py/emitglue: Always flush caches when assigning native ARM code.

Prior to this commit, cache flushing for ARM native code was done only in
the assembler code asm_thumb_end_pass()/asm_arm_end_pass(), at the last
pass of the assembler.  But this misses flushing the cache when loading
native code from an .mpy file, ie in persistentcode.c.

The change here makes sure the cache is always flushed/cleaned/invalidated
when assigning native code on ARM architectures.

This problem was found running tests/micropython/import_mpy_native_gc.py on
the mimxrt port.

Signed-off-by: Damien George <damien@micropython.org>

py/asmthumb.c

@@ -35,7 +35,6 @@
 
 #include "py/mpstate.h"
 #include "py/persistentcode.h"
-#include "py/mphal.h"
 #include "py/asmthumb.h"
 
 #define UNSIGNED_FIT5(x) ((uint32_t)(x) < 32)
@@ -62,20 +61,6 @@ static inline byte *asm_thumb_get_cur_to_write_bytes(asm_thumb_t *as, int n) {
     return mp_asm_base_get_cur_to_write_bytes(&as->base, n);
 }
 
-void asm_thumb_end_pass(asm_thumb_t *as) {
-    (void)as;
-    // could check labels are resolved...
-
-    #if __ICACHE_PRESENT == 1
-    if (as->base.pass == MP_ASM_PASS_EMIT) {
-        // flush D-cache, so the code emitted is stored in memory
-        MP_HAL_CLEAN_DCACHE(as->base.code_base, as->base.code_size);
-        // invalidate I-cache
-        SCB_InvalidateICache();
-    }
-    #endif
-}
-
 /*
 STATIC void asm_thumb_write_byte_1(asm_thumb_t *as, byte b1) {
     byte *c = asm_thumb_get_cur_to_write_bytes(as, 1);