aboutsummaryrefslogtreecommitdiff
path: root/src
diff options
context:
space:
mode:
Diffstat (limited to 'src')
-rw-r--r--src/common/fiber.cpp4
-rw-r--r--src/common/host_memory.cpp22
-rw-r--r--src/video_core/buffer_cache/buffer_cache.h4
-rw-r--r--src/video_core/renderer_vulkan/vk_compute_pass.cpp6
-rw-r--r--src/video_core/renderer_vulkan/vk_texture_cache.cpp2
-rw-r--r--src/video_core/renderer_vulkan/vk_update_descriptor.cpp8
-rw-r--r--src/video_core/renderer_vulkan/vk_update_descriptor.h3
-rw-r--r--src/video_core/texture_cache/texture_cache.h16
8 files changed, 50 insertions, 15 deletions
diff --git a/src/common/fiber.cpp b/src/common/fiber.cpp
index 0e7f28c5b9..08558a0026 100644
--- a/src/common/fiber.cpp
+++ b/src/common/fiber.cpp
@@ -25,8 +25,8 @@ struct Fiber::FiberImpl {
FiberImpl() {}
u32 canary_1 = CANARY_VALUE;
- std::array<u8, DEFAULT_STACK_SIZE> stack{};
- std::array<u8, DEFAULT_STACK_SIZE> rewind_stack{};
+ std::array<u8, DEFAULT_STACK_SIZE> stack;
+ std::array<u8, DEFAULT_STACK_SIZE> rewind_stack;
u32 canary_2 = CANARY_VALUE;
boost::context::detail::fcontext_t context{};
diff --git a/src/common/host_memory.cpp b/src/common/host_memory.cpp
index 75a9da80e9..147eba8477 100644
--- a/src/common/host_memory.cpp
+++ b/src/common/host_memory.cpp
@@ -51,6 +51,7 @@
#endif // ^^^ POSIX ^^^
+#include <cstdlib>
#include <mutex>
#include <random>
@@ -517,6 +518,14 @@ public:
, virtual_size{virtual_size_}
{}
+#ifdef __linux__
+ bool PunchHole(size_t offset, size_t length) {
+ return fd >= 0 &&
+ fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, static_cast<off_t>(offset),
+ static_cast<off_t>(length)) == 0;
+ }
+#endif
+
bool Init() {
long page_size = sysconf(_SC_PAGESIZE);
ASSERT_MSG(page_size == 0x1000, "page size {:#x} is incompatible with 4K paging", page_size);
@@ -791,6 +800,19 @@ void HostMemory::Protect(size_t virtual_offset, size_t length, MemoryPermission
}
void HostMemory::ClearBackingRegion(size_t physical_offset, size_t length, u32 fill_value) {
+#ifdef __linux__
+ const size_t first = AlignUp(physical_offset, PageAlignment);
+ const size_t last = AlignDown(physical_offset + length, PageAlignment);
+ static const bool punch = [] {
+ const char* value = std::getenv("EDEN_PUNCH_HOLE");
+ return value == nullptr || value[0] != '0';
+ }();
+ if (punch && fill_value == 0 && impl && last > first && impl->PunchHole(first, last - first)) {
+ std::memset(backing_base + physical_offset, 0, first - physical_offset);
+ std::memset(backing_base + last, 0, physical_offset + length - last);
+ return;
+ }
+#endif
std::memset(backing_base + physical_offset, fill_value, length);
}
diff --git a/src/video_core/buffer_cache/buffer_cache.h b/src/video_core/buffer_cache/buffer_cache.h
index e09a435dcc..a3358048dc 100644
--- a/src/video_core/buffer_cache/buffer_cache.h
+++ b/src/video_core/buffer_cache/buffer_cache.h
@@ -1651,10 +1651,10 @@ void BufferCache<P>::MarkWrittenBuffer(BufferId buffer_id, DAddr device_addr, u3
template <class P>
BufferId BufferCache<P>::FindBuffer(DAddr device_addr, u32 size, bool sparse_compatible) {
- if (device_addr == 0) {
+ const u64 page = device_addr >> CACHING_PAGEBITS;
+ if (device_addr == 0 || page >= page_table.size()) {
return NULL_BUFFER_ID;
}
- const u64 page = device_addr >> CACHING_PAGEBITS;
const BufferId buffer_id = page_table[page];
if (buffer_id) {
Buffer& buffer = slot_buffers[buffer_id];
diff --git a/src/video_core/renderer_vulkan/vk_compute_pass.cpp b/src/video_core/renderer_vulkan/vk_compute_pass.cpp
index 691be728d2..cb8dcde42f 100644
--- a/src/video_core/renderer_vulkan/vk_compute_pass.cpp
+++ b/src/video_core/renderer_vulkan/vk_compute_pass.cpp
@@ -801,11 +801,11 @@ void ASTCDecoderPass::AssembleInto(const VideoCommon::ImageInfo& info, u32 skip,
cmdbuf.PipelineBarrier(VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT,
vk::PIPELINE_STAGE_GRAPHICS_COMPUTE, 0, image_barrier);
});
- // Each decode ends with the GPU thread waiting for the host GPU to go idle. Measured here
- // (count and time per 5 s); EDEN_NX2_ASTC_FLUSH=1 submits without waiting instead.
+ // Each decode ends with a submit to the host GPU. Measured here
+ // (count and time per 5 s); EDEN_NX2_ASTC_FLUSH=0 waits for the host GPU to go idle instead.
static const bool flush_only = [] {
const char* value = std::getenv("EDEN_NX2_ASTC_FLUSH");
- return value != nullptr && value[0] == '1';
+ return value == nullptr || value[0] != '0';
}();
if (!target.wait) {
return;
diff --git a/src/video_core/renderer_vulkan/vk_texture_cache.cpp b/src/video_core/renderer_vulkan/vk_texture_cache.cpp
index 4e428229f6..b0e5eacb32 100644
--- a/src/video_core/renderer_vulkan/vk_texture_cache.cpp
+++ b/src/video_core/renderer_vulkan/vk_texture_cache.cpp
@@ -4267,7 +4267,7 @@ void TextureCacheRuntime::TranscodeAstcToBcn(
.aspect_mask = VK_IMAGE_ASPECT_COLOR_BIT,
.initialized = false,
.level_view = [&pending](s32 level) { return *pending.views[level]; },
- .wait = false,
+ .wait = true,
},
map, swizzles);
diff --git a/src/video_core/renderer_vulkan/vk_update_descriptor.cpp b/src/video_core/renderer_vulkan/vk_update_descriptor.cpp
index 742a8d9969..29f3ee71a1 100644
--- a/src/video_core/renderer_vulkan/vk_update_descriptor.cpp
+++ b/src/video_core/renderer_vulkan/vk_update_descriptor.cpp
@@ -20,10 +20,10 @@ UpdateDescriptorQueue::UpdateDescriptorQueue(const Device& device_, size_t frame
bool supports_descriptor_buffer_)
: device{device_}, frame_payload_size{frame_payload_size_},
supports_descriptor_buffer{supports_descriptor_buffer_},
- payload(frame_payload_size_ * FRAMES_IN_FLIGHT)
+ payload(std::make_unique_for_overwrite<DescriptorUpdateEntry[]>(frame_payload_size_ * FRAMES_IN_FLIGHT))
{
- payload_start = payload.data();
- payload_cursor = payload.data();
+ payload_start = payload.get();
+ payload_cursor = payload.get();
}
UpdateDescriptorQueue::~UpdateDescriptorQueue() = default;
@@ -32,7 +32,7 @@ void UpdateDescriptorQueue::TickFrame() {
if (++frame_index >= FRAMES_IN_FLIGHT) {
frame_index = 0;
}
- payload_start = payload.data() + frame_index * frame_payload_size;
+ payload_start = payload.get() + frame_index * frame_payload_size;
payload_cursor = payload_start;
}
diff --git a/src/video_core/renderer_vulkan/vk_update_descriptor.h b/src/video_core/renderer_vulkan/vk_update_descriptor.h
index 9f30e65dbd..4d393376b4 100644
--- a/src/video_core/renderer_vulkan/vk_update_descriptor.h
+++ b/src/video_core/renderer_vulkan/vk_update_descriptor.h
@@ -6,6 +6,7 @@
#pragma once
+#include <memory>
#include <variant>
#include <vector>
#include "video_core/vulkan_common/vulkan_wrapper.h"
@@ -122,7 +123,7 @@ private:
DescriptorUpdateEntry* payload_cursor = nullptr;
DescriptorUpdateEntry* payload_start = nullptr;
const DescriptorUpdateEntry* upload_start = nullptr;
- std::vector<DescriptorUpdateEntry> payload;
+ std::unique_ptr<DescriptorUpdateEntry[]> payload;
};
// TODO: should these be separate classes instead?
diff --git a/src/video_core/texture_cache/texture_cache.h b/src/video_core/texture_cache/texture_cache.h
index 32775b8719..55ec4c64df 100644
--- a/src/video_core/texture_cache/texture_cache.h
+++ b/src/video_core/texture_cache/texture_cache.h
@@ -125,6 +125,7 @@ template <class P>
void TextureCache<P>::RunGarbageCollector() {
bool high_priority_mode = false;
bool aggressive_mode = false;
+ bool evict_old_costly = false;
u64 ticks_to_destroy = 0;
size_t num_iterations = 0;
const auto Configure = [&](bool allow_aggressive) {
@@ -139,7 +140,8 @@ void TextureCache<P>::RunGarbageCollector() {
ticks_to_destroy = (std::max)(ticks_to_destroy, min_age);
num_iterations = aggressive_mode ? 40 : (high_priority_mode ? 20 : 10);
};
- const auto Cleanup = [this, &num_iterations, &high_priority_mode, &aggressive_mode](ImageId image_id) {
+ const auto Cleanup = [this, &num_iterations, &high_priority_mode, &aggressive_mode,
+ &evict_old_costly](ImageId image_id) {
if (num_iterations == 0) {
return true;
}
@@ -149,7 +151,8 @@ void TextureCache<P>::RunGarbageCollector() {
return false;
}
const bool must_download = IsDownloadable(image) && False(image.flags & ImageFlagBits::BadOverlap);
- if ((!aggressive_mode && True(image.flags & ImageFlagBits::CostlyLoad)) || (!high_priority_mode && must_download)) {
+ if ((!aggressive_mode && !evict_old_costly && True(image.flags & ImageFlagBits::CostlyLoad)) ||
+ (!high_priority_mode && must_download)) {
return false;
}
if (must_download) {
@@ -176,6 +179,15 @@ void TextureCache<P>::RunGarbageCollector() {
return false;
};
Configure(false);
+ static const u64 old_age = [] {
+ const char* value = std::getenv("EDEN_NX2_TC_OLD_AGE");
+ return value != nullptr ? std::strtoull(value, nullptr, 10) : 1800ULL;
+ }();
+ if (high_priority_mode && old_age != 0 && frame_tick > old_age) {
+ evict_old_costly = true;
+ lru_cache.ForEachItemBelow(frame_tick - old_age, Cleanup);
+ evict_old_costly = false;
+ }
lru_cache.ForEachItemBelow(frame_tick - ticks_to_destroy, Cleanup);
if (total_used_memory >= critical_memory) {
Configure(true);
generated by cgit v1.2.3 (git 2.39.1) at 2026-11-04 03:10:09 +0000