[vk, qcom] Binding buffer limits

src/video_core/buffer_cache/buffer_cache.h

@@ -433,6 +433,12 @@ void BufferCache<P>::SetComputeUniformBufferState(u32 mask,
 
 template <class P>
 void BufferCache<P>::UnbindGraphicsStorageBuffers(size_t stage) {
+    if constexpr (requires { runtime.ShouldLimitDynamicStorageBuffers(); }) {
+        if (runtime.ShouldLimitDynamicStorageBuffers()) {
+            channel_state->total_graphics_storage_buffers -=
+                static_cast<u32>(std::popcount(channel_state->enabled_storage_buffers[stage]));
+        }
+    }
     channel_state->enabled_storage_buffers[stage] = 0;
     channel_state->written_storage_buffers[stage] = 0;
 }
@@ -440,8 +446,26 @@ void BufferCache<P>::UnbindGraphicsStorageBuffers(size_t stage) {
 template <class P>
 bool BufferCache<P>::BindGraphicsStorageBuffer(size_t stage, size_t ssbo_index, u32 cbuf_index,
                                                u32 cbuf_offset, bool is_written) {
+    const bool already_enabled =
+        ((channel_state->enabled_storage_buffers[stage] >> ssbo_index) & 1U) != 0;
+    if constexpr (requires { runtime.ShouldLimitDynamicStorageBuffers(); }) {
+        if (runtime.ShouldLimitDynamicStorageBuffers() && !already_enabled) {
+            const u32 max_bindings = runtime.GetMaxDynamicStorageBuffers();
+            if (channel_state->total_graphics_storage_buffers >= max_bindings) {
+                LOG_WARNING(HW_GPU,
+                            "Skipping graphics storage buffer {} due to driver limit {}",
+                            ssbo_index, max_bindings);
+                return false;
+            }
+        }
+    }
     channel_state->enabled_storage_buffers[stage] |= 1U << ssbo_index;
     channel_state->written_storage_buffers[stage] |= (is_written ? 1U : 0U) << ssbo_index;
+    if constexpr (requires { runtime.ShouldLimitDynamicStorageBuffers(); }) {
+        if (runtime.ShouldLimitDynamicStorageBuffers() && !already_enabled) {
+            ++channel_state->total_graphics_storage_buffers;
+        }
+    }
 
     const auto& cbufs = maxwell3d->state.shader_stages[stage];
     const GPUVAddr ssbo_addr = cbufs.const_buffers[cbuf_index].address + cbuf_offset;
@@ -472,6 +496,12 @@ void BufferCache<P>::BindGraphicsTextureBuffer(size_t stage, size_t tbo_index, G
 
 template <class P>
 void BufferCache<P>::UnbindComputeStorageBuffers() {
+    if constexpr (requires { runtime.ShouldLimitDynamicStorageBuffers(); }) {
+        if (runtime.ShouldLimitDynamicStorageBuffers()) {
+            channel_state->total_compute_storage_buffers -=
+                static_cast<u32>(std::popcount(channel_state->enabled_compute_storage_buffers));
+        }
+    }
     channel_state->enabled_compute_storage_buffers = 0;
     channel_state->written_compute_storage_buffers = 0;
     channel_state->image_compute_texture_buffers = 0;
@@ -485,8 +515,26 @@ void BufferCache<P>::BindComputeStorageBuffer(size_t ssbo_index, u32 cbuf_index,
                   ssbo_index);
         return;
     }
+    const bool already_enabled =
+        ((channel_state->enabled_compute_storage_buffers >> ssbo_index) & 1U) != 0;
+    if constexpr (requires { runtime.ShouldLimitDynamicStorageBuffers(); }) {
+        if (runtime.ShouldLimitDynamicStorageBuffers() && !already_enabled) {
+            const u32 max_bindings = runtime.GetMaxDynamicStorageBuffers();
+            if (channel_state->total_compute_storage_buffers >= max_bindings) {
+                LOG_WARNING(HW_GPU,
+                            "Skipping compute storage buffer {} due to driver limit {}",
+                            ssbo_index, max_bindings);
+                return;
+            }
+        }
+    }
     channel_state->enabled_compute_storage_buffers |= 1U << ssbo_index;
     channel_state->written_compute_storage_buffers |= (is_written ? 1U : 0U) << ssbo_index;
+    if constexpr (requires { runtime.ShouldLimitDynamicStorageBuffers(); }) {
+        if (runtime.ShouldLimitDynamicStorageBuffers() && !already_enabled) {
+            ++channel_state->total_compute_storage_buffers;
+        }
+    }
 
     const auto& launch_desc = kepler_compute->launch_description;
     if (((launch_desc.const_buffer_enable_mask >> cbuf_index) & 1) == 0) {

src/video_core/buffer_cache/buffer_cache_base.h

@@ -8,6 +8,7 @@
 
 #include <algorithm>
 #include <array>
+#include <bit>
 #include <functional>
 #include <memory>
 #include <mutex>
@@ -132,6 +133,9 @@ public:
     u32 enabled_compute_storage_buffers = 0;
     u32 written_compute_storage_buffers = 0;
 
+    u32 total_graphics_storage_buffers = 0;
+    u32 total_compute_storage_buffers = 0;
+
     std::array<u32, NUM_STAGES> enabled_texture_buffers{};
     std::array<u32, NUM_STAGES> written_texture_buffers{};
     std::array<u32, NUM_STAGES> image_texture_buffers{};

src/video_core/renderer_vulkan/vk_buffer_cache.cpp

@@ -333,6 +333,13 @@ BufferCacheRuntime::BufferCacheRuntime(const Device& device_, MemoryAllocator& m
       staging_pool{staging_pool_}, guest_descriptor_queue{guest_descriptor_queue_},
       quad_index_pass(device, scheduler, descriptor_pool, staging_pool,
                       compute_pass_descriptor_queue) {
+    const VkDriverIdKHR driver_id = device.GetDriverID();
+    limit_dynamic_storage_buffers = driver_id == VK_DRIVER_ID_QUALCOMM_PROPRIETARY ||
+                                    driver_id == VK_DRIVER_ID_MESA_TURNIP ||
+                                    driver_id == VK_DRIVER_ID_ARM_PROPRIETARY;
+    if (limit_dynamic_storage_buffers) {
+        max_dynamic_storage_buffers = device.GetMaxDescriptorSetStorageBuffersDynamic();
+    }
     if (device.GetDriverID() != VK_DRIVER_ID_QUALCOMM_PROPRIETARY) {
         // TODO: FixMe: Uint8Pass compute shader does not build on some Qualcomm drivers.
         uint8_pass = std::make_unique<Uint8Pass>(device, scheduler, descriptor_pool, staging_pool,

src/video_core/renderer_vulkan/vk_buffer_cache.h

@@ -6,6 +6,8 @@
 
 #pragma once
 
+#include <limits>
+
 #include "video_core/buffer_cache/buffer_cache_base.h"
 #include "video_core/buffer_cache/memory_tracker_base.h"
 #include "video_core/buffer_cache/usage_tracker.h"
@@ -155,6 +157,14 @@ public:
         guest_descriptor_queue.AddTexelBuffer(buffer.View(offset, size, format));
     }
 
+    bool ShouldLimitDynamicStorageBuffers() const {
+        return limit_dynamic_storage_buffers;
+    }
+
+    u32 GetMaxDynamicStorageBuffers() const {
+        return max_dynamic_storage_buffers;
+    }
+
 private:
     void BindBuffer(VkBuffer buffer, u32 offset, u32 size) {
         guest_descriptor_queue.AddBuffer(buffer, offset, size);
@@ -194,6 +204,9 @@ private:
 
     std::unique_ptr<Uint8Pass> uint8_pass;
     QuadIndexedPass quad_index_pass;
+
+    bool limit_dynamic_storage_buffers = false;
+    u32 max_dynamic_storage_buffers = std::numeric_limits<u32>::max();
 };
 
 struct BufferCacheParams {

src/video_core/vulkan_common/vulkan_device.h

@@ -326,6 +326,16 @@ public:
         return properties.properties.limits.maxComputeSharedMemorySize;
     }
 
+    /// Returns the maximum number of dynamic storage buffer descriptors per set.
+    u32 GetMaxDescriptorSetStorageBuffersDynamic() const {
+        return properties.properties.limits.maxDescriptorSetStorageBuffersDynamic;
+    }
+
+    /// Returns the maximum number of dynamic uniform buffer descriptors per set.
+    u32 GetMaxDescriptorSetUniformBuffersDynamic() const {
+        return properties.properties.limits.maxDescriptorSetUniformBuffersDynamic;
+    }
+
     /// Returns float control properties of the device.
     const VkPhysicalDeviceFloatControlsPropertiesKHR& FloatControlProperties() const {
         return properties.float_controls;