apfl/src/bytecode.c

112 lines
2.7 KiB
C
Raw Normal View History

Implement mark&sweep garbage collection and bytecode compilation Instead of the previous refcount base garbage collection, we're now using a basic tri-color mark&sweep collector. This is done to support cyclical value relationships in the future (functions can form cycles, all values implemented up to this point can not). The collector maintains a set of roots and a set of objects (grouped into blocks). The GC enabled objects are no longer allocated manually, but will be allocated by the GC. The GC also wraps an allocator, this way the GC knows, if we ran out of memory and will try to get out of this situation by performing a full collection cycle. The tri-color abstraction was chosen for two reasons: - We don't have to maintain a list of objects that need to be marked, we can simply grab the next grey one. - It should allow us to later implement incremental collection (right now we only do a stop-the-world collection). This also switches to a bytecode based evaluation of the code: We no longer directly evaluate the AST, but first compile it into a series of instructions, that are evaluated in a separate step. This was done in preparation for inplementing functions: We only need to turn a function body into instructions instead of evaluating the node again with each call of the function. Also, since an instruction list is implemented as a GC object, this then removes manual memory management of the function body and it's child nodes. Since the GC and the bytecode go hand in hand, this was done in one (giant) commit. As a downside, we've now lost the ability do do list matching on assignments. I've already started to work on implementing this in the new architecture, but left it out of this commit, as it's already quite a large commit :)
2022-04-11 20:24:22 +00:00
#include <assert.h>
#include "apfl.h"
#include "alloc.h"
#include "bytecode.h"
#include "gc.h"
struct instruction_list *
apfl_instructions_new(struct gc *gc, int line)
{
struct instruction_list *ilist = apfl_gc_new_instructions(gc);
if (ilist == NULL) {
return NULL;
}
*ilist = (struct instruction_list) {
.instructions = NULL,
.len = 0,
.cap = 0,
.line = line,
};
return ilist;
}
void
apfl_instructions_deinit(struct apfl_allocator allocator, struct instruction_list *ilist)
{
FREE_LIST(allocator, ilist->instructions, ilist->cap);
}
#define GET_ARGUMENT(ilist, i, arg) \
do { \
if (i >= ilist->len) { \
return; \
} \
arg = ilist->instructions[++i]; \
} while (0)
void
apfl_gc_instructions_traverse(struct instruction_list *ilist, gc_visitor cb, void *opaque)
{
union instruction_or_arg arg;
for (size_t i = 0; i < ilist->len; i++) {
switch (ilist->instructions[i].instruction) {
case INSN_NIL:
case INSN_TRUE:
case INSN_FALSE:
case INSN_LIST_APPEND:
case INSN_LIST_EXPAND_INTO:
case INSN_DICT:
case INSN_DICT_APPEND_KVPAIR:
case INSN_GET_MEMBER:
case INSN_NEXT_LINE:
break;
case INSN_NUMBER:
case INSN_LIST:
case INSN_SET_LINE:
i++;
break;
case INSN_STRING:
case INSN_VAR_GET:
case INSN_VAR_SET:
case INSN_VAR_NEW:
GET_ARGUMENT(ilist, i, arg);
cb(opaque, GC_OBJECT_FROM(arg.string, GC_TYPE_STRING));
break;
Implement mark&sweep garbage collection and bytecode compilation Instead of the previous refcount base garbage collection, we're now using a basic tri-color mark&sweep collector. This is done to support cyclical value relationships in the future (functions can form cycles, all values implemented up to this point can not). The collector maintains a set of roots and a set of objects (grouped into blocks). The GC enabled objects are no longer allocated manually, but will be allocated by the GC. The GC also wraps an allocator, this way the GC knows, if we ran out of memory and will try to get out of this situation by performing a full collection cycle. The tri-color abstraction was chosen for two reasons: - We don't have to maintain a list of objects that need to be marked, we can simply grab the next grey one. - It should allow us to later implement incremental collection (right now we only do a stop-the-world collection). This also switches to a bytecode based evaluation of the code: We no longer directly evaluate the AST, but first compile it into a series of instructions, that are evaluated in a separate step. This was done in preparation for inplementing functions: We only need to turn a function body into instructions instead of evaluating the node again with each call of the function. Also, since an instruction list is implemented as a GC object, this then removes manual memory management of the function body and it's child nodes. Since the GC and the bytecode go hand in hand, this was done in one (giant) commit. As a downside, we've now lost the ability do do list matching on assignments. I've already started to work on implementing this in the new architecture, but left it out of this commit, as it's already quite a large commit :)
2022-04-11 20:24:22 +00:00
}
}
}
const char *
apfl_instruction_to_string(enum instruction insn)
{
switch (insn) {
case INSN_NIL:
return "INSN_NIL";
case INSN_TRUE:
return "INSN_TRUE";
case INSN_FALSE:
return "INSN_FALSE";
case INSN_NUMBER:
return "INSN_NUMBER";
case INSN_STRING:
return "INSN_STRING";
case INSN_LIST:
return "INSN_LIST";
case INSN_LIST_APPEND:
return "INSN_LIST_APPEND";
case INSN_LIST_EXPAND_INTO:
return "INSN_LIST_EXPAND_INTO";
case INSN_DICT:
return "INSN_DICT";
case INSN_DICT_APPEND_KVPAIR:
return "INSN_DICT_APPEND_KVPAIR";
case INSN_GET_MEMBER:
return "INSN_GET_MEMBER";
case INSN_VAR_GET:
return "INSN_VAR_GET";
case INSN_VAR_SET:
return "INSN_VAR_SET";
case INSN_VAR_NEW:
return "INSN_VAR_NEW";
case INSN_NEXT_LINE:
return "INSN_NEXT_LINE";
case INSN_SET_LINE:
return "INSN_SET_LINE";
}
return "??";
}