raphiaura/KytyPS5
1
0
Fork 0
mirror of https://github.com/KytyPS5/KytyPS5.git synced 2026-10-20 02:47:02 +02:00
Code Issues Packages Projects Releases Wiki Activity

refactor renderer

Browse Source
This commit is contained in:
nmzik
2026-07-27 02:24:50 +02:00
parent a720b28b7f
commit a20cf5d298
112 changed files with 18269 additions and 18368 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/graphics/guest_gpu/command_processor/commandProcessor.h
+9 -16
View File
@@ -11,8 +11,6 @@
namespace Libs::Graphics {
inline constexpr uint32_t AcquireGcrGl2Writeback = 1u << 15u;
bool TestWaitRegMemValue(uint64_t value, uint64_t ref, uint64_t mask, uint32_t func);
enum class Pm4ProcessResult { Complete, Blocked };
@@ -45,7 +43,7 @@ public:
int64_t flip_arg = 0;
};
CommandProcessor() = default;
explicit CommandProcessor(RenderContext& renderer): m_renderer(renderer) {}
~CommandProcessor() = default;
KYTY_CLASS_NO_COPY(CommandProcessor);
@@ -60,16 +58,13 @@ public:
if (m_readback_active) {
EXIT("nested command-processor readback transaction\n");
}
m_readback_active = true;
m_readback_finished = false;
m_readback_active = true;
}
void FinishReadbackTransaction();
void EndReadbackTransaction() {
if (!m_readback_active) {
EXIT("command-processor readback transaction is not active\n");
}
m_readback_active = false;
m_readback_finished = false;
m_readback_active = false;
}
HW::Context& GetCtx() { return m_ctx; }
@@ -106,12 +101,10 @@ public:
void Flip(void* dst_gpu_addr, uint32_t value);
void FlipWithInterrupt(uint32_t eop_event_type, uint32_t cache_action, void* dst_gpu_addr,
uint32_t value);
void PrepareCpuFlip();
void PrepareCpuFlip(uint64_t request_id);
void SynchronizeGpu();
void MemoryBarrier();
void EmitGlobalBarrier();
void TriggerEopEventAtEndOfPipe(uint32_t interrupt_context_id);
void RenderTextureBarrier(uint64_t vaddr, uint64_t size);
void DepthStencilBarrier(uint64_t vaddr, uint64_t size);
void DispatchDirect(uint32_t thread_group_x, uint32_t thread_group_y, uint32_t thread_group_z,
uint32_t mode);
void DispatchIndirect(uint32_t data_offset, uint32_t mode);
@@ -160,11 +153,12 @@ private:
void ProcessPm4(Pm4Execution& execution, size_t stop_depth);
void SuspendPm4();
CommandScheduler& GetScheduler() const { return GetRenderContext().GetCommandScheduler(); }
CommandScheduler& GetScheduler() const { return m_renderer.GetCommandScheduler(); }
RenderCommandBuffer& CurrentBuffer() { return GetScheduler().Current(); }
void CheckBuffer() const { GetScheduler().CheckActive(); }
GpuResourceManager& GetGpuResources() const { return GetRenderContext().GetGpuResources(); }
GpuResourceManager& GetGpuResources() const { return m_renderer.GetGpuResources(); }
RenderContext& m_renderer;
HW::Context m_ctx;
HW::UserConfig m_ucfg;
HW::Shader m_sh_ctx;
@@ -179,8 +173,7 @@ private:
uint32_t m_de_count = 0;
uint32_t m_ce_count = 0;
bool m_ce_complete = false;
bool m_readback_active = false;
bool m_readback_finished = false;
bool m_readback_active = false;
uint32_t m_const_ram[0x3000] = {0};
src/graphics/guest_gpu/command_processor/pm4Handlers.cpp
+4 -224
View File
@@ -6,7 +6,6 @@
#include "graphics/guest_gpu/command_processor/pm4Dispatch.h"
#include "graphics/guest_gpu/graphicsRun.h"
#include "graphics/host_gpu/graphicContext.h"
#include "graphics/host_gpu/objects/label.h"
#include "graphics/host_gpu/renderer/render.h"
#include "graphics/host_gpu/renderer/renderContext.h"
#include "graphics/presentation/videoOut.h"
@@ -1764,230 +1763,11 @@ static bool HwUcTrySetFakeRegisterRange(uint32_t cmd_offset, const uint32_t* buf
return true;
}
// NOLINTNEXTLINE(readability-function-cognitive-complexity)
KYTY_CP_OP_PARSER(CpOpAcquireMem) {
KYTY_PROFILER_FUNCTION();
EXIT_NOT_IMPLEMENTED(cmd_id != 0xC0055800 && cmd_id != 0xc0061050);
bool custom = (cmd_id == 0xc0061050);
uint32_t engine = buffer[0] >> 31u;
uint32_t stall_mode = (custom ? 1u : engine);
uint32_t cache_action = buffer[0] & 0x7fffffffu;
uint64_t size_lo = buffer[1];
uint32_t size_hi = buffer[2];
uint64_t base_lo = buffer[3];
uint32_t base_hi = buffer[4];
uint32_t poll = buffer[5];
[[maybe_unused]] uint32_t gcr_cntl = (custom ? buffer[6] : 0);
uint32_t target_mask = cache_action & 0x00007FC0u;
uint32_t extended_action = cache_action & 0x2E000000u;
uint32_t action =
((cache_action & 0x00C00000u) >> 0x12u) | ((cache_action & 0x00058000u) >> 0xfu);
if (custom && engine > 1) {
LOGF("\t warning: custom acquire_mem unsupported engine: %" PRIu32 "\n", engine);
}
// EXIT_NOT_IMPLEMENTED(stall_mode != 1);
EXIT_NOT_IMPLEMENTED(size_hi != 0);
EXIT_NOT_IMPLEMENTED(base_hi != 0);
if (poll != 10) {
LOGF("\t warning: acquire_mem unexpected poll interval: %" PRIu32 "\n", poll);
}
switch (cache_action) {
case 0x00000000: {
if (custom && gcr_cntl != 0) {
LOGF("\t custom acquire_mem GCR-only barrier, gcr_cntl = 0x%08" PRIx32
", base = 0x%016" PRIx64 ", size = 0x%016" PRIx64 "\n",
gcr_cntl, base_lo << 8u, size_lo << 8u);
cp.MemoryBarrier();
if ((gcr_cntl & AcquireGcrGl2Writeback) != 0) {
cp.SynchronizeGpu();
}
}
} break;
case 0x00000040:
case 0x00003fc0:
case 0x00004000:
case 0x00007fc0: {
// target_mask set, no CB/DB action bits. Treat as an ordering barrier.
EXIT_IF(target_mask != cache_action);
EXIT_IF(extended_action != 0x00000000);
EXIT_IF(action != 0x00);
LOGF("\t temporary: acquire_mem target-mask-only barrier, target_mask = 0x%08" PRIx32
", gcr_cntl = 0x%08" PRIx32 ", base = 0x%016" PRIx64 ", size = 0x%016" PRIx64 "\n",
target_mask, gcr_cntl, base_lo << 8u, size_lo << 8u);
cp.MemoryBarrier();
} break;
case 0x02000000: {
// target_mask: 0x00000000 (none)
// extended_action: 0x02000000 (FlushAndInvalidateCbCache)
// action: 0x00 (none)
EXIT_IF(target_mask != 0x00000000);
EXIT_IF(extended_action != 0x02000000);
EXIT_IF(action != 0x00);
LOGF("\t temporary: acquire_mem CB-cache-only barrier, gcr_cntl = 0x%08" PRIx32
", base = 0x%016" PRIx64 ", size = 0x%016" PRIx64 "\n",
gcr_cntl, base_lo << 8u, size_lo << 8u);
cp.MemoryBarrier();
} break;
case 0x04000000: {
// target_mask: 0x00000000 (none)
// extended_action: 0x04000000 (FlushAndInvalidateDbCache)
// action: 0x00 (none)
EXIT_IF(target_mask != 0x00000000);
EXIT_IF(extended_action != 0x04000000);
EXIT_IF(action != 0x00);
LOGF("\t temporary: acquire_mem DB-cache-only barrier, gcr_cntl = 0x%08" PRIx32
", base = 0x%016" PRIx64 ", size = 0x%016" PRIx64 "\n",
gcr_cntl, base_lo << 8u, size_lo << 8u);
cp.MemoryBarrier();
} break;
case 0x04004000:
case 0x04007fc0: {
// target_mask: 0x00004000 (Depth Target), 0x00007fc0 (all rt and depth)
// extended_action: 0x04000000 (FlushAndInvalidateDbCache)
// action: 0x00 (none)
EXIT_IF(target_mask != 0x00004000 && target_mask != 0x00007FC0);
EXIT_IF(extended_action != 0x04000000);
EXIT_IF(action != 0x00);
LOGF("\t temporary: acquire_mem DB target barrier, target_mask = 0x%08" PRIx32
", gcr_cntl = 0x%08" PRIx32 ", base = 0x%016" PRIx64 ", size = 0x%016" PRIx64 "\n",
target_mask, gcr_cntl, base_lo << 8u, size_lo << 8u);
if (size_lo != 0) {
cp.DepthStencilBarrier(base_lo << 8u, size_lo << 8u);
} else {
cp.MemoryBarrier();
}
} break;
case 0x02c40040:
case 0x02c43fc0:
case 0x02c47fc0: {
// target_mask: 0x00000040 (rt0), 0x00003fc0 (all rt), 0x00007fc0 (all rt and depth)
// extended_action: 0x02000000 (FlushAndInvalidateCbCache)
// action: 0x38 (WriteBackAndInvalidateL1andL2)
EXIT_IF(target_mask != 0x00000040 && target_mask != 0x00003FC0 &&
target_mask != 0x00007FC0);
EXIT_IF(extended_action != 0x02000000);
EXIT_IF(action != 0x38);
EXIT_NOT_IMPLEMENTED(size_lo == 0);
EXIT_NOT_IMPLEMENTED(base_lo == 0);
cp.RenderTextureBarrier(base_lo << 8u, size_lo << 8u);
cp.SynchronizeGpu();
} break;
case 0x02003fc0:
case 0x02007fc0: {
// target_mask: 0x00003FC0 (all rt), 0x00007fc0 (all rt and depth)
// extended_action: 0x02000000 (FlushAndInvalidateCbCache)
// action: 0x00 (none)
EXIT_IF(target_mask != 0x00003FC0 && target_mask != 0x00007fc0);
EXIT_IF(extended_action != 0x02000000);
EXIT_IF(action != 0x00);
if (size_lo == 0) {
if (base_lo != 0) {
LOGF("\t warning: acquire_mem CB-cache barrier with non-zero base");
}
cp.MemoryBarrier();
} else {
EXIT_NOT_IMPLEMENTED(base_lo == 0);
cp.RenderTextureBarrier(base_lo << 8u, size_lo << 8u);
}
} break;
case 0x00C40000: {
// target_mask: 0x00000000 (none)
// extended_action: 0x00000000 (none)
// action: 0x38 (WriteBackAndInvalidateL1andL2)
EXIT_IF(target_mask != 0x00000000);
EXIT_IF(extended_action != 0x00000000);
EXIT_IF(action != 0x38);
EXIT_NOT_IMPLEMENTED(size_lo != 1);
EXIT_NOT_IMPLEMENTED(base_lo != 0);
cp.MemoryBarrier();
cp.SynchronizeGpu();
} break;
case 0x00400000: {
// target_mask: 0x00000000 (none)
// extended_action: 0x00000000 (none)
// action: 0x10 (InvalidateL1)
EXIT_IF(target_mask != 0x00000000);
EXIT_IF(extended_action != 0x00000000);
EXIT_IF(action != 0x10);
EXIT_NOT_IMPLEMENTED(size_lo != 1);
EXIT_NOT_IMPLEMENTED(base_lo != 0);
cp.MemoryBarrier();
} break;
case 0x04c44000: {
// target_mask: 0x00004000 (Depth Target)
// extended_action: 0x04000000 (FlushAndInvalidateDbCache)
// action: 0x38 (WriteBackAndInvalidateL1andL2)
EXIT_IF(target_mask != 0x00004000);
EXIT_IF(extended_action != 0x04000000);
EXIT_IF(action != 0x38);
cp.DepthStencilBarrier(base_lo << 8u, size_lo << 8u);
cp.SynchronizeGpu();
} break;
case 0x06000040:
case 0x06000080:
case 0x06003fc0:
case 0x06007fc0: {
// target_mask: 0x00000040 (rt0), 0x00000080 (rt1), 0x00003fc0 (all rt), 0x00007fc0
// (all rt and depth) extended_action: 0x06000000 (Flush Cb & Db) action: 0x00
// (none)
if (gcr_cntl != 0 && gcr_cntl != 0x280 && gcr_cntl != 0x300) {
LOGF("\t temporary: acquire_mem CB+DB barrier with unhandled GCR control "
"0x%08" PRIx32 "\n",
gcr_cntl);
}
EXIT_IF(target_mask != 0x00000040 && target_mask != 0x00000080 &&
target_mask != 0x00003fc0 && target_mask != 0x00007fc0);
EXIT_IF(extended_action != 0x06000000);
EXIT_IF(action != 0x00);
if (size_lo != 0) {
if ((target_mask & 0x00003fc0) != 0) {
cp.RenderTextureBarrier(base_lo << 8u, size_lo << 8u);
}
if ((target_mask & 0x00004000) != 0) {
cp.DepthStencilBarrier(base_lo << 8u, size_lo << 8u);
}
} else {
cp.MemoryBarrier();
}
} break;
default:
EXIT("unknown barrier: 0x%08" PRIx32 ", 0x%08" PRIx32 ", 0x%08" PRIx32 ", 0x%08" PRIx32
"\n",
cache_action, target_mask, extended_action, action);
}
if (stall_mode == 0) {
cp.BufferWait();
}
return (custom ? 7 : 6);
return (cmd_id == 0xc0061050 ? 7 : 6);
}
KYTY_CP_OP_PARSER(CpOpDispatchDirect) {
@@ -2930,7 +2710,7 @@ KYTY_CP_OP_PARSER(CpOpReleaseMem) {
if (data_sel == 0 || interrupt_selector == 4) {
if (eop_event_type != 0x28 || gcr_cntl != 0) {
cp.MemoryBarrier();
cp.EmitGlobalBarrier();
}
if (gl2_writeback) {
@@ -2944,7 +2724,7 @@ KYTY_CP_OP_PARSER(CpOpReleaseMem) {
if (release_dst == ReleaseMemDstMemory && dst_gpu_addr == nullptr) {
if (eop_event_type != 0x28 || gcr_cntl != 0) {
cp.MemoryBarrier();
cp.EmitGlobalBarrier();
}
if (gl2_writeback) {
@@ -2957,7 +2737,7 @@ KYTY_CP_OP_PARSER(CpOpReleaseMem) {
}
if (ReleaseMemGcrNeedsBarrier(eop_event_type, gcr_cntl)) {
cp.MemoryBarrier();
cp.EmitGlobalBarrier();
}
auto cache_action = ReleaseMemCacheActionFromGcr(gcr_cntl);