return ResultSessionClosed when a session is closed

- [x] I have read and followed the [Contribution Guidelines](https://git.eden-emu.dev/eden-emu/eden/src/branch/master/CONTRIBUTING.md#code-contributions).
- [x] I have read and followed the [AI Policy](https://git.eden-emu.dev/eden-emu/eden/src/branch/master/docs/policies/AI.md)
- [x] I have read and followed the [Coding Guidelines](https://git.eden-emu.dev/eden-emu/eden/src/branch/master/docs/policies/Coding.md) to the best of my ability.

-------------------
This one deserves a long story, but imma try to resume:

During investigating Absolum 1.2 black screen of death upon loading intro video, i've discovered guest was aborting for failing to allocate room for the video.

By logging everything prior to crash and decoding guest side instructions managed to confirm its media allocator was reading data faster than it was updating free available bucket list.

Since the IStorage::Read was happening 247 times before the crash, i've decided to add a very small sleep there, and boom, not only Absolum but some other titles got the same issue fixed.

But i was unsatisfied with the sleep and kept tracking guest instructions upstream in order to find a sync point for the read worker and the memory allocation update. But unfortunately the media allocator helpers live in guest, accessing memory directly via MMU, so any sync signaling would need to come from some dynarmic hack.

It's been 6 days now, so i've decided to polish the sleep: Moved it upstream to where i could have access for proper predicate, and added machinery to service and nvhost to support that. Now the sleep is restricted only for nvdec istorage reads. Any other reads will flow normally.

TL;DR: currently our code is so blazing async that guest is capable to request reads before its very self refresh it have freed room to do so. The sleep accepted as broadly stable was 600 us (MICROseconds), and it affects ONLY nvdec chunk reading.
Reports confirm that now videos are smoother now.

Code was polished at my knowledge limits.
Mostly machinery to track when a request comes from a process with nvdec active, and is istorage read.
I can provide more details if it comes to be needed.

Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/4316
Reviewed-by: MaranBr <maranbr@eden-emu.dev>
Reviewed-by: Samuel <lizzie@eden-emu.dev>

externals/bc_decoder/bc_decoder.h

@@ -1,23 +1,43 @@
 // SPDX-License-Identifier: MPL-2.0
-// Copyright 2022 Skyline Team and Contributors (https://github.com/skyline-emu/)
+// Copyright © 2022 Skyline Team and Contributors (https://github.com/skyline-emu/)
 
 #pragma once
 
 #include <cstdint>
 
 namespace bcn {
-    /// @brief Decodes a BC1 encoded image to R8G8B8A8
-    void DecodeBc1(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height, bool isSigned);
-    /// @brief Decodes a BC2 encoded image to R8G8B8A8
-    void DecodeBc2(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height, bool isSigned);
-    //// @brief Decodes a BC3 encoded image to R8G8B8A8
-    void DecodeBc3(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height, bool isSigned);
-    /// @brief Decodes a BC4 encoded image to R8
+    /**
+     * @brief Decodes a BC1 encoded image to R8G8B8A8
+     */
+    void DecodeBc1(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height);
+
+    /**
+     * @brief Decodes a BC2 encoded image to R8G8B8A8
+     */
+    void DecodeBc2(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height);
+
+    /**
+     * @brief Decodes a BC3 encoded image to R8G8B8A8
+     */
+    void DecodeBc3(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height);
+
+    /**
+     * @brief Decodes a BC4 encoded image to R8
+     */
     void DecodeBc4(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height, bool isSigned);
-    //// @brief Decodes a BC5 encoded image to R8G8
+
+    /**
+     * @brief Decodes a BC5 encoded image to R8G8
+     */
     void DecodeBc5(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height, bool isSigned);
-    //// @brief Decodes a BC6 encoded image to R16G16B16A16
+
+    /**
+     * @brief Decodes a BC6 encoded image to R16G16B16A16
+     */
     void DecodeBc6(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height, bool isSigned);
-    /// @brief Decodes a BC7 encoded image to R8G8B8A8
-    void DecodeBc7(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height, bool isSigned);
+
+    /**
+     * @brief Decodes a BC7 encoded image to R8G8B8A8
+     */
+    void DecodeBc7(const uint8_t *src, uint8_t *dst, size_t x, size_t y, size_t width, size_t height);
 }

src/core/core.cpp

@@ -4,6 +4,7 @@
 #include <array>
 #include <atomic>
 #include <memory>
+#include <unordered_map>
 #include <utility>
 
 #include "game_settings.h"
@@ -248,12 +249,30 @@ struct System::Impl {
         }
     }
 
-    void SetNVDECActive(bool is_nvdec_active) {
-        nvdec_active = is_nvdec_active;
+    void NotifyNVDECChannelOpen(u64 process_id) {
+        std::scoped_lock lock{nvdec_active_mutex};
+        ++nvdec_active_channels[process_id];
+    }
+
+    void NotifyNVDECChannelClose(u64 process_id) {
+        std::scoped_lock lock{nvdec_active_mutex};
+        const auto it = nvdec_active_channels.find(process_id);
+        if (it == nvdec_active_channels.end()) {
+            return;
+        }
+        if (--it->second == 0) {
+            nvdec_active_channels.erase(it);
+        }
     }
 
     bool GetNVDECActive() {
-        return nvdec_active;
+        std::scoped_lock lock{nvdec_active_mutex};
+        return !nvdec_active_channels.empty();
+    }
+
+    bool IsNVDECActiveForProcess(u64 process_id) {
+        std::scoped_lock lock{nvdec_active_mutex};
+        return nvdec_active_channels.contains(process_id);
     }
 
     void InitializeDebugger(System& system, u16 port) {
@@ -505,6 +524,8 @@ struct System::Impl {
 
     mutable std::mutex suspend_guard;
     std::mutex general_channel_mutex;
+    std::mutex nvdec_active_mutex;
+    std::unordered_map<u64, u32> nvdec_active_channels;
     std::atomic_bool is_paused{};
     std::atomic_bool is_shutting_down{};
     std::atomic_bool is_powered_on{};
@@ -512,7 +533,6 @@ struct System::Impl {
     bool extended_memory_layout : 1 = false;
     bool exit_locked : 1 = false;
     bool exit_requested : 1 = false;
-    bool nvdec_active : 1 = false;
 
     void EnsureGeneralChannelInitialized(System& system) {
         if (!general_channel_event) {
@@ -576,14 +596,22 @@ void System::UnstallApplication() {
     impl->UnstallApplication();
 }
 
-void System::SetNVDECActive(bool is_nvdec_active) {
-    impl->SetNVDECActive(is_nvdec_active);
+void System::NotifyNVDECChannelOpen(u64 process_id) {
+    impl->NotifyNVDECChannelOpen(process_id);
+}
+
+void System::NotifyNVDECChannelClose(u64 process_id) {
+    impl->NotifyNVDECChannelClose(process_id);
 }
 
 bool System::GetNVDECActive() {
     return impl->GetNVDECActive();
 }
 
+bool System::IsNVDECActiveForProcess(u64 process_id) {
+    return impl->IsNVDECActiveForProcess(process_id);
+}
+
 void System::InitializeDebugger() {
     impl->InitializeDebugger(*this, Settings::values.gdbstub_port.GetValue());
 }

src/core/core.h

@@ -191,8 +191,10 @@ public:
     std::unique_lock<std::mutex> StallApplication();
     void UnstallApplication();
 
-    void SetNVDECActive(bool is_nvdec_active);
+    void NotifyNVDECChannelOpen(u64 process_id);
+    void NotifyNVDECChannelClose(u64 process_id);
     [[nodiscard]] bool GetNVDECActive();
+    [[nodiscard]] bool IsNVDECActiveForProcess(u64 process_id);
 
     /**
      * Initialize the debugger.

src/core/hle/kernel/k_server_session.cpp

@@ -1216,7 +1216,7 @@ Result KServerSession::ReceiveRequest(KernelCore& kernel, uintptr_t server_messa
 }
 
 Result KServerSession::SendReply(KernelCore& kernel, uintptr_t server_message, uintptr_t server_buffer_size,
-                                 KPhysicalAddress server_message_paddr, bool is_hle) {
+                                 KPhysicalAddress server_message_paddr, bool is_hle, bool session_closed) {
     // Lock the session.
     KScopedLightLock lk{m_lock};
 
@@ -1248,7 +1248,7 @@ Result KServerSession::SendReply(KernelCore& kernel, uintptr_t server_message, u
     KEvent* event = request->GetEvent();
 
     // Check whether we're closed.
-    const bool closed = (client_thread == nullptr || m_parent->IsClientClosed());
+    const bool closed = (client_thread == nullptr || m_parent->IsClientClosed() || session_closed);
 
     Result result = ResultSuccess;
     if (!closed) {

src/core/hle/kernel/k_server_session.h

@@ -54,14 +54,14 @@ public:
 
     Result OnRequest(KernelCore& kernel, KSessionRequest* request);
     Result SendReply(KernelCore& kernel, uintptr_t server_message, uintptr_t server_buffer_size,
-                     KPhysicalAddress server_message_paddr, bool is_hle = false);
+                     KPhysicalAddress server_message_paddr, bool is_hle = false, bool session_closed = false);
     Result ReceiveRequest(KernelCore& kernel, uintptr_t server_message, uintptr_t server_buffer_size,
                           KPhysicalAddress server_message_paddr,
                           std::shared_ptr<Service::HLERequestContext>* out_context = nullptr,
                           std::weak_ptr<Service::SessionRequestManager> manager = {});
 
-    Result SendReplyHLE(KernelCore& kernel) {
-        R_RETURN(this->SendReply(kernel, 0, 0, 0, true));
+    Result SendReplyHLE(KernelCore& kernel, bool session_closed = false) {
+        R_RETURN(this->SendReply(kernel, 0, 0, 0, true, session_closed));
     }
 
     Result ReceiveRequestHLE(KernelCore& kernel, std::shared_ptr<Service::HLERequestContext>* out_context,

src/core/hle/service/nvdrv/devices/nvhost_nvdec.cpp

@@ -8,6 +8,7 @@
 #include "common/assert.h"
 #include "common/logging.h"
 #include "core/core.h"
+#include "core/hle/kernel/k_process.h"
 #include "core/hle/service/nvdrv/core/container.h"
 #include "core/hle/service/nvdrv/devices/ioctl_serialization.h"
 #include "core/hle/service/nvdrv/devices/nvhost_nvdec.h"
@@ -71,17 +72,23 @@ NvResult nvhost_nvdec::Ioctl3(DeviceFD fd, Ioctl command, std::span<const u8> in
 
 void nvhost_nvdec::OnOpen(NvCore::SessionId session_id, DeviceFD fd) {
     LOG_INFO(Service_NVDRV, "NVDEC video stream started");
-    system.SetNVDECActive(true);
     sessions[fd] = session_id;
+    if (const auto* session = core.GetSession(session_id);
+        session != nullptr && session->process != nullptr) {
+        system.NotifyNVDECChannelOpen(session->process->GetId());
+    }
     host1x.StartDevice(fd, Tegra::Host1x::ChannelType::NvDec, channel_syncpoint);
 }
 
 void nvhost_nvdec::OnClose(DeviceFD fd) {
     LOG_INFO(Service_NVDRV, "NVDEC video stream ended");
     host1x.StopDevice(fd, Tegra::Host1x::ChannelType::NvDec);
-    system.SetNVDECActive(false);
     auto it = sessions.find(fd);
     if (it != sessions.end()) {
+        if (const auto* session = core.GetSession(it->second);
+            session != nullptr && session->process != nullptr) {
+            system.NotifyNVDECChannelClose(session->process->GetId());
+        }
         sessions.erase(it);
     }
 }

src/core/hle/service/server_manager.cpp

@@ -393,7 +393,7 @@ Result ServerManager::CompleteSyncRequest(Session* session) {
     }
 
     // Send the reply.
-    res = server_session->SendReplyHLE(m_system.Kernel());
+    res = server_session->SendReplyHLE(m_system.Kernel(), service_res == IPC::ResultSessionClosed);
 
     // If the session has been closed, we're done.
     if (res == Kernel::ResultSessionClosed || service_res == IPC::ResultSessionClosed) {

src/core/hle/service/service.cpp

@@ -4,12 +4,16 @@
 // SPDX-FileCopyrightText: Copyright 2018 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include <chrono>
 #include <fmt/ranges.h>
+#include <string_view>
+#include <thread>
 #include "common/assert.h"
 #include "common/logging.h"
 #include "common/settings.h"
 #include "core/core.h"
 #include "core/hle/ipc.h"
+#include "core/hle/kernel/k_process.h"
 #include "core/hle/kernel/kernel.h"
 #include "core/hle/service/ipc_helpers.h"
 #include "core/hle/service/service.h"
@@ -33,6 +37,7 @@ ServiceFrameworkBase::ServiceFrameworkBase(Core::System& system_, const char* se
     : SessionRequestHandler(system_.Kernel(), service_name_)
     , system{system_}
     , service_name{service_name_}
+    , is_i_storage{std::string_view{service_name_} == "IStorage"}
     , handler_invoker{handler_invoker_}
     , max_sessions{max_sessions_}
 {}
@@ -77,13 +82,22 @@ void ServiceFrameworkBase::ReportUnimplementedFunction(HLERequestContext& ctx,
 }
 
 void ServiceFrameworkBase::InvokeRequest(HLERequestContext& ctx) {
-    auto it = handlers.find(ctx.GetCommand());
+    const auto command = ctx.GetCommand();
+    auto it = handlers.find(command);
+    const bool is_cmd_read = command == 0;
     FunctionInfoBase const* info = it == handlers.end() ? nullptr : &it->second;
     if (info == nullptr || info->handler_callback == nullptr)
         return ReportUnimplementedFunction(ctx, info);
 
     LOG_TRACE(Service, "{}", MakeFunctionString(info->name, GetServiceName(), ctx.CommandBuffer()));
     handler_invoker(this, info->handler_callback, ctx);
+
+    if (is_i_storage && is_cmd_read) {
+        const auto* const process = ctx.GetThread().GetOwnerProcess();
+        if (process != nullptr && system.IsNVDECActiveForProcess(process->GetId())) {
+            std::this_thread::sleep_for(std::chrono::microseconds{600});
+        }
+    }
 }
 
 void ServiceFrameworkBase::InvokeRequestTipc(HLERequestContext& ctx) {

src/core/hle/service/service.h

@@ -107,6 +107,8 @@ protected:
     Core::System& system;
     /// Identifier string used to connect to the service.
     const char* service_name;
+    /// Whether this is the IStorage service.
+    const bool is_i_storage;
     /// Function used to safely up-cast pointers to the derived class before invoking a handler.
     InvokerFn* handler_invoker;
     /// Maximum number of concurrent sessions that this service can handle.

src/video_core/texture_cache/decode_bc.cpp

@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
@@ -9,7 +9,6 @@
 #include <span>
 #include <bc_decoder.h>
 
-#include "common/assert.h"
 #include "common/common_types.h"
 #include "video_core/texture_cache/decode_bc.h"
 
@@ -23,8 +22,11 @@ using VideoCore::Surface::PixelFormat;
 constexpr bool IsSigned(PixelFormat pixel_format) {
     switch (pixel_format) {
     case PixelFormat::BC4_SNORM:
+    case PixelFormat::BC4_UNORM:
     case PixelFormat::BC5_SNORM:
+    case PixelFormat::BC5_UNORM:
     case PixelFormat::BC6H_SFLOAT:
+    case PixelFormat::BC6H_UFLOAT:
         return true;
     default:
         return false;
@@ -60,28 +62,9 @@ u32 ConvertedBytesPerBlock(VideoCore::Surface::PixelFormat pixel_format) {
     }
 }
 
-void DecompressBCn(std::span<const u8> input, std::span<u8> output, BufferImageCopy& copy, VideoCore::Surface::PixelFormat pixel_format) {
-    auto const f = [pixel_format]{
-        switch (pixel_format) {
-        case PixelFormat::BC1_RGBA_UNORM:
-        case PixelFormat::BC1_RGBA_SRGB: return &bcn::DecodeBc1;
-        case PixelFormat::BC2_UNORM:
-        case PixelFormat::BC2_SRGB: return &bcn::DecodeBc2;
-        case PixelFormat::BC3_UNORM:
-        case PixelFormat::BC3_SRGB: return &bcn::DecodeBc3;
-        case PixelFormat::BC4_SNORM:
-        case PixelFormat::BC4_UNORM: return &bcn::DecodeBc4;
-        case PixelFormat::BC5_SNORM:
-        case PixelFormat::BC5_UNORM: return &bcn::DecodeBc5;
-        case PixelFormat::BC6H_SFLOAT:
-        case PixelFormat::BC6H_UFLOAT: return &bcn::DecodeBc6;
-        case PixelFormat::BC7_SRGB:
-        case PixelFormat::BC7_UNORM: return &bcn::DecodeBc7;
-        default:
-            UNREACHABLE_MSG("Unimplemented BCn decompression {}", pixel_format);
-            return &bcn::DecodeBc1;
-        }
-    }();
+template <auto decompress, PixelFormat pixel_format>
+void DecompressBlocks(std::span<const u8> input, std::span<u8> output, BufferImageCopy& copy,
+                      bool is_signed = false) {
     const u32 out_bpp = ConvertedBytesPerBlock(pixel_format);
     const u32 block_size = BlockSize(pixel_format);
     const u32 width = copy.image_extent.width;
@@ -99,7 +82,11 @@ void DecompressBCn(std::span<const u8> input, std::span<u8> output, BufferImageC
             for (u32 x = 0; x < width; x += block_width) {
                 const u8* src = input.data() + src_offset;
                 u8* const dst = output.data() + dst_offset;
-                f(src, dst, x, y, width, height, IsSigned(pixel_format));
+                if constexpr (IsSigned(pixel_format)) {
+                    decompress(src, dst, x, y, width, height, is_signed);
+                } else {
+                    decompress(src, dst, x, y, width, height);
+                }
                 src_offset += block_size;
                 dst_offset += block_width * out_bpp;
             }
@@ -109,4 +96,43 @@ void DecompressBCn(std::span<const u8> input, std::span<u8> output, BufferImageC
     }
 }
 
+void DecompressBCn(std::span<const u8> input, std::span<u8> output, BufferImageCopy& copy,
+                   VideoCore::Surface::PixelFormat pixel_format) {
+    switch (pixel_format) {
+    case PixelFormat::BC1_RGBA_UNORM:
+    case PixelFormat::BC1_RGBA_SRGB:
+        DecompressBlocks<bcn::DecodeBc1, PixelFormat::BC1_RGBA_UNORM>(input, output, copy);
+        break;
+    case PixelFormat::BC2_UNORM:
+    case PixelFormat::BC2_SRGB:
+        DecompressBlocks<bcn::DecodeBc2, PixelFormat::BC2_UNORM>(input, output, copy);
+        break;
+    case PixelFormat::BC3_UNORM:
+    case PixelFormat::BC3_SRGB:
+        DecompressBlocks<bcn::DecodeBc3, PixelFormat::BC3_UNORM>(input, output, copy);
+        break;
+    case PixelFormat::BC4_SNORM:
+    case PixelFormat::BC4_UNORM:
+        DecompressBlocks<bcn::DecodeBc4, PixelFormat::BC4_UNORM>(
+            input, output, copy, pixel_format == PixelFormat::BC4_SNORM);
+        break;
+    case PixelFormat::BC5_SNORM:
+    case PixelFormat::BC5_UNORM:
+        DecompressBlocks<bcn::DecodeBc5, PixelFormat::BC5_UNORM>(
+            input, output, copy, pixel_format == PixelFormat::BC5_SNORM);
+        break;
+    case PixelFormat::BC6H_SFLOAT:
+    case PixelFormat::BC6H_UFLOAT:
+        DecompressBlocks<bcn::DecodeBc6, PixelFormat::BC6H_UFLOAT>(
+            input, output, copy, pixel_format == PixelFormat::BC6H_SFLOAT);
+        break;
+    case PixelFormat::BC7_SRGB:
+    case PixelFormat::BC7_UNORM:
+        DecompressBlocks<bcn::DecodeBc7, PixelFormat::BC7_UNORM>(input, output, copy);
+        break;
+    default:
+        LOG_WARNING(HW_GPU, "Unimplemented BCn decompression {}", pixel_format);
+    }
+}
+
 } // namespace VideoCommon

src/video_core/texture_cache/util.cpp

@@ -1,4 +1,4 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-FileCopyrightText: Copyright 2025 Eden Emulator Project
 // SPDX-License-Identifier: GPL-3.0-or-later
 
 // SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
@@ -922,7 +922,8 @@ boost::container::small_vector<BufferImageCopy, 16> UnswizzleImage(Tegra::Memory
     return copies;
 }
 
-void ConvertImage(std::span<const u8> input, const ImageInfo& info, std::span<u8> output, std::span<BufferImageCopy> copies) {
+void ConvertImage(std::span<const u8> input, const ImageInfo& info, std::span<u8> output,
+                  std::span<BufferImageCopy> copies) {
     u32 output_offset = 0;
     Common::ScratchBuffer<u8> decode_scratch;
 
@@ -954,10 +955,10 @@ void ConvertImage(std::span<const u8> input, const ImageInfo& info, std::span<u8
         } else if (astc) {
             // BC1 uses 0.5 bytes per texel
             // BC3 uses 1 byte per texel
-            auto const compress = recompression_setting == Settings::AstcRecompression::Bc1
-                ? Tegra::Texture::BCN::CompressBC1
-                : Tegra::Texture::BCN::CompressBC3;
-            const auto bpp_div = compress == Tegra::Texture::BCN::CompressBC1 ? 2 : 1;
+            const auto compress = recompression_setting == Settings::AstcRecompression::Bc1
+                                      ? Tegra::Texture::BCN::CompressBC1
+                                      : Tegra::Texture::BCN::CompressBC3;
+            const auto bpp_div = recompression_setting == Settings::AstcRecompression::Bc1 ? 2 : 1;
 
             const u32 plane_dim = copy.image_extent.width * copy.image_extent.height;
             const u32 level_size = plane_dim * copy.image_extent.depth *
@@ -974,12 +975,18 @@ void ConvertImage(std::span<const u8> input, const ImageInfo& info, std::span<u8
                      copy.image_subresource.num_layers * copy.image_extent.depth,
                      output.subspan(output_offset));
 
-            const u32 aligned_plane_dim = Common::AlignUp(copy.image_extent.width, 4) * Common::AlignUp(copy.image_extent.height, 4);
-            copy.buffer_size = (aligned_plane_dim * copy.image_extent.depth * copy.image_subresource.num_layers) / bpp_div;
-            output_offset += u32(copy.buffer_size);
+            const u32 aligned_plane_dim = Common::AlignUp(copy.image_extent.width, 4) *
+                                          Common::AlignUp(copy.image_extent.height, 4);
+
+            copy.buffer_size =
+                (aligned_plane_dim * copy.image_extent.depth * copy.image_subresource.num_layers) /
+                bpp_div;
+            output_offset += static_cast<u32>(copy.buffer_size);
         } else {
             DecompressBCn(input_offset, output.subspan(output_offset), copy, info.format);
-            output_offset += copy.image_extent.width * copy.image_extent.height * copy.image_subresource.num_layers * ConvertedBytesPerBlock(info.format);
+            output_offset += copy.image_extent.width * copy.image_extent.height *
+                             copy.image_subresource.num_layers *
+                             ConvertedBytesPerBlock(info.format);
         }
 
         copy.buffer_row_length = mip_size.width;