Various fixes to how timer differences are calculated (qmk#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)
BorisTestov · Apr 11, 2020 · 04a6b14 · 04a6b14
1 parent 68b08e7
commit 04a6b14
Show file tree

Hide file tree

Showing 3 changed files with 26 additions and 3 deletions.
diff --git a/quantum/debounce/eager_pk.c b/quantum/debounce/eager_pk.c
@@ -44,6 +44,16 @@ 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);
 
@@ -59,7 +69,7 @@ void debounce_init(uint8_t num_rows) {
 }
 
 void debounce(matrix_row_t raw[], matrix_row_t cooked[], uint8_t num_rows, bool changed) {
-    uint8_t current_time = timer_read() % MAX_DEBOUNCE;
+    uint8_t current_time = wrapping_timer_read();
     if (counters_need_update) {
         update_debounce_counters(num_rows, current_time);
     }

diff --git a/quantum/debounce/eager_pr.c b/quantum/debounce/eager_pr.c
@@ -36,6 +36,16 @@ static bool                counters_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);
 
@@ -48,7 +58,7 @@ void debounce_init(uint8_t num_rows) {
 }
 
 void debounce(matrix_row_t raw[], matrix_row_t cooked[], uint8_t num_rows, bool changed) {
-    uint8_t current_time  = timer_read() % MAX_DEBOUNCE;
+    uint8_t current_time  = wrapping_timer_read();
     bool    needed_update = counters_need_update;
     if (counters_need_update) {
         update_debounce_counters(num_rows, current_time);

diff --git a/tmk_core/common/timer.h b/tmk_core/common/timer.h
@@ -25,7 +25,10 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 #    include "avr/timer_avr.h"
 #endif
 
-#define TIMER_DIFF(a, b, max) ((a) >= (b) ? (a) - (b) : (max) - (b) + (a))
+#define TIMER_DIFF(a, b, max) ((max == UINT8_MAX) ? ((uint8_t)((a)-(b))) : ( \
+                               (max == UINT16_MAX) ? ((uint16_t)((a)-(b))) : ( \
+                               (max == UINT32_MAX) ? ((uint32_t)((a)-(b))) : ( \
+                               (a) >= (b) ? (a) - (b) : (max) + 1 - (b) + (a) ))))
 #define TIMER_DIFF_8(a, b) TIMER_DIFF(a, b, UINT8_MAX)
 #define TIMER_DIFF_16(a, b) TIMER_DIFF(a, b, UINT16_MAX)
 #define TIMER_DIFF_32(a, b) TIMER_DIFF(a, b, UINT32_MAX)