2 files changed, 58 insertions, 21 deletions

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c
index deb96de54b00..ee2431a7804e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c
@@ -71,6 +71,10 @@ nvkm_pci_intr(int irq, void *arg)
         struct nvkm_pci *pci = arg;
         struct nvkm_device *device = pci->subdev.device;
         bool handled = false;
+
+        if (pci->irq < 0)
+                return IRQ_HANDLED;
+
         nvkm_mc_intr_unarm(device);
         if (pci->msi)
                 pci->func->msi_rearm(pci);
@@ -84,11 +88,6 @@ nvkm_pci_fini(struct nvkm_subdev *subdev, bool suspend)
 {
         struct nvkm_pci *pci = nvkm_pci(subdev);
 
-        if (pci->irq >= 0) {
-                free_irq(pci->irq, pci);
-                pci->irq = -1;
-        }
-
         if (pci->agp.bridge)
                 nvkm_agp_fini(pci);
 
@@ -108,8 +107,20 @@ static int
 nvkm_pci_oneinit(struct nvkm_subdev *subdev)
 {
         struct nvkm_pci *pci = nvkm_pci(subdev);
-        if (pci_is_pcie(pci->pdev))
-                return nvkm_pcie_oneinit(pci);
+        struct pci_dev *pdev = pci->pdev;
+        int ret;
+
+        if (pci_is_pcie(pci->pdev)) {
+                ret = nvkm_pcie_oneinit(pci);
+                if (ret)
+                        return ret;
+        }
+
+        ret = request_irq(pdev->irq, nvkm_pci_intr, IRQF_SHARED, "nvkm", pci);
+        if (ret)
+                return ret;
+
+        pci->irq = pdev->irq;
         return 0;
 }
 
@@ -117,7 +128,6 @@ static int
 nvkm_pci_init(struct nvkm_subdev *subdev)
 {
         struct nvkm_pci *pci = nvkm_pci(subdev);
-        struct pci_dev *pdev = pci->pdev;
         int ret;
 
         if (pci->agp.bridge) {
@@ -131,28 +141,34 @@ nvkm_pci_init(struct nvkm_subdev *subdev)
         if (pci->func->init)
                 pci->func->init(pci);
 
-        ret = request_irq(pdev->irq, nvkm_pci_intr, IRQF_SHARED, "nvkm", pci);
-        if (ret)
-                return ret;
-
-        pci->irq = pdev->irq;
-
         /* Ensure MSI interrupts are armed, for the case where there are
          * already interrupts pending (for whatever reason) at load time.
          */
         if (pci->msi)
                 pci->func->msi_rearm(pci);
 
-        return ret;
+        return 0;
 }
 
 static void *
 nvkm_pci_dtor(struct nvkm_subdev *subdev)
 {
         struct nvkm_pci *pci = nvkm_pci(subdev);
+
         nvkm_agp_dtor(pci);
+
+        if (pci->irq >= 0) {
+                /* freq_irq() will call the handler, we use pci->irq == -1
+                 * to signal that it's been torn down and should be a noop.
+                 */
+                int irq = pci->irq;
+                pci->irq = -1;
+                free_irq(irq, pci);
+        }
+
         if (pci->msi)
                 pci_disable_msi(pci->pdev);
+
         return nvkm_pci(subdev);
 }
 
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 638540943c61..c94cce96544c 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -146,7 +146,7 @@ vc4_save_hang_state(struct drm_device *dev)
         struct vc4_exec_info *exec[2];
         struct vc4_bo *bo;
         unsigned long irqflags;
-        unsigned int i, j, unref_list_count, prev_idx;
+        unsigned int i, j, k, unref_list_count;
 
         kernel_state = kcalloc(1, sizeof(*kernel_state), GFP_KERNEL);
         if (!kernel_state)
@@ -182,7 +182,7 @@ vc4_save_hang_state(struct drm_device *dev)
                 return;
         }
 
-        prev_idx = 0;
+        k = 0;
         for (i = 0; i < 2; i++) {
                 if (!exec[i])
                         continue;
@@ -197,7 +197,7 @@ vc4_save_hang_state(struct drm_device *dev)
                         WARN_ON(!refcount_read(&bo->usecnt));
                         refcount_inc(&bo->usecnt);
                         drm_gem_object_get(&exec[i]->bo[j]->base);
-                        kernel_state->bo[j + prev_idx] = &exec[i]->bo[j]->base;
+                        kernel_state->bo[k++] = &exec[i]->bo[j]->base;
                 }
 
                 list_for_each_entry(bo, &exec[i]->unref_list, unref_head) {
@@ -205,12 +205,12 @@ vc4_save_hang_state(struct drm_device *dev)
                          * because they are naturally unpurgeable.
                          */
                         drm_gem_object_get(&bo->base.base);
-                        kernel_state->bo[j + prev_idx] = &bo->base.base;
-                        j++;
+                        kernel_state->bo[k++] = &bo->base.base;
                 }
-                prev_idx = j + 1;
         }
 
+        WARN_ON_ONCE(k != state->bo_count);
+
         if (exec[0])
                 state->start_bin = exec[0]->ct0ca;
         if (exec[1])
@@ -436,6 +436,19 @@ vc4_flush_caches(struct drm_device *dev)
                   VC4_SET_FIELD(0xf, V3D_SLCACTL_ICC));
 }
 
+static void
+vc4_flush_texture_caches(struct drm_device *dev)
+{
+        struct vc4_dev *vc4 = to_vc4_dev(dev);
+
+        V3D_WRITE(V3D_L2CACTL,
+                  V3D_L2CACTL_L2CCLR);
+
+        V3D_WRITE(V3D_SLCACTL,
+                  VC4_SET_FIELD(0xf, V3D_SLCACTL_T1CC) |
+                  VC4_SET_FIELD(0xf, V3D_SLCACTL_T0CC));
+}
+
 /* Sets the registers for the next job to be actually be executed in
  * the hardware.
  *
@@ -474,6 +487,14 @@ vc4_submit_next_render_job(struct drm_device *dev)
         if (!exec)
                 return;
 
+        /* A previous RCL may have written to one of our textures, and
+         * our full cache flush at bin time may have occurred before
+         * that RCL completed.  Flush the texture cache now, but not
+         * the instructions or uniforms (since we don't write those
+         * from an RCL).
+         */
+        vc4_flush_texture_caches(dev);
+
         submit_cl(dev, 1, exec->ct1ca, exec->ct1ea);
 }