rhi: Better handling of device loss

Starting with D3D11. The other backends will follow later.

Change-Id: I4f165c9f1743df0fb00bdce1e898917575bf5f6e
Reviewed-by: Christian Strømme <christian.stromme@qt.io>

13 files changed, 90 insertions, 3 deletions

diff --git a/src/gui/rhi/qrhi.cpp b/src/gui/rhi/qrhi.cpp
index 5ad433cf23..fbdc90bd1b 100644
--- a/src/gui/rhi/qrhi.cpp
+++ b/src/gui/rhi/qrhi.cpp
@@ -455,7 +455,7 @@ Q_LOGGING_CATEGORY(QRHI_LOG_INFO, "qt.rhi.general")
 
     \value FrameOpDeviceLost The graphics device was lost. This can be
     recoverable by attempting to repeat the operation (such as, beginFrame())
-    and releasing and reinitializing all objects backed by native graphics
+    after releasing and reinitializing all objects backed by native graphics
     resources.
  */
 
@@ -5046,6 +5046,47 @@ void QRhi::releaseCachedResources()
 }
 
 /*!
+    \return true if the graphics device was lost.
+
+    The loss of the device is typically detected in beginFrame(), endFrame() or
+    QRhiSwapChain::buildOrResize(), depending on the backend and the underlying
+    native APIs. The most common is endFrame() because that is where presenting
+    happens. With some backends QRhiSwapChain::buildOrResize() can also fail
+    due to a device loss. Therefore this function is provided as a generic way
+    to check if a device loss was detected by a previous operation.
+
+    When the device is lost, no further operations should be done via the QRhi.
+    Rather, all QRhi resources should be released, followed by destroying the
+    QRhi. A new QRhi can then be attempted to be created. If successful, all
+    graphics resources must be reinitialized. If not, try again later,
+    repeatedly.
+
+    While simple applications may decide to not care about device loss,
+    on the commonly used desktop platforms a device loss can happen
+    due to a variety of reasons, including physically disconnecting the
+    graphics adapter, disabling the device or driver, uninstalling or upgrading
+    the graphics driver, or due to errors that lead to a graphics device reset.
+    Some of these can happen under perfectly normal circumstances as well, for
+    example the upgrade of the graphics driver to a newer version is a common
+    task that can happen at any time while a Qt application is running. Users
+    may very well expect applications to be able to survive this, even when the
+    application is actively using an API like OpenGL or Direct3D.
+
+    Qt's own frameworks built on top of QRhi, such as, Qt Quick, can be
+    expected to handle and take appropriate measures when a device loss occurs.
+    If the data for graphics resources, such as textures and buffers, are still
+    available on the CPU side, such an event may not be noticeable on the
+    application level at all since graphics resources can seamlessly be
+    reinitialized then. However, applications and libraries working directly
+    with QRhi are expected to be prepared to check and handle device loss
+    situations themselves.
+ */
+bool QRhi::isDeviceLost() const
+{
+    return d->isDeviceLost();
+}
+
+/*!
     \return a new graphics pipeline resource.
 
     \sa QRhiResource::release()
diff --git a/src/gui/rhi/qrhi_p.h b/src/gui/rhi/qrhi_p.h
index 928d1f8fa7..51e70af18e 100644
--- a/src/gui/rhi/qrhi_p.h
+++ b/src/gui/rhi/qrhi_p.h
@@ -1422,6 +1422,8 @@ public:
 
     void releaseCachedResources();
 
+    bool isDeviceLost() const;
+
 protected:
     QRhi();
 
diff --git a/src/gui/rhi/qrhi_p_p.h b/src/gui/rhi/qrhi_p_p.h
index b69757ae6d..7c0b000c33 100644
--- a/src/gui/rhi/qrhi_p_p.h
+++ b/src/gui/rhi/qrhi_p_p.h
@@ -158,6 +158,7 @@ public:
     virtual void sendVMemStatsToProfiler() = 0;
     virtual void makeThreadLocalNativeContextCurrent() = 0;
     virtual void releaseCachedResources() = 0;
+    virtual bool isDeviceLost() const = 0;
 
     bool isCompressedFormat(QRhiTexture::Format format) const;
     void compressedFormatInfo(QRhiTexture::Format format, const QSize &size,
diff --git a/src/gui/rhi/qrhid3d11.cpp b/src/gui/rhi/qrhid3d11.cpp
index 119234035a..2350691dc0 100644
--- a/src/gui/rhi/qrhid3d11.cpp
+++ b/src/gui/rhi/qrhid3d11.cpp
@@ -267,6 +267,8 @@ bool QRhiD3D11::create(QRhi::Flags flags)
     if (FAILED(context->QueryInterface(IID_ID3DUserDefinedAnnotation, reinterpret_cast<void **>(&annotations))))
         annotations = nullptr;
 
+    deviceLost = false;
+
     nativeHandlesStruct.dev = dev;
     nativeHandlesStruct.context = context;
 
@@ -487,6 +489,11 @@ void QRhiD3D11::releaseCachedResources()
     clearShaderCache();
 }
 
+bool QRhiD3D11::isDeviceLost() const
+{
+    return deviceLost;
+}
+
 QRhiRenderBuffer *QRhiD3D11::createRenderBuffer(QRhiRenderBuffer::Type type, const QSize &pixelSize,
                                                 int sampleCount, QRhiRenderBuffer::Flags flags)
 {
@@ -1003,8 +1010,14 @@ QRhi::FrameOpResult QRhiD3D11::endFrame(QRhiSwapChain *swapChain, QRhi::EndFrame
     if (!flags.testFlag(QRhi::SkipPresent)) {
         const UINT presentFlags = 0;
         HRESULT hr = swapChainD->swapChain->Present(swapChainD->swapInterval, presentFlags);
-        if (FAILED(hr))
+        if (hr == DXGI_ERROR_DEVICE_REMOVED || hr == DXGI_ERROR_DEVICE_RESET) {
+            qWarning("Device loss detected in Present()");
+            deviceLost = true;
+            return QRhi::FrameOpDeviceLost;
+        } else if (FAILED(hr)) {
             qWarning("Failed to present: %s", qPrintable(comErrorMessage(hr)));
+            return QRhi::FrameOpError;
+        }
 
         // move on to the next buffer
         swapChainD->currentFrameSlot = (swapChainD->currentFrameSlot + 1) % QD3D11SwapChain::BUFFER_COUNT;
@@ -3850,7 +3863,11 @@ bool QD3D11SwapChain::buildOrResize()
         const UINT count = useFlipDiscard ? BUFFER_COUNT : 1;
         HRESULT hr = swapChain->ResizeBuffers(count, UINT(pixelSize.width()), UINT(pixelSize.height()),
                                               colorFormat, swapChainFlags);
-        if (FAILED(hr)) {
+        if (hr == DXGI_ERROR_DEVICE_REMOVED || hr == DXGI_ERROR_DEVICE_RESET) {
+            qWarning("Device loss detected in ResizeBuffers()");
+            rhiD->deviceLost = true;
+            return false;
+        } else if (FAILED(hr)) {
             qWarning("Failed to resize D3D11 swapchain: %s", qPrintable(comErrorMessage(hr)));
             return false;
         }
diff --git a/src/gui/rhi/qrhid3d11_p_p.h b/src/gui/rhi/qrhid3d11_p_p.h
index cc4e095d10..da7fe84b1a 100644
--- a/src/gui/rhi/qrhid3d11_p_p.h
+++ b/src/gui/rhi/qrhid3d11_p_p.h
@@ -633,6 +633,7 @@ public:
     void sendVMemStatsToProfiler() override;
     void makeThreadLocalNativeContextCurrent() override;
     void releaseCachedResources() override;
+    bool isDeviceLost() const override;
 
     void enqueueSubresUpload(QD3D11Texture *texD, QD3D11CommandBuffer *cbD,
                              int layer, int level, const QRhiTextureSubresourceUploadDescription &subresDesc);
@@ -658,6 +659,7 @@ public:
     IDXGIFactory1 *dxgiFactory = nullptr;
     bool hasDxgi2 = false;
     bool supportsFlipDiscardSwapchain = false;
+    bool deviceLost = false;
     QRhiD3D11NativeHandles nativeHandlesStruct;
 
     struct {
diff --git a/src/gui/rhi/qrhigles2.cpp b/src/gui/rhi/qrhigles2.cpp
index 4d91ac45bd..d408490b34 100644
--- a/src/gui/rhi/qrhigles2.cpp
+++ b/src/gui/rhi/qrhigles2.cpp
@@ -772,6 +772,11 @@ void QRhiGles2::releaseCachedResources()
     m_shaderCache.clear();
 }
 
+bool QRhiGles2::isDeviceLost() const
+{
+    return false;
+}
+
 QRhiRenderBuffer *QRhiGles2::createRenderBuffer(QRhiRenderBuffer::Type type, const QSize &pixelSize,
                                                 int sampleCount, QRhiRenderBuffer::Flags flags)
 {
diff --git a/src/gui/rhi/qrhigles2_p_p.h b/src/gui/rhi/qrhigles2_p_p.h
index 877eb88d27..3664e7162b 100644
--- a/src/gui/rhi/qrhigles2_p_p.h
+++ b/src/gui/rhi/qrhigles2_p_p.h
@@ -666,6 +666,7 @@ public:
     void sendVMemStatsToProfiler() override;
     void makeThreadLocalNativeContextCurrent() override;
     void releaseCachedResources() override;
+    bool isDeviceLost() const override;
 
     bool ensureContext(QSurface *surface = nullptr) const;
     void executeDeferredReleases();
diff --git a/src/gui/rhi/qrhimetal.mm b/src/gui/rhi/qrhimetal.mm
index 3bf95ad676..770786db98 100644
--- a/src/gui/rhi/qrhimetal.mm
+++ b/src/gui/rhi/qrhimetal.mm
@@ -596,6 +596,11 @@ void QRhiMetal::releaseCachedResources()
     d->shaderCache.clear();
 }
 
+bool QRhiMetal::isDeviceLost() const
+{
+    return false;
+}
+
 QRhiRenderBuffer *QRhiMetal::createRenderBuffer(QRhiRenderBuffer::Type type, const QSize &pixelSize,
                                                 int sampleCount, QRhiRenderBuffer::Flags flags)
 {
diff --git a/src/gui/rhi/qrhimetal_p_p.h b/src/gui/rhi/qrhimetal_p_p.h
index 01b0bf4f56..633e9b8de4 100644
--- a/src/gui/rhi/qrhimetal_p_p.h
+++ b/src/gui/rhi/qrhimetal_p_p.h
@@ -418,6 +418,7 @@ public:
     void sendVMemStatsToProfiler() override;
     void makeThreadLocalNativeContextCurrent() override;
     void releaseCachedResources() override;
+    bool isDeviceLost() const override;
 
     void executeDeferredReleases(bool forced = false);
     void finishActiveReadbacks(bool forced = false);
diff --git a/src/gui/rhi/qrhinull.cpp b/src/gui/rhi/qrhinull.cpp
index 29a3968bfc..b58d9f5c56 100644
--- a/src/gui/rhi/qrhinull.cpp
+++ b/src/gui/rhi/qrhinull.cpp
@@ -179,6 +179,11 @@ void QRhiNull::releaseCachedResources()
     // nothing to do here
 }
 
+bool QRhiNull::isDeviceLost() const
+{
+    return false;
+}
+
 QRhiRenderBuffer *QRhiNull::createRenderBuffer(QRhiRenderBuffer::Type type, const QSize &pixelSize,
                                                int sampleCount, QRhiRenderBuffer::Flags flags)
 {
diff --git a/src/gui/rhi/qrhinull_p_p.h b/src/gui/rhi/qrhinull_p_p.h
index b43f830d5e..d6dbdbdc75 100644
--- a/src/gui/rhi/qrhinull_p_p.h
+++ b/src/gui/rhi/qrhinull_p_p.h
@@ -284,6 +284,7 @@ public:
     void sendVMemStatsToProfiler() override;
     void makeThreadLocalNativeContextCurrent() override;
     void releaseCachedResources() override;
+    bool isDeviceLost() const override;
 
     QRhiNullNativeHandles nativeHandlesStruct;
     QRhiSwapChain *currentSwapChain = nullptr;
diff --git a/src/gui/rhi/qrhivulkan.cpp b/src/gui/rhi/qrhivulkan.cpp
index c4f298dafb..5dd4b12329 100644
--- a/src/gui/rhi/qrhivulkan.cpp
+++ b/src/gui/rhi/qrhivulkan.cpp
@@ -3750,6 +3750,11 @@ void QRhiVulkan::releaseCachedResources()
     // nothing to do here
 }
 
+bool QRhiVulkan::isDeviceLost() const
+{
+    return false;
+}
+
 QRhiRenderBuffer *QRhiVulkan::createRenderBuffer(QRhiRenderBuffer::Type type, const QSize &pixelSize,
                                                  int sampleCount, QRhiRenderBuffer::Flags flags)
 {
diff --git a/src/gui/rhi/qrhivulkan_p_p.h b/src/gui/rhi/qrhivulkan_p_p.h
index 23cc80b814..0f16c54779 100644
--- a/src/gui/rhi/qrhivulkan_p_p.h
+++ b/src/gui/rhi/qrhivulkan_p_p.h
@@ -713,6 +713,7 @@ public:
     void sendVMemStatsToProfiler() override;
     void makeThreadLocalNativeContextCurrent() override;
     void releaseCachedResources() override;
+    bool isDeviceLost() const override;
 
     VkResult createDescriptorPool(VkDescriptorPool *pool);
     bool allocateDescriptorSet(VkDescriptorSetAllocateInfo *allocInfo, VkDescriptorSet *result, int *resultPoolIndex);