Calchan/eden
1
0
Fork 0
forked from eden-emu/eden
Code Pull requests Activity

[heap_tracker] revert use of ::map, use old rb tree

Browse source 
Signed-off-by: lizzie <lizzie@eden-emu.dev>
This commit is contained in:
lizzie 2025-08-31 20:16:21 +00:00 • committed by crueter
parent 0f5680ece9
commit adbb1789b1
3 changed files with 168 additions and 92 deletions
Download patch file Download diff file Expand all files Collapse all files

180
src/common/heap_tracker.cpp
View file

@ -1,94 +1,112 @@
// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later
#include <fstream>
#include <vector>
#include "common/heap_tracker.h"
#include "common/logging/log.h"
#include "common/assert.h"
namespace Common {
namespace {
s64 GetMaxPermissibleResidentMapCount() {
inline s64 GetMaxPermissibleResidentMapCount() {
// Default value.
s64 value = 65530;
// Try to read how many mappings we can make.
std::ifstream s("/proc/sys/vm/max_map_count");
s >> value;
// Print, for debug.
LOG_INFO(HW_Memory, "Current maximum map count: {}", value);
// Allow 20000 maps for other code and to account for split inaccuracy.
return std::max<s64>(value - 20000, 0);
long int value = 65530;
std::unique_ptr<FILE, decltype(&fclose)> fp(fopen("/proc/sys/vm/max_map_count", "rt"), &fclose);
if (fp.get())
fscanf(fp.get(), "%li", &value);
LOG_INFO(HW_Memory, "Max map count: {}", value);
// Allow 32767 maps for other code and to account for split inaccuracy.
return std::max<s64>(s64(value) - 32767, 0);
}
} // namespace
HeapTracker::HeapTracker(Common::HostMemory& buffer)
: m_buffer(buffer), m_max_resident_map_count(GetMaxPermissibleResidentMapCount()) {}
HeapTracker::~HeapTracker() = default;
void HeapTracker::Map(size_t virtual_offset, size_t host_offset, size_t length,
MemoryPermission perm, bool is_separate_heap) {
bool rebuild_required = false;
// When mapping other memory, map pages immediately.
if (!is_separate_heap) {
m_buffer.Map(virtual_offset, host_offset, length, perm, false);
return;
}
{
// We are mapping part of a separate heap and insert into mappings.
// We are mapping part of a separate heap.
std::scoped_lock lk{m_lock};
m_map_count++;
const auto it = m_mappings.insert_or_assign(virtual_offset, SeparateHeapMap{
auto* const map = new SeparateHeapMap{
.vaddr = virtual_offset,
.paddr = host_offset,
.size = length,
.tick = m_tick++,
.perm = perm,
.is_resident = false,
});
};
// Insert into mappings.
m_map_count++;
const auto it = m_mappings.insert(*map);
// Update tick before possible rebuild.
it.first->second.tick = m_tick++;
it->tick = m_tick++;
// Check if we need to rebuild.
if (m_resident_map_count >= m_max_resident_map_count)
if (m_resident_map_count >= m_max_resident_map_count) {
rebuild_required = true;
}
// Map the area.
m_buffer.Map(it.first->first, it.first->second.paddr, it.first->second.size, it.first->second.perm, false);
m_buffer.Map(it->vaddr, it->paddr, it->size, it->perm, false);
// This map is now resident.
it.first->second.is_resident = true;
it->is_resident = true;
m_resident_map_count++;
m_resident_mappings.insert(*it.first);
m_resident_mappings.insert(*it);
}
// A rebuild was required, so perform it now.
if (rebuild_required)
if (rebuild_required) {
// A rebuild was required, so perform it now.
this->RebuildSeparateHeapAddressSpace();
}
}
void HeapTracker::Unmap(size_t virtual_offset, size_t size, bool is_separate_heap) {
// If this is a separate heap...
if (is_separate_heap) {
std::scoped_lock lk{m_lock};
const SeparateHeapMap key{
.vaddr = virtual_offset,
};
// Split at the boundaries of the region we are removing.
this->SplitHeapMapLocked(virtual_offset);
this->SplitHeapMapLocked(virtual_offset + size);
// Erase all mappings in range.
auto it = m_mappings.find(virtual_offset);
while (it != m_mappings.end() && it->first < virtual_offset + size) {
auto it = m_mappings.find(key);
while (it != m_mappings.end() && it->vaddr < virtual_offset + size) {
// Get underlying item.
auto* const item = std::addressof(*it);
// If resident, erase from resident map.
if (it->second.is_resident) {
if (item->is_resident) {
ASSERT(--m_resident_map_count >= 0);
m_resident_mappings.erase(m_resident_mappings.find(it->first));
m_resident_mappings.erase(m_resident_mappings.iterator_to(*item));
}
// Erase from map.
ASSERT(--m_map_count >= 0);
it = m_mappings.erase(it);
// Free the item.
delete item;
}
}
// Unmap pages.
m_buffer.Unmap(virtual_offset, size, false);
}
@ -110,32 +128,41 @@ void HeapTracker::Protect(size_t virtual_offset, size_t size, MemoryPermission p
{
std::scoped_lock lk2{m_lock};
const SeparateHeapMap key{
.vaddr = next,
};
// Try to get the next mapping corresponding to this address.
const auto it = m_mappings.find(next);
const auto it = m_mappings.nfind(key);
if (it == m_mappings.end()) {
// There are no separate heap mappings remaining.
next = end;
should_protect = true;
} else if (it->first == cur) {
} else if (it->vaddr == cur) {
// We are in range.
// Update permission bits.
it->second.perm = perm;
it->perm = perm;
// Determine next address and whether we should protect.
next = cur + it->second.size;
should_protect = it->second.is_resident;
next = cur + it->size;
should_protect = it->is_resident;
} else /* if (it->vaddr > cur) */ {
// We weren't in range, but there is a block coming up that will be.
next = it->first;
next = it->vaddr;
should_protect = true;
}
}
// Clamp to end.
next = std::min(next, end);
// Reprotect, if we need to.
if (should_protect)
if (should_protect) {
m_buffer.Protect(cur, next - cur, perm);
}
// Advance.
cur = next;
}
@ -143,18 +170,23 @@ void HeapTracker::Protect(size_t virtual_offset, size_t size, MemoryPermission p
void HeapTracker::RebuildSeparateHeapAddressSpace() {
std::scoped_lock lk{m_rebuild_lock, m_lock};
ASSERT(!m_resident_mappings.empty());
// Dump half of the mappings.
//
// Despite being worse in theory, this has proven to be better in practice than more
// regularly dumping a smaller amount, because it significantly reduces average case
// lock contention.
std::size_t const desired_count = std::min(m_resident_map_count, m_max_resident_map_count) / 2;
std::size_t const evict_count = m_resident_map_count - desired_count;
const size_t desired_count = std::min(m_resident_map_count, m_max_resident_map_count) / 2;
const size_t evict_count = m_resident_map_count - desired_count;
auto it = m_resident_mappings.begin();
for (std::size_t i = 0; i < evict_count && it != m_resident_mappings.end(); i++) {
for (size_t i = 0; i < evict_count && it != m_resident_mappings.end(); i++) {
// Unmark and unmap.
it->second.is_resident = false;
m_buffer.Unmap(it->first, it->second.size, false);
it->is_resident = false;
m_buffer.Unmap(it->vaddr, it->size, false);
// Advance.
ASSERT(--m_resident_map_count >= 0);
it = m_resident_mappings.erase(it);
@ -163,30 +195,46 @@ void HeapTracker::RebuildSeparateHeapAddressSpace() {
void HeapTracker::SplitHeapMap(VAddr offset, size_t size) {
std::scoped_lock lk{m_lock};
this->SplitHeapMapLocked(offset);
this->SplitHeapMapLocked(offset + size);
}
void HeapTracker::SplitHeapMapLocked(VAddr offset) {
if (auto it = this->GetNearestHeapMapLocked(offset); it != m_mappings.end() && it->first != offset) {
// Adjust left iterator
auto const orig_size = it->second.size;
auto const left_size = offset - it->first;
it->second.size = left_size;
// Insert the new right map.
auto const right = SeparateHeapMap{
.paddr = it->second.paddr + left_size,
.size = orig_size - left_size,
.tick = it->second.tick,
.perm = it->second.perm,
.is_resident = it->second.is_resident,
};
m_map_count++;
auto rit = m_mappings.insert_or_assign(it->first + left_size, right);
if (rit.first->second.is_resident) {
m_resident_map_count++;
m_resident_mappings.insert(*rit.first);
}
const auto it = m_mappings.find(SeparateHeapMap{
.vaddr = offset,
});
if (it == m_mappings.end() || it->vaddr == offset) {
// Not contained or no split required.
return;
}
// Cache the original values.
auto* const left = std::addressof(*it);
const size_t orig_size = left->size;
// Adjust the left map.
const size_t left_size = offset - left->vaddr;
left->size = left_size;
// Create the new right map.
auto* const right = new SeparateHeapMap{
.vaddr = left->vaddr + left_size,
.paddr = left->paddr + left_size,
.size = orig_size - left_size,
.tick = left->tick,
.perm = left->perm,
.is_resident = left->is_resident,
};
// Insert the new right map.
m_map_count++;
m_mappings.insert(*right);
// If resident, also insert into resident map.
if (right->is_resident) {
m_resident_map_count++;
m_resident_mappings.insert(*right);
}
}

76
src/common/heap_tracker.h
View file

@ -1,54 +1,82 @@
// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
// SPDX-License-Identifier: GPL-3.0-or-later
// SPDX-FileCopyrightText: Copyright 2023 yuzu Emulator Project
// SPDX-License-Identifier: GPL-2.0-or-later
#pragma once
#include <atomic>
#include <mutex>
#include <set>
#include <shared_mutex>
#include <boost/container/map.hpp>
#include "common/host_memory.h"
#include "common/intrusive_red_black_tree.h"
namespace Common {
struct SeparateHeapMap {
PAddr paddr{}; //8
std::size_t size{}; //8 (16)
std::size_t tick{}; //8 (24)
// 4 bits needed, sync with host_memory.h if needed
MemoryPermission perm : 4 = MemoryPermission::Read;
bool is_resident : 1 = false;
Common::IntrusiveRedBlackTreeNode addr_node{};
Common::IntrusiveRedBlackTreeNode tick_node{};
VAddr vaddr{};
PAddr paddr{};
size_t size{};
size_t tick{};
MemoryPermission perm{};
bool is_resident{};
};
struct SeparateHeapMapAddrComparator {
static constexpr int Compare(const SeparateHeapMap& lhs, const SeparateHeapMap& rhs) {
if (lhs.vaddr < rhs.vaddr) {
return -1;
} else if (lhs.vaddr <= (rhs.vaddr + rhs.size - 1)) {
return 0;
} else {
return 1;
}
}
};
struct SeparateHeapMapTickComparator {
static constexpr int Compare(const SeparateHeapMap& lhs, const SeparateHeapMap& rhs) {
if (lhs.tick < rhs.tick) {
return -1;
} else if (lhs.tick > rhs.tick) {
return 1;
} else {
return SeparateHeapMapAddrComparator::Compare(lhs, rhs);
}
}
};
static_assert(sizeof(SeparateHeapMap) == 32); //half a cache line! good for coherency
class HeapTracker {
public:
explicit HeapTracker(Common::HostMemory& buffer);
~HeapTracker();
void Map(size_t virtual_offset, size_t host_offset, size_t length, MemoryPermission perm, bool is_separate_heap);
~HeapTracker() = default;
void Map(size_t virtual_offset, size_t host_offset, size_t length, MemoryPermission perm,
bool is_separate_heap);
void Unmap(size_t virtual_offset, size_t size, bool is_separate_heap);
void Protect(size_t virtual_offset, size_t length, MemoryPermission perm);
inline u8* VirtualBasePointer() noexcept {
return m_buffer.VirtualBasePointer();
}
private:
// TODO: You may want to "fake-map" the first 2GB of 64-bit address space
// and dedicate it entirely to a recursive PTE mapping :)
// However Ankerl would be way better than using an RB tree, in all senses - but
// there is a strict requirement for ordering to be imposed accross the map itself
// which is not achievable with the unordered property.
using AddrTree = boost::container::map<VAddr, SeparateHeapMap>;
AddrTree m_mappings;
using TicksTree = boost::container::map<VAddr, SeparateHeapMap>;
TicksTree m_resident_mappings;
using AddrTreeTraits =
Common::IntrusiveRedBlackTreeMemberTraitsDeferredAssert<&SeparateHeapMap::addr_node>;
using AddrTree = AddrTreeTraits::TreeType<SeparateHeapMapAddrComparator>;
using TickTreeTraits =
Common::IntrusiveRedBlackTreeMemberTraitsDeferredAssert<&SeparateHeapMap::tick_node>;
using TickTree = TickTreeTraits::TreeType<SeparateHeapMapTickComparator>;
AddrTree m_mappings{};
TickTree m_resident_mappings{};
private:
void SplitHeapMap(VAddr offset, size_t size);
void SplitHeapMapLocked(VAddr offset);
void RebuildSeparateHeapAddressSpace();
inline HeapTracker::AddrTree::iterator GetNearestHeapMapLocked(VAddr offset) noexcept {
return m_mappings.find(offset);
}
private:
Common::HostMemory& m_buffer;
const s64 m_max_resident_map_count;

4
src/core/memory.cpp
View file

@ -60,7 +60,7 @@ struct Memory::Impl {
current_page_table->fastmem_arena = nullptr;
}
#ifdef __linux__
#ifdef __unix__
buffer.emplace(system.DeviceMemory().buffer);
#else
buffer = std::addressof(system.DeviceMemory().buffer);
@ -1023,7 +1023,7 @@ struct Memory::Impl {
std::span<Core::GPUDirtyMemoryManager> gpu_dirty_managers;
std::mutex sys_core_guard;
#ifdef __linux__
#ifdef __unix__
std::optional<Common::HeapTracker> buffer;
#else
Common::HostMemory* buffer{};