Add GPU IRQ variants of all display list APIs

5 files changed, 218 insertions, 114 deletions

diff --git a/libpsn00b/include/psxgpu.h b/libpsn00b/include/psxgpu.h
index 2e9e4eb..d7f1ad5 100644
--- a/libpsn00b/include/psxgpu.h
+++ b/libpsn00b/include/psxgpu.h
@@ -606,10 +606,15 @@ void MoveImage2(const RECT *rect, int x, int y);
 void ClearOTagR(uint32_t *ot, size_t length);
 void ClearOTag(uint32_t *ot, size_t length);
 int DrawOTag(const uint32_t *ot);
+int DrawOTagIRQ(const uint32_t *ot);
 int DrawOTagEnv(const uint32_t *ot, DRAWENV *env);
+int DrawOTagEnvIRQ(const uint32_t *ot, DRAWENV *env);
 void DrawOTag2(const uint32_t *ot);
+void DrawOTagIRQ2(const uint32_t *ot);
 int DrawBuffer(const uint32_t *buf, size_t length);
+int DrawBufferIRQ(const uint32_t *buf, size_t length);
 void DrawBuffer2(const uint32_t *buf, size_t length);
+void DrawBufferIRQ2(const uint32_t *buf, size_t length);
 void DrawPrim(const uint32_t *pri);
 
 void AddPrim(uint32_t *ot, const void *pri);
diff --git a/libpsn00b/psxgpu/common.c b/libpsn00b/psxgpu/common.c
index 8af6c5b..7e0758b 100644
--- a/libpsn00b/psxgpu/common.c
+++ b/libpsn00b/psxgpu/common.c
@@ -270,87 +270,6 @@ void *DrawSyncCallback(void (*func)(void)) {
 	return old_callback;
 }
 
-/* OT and primitive drawing API */
-
-void ClearOTagR(uint32_t *ot, size_t length) {
-	_sdk_validate_args_void(ot && length);
-
-	DMA_MADR(DMA_OTC) = (uint32_t) &ot[length - 1];
-	DMA_BCR(DMA_OTC)  = length & 0xffff;
-	DMA_CHCR(DMA_OTC) = 0x11000002;
-
-	while (DMA_CHCR(DMA_OTC) & (1 << 24))
-		__asm__ volatile("");
-}
-
-void ClearOTag(uint32_t *ot, size_t length) {
-	_sdk_validate_args_void(ot && length);
-
-	// DMA6 only supports writing to RAM in reverse order (last to first), so
-	// the OT has to be cleared in software here. This function is thus much
-	// slower than ClearOTagR().
-	// https://problemkaputt.de/psx-spx.htm#dmachannels
-	for (int i = 0; i < (length - 1); i++)
-		ot[i] = (uint32_t) &ot[i + 1] & 0x7fffff;
-		//setaddr(&ot[i], &ot[i + 1]);
-
-	ot[length - 1] = 0xffffff;
-	//termPrim(&ot[length - 1]);
-}
-
-void AddPrim(uint32_t *ot, const void *pri) {
-	_sdk_validate_args_void(ot && pri);
-
-	addPrim(ot, pri);
-}
-
-int DrawOTag(const uint32_t *ot) {
-	_sdk_validate_args(ot, -1);
-
-	return EnqueueDrawOp((void *) &DrawOTag2, (uint32_t) ot, 0, 0);
-}
-
-void DrawOTag2(const uint32_t *ot) {
-	_sdk_validate_args_void(ot);
-
-	SetDrawOpType(DRAWOP_TYPE_DMA);
-	GPU_GP1 = 0x04000002; // Enable DMA request, route to GP0
-
-	while (DMA_CHCR(DMA_GPU) & (1 << 24))
-		__asm__ volatile("");
-
-	DMA_MADR(DMA_GPU) = (uint32_t) ot;
-	DMA_BCR(DMA_GPU)  = 0;
-	DMA_CHCR(DMA_GPU) = 0x01000401;
-}
-
-int DrawBuffer(const uint32_t *buf, size_t length) {
-	_sdk_validate_args(buf && length && (length <= 0xffff), -1);
-
-	return EnqueueDrawOp((void *) &DrawBuffer2, (uint32_t) buf, length, 0);
-}
-
-void DrawBuffer2(const uint32_t *buf, size_t length) {
-	_sdk_validate_args_void(buf && length && (length <= 0xffff));
-
-	SetDrawOpType(DRAWOP_TYPE_DMA);
-	GPU_GP1 = 0x04000002; // Enable DMA request, route to GP0
-
-	while (DMA_CHCR(DMA_GPU) & (1 << 24))
-		__asm__ volatile("");
-
-	DMA_MADR(DMA_GPU) = (uint32_t) buf;
-	DMA_BCR(DMA_GPU)  = 0x00000001 | (length << 16);
-	DMA_CHCR(DMA_GPU) = 0x01000201;
-}
-
-void DrawPrim(const uint32_t *pri) {
-	_sdk_validate_args_void(pri);
-
-	DrawSync(0);
-	DrawBuffer2(&pri[1], getlen(pri));
-}
-
 /* Queue pause/resume API */
 
 int IsIdleGPU(int timeout) {
diff --git a/libpsn00b/psxgpu/drawing.c b/libpsn00b/psxgpu/drawing.c
new file mode 100644
index 0000000..161b2f7
--- /dev/null
+++ b/libpsn00b/psxgpu/drawing.c
@@ -0,0 +1,148 @@
+/*
+ * PSn00bSDK GPU library (drawing/display list functions)
+ * (C) 2022-2023 spicyjpeg - MPL licensed
+ */
+
+#include <stdint.h>
+#include <assert.h>
+#include <psxetc.h>
+#include <psxgpu.h>
+#include <hwregs_c.h>
+
+/* Private utilities */
+
+// This function is actually referenced in env.c as well, so it can't be static.
+void _send_linked_list(GPU_DrawOpType type, const uint32_t *ot) {
+	SetDrawOpType(type);
+	GPU_GP1 = 0x04000002; // Enable DMA request, route to GP0
+
+	while (DMA_CHCR(DMA_GPU) & (1 << 24))
+		__asm__ volatile("");
+
+	DMA_MADR(DMA_GPU) = (uint32_t) ot;
+	DMA_BCR(DMA_GPU)  = 0;
+	DMA_CHCR(DMA_GPU) = 0x01000401;
+}
+
+static void _send_buffer(
+	GPU_DrawOpType type, const uint32_t *buf, size_t length
+) {
+	SetDrawOpType(type);
+	GPU_GP1 = 0x04000002; // Enable DMA request, route to GP0
+
+	while (DMA_CHCR(DMA_GPU) & (1 << 24))
+		__asm__ volatile("");
+
+	DMA_MADR(DMA_GPU) = (uint32_t) buf;
+	DMA_BCR(DMA_GPU)  = 0x00000001 | (length << 16);
+	DMA_CHCR(DMA_GPU) = 0x01000201;
+}
+
+/* Buffer and primitive drawing API */
+
+int DrawOTag(const uint32_t *ot) {
+	_sdk_validate_args(ot, -1);
+
+	return EnqueueDrawOp(
+		(void *)   &_send_linked_list,
+		(uint32_t) DRAWOP_TYPE_DMA,
+		(uint32_t) ot,
+		0
+	);
+}
+
+int DrawOTagIRQ(const uint32_t *ot) {
+	_sdk_validate_args(ot, -1);
+
+	return EnqueueDrawOp(
+		(void *)   &_send_linked_list,
+		(uint32_t) DRAWOP_TYPE_GPU_IRQ,
+		(uint32_t) ot,
+		0
+	);
+}
+
+int DrawBuffer(const uint32_t *buf, size_t length) {
+	_sdk_validate_args(buf && length && (length <= 0xffff), -1);
+
+	return EnqueueDrawOp(
+		(void *)   &DrawBuffer2,
+		(uint32_t) DRAWOP_TYPE_DMA,
+		(uint32_t) buf,
+		(uint32_t) length
+	);
+}
+
+int DrawBufferIRQ(const uint32_t *buf, size_t length) {
+	_sdk_validate_args(buf && length && (length <= 0xffff), -1);
+
+	return EnqueueDrawOp(
+		(void *)   &DrawBuffer2,
+		(uint32_t) DRAWOP_TYPE_GPU_IRQ,
+		(uint32_t) buf,
+		(uint32_t) length
+	);
+}
+
+void DrawOTag2(const uint32_t *ot) {
+	_sdk_validate_args_void(ot);
+
+	_send_linked_list(DRAWOP_TYPE_DMA, ot);
+}
+
+void DrawOTagIRQ2(const uint32_t *ot) {
+	_sdk_validate_args_void(ot);
+
+	_send_linked_list(DRAWOP_TYPE_GPU_IRQ, ot);
+}
+
+void DrawBuffer2(const uint32_t *buf, size_t length) {
+	_sdk_validate_args_void(buf && length && (length <= 0xffff));
+
+	_send_buffer(DRAWOP_TYPE_DMA, buf, length);
+}
+
+void DrawBufferIRQ2(const uint32_t *buf, size_t length) {
+	_sdk_validate_args_void(buf && length && (length <= 0xffff));
+
+	_send_buffer(DRAWOP_TYPE_GPU_IRQ, buf, length);
+}
+
+void DrawPrim(const uint32_t *pri) {
+	_sdk_validate_args_void(pri);
+
+	DrawSync(0);
+	DrawBuffer2(&pri[1], getlen(pri));
+}
+
+/* Helper functions */
+
+void ClearOTagR(uint32_t *ot, size_t length) {
+	_sdk_validate_args_void(ot && length);
+
+	DMA_MADR(DMA_OTC) = (uint32_t) &ot[length - 1];
+	DMA_BCR(DMA_OTC)  = length & 0xffff;
+	DMA_CHCR(DMA_OTC) = 0x11000002;
+
+	while (DMA_CHCR(DMA_OTC) & (1 << 24))
+		__asm__ volatile("");
+}
+
+void ClearOTag(uint32_t *ot, size_t length) {
+	_sdk_validate_args_void(ot && length);
+
+	// DMA6 only supports writing to RAM in reverse order (last to first), so
+	// the OT has to be cleared in software here. This function is thus much
+	// slower than ClearOTagR().
+	// https://problemkaputt.de/psx-spx.htm#dmachannels
+	for (int i = 0; i < (length - 1); i++)
+		ot[i] = (uint32_t) &ot[i + 1] & 0x7fffff;
+
+	ot[length - 1] = 0xffffff;
+}
+
+void AddPrim(uint32_t *ot, const void *pri) {
+	_sdk_validate_args_void(ot && pri);
+
+	addPrim(ot, pri);
+}
diff --git a/libpsn00b/psxgpu/env.c b/libpsn00b/psxgpu/env.c
index c9e6142..236ae4b 100644
--- a/libpsn00b/psxgpu/env.c
+++ b/libpsn00b/psxgpu/env.c
@@ -34,37 +34,7 @@ static inline uint32_t _get_window_mask(int size) {
 	return mask & 0x1f;
 }
 
-/* Drawing API */
-
-DRAWENV *SetDefDrawEnv(DRAWENV *env, int x, int y, int w, int h) {
-	_sdk_validate_args(env && (w > 0) && (h > 0), 0);
-
-	env->clip.x = x;
-	env->clip.y = y;
-	env->clip.w = w;
-	env->clip.h = h;
-
-	env->ofs[0] = 0;
-	env->ofs[1] = 0;
-
-	env->tw.x = 0;
-	env->tw.y = 0;
-	env->tw.w = 256;
-	env->tw.h = 256;
-
-	env->tpage = 0x0a;
-	env->dtd   = 1;
-	env->dfe   = 0;
-	env->isbg  = 0;
-	setRGB0(env, 0, 0, 0);
-
-	env->dr_env.tag = 0;
-	return env;
-}
-
-int DrawOTagEnv(const uint32_t *ot, DRAWENV *env) {
-	_sdk_validate_args(ot && env, -1);
-
+static const uint32_t *_build_drawenv_ot(const uint32_t *ot, DRAWENV *env) {
 	// All commands are grouped into a single display list packet for
 	// performance reasons using tagless primitives (the GPU does not care
 	// about the grouping as the display list is parsed by the CPU).
@@ -101,7 +71,59 @@ int DrawOTagEnv(const uint32_t *ot, DRAWENV *env) {
 		setWH(fill, env->clip.w, _min(env->clip.h, 0x1ff));
 	}
 
-	return EnqueueDrawOp((void *) &DrawOTag2, (uint32_t) prim, 0, 0);
+	return (const uint32_t *) prim;
+}
+
+/* Drawing API */
+
+void _send_linked_list(GPU_DrawOpType type, const uint32_t *ot);
+
+DRAWENV *SetDefDrawEnv(DRAWENV *env, int x, int y, int w, int h) {
+	_sdk_validate_args(env && (w > 0) && (h > 0), 0);
+
+	env->clip.x = x;
+	env->clip.y = y;
+	env->clip.w = w;
+	env->clip.h = h;
+
+	env->ofs[0] = 0;
+	env->ofs[1] = 0;
+
+	env->tw.x = 0;
+	env->tw.y = 0;
+	env->tw.w = 256;
+	env->tw.h = 256;
+
+	env->tpage = 0x0a;
+	env->dtd   = 1;
+	env->dfe   = 0;
+	env->isbg  = 0;
+	setRGB0(env, 0, 0, 0);
+
+	env->dr_env.tag = 0;
+	return env;
+}
+
+int DrawOTagEnv(const uint32_t *ot, DRAWENV *env) {
+	_sdk_validate_args(ot && env, -1);
+
+	return EnqueueDrawOp(
+		(void *)   &_send_linked_list,
+		(uint32_t) DRAWOP_TYPE_DMA,
+		(uint32_t) _build_drawenv_ot(ot, env),
+		0
+	);
+}
+
+int DrawOTagEnvIRQ(const uint32_t *ot, DRAWENV *env) {
+	_sdk_validate_args(ot && env, -1);
+
+	return EnqueueDrawOp(
+		(void *)   &_send_linked_list,
+		(uint32_t) DRAWOP_TYPE_GPU_IRQ,
+		(uint32_t) _build_drawenv_ot(ot, env),
+		0
+	);
 }
 
 void PutDrawEnv(DRAWENV *env) {
diff --git a/libpsn00b/psxgpu/image.c b/libpsn00b/psxgpu/image.c
index a08e293..e02c3c2 100644
--- a/libpsn00b/psxgpu/image.c
+++ b/libpsn00b/psxgpu/image.c
@@ -104,7 +104,17 @@ int StoreImage(const RECT *rect, uint32_t *data) {
 int MoveImage(const RECT *rect, int x, int y) {
 	_sdk_validate_args(rect, -1);
 
-	return EnqueueDrawOp((void *) &MoveImage2, (uint32_t) rect, x, y);
+	int index = _next_saved_rect;
+
+	_saved_rects[index] = *rect;
+	_next_saved_rect    = (index + 1) % QUEUE_LENGTH;
+
+	return EnqueueDrawOp(
+		(void *)   &MoveImage2,
+		(uint32_t) &_saved_rects[index],
+		(uint32_t) x,
+		(uint32_t) y
+	);
 }
 
 void LoadImage2(const RECT *rect, const uint32_t *data) {