[core] use memcpy instead of hand rolling aligned cases
Hand rolling memcpy like this is always frowned upon because the compiler has more insight on whats going on (plus the code resolves to a worse version of itself on assembly). This removes some branches that are just straight up redundant. May save stuff especially for systems without fastmem enabled. Signed-off-by: lizzie <lizzie@eden-emu.dev>
This commit is contained in:
parent
83730cd4c1
commit
bc032f65a5
1 changed files with 36 additions and 167 deletions
|
@ -10,6 +10,7 @@
|
||||||
#include <mutex>
|
#include <mutex>
|
||||||
#include <span>
|
#include <span>
|
||||||
#include <thread>
|
#include <thread>
|
||||||
|
#include <type_traits>
|
||||||
#include <vector>
|
#include <vector>
|
||||||
|
|
||||||
#include "common/assert.h"
|
#include "common/assert.h"
|
||||||
|
@ -681,22 +682,17 @@ struct Memory::Impl {
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
[[nodiscard]] u8* GetPointerImpl(u64 vaddr, auto on_unmapped, auto on_rasterizer) const {
|
template<typename F, typename G>
|
||||||
|
[[nodiscard]] u8* GetPointerImpl(u64 vaddr, F&& on_unmapped, G&& on_rasterizer) const {
|
||||||
// AARCH64 masks the upper 16 bit of all memory accesses
|
// AARCH64 masks the upper 16 bit of all memory accesses
|
||||||
vaddr = vaddr & 0xffffffffffffULL;
|
vaddr &= 0xffffffffffffULL;
|
||||||
if (!AddressSpaceContains(*current_page_table, vaddr, 1)) [[unlikely]] {
|
if (AddressSpaceContains(*current_page_table, vaddr, 1)) [[likely]] {
|
||||||
on_unmapped();
|
|
||||||
return nullptr;
|
|
||||||
} else {
|
|
||||||
// Avoid adding any extra logic to this fast-path block
|
// Avoid adding any extra logic to this fast-path block
|
||||||
const uintptr_t raw_pointer = current_page_table->pointers[vaddr >> YUZU_PAGEBITS].Raw();
|
const uintptr_t raw_pointer = current_page_table->pointers[vaddr >> YUZU_PAGEBITS].Raw();
|
||||||
if (const uintptr_t pointer = Common::PageTable::PageInfo::ExtractPointer(raw_pointer)) {
|
if (const uintptr_t pointer = Common::PageTable::PageInfo::ExtractPointer(raw_pointer)) [[likely]] {
|
||||||
return reinterpret_cast<u8*>(pointer + vaddr);
|
return reinterpret_cast<u8*>(pointer + vaddr);
|
||||||
} else {
|
} else {
|
||||||
switch (Common::PageTable::PageInfo::ExtractType(raw_pointer)) {
|
switch (Common::PageTable::PageInfo::ExtractType(raw_pointer)) {
|
||||||
case Common::PageType::Unmapped:
|
|
||||||
on_unmapped();
|
|
||||||
return nullptr;
|
|
||||||
case Common::PageType::Memory:
|
case Common::PageType::Memory:
|
||||||
ASSERT_MSG(false, "Mapped memory page without a pointer @ 0x{:016X}", vaddr);
|
ASSERT_MSG(false, "Mapped memory page without a pointer @ 0x{:016X}", vaddr);
|
||||||
return nullptr;
|
return nullptr;
|
||||||
|
@ -707,11 +703,18 @@ struct Memory::Impl {
|
||||||
on_rasterizer();
|
on_rasterizer();
|
||||||
return host_ptr;
|
return host_ptr;
|
||||||
}
|
}
|
||||||
|
case Common::PageType::Unmapped: [[unlikely]] {
|
||||||
|
on_unmapped();
|
||||||
|
return nullptr;
|
||||||
|
}
|
||||||
default:
|
default:
|
||||||
UNREACHABLE();
|
UNREACHABLE();
|
||||||
}
|
}
|
||||||
return nullptr;
|
return nullptr;
|
||||||
}
|
}
|
||||||
|
} else {
|
||||||
|
on_unmapped();
|
||||||
|
return nullptr;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -729,172 +732,38 @@ struct Memory::Impl {
|
||||||
GetInteger(vaddr), []() {}, []() {});
|
GetInteger(vaddr), []() {}, []() {});
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/// @brief Reads a particular data type out of memory at the given virtual address.
|
||||||
* Reads a particular data type out of memory at the given virtual address.
|
/// @param vaddr The virtual address to read the data type from.
|
||||||
*
|
/// @tparam T The data type to read out of memory.
|
||||||
* @param vaddr The virtual address to read the data type from.
|
/// @returns The instance of T read from the specified virtual address.
|
||||||
*
|
|
||||||
* @tparam T The data type to read out of memory. This type *must* be
|
|
||||||
* trivially copyable, otherwise the behavior of this function
|
|
||||||
* is undefined.
|
|
||||||
*
|
|
||||||
* @returns The instance of T read from the specified virtual address.
|
|
||||||
*/
|
|
||||||
template <typename T>
|
template <typename T>
|
||||||
T Read(Common::ProcessAddress vaddr) {
|
inline T Read(Common::ProcessAddress vaddr) requires(std::is_trivially_copyable_v<T>) noexcept {
|
||||||
// Fast path for aligned reads of common sizes
|
|
||||||
const u64 addr = GetInteger(vaddr);
|
const u64 addr = GetInteger(vaddr);
|
||||||
if constexpr (std::is_same_v<T, u8> || std::is_same_v<T, s8>) {
|
if (auto const ptr = GetPointerImpl(addr, [addr]() {
|
||||||
// 8-bit reads are always aligned
|
LOG_ERROR(HW_Memory, "Unmapped Read{} @ 0x{:016X}", sizeof(T) * 8, addr);
|
||||||
const u8* const ptr = GetPointerImpl(
|
}, [&]() {
|
||||||
addr,
|
HandleRasterizerDownload(addr, sizeof(T));
|
||||||
[addr]() {
|
}); ptr) [[likely]] {
|
||||||
LOG_ERROR(HW_Memory, "Unmapped Read8 @ 0x{:016X}", addr);
|
// It may be tempting to rewrite this particular section to use "reinterpret_cast";
|
||||||
},
|
// afterall, it's trivially copyable so surely it can be copied ov- Alignment.
|
||||||
[&]() { HandleRasterizerDownload(addr, sizeof(T)); });
|
// Remember, alignment. memcpy() will deal with all the alignment extremely fast.
|
||||||
if (ptr) {
|
T result{};
|
||||||
return static_cast<T>(*ptr);
|
|
||||||
}
|
|
||||||
return 0;
|
|
||||||
} else if constexpr (std::is_same_v<T, u16_le> || std::is_same_v<T, s16_le>) {
|
|
||||||
// Check alignment for 16-bit reads
|
|
||||||
if ((addr & 1) == 0) {
|
|
||||||
const u8* const ptr = GetPointerImpl(
|
|
||||||
addr,
|
|
||||||
[addr]() {
|
|
||||||
LOG_ERROR(HW_Memory, "Unmapped Read16 @ 0x{:016X}", addr);
|
|
||||||
},
|
|
||||||
[&]() { HandleRasterizerDownload(addr, sizeof(T)); });
|
|
||||||
if (ptr) {
|
|
||||||
return static_cast<T>(*reinterpret_cast<const u16*>(ptr));
|
|
||||||
}
|
|
||||||
}
|
|
||||||
} else if constexpr (std::is_same_v<T, u32_le> || std::is_same_v<T, s32_le>) {
|
|
||||||
// Check alignment for 32-bit reads
|
|
||||||
if ((addr & 3) == 0) {
|
|
||||||
const u8* const ptr = GetPointerImpl(
|
|
||||||
addr,
|
|
||||||
[addr]() {
|
|
||||||
LOG_ERROR(HW_Memory, "Unmapped Read32 @ 0x{:016X}", addr);
|
|
||||||
},
|
|
||||||
[&]() { HandleRasterizerDownload(addr, sizeof(T)); });
|
|
||||||
if (ptr) {
|
|
||||||
return static_cast<T>(*reinterpret_cast<const u32*>(ptr));
|
|
||||||
}
|
|
||||||
}
|
|
||||||
} else if constexpr (std::is_same_v<T, u64_le> || std::is_same_v<T, s64_le>) {
|
|
||||||
// Check alignment for 64-bit reads
|
|
||||||
if ((addr & 7) == 0) {
|
|
||||||
const u8* const ptr = GetPointerImpl(
|
|
||||||
addr,
|
|
||||||
[addr]() {
|
|
||||||
LOG_ERROR(HW_Memory, "Unmapped Read64 @ 0x{:016X}", addr);
|
|
||||||
},
|
|
||||||
[&]() { HandleRasterizerDownload(addr, sizeof(T)); });
|
|
||||||
if (ptr) {
|
|
||||||
return static_cast<T>(*reinterpret_cast<const u64*>(ptr));
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// Fall back to the general case for other types or unaligned access
|
|
||||||
T result = 0;
|
|
||||||
const u8* const ptr = GetPointerImpl(
|
|
||||||
addr,
|
|
||||||
[addr]() {
|
|
||||||
LOG_ERROR(HW_Memory, "Unmapped Read{} @ 0x{:016X}", sizeof(T) * 8, addr);
|
|
||||||
},
|
|
||||||
[&]() { HandleRasterizerDownload(addr, sizeof(T)); });
|
|
||||||
if (ptr) {
|
|
||||||
std::memcpy(&result, ptr, sizeof(T));
|
std::memcpy(&result, ptr, sizeof(T));
|
||||||
|
return result;
|
||||||
}
|
}
|
||||||
return result;
|
return T{};
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/// @brief Writes a particular data type to memory at the given virtual address.
|
||||||
* Writes a particular data type to memory at the given virtual address.
|
/// @param vaddr The virtual address to write the data type to.
|
||||||
*
|
/// @tparam T The data type to write to memory.
|
||||||
* @param vaddr The virtual address to write the data type to.
|
|
||||||
*
|
|
||||||
* @tparam T The data type to write to memory. This type *must* be
|
|
||||||
* trivially copyable, otherwise the behavior of this function
|
|
||||||
* is undefined.
|
|
||||||
*/
|
|
||||||
template <typename T>
|
template <typename T>
|
||||||
void Write(Common::ProcessAddress vaddr, const T data) {
|
inline void Write(Common::ProcessAddress vaddr, const T data) requires(std::is_trivially_copyable_v<T>) noexcept {
|
||||||
// Fast path for aligned writes of common sizes
|
|
||||||
const u64 addr = GetInteger(vaddr);
|
const u64 addr = GetInteger(vaddr);
|
||||||
if constexpr (std::is_same_v<T, u8> || std::is_same_v<T, s8>) {
|
if (auto const ptr = GetPointerImpl(addr, [addr, data]() {
|
||||||
// 8-bit writes are always aligned
|
LOG_ERROR(HW_Memory, "Unmapped Write{} @ 0x{:016X} = 0x{:016X}", sizeof(T) * 8, addr, u64(data));
|
||||||
u8* const ptr = GetPointerImpl(
|
}, [&]() { HandleRasterizerWrite(addr, sizeof(T)); }); ptr) [[likely]]
|
||||||
addr,
|
|
||||||
[addr, data]() {
|
|
||||||
LOG_ERROR(HW_Memory, "Unmapped Write8 @ 0x{:016X} = 0x{:02X}", addr,
|
|
||||||
static_cast<u8>(data));
|
|
||||||
},
|
|
||||||
[&]() { HandleRasterizerWrite(addr, sizeof(T)); });
|
|
||||||
if (ptr) {
|
|
||||||
*ptr = static_cast<u8>(data);
|
|
||||||
}
|
|
||||||
return;
|
|
||||||
} else if constexpr (std::is_same_v<T, u16_le> || std::is_same_v<T, s16_le>) {
|
|
||||||
// Check alignment for 16-bit writes
|
|
||||||
if ((addr & 1) == 0) {
|
|
||||||
u8* const ptr = GetPointerImpl(
|
|
||||||
addr,
|
|
||||||
[addr, data]() {
|
|
||||||
LOG_ERROR(HW_Memory, "Unmapped Write16 @ 0x{:016X} = 0x{:04X}", addr,
|
|
||||||
static_cast<u16>(data));
|
|
||||||
},
|
|
||||||
[&]() { HandleRasterizerWrite(addr, sizeof(T)); });
|
|
||||||
if (ptr) {
|
|
||||||
*reinterpret_cast<u16*>(ptr) = static_cast<u16>(data);
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
} else if constexpr (std::is_same_v<T, u32_le> || std::is_same_v<T, s32_le>) {
|
|
||||||
// Check alignment for 32-bit writes
|
|
||||||
if ((addr & 3) == 0) {
|
|
||||||
u8* const ptr = GetPointerImpl(
|
|
||||||
addr,
|
|
||||||
[addr, data]() {
|
|
||||||
LOG_ERROR(HW_Memory, "Unmapped Write32 @ 0x{:016X} = 0x{:08X}", addr,
|
|
||||||
static_cast<u32>(data));
|
|
||||||
},
|
|
||||||
[&]() { HandleRasterizerWrite(addr, sizeof(T)); });
|
|
||||||
if (ptr) {
|
|
||||||
*reinterpret_cast<u32*>(ptr) = static_cast<u32>(data);
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
} else if constexpr (std::is_same_v<T, u64_le> || std::is_same_v<T, s64_le>) {
|
|
||||||
// Check alignment for 64-bit writes
|
|
||||||
if ((addr & 7) == 0) {
|
|
||||||
u8* const ptr = GetPointerImpl(
|
|
||||||
addr,
|
|
||||||
[addr, data]() {
|
|
||||||
LOG_ERROR(HW_Memory, "Unmapped Write64 @ 0x{:016X} = 0x{:016X}", addr,
|
|
||||||
static_cast<u64>(data));
|
|
||||||
},
|
|
||||||
[&]() { HandleRasterizerWrite(addr, sizeof(T)); });
|
|
||||||
if (ptr) {
|
|
||||||
*reinterpret_cast<u64*>(ptr) = static_cast<u64>(data);
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
// Fall back to the general case for other types or unaligned access
|
|
||||||
u8* const ptr = GetPointerImpl(
|
|
||||||
addr,
|
|
||||||
[addr, data]() {
|
|
||||||
LOG_ERROR(HW_Memory, "Unmapped Write{} @ 0x{:016X} = 0x{:016X}", sizeof(T) * 8,
|
|
||||||
addr, static_cast<u64>(data));
|
|
||||||
},
|
|
||||||
[&]() { HandleRasterizerWrite(addr, sizeof(T)); });
|
|
||||||
if (ptr) {
|
|
||||||
std::memcpy(ptr, &data, sizeof(T));
|
std::memcpy(ptr, &data, sizeof(T));
|
||||||
}
|
|
||||||
}
|
}
|
||||||
|
|
||||||
template <typename T>
|
template <typename T>
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue