24
    4c70:       86 1b           sub     r24, r22
    4c72:       96 17           cp      r25, r22
    4c74:       08 f4           brcc    .+2             ; 0x4c78 <test+0xa>
    4c76:       81 50           subi    r24, 0x01       ; 1
    4c78:       08 95           ret
But with this commit, it gets translated to a single instruction:
00004c40 <test>:
    4c40:       86 1b           sub     r24, r22
    4c42:       08 95           ret

This unfortunately doesn't always work so nicely, for example the following C code:
int __attribute__ ((noinline)) test(uint8_t current_timer, uint8_t start_timer)
{
    return TIMER_DIFF_8(current_timer, start_timer);
}
(Note: return type changed to int)
With the original code it gets translated to:
00004c6e <test>:
    4c6e:       28 2f           mov     r18, r24
    4c70:       30 e0           ldi     r19, 0x00       ; 0
    4c72:       46 2f           mov     r20, r22
    4c74:       50 e0           ldi     r21, 0x00       ; 0
    4c76:       86 17           cp      r24, r22
    4c78:       20 f0           brcs    .+8             ; 0x4c82 <test+0x14>
    4c7a:       c9 01           movw    r24, r18
    4c7c:       84 1b           sub     r24, r20
    4c7e:       95 0b           sbc     r25, r21
    4c80:       08 95           ret
    4c82:       c9 01           movw    r24, r18
    4c84:       84 1b           sub     r24, r20
    4c86:       95 0b           sbc     r25, r21
    4c88:       81 50           subi    r24, 0x01       ; 1
    4c8a:       9f 4f           sbci    r25, 0xFF       ; 255
    4c8c:       08 95           ret
Wth this commit it gets translated to:
00004c40 <test>:
    4c40:       28 2f           mov     r18, r24
    4c42:       30 e0           ldi     r19, 0x00       ; 0
    4c44:       46 2f           mov     r20, r22
    4c46:       50 e0           ldi     r21, 0x00       ; 0
    4c48:       86 17           cp      r24, r22
    4c4a:       20 f0           brcs    .+8             ; 0x4c54 <test+0x14>
    4c4c:       c9 01           movw    r24, r18
    4c4e:       84 1b           sub     r24, r20
    4c50:       95 0b           sbc     r25, r21
    4c52:       08 95           ret
    4c54:       c9 01           movw    r24, r18
    4c56:       84 1b           sub     r24, r20
    4c58:       95 0b           sbc     r25, r21
    4c5a:       93 95           inc     r25
    4c5c:       08 95           ret
There is not much performance improvement in this case, however at least with this
commit it functions correctly.

Note: The following commit will improve compiler output for the latter example.

* tmk_core/common: Improve code generation for TIMER_DIFF* macros

Because of integer promotion the compiler is having a hard time generating
efficient code to calculate TIMER_DIFF* macros in some situations.
In the below example, the return value is "int", and this is causing the
trouble.

Example C code:

int __attribute__ ((noinline)) test(uint8_t current_timer, uint8_t start_timer)
{
    return TIMER_DIFF_8(current_timer, start_timer);
}

BEFORE: (with -Os)

00004c40 <test>:
    4c40:       28 2f           mov     r18, r24
    4c42:       30 e0           ldi     r19, 0x00       ; 0
    4c44:       46 2f           mov     r20, r22
    4c46:       50 e0           ldi     r21, 0x00       ; 0
    4c48:       86 17           cp      r24, r22
    4c4a:       20 f0           brcs    .+8             ; 0x4c54 <test+0x14>
    4c4c:       c9 01           movw    r24, r18
    4c4e:       84 1b           sub     r24, r20
    4c50:       95 0b           sbc     r25, r21
    4c52:       08 95           ret
    4c54:       c9 01           movw    r24, r18
    4c56:       84 1b           sub     r24, r20
    4c58:       95 0b           sbc     r25, r21
    4c5a:       93 95           inc     r25
    4c5c:       08 95           ret

AFTER: (with -Os)

00004c40 <test>:
    4c40:       86 1b           sub     r24, r22
    4c42:       90 e0           ldi     r25, 0x00       ; 0
    4c44:       08 95           ret

Note: the example is showing -Os but improvements can be seen at all optimization levels,
including -O0. We never use -O0, but I tested it to make sure that no extra code is
generated in that case.OA

* quantum/debounce: Fix custom wrapping timers in eager_pr and eager_pk debounce algorithms

Please see the below simulated sequence of events:
Column A is the 16-bit value returned by read_timer();
Column B is the value returned by custom_wrap_timer_read();
Column C is the original code: (timer_read() % MAX_DEBOUNCE)

    A,     B,     C
65530,    19,    30
65531,    20,    31
65532,    21,    32
65533,    22,    33
65534,    23,    34
65535,    24,    35
    0     25,     0
    1,    26,     1
    2,    27,     2
    3,    28,     3
    4,    29,     4
    5,    30,     5

read_timer() wraps about every 1.09 seconds, and so debouncing might
fail at these times without this commit.

* quantum/debounce/eager_pr and eager_pk: modifications for code readability according to code review.

* quantum/debounce/eager_pr and eager_pk: modifications for code readability according to code review. (2)
2020-04-11 10:14:28 +10:00

125 lines
4.4 KiB
C

/*
Copyright 2017 Alex Ong<the.onga@gmail.com>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
/*
Basic per-key algorithm. Uses an 8-bit counter per key.
After pressing a key, it immediately changes state, and sets a counter.
No further inputs are accepted until DEBOUNCE milliseconds have occurred.
*/
#include "matrix.h"
#include "timer.h"
#include "quantum.h"
#include <stdlib.h>
#ifndef DEBOUNCE
# define DEBOUNCE 5
#endif
#if (MATRIX_COLS <= 8)
# define ROW_SHIFTER ((uint8_t)1)
#elif (MATRIX_COLS <= 16)
# define ROW_SHIFTER ((uint16_t)1)
#elif (MATRIX_COLS <= 32)
# define ROW_SHIFTER ((uint32_t)1)
#endif
#define debounce_counter_t uint8_t
static debounce_counter_t *debounce_counters;
static bool counters_need_update;
static bool matrix_need_update;
#define DEBOUNCE_ELAPSED 251
#define MAX_DEBOUNCE (DEBOUNCE_ELAPSED - 1)
static uint8_t wrapping_timer_read(void) {
static uint16_t time = 0;
static uint8_t last_result = 0;
uint16_t new_time = timer_read();
uint16_t diff = new_time - time;
time = new_time;
last_result = (last_result + diff) % (MAX_DEBOUNCE + 1);
return last_result;
}
void update_debounce_counters(uint8_t num_rows, uint8_t current_time);
void transfer_matrix_values(matrix_row_t raw[], matrix_row_t cooked[], uint8_t num_rows, uint8_t current_time);
// we use num_rows rather than MATRIX_ROWS to support split keyboards
void debounce_init(uint8_t num_rows) {
debounce_counters = (debounce_counter_t *)malloc(num_rows * MATRIX_COLS * sizeof(debounce_counter_t));
int i = 0;
for (uint8_t r = 0; r < num_rows; r++) {
for (uint8_t c = 0; c < MATRIX_COLS; c++) {
debounce_counters[i++] = DEBOUNCE_ELAPSED;
}
}
}
void debounce(matrix_row_t raw[], matrix_row_t cooked[], uint8_t num_rows, bool changed) {
uint8_t current_time = wrapping_timer_read();
if (counters_need_update) {
update_debounce_counters(num_rows, current_time);
}
if (changed || matrix_need_update) {
transfer_matrix_values(raw, cooked, num_rows, current_time);
}
}
// If the current time is > debounce counter, set the counter to enable input.
void update_debounce_counters(uint8_t num_rows, uint8_t current_time) {
counters_need_update = false;
debounce_counter_t *debounce_pointer = debounce_counters;
for (uint8_t row = 0; row < num_rows; row++) {
for (uint8_t col = 0; col < MATRIX_COLS; col++) {
if (*debounce_pointer != DEBOUNCE_ELAPSED) {
if (TIMER_DIFF(current_time, *debounce_pointer, MAX_DEBOUNCE) >= DEBOUNCE) {
*debounce_pointer = DEBOUNCE_ELAPSED;
} else {
counters_need_update = true;
}
}
debounce_pointer++;
}
}
}
// upload from raw_matrix to final matrix;
void transfer_matrix_values(matrix_row_t raw[], matrix_row_t cooked[], uint8_t num_rows, uint8_t current_time) {
matrix_need_update = false;
debounce_counter_t *debounce_pointer = debounce_counters;
for (uint8_t row = 0; row < num_rows; row++) {
matrix_row_t delta = raw[row] ^ cooked[row];
matrix_row_t existing_row = cooked[row];
for (uint8_t col = 0; col < MATRIX_COLS; col++) {
matrix_row_t col_mask = (ROW_SHIFTER << col);
if (delta & col_mask) {
if (*debounce_pointer == DEBOUNCE_ELAPSED) {
*debounce_pointer = current_time;
counters_need_update = true;
existing_row ^= col_mask; // flip the bit.
} else {
matrix_need_update = true;
}
}
debounce_pointer++;
}
cooked[row] = existing_row;
}
}
bool debounce_active(void) { return true; }