5 files changed, 186 insertions, 49 deletions

diff --git a/src/video_core/vulkan_common/vulkan_device.cpp b/src/video_core/vulkan_common/vulkan_device.cpp
index 631d5e378..541f0c1da 100644
--- a/src/video_core/vulkan_common/vulkan_device.cpp
+++ b/src/video_core/vulkan_common/vulkan_device.cpp
@@ -603,6 +603,7 @@ Device::Device(VkInstance instance_, vk::PhysicalDevice physical_, VkSurfaceKHR
     };
 
     const VmaAllocatorCreateInfo allocator_info = {
+        .flags = VMA_ALLOCATOR_CREATE_EXTERNALLY_SYNCHRONIZED_BIT,
         .physicalDevice = physical,
         .device = *logical,
         .pVulkanFunctions = &functions,
diff --git a/src/video_core/vulkan_common/vulkan_memory_allocator.cpp b/src/video_core/vulkan_common/vulkan_memory_allocator.cpp
index 7f860cccd..d2e1ef58e 100644
--- a/src/video_core/vulkan_common/vulkan_memory_allocator.cpp
+++ b/src/video_core/vulkan_common/vulkan_memory_allocator.cpp
@@ -51,11 +51,59 @@ struct Range {
     case MemoryUsage::Download:
         return VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT |
                VK_MEMORY_PROPERTY_HOST_CACHED_BIT;
+    case MemoryUsage::Stream:
+        return VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT | VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT |
+               VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
     }
     ASSERT_MSG(false, "Invalid memory usage={}", usage);
     return VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
 }
 
+[[nodiscard]] VkMemoryPropertyFlags MemoryUsageRequiredVmaFlags(MemoryUsage usage) {
+    switch (usage) {
+    case MemoryUsage::DeviceLocal:
+        return VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT;
+    case MemoryUsage::Upload:
+    case MemoryUsage::Stream:
+        return VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT;
+    case MemoryUsage::Download:
+        return VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_CACHED_BIT;
+    }
+    ASSERT_MSG(false, "Invalid memory usage={}", usage);
+    return {};
+}
+
+[[nodiscard]] VkMemoryPropertyFlags MemoryUsagePreferedVmaFlags(MemoryUsage usage) {
+    return usage != MemoryUsage::DeviceLocal ? VK_MEMORY_PROPERTY_HOST_COHERENT_BIT
+                                             : VkMemoryPropertyFlags{};
+}
+
+[[nodiscard]] VmaAllocationCreateFlags MemoryUsageVmaFlags(MemoryUsage usage) {
+    switch (usage) {
+    case MemoryUsage::Upload:
+    case MemoryUsage::Stream:
+        return VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT;
+    case MemoryUsage::Download:
+        return VMA_ALLOCATION_CREATE_HOST_ACCESS_RANDOM_BIT;
+    case MemoryUsage::DeviceLocal:
+        return VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT |
+               VMA_ALLOCATION_CREATE_HOST_ACCESS_ALLOW_TRANSFER_INSTEAD_BIT;
+    }
+    return {};
+}
+
+[[nodiscard]] VmaMemoryUsage MemoryUsageVma(MemoryUsage usage) {
+    switch (usage) {
+    case MemoryUsage::DeviceLocal:
+    case MemoryUsage::Stream:
+        return VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
+    case MemoryUsage::Upload:
+    case MemoryUsage::Download:
+        return VMA_MEMORY_USAGE_AUTO_PREFER_HOST;
+    }
+    return VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
+}
+
 } // Anonymous namespace
 
 class MemoryAllocation {
@@ -178,17 +226,18 @@ void MemoryCommit::Release() {
 }
 
 MemoryAllocator::MemoryAllocator(const Device& device_)
-    : device{device_}, properties{device_.GetPhysical().GetMemoryProperties().memoryProperties},
+    : device{device_}, allocator{device.GetAllocator()},
+      properties{device_.GetPhysical().GetMemoryProperties().memoryProperties},
       buffer_image_granularity{
           device_.GetPhysical().GetProperties().limits.bufferImageGranularity} {}
 
 MemoryAllocator::~MemoryAllocator() = default;
 
 vk::Image MemoryAllocator::CreateImage(const VkImageCreateInfo& ci) const {
-    const VmaAllocationCreateInfo alloc_info = {
+    const VmaAllocationCreateInfo alloc_ci = {
         .flags = VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT,
         .usage = VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE,
-        .requiredFlags = 0,
+        .requiredFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT,
         .preferredFlags = 0,
         .pool = VK_NULL_HANDLE,
         .pUserData = nullptr,
@@ -196,12 +245,40 @@ vk::Image MemoryAllocator::CreateImage(const VkImageCreateInfo& ci) const {
 
     VkImage handle{};
     VmaAllocation allocation{};
-    vk::Check(
-        vmaCreateImage(device.GetAllocator(), &ci, &alloc_info, &handle, &allocation, nullptr));
-    return vk::Image(handle, *device.GetLogical(), device.GetAllocator(), allocation,
+
+    vk::Check(vmaCreateImage(allocator, &ci, &alloc_ci, &handle, &allocation, nullptr));
+
+    return vk::Image(handle, *device.GetLogical(), allocator, allocation,
                      device.GetDispatchLoader());
 }
 
+vk::Buffer MemoryAllocator::CreateBuffer(const VkBufferCreateInfo& ci, MemoryUsage usage) const {
+    const VmaAllocationCreateInfo alloc_ci = {
+        .flags = VMA_ALLOCATION_CREATE_WITHIN_BUDGET_BIT | VMA_ALLOCATION_CREATE_MAPPED_BIT |
+                 MemoryUsageVmaFlags(usage),
+        .usage = MemoryUsageVma(usage),
+        .requiredFlags = MemoryUsageRequiredVmaFlags(usage),
+        .preferredFlags = MemoryUsagePreferedVmaFlags(usage),
+        .pool = VK_NULL_HANDLE,
+        .pUserData = nullptr,
+    };
+
+    VkBuffer handle{};
+    VmaAllocationInfo alloc_info{};
+    VmaAllocation allocation{};
+    VkMemoryPropertyFlags property_flags{};
+
+    vk::Check(vmaCreateBuffer(allocator, &ci, &alloc_ci, &handle, &allocation, &alloc_info));
+    vmaGetAllocationMemoryProperties(allocator, allocation, &property_flags);
+
+    u8* data = reinterpret_cast<u8*>(alloc_info.pMappedData);
+    const std::span<u8> mapped_data = data ? std::span<u8>{data, ci.size} : std::span<u8>{};
+    const bool is_coherent = property_flags & VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
+
+    return vk::Buffer(handle, *device.GetLogical(), allocator, allocation, mapped_data, is_coherent,
+                      device.GetDispatchLoader());
+}
+
 MemoryCommit MemoryAllocator::Commit(const VkMemoryRequirements& requirements, MemoryUsage usage) {
     // Find the fastest memory flags we can afford with the current requirements
     const u32 type_mask = requirements.memoryTypeBits;
@@ -221,12 +298,6 @@ MemoryCommit MemoryAllocator::Commit(const VkMemoryRequirements& requirements, M
     return TryCommit(requirements, flags).value();
 }
 
-MemoryCommit MemoryAllocator::Commit(const vk::Buffer& buffer, MemoryUsage usage) {
-    auto commit = Commit(device.GetLogical().GetBufferMemoryRequirements(*buffer), usage);
-    buffer.BindMemory(commit.Memory(), commit.Offset());
-    return commit;
-}
-
 bool MemoryAllocator::TryAllocMemory(VkMemoryPropertyFlags flags, u32 type_mask, u64 size) {
     const u32 type = FindType(flags, type_mask).value();
     vk::DeviceMemory memory = device.GetLogical().TryAllocateMemory({
@@ -302,16 +373,4 @@ std::optional<u32> MemoryAllocator::FindType(VkMemoryPropertyFlags flags, u32 ty
     return std::nullopt;
 }
 
-bool IsHostVisible(MemoryUsage usage) noexcept {
-    switch (usage) {
-    case MemoryUsage::DeviceLocal:
-        return false;
-    case MemoryUsage::Upload:
-    case MemoryUsage::Download:
-        return true;
-    }
-    ASSERT_MSG(false, "Invalid memory usage={}", usage);
-    return false;
-}
-
 } // namespace Vulkan
diff --git a/src/video_core/vulkan_common/vulkan_memory_allocator.h b/src/video_core/vulkan_common/vulkan_memory_allocator.h
index f9ee53cfb..f449bc8d0 100644
--- a/src/video_core/vulkan_common/vulkan_memory_allocator.h
+++ b/src/video_core/vulkan_common/vulkan_memory_allocator.h
@@ -9,6 +9,8 @@
 #include "common/common_types.h"
 #include "video_core/vulkan_common/vulkan_wrapper.h"
 
+VK_DEFINE_HANDLE(VmaAllocator)
+
 namespace Vulkan {
 
 class Device;
@@ -17,9 +19,11 @@ class MemoryAllocation;
 
 /// Hints and requirements for the backing memory type of a commit
 enum class MemoryUsage {
-    DeviceLocal, ///< Hints device local usages, fastest memory type to read and write from the GPU
+    DeviceLocal, ///< Requests device local host visible buffer, falling back to device local
+                 ///< memory.
     Upload,      ///< Requires a host visible memory type optimized for CPU to GPU uploads
     Download,    ///< Requires a host visible memory type optimized for GPU to CPU readbacks
+    Stream,      ///< Requests device local host visible buffer, falling back host memory.
 };
 
 /// Ownership handle of a memory commitment.
@@ -82,6 +86,8 @@ public:
 
     vk::Image CreateImage(const VkImageCreateInfo& ci) const;
 
+    vk::Buffer CreateBuffer(const VkBufferCreateInfo& ci, MemoryUsage usage) const;
+
     /**
      * Commits a memory with the specified requirements.
      *
@@ -113,13 +119,11 @@ private:
     std::optional<u32> FindType(VkMemoryPropertyFlags flags, u32 type_mask) const;
 
     const Device& device;                                       ///< Device handle.
+    VmaAllocator allocator;                                     ///< Vma allocator.
     const VkPhysicalDeviceMemoryProperties properties;          ///< Physical device properties.
     std::vector<std::unique_ptr<MemoryAllocation>> allocations; ///< Current allocations.
     VkDeviceSize buffer_image_granularity; // The granularity for adjacent offsets between buffers
                                            // and optimal images
 };
 
-/// Returns true when a memory usage is guaranteed to be host visible.
-bool IsHostVisible(MemoryUsage usage) noexcept;
-
 } // namespace Vulkan
diff --git a/src/video_core/vulkan_common/vulkan_wrapper.cpp b/src/video_core/vulkan_common/vulkan_wrapper.cpp
index 5d088dc58..c01a9478e 100644
--- a/src/video_core/vulkan_common/vulkan_wrapper.cpp
+++ b/src/video_core/vulkan_common/vulkan_wrapper.cpp
@@ -561,14 +561,28 @@ void Image::Release() const noexcept {
     }
 }
 
-void Buffer::BindMemory(VkDeviceMemory memory, VkDeviceSize offset) const {
-    Check(dld->vkBindBufferMemory(owner, handle, memory, offset));
+void Buffer::Flush() const {
+    if (!is_coherent) {
+        vmaFlushAllocation(allocator, allocation, 0, VK_WHOLE_SIZE);
+    }
+}
+
+void Buffer::Invalidate() const {
+    if (!is_coherent) {
+        vmaInvalidateAllocation(allocator, allocation, 0, VK_WHOLE_SIZE);
+    }
 }
 
 void Buffer::SetObjectNameEXT(const char* name) const {
     SetObjectName(dld, owner, handle, VK_OBJECT_TYPE_BUFFER, name);
 }
 
+void Buffer::Release() const noexcept {
+    if (handle) {
+        vmaDestroyBuffer(allocator, handle, allocation);
+    }
+}
+
 void BufferView::SetObjectNameEXT(const char* name) const {
     SetObjectName(dld, owner, handle, VK_OBJECT_TYPE_BUFFER_VIEW, name);
 }
@@ -707,12 +721,6 @@ Queue Device::GetQueue(u32 family_index) const noexcept {
     return Queue(queue, *dld);
 }
 
-Buffer Device::CreateBuffer(const VkBufferCreateInfo& ci) const {
-    VkBuffer object;
-    Check(dld->vkCreateBuffer(handle, &ci, nullptr, &object));
-    return Buffer(object, handle, *dld);
-}
-
 BufferView Device::CreateBufferView(const VkBufferViewCreateInfo& ci) const {
     VkBufferView object;
     Check(dld->vkCreateBufferView(handle, &ci, nullptr, &object));
diff --git a/src/video_core/vulkan_common/vulkan_wrapper.h b/src/video_core/vulkan_common/vulkan_wrapper.h
index 8ec708774..44fce47a5 100644
--- a/src/video_core/vulkan_common/vulkan_wrapper.h
+++ b/src/video_core/vulkan_common/vulkan_wrapper.h
@@ -673,6 +673,84 @@ private:
     const DeviceDispatch* dld = nullptr;
 };
 
+class Buffer {
+public:
+    explicit Buffer(VkBuffer handle_, VkDevice owner_, VmaAllocator allocator_,
+                    VmaAllocation allocation_, std::span<u8> mapped_, bool is_coherent_,
+                    const DeviceDispatch& dld_) noexcept
+        : handle{handle_}, owner{owner_}, allocator{allocator_},
+          allocation{allocation_}, mapped{mapped_}, is_coherent{is_coherent_}, dld{&dld_} {}
+    Buffer() = default;
+
+    Buffer(const Buffer&) = delete;
+    Buffer& operator=(const Buffer&) = delete;
+
+    Buffer(Buffer&& rhs) noexcept
+        : handle{std::exchange(rhs.handle, nullptr)}, owner{rhs.owner}, allocator{rhs.allocator},
+          allocation{rhs.allocation}, mapped{rhs.mapped},
+          is_coherent{rhs.is_coherent}, dld{rhs.dld} {}
+
+    Buffer& operator=(Buffer&& rhs) noexcept {
+        Release();
+        handle = std::exchange(rhs.handle, nullptr);
+        owner = rhs.owner;
+        allocator = rhs.allocator;
+        allocation = rhs.allocation;
+        mapped = rhs.mapped;
+        is_coherent = rhs.is_coherent;
+        dld = rhs.dld;
+        return *this;
+    }
+
+    ~Buffer() noexcept {
+        Release();
+    }
+
+    VkBuffer operator*() const noexcept {
+        return handle;
+    }
+
+    void reset() noexcept {
+        Release();
+        handle = nullptr;
+    }
+
+    explicit operator bool() const noexcept {
+        return handle != nullptr;
+    }
+
+    /// Returns the host mapped memory, an empty span otherwise.
+    std::span<u8> Mapped() noexcept {
+        return mapped;
+    }
+
+    std::span<const u8> Mapped() const noexcept {
+        return mapped;
+    }
+
+    /// Returns true if the buffer is mapped to the host.
+    bool IsHostVisible() const noexcept {
+        return !mapped.empty();
+    }
+
+    void Flush() const;
+
+    void Invalidate() const;
+
+    void SetObjectNameEXT(const char* name) const;
+
+private:
+    void Release() const noexcept;
+
+    VkBuffer handle = nullptr;
+    VkDevice owner = nullptr;
+    VmaAllocator allocator = nullptr;
+    VmaAllocation allocation = nullptr;
+    std::span<u8> mapped = {};
+    bool is_coherent = false;
+    const DeviceDispatch* dld = nullptr;
+};
+
 class Queue {
 public:
     /// Construct an empty queue handle.
@@ -696,17 +774,6 @@ private:
     const DeviceDispatch* dld = nullptr;
 };
 
-class Buffer : public Handle<VkBuffer, VkDevice, DeviceDispatch> {
-    using Handle<VkBuffer, VkDevice, DeviceDispatch>::Handle;
-
-public:
-    /// Attaches a memory allocation.
-    void BindMemory(VkDeviceMemory memory, VkDeviceSize offset) const;
-
-    /// Set object name.
-    void SetObjectNameEXT(const char* name) const;
-};
-
 class BufferView : public Handle<VkBufferView, VkDevice, DeviceDispatch> {
     using Handle<VkBufferView, VkDevice, DeviceDispatch>::Handle;
 
@@ -886,8 +953,6 @@ public:
 
     Queue GetQueue(u32 family_index) const noexcept;
 
-    Buffer CreateBuffer(const VkBufferCreateInfo& ci) const;
-
     BufferView CreateBufferView(const VkBufferViewCreateInfo& ci) const;
 
     ImageView CreateImageView(const VkImageViewCreateInfo& ci) const;