6 files changed, 64 insertions, 15 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 7b4e657a95c7..c3df75a9f65d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -1443,7 +1443,8 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
 		effective_mode &= ~S_IWUSR;
 
 	if ((adev->flags & AMD_IS_APU) &&
-	    (attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr ||
+	    (attr == &sensor_dev_attr_power1_average.dev_attr.attr ||
+	     attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr ||
 	     attr == &sensor_dev_attr_power1_cap_min.dev_attr.attr||
 	     attr == &sensor_dev_attr_power1_cap.dev_attr.attr))
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index 1c5d97f4b4dd..8dcf6227ab99 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -37,6 +37,7 @@
 #include "amdgpu_display.h"
 #include <drm/amdgpu_drm.h>
 #include <linux/dma-buf.h>
+#include <linux/dma-fence-array.h>
 
 static const struct dma_buf_ops amdgpu_dmabuf_ops;
 
@@ -188,6 +189,48 @@ error:
 	return ERR_PTR(ret);
 }
 
+static int
+__reservation_object_make_exclusive(struct reservation_object *obj)
+{
+	struct dma_fence **fences;
+	unsigned int count;
+	int r;
+
+	if (!reservation_object_get_list(obj)) /* no shared fences to convert */
+		return 0;
+
+	r = reservation_object_get_fences_rcu(obj, NULL, &count, &fences);
+	if (r)
+		return r;
+
+	if (count == 0) {
+		/* Now that was unexpected. */
+	} else if (count == 1) {
+		reservation_object_add_excl_fence(obj, fences[0]);
+		dma_fence_put(fences[0]);
+		kfree(fences);
+	} else {
+		struct dma_fence_array *array;
+
+		array = dma_fence_array_create(count, fences,
+					       dma_fence_context_alloc(1), 0,
+					       false);
+		if (!array)
+			goto err_fences_put;
+
+		reservation_object_add_excl_fence(obj, &array->base);
+		dma_fence_put(&array->base);
+	}
+
+	return 0;
+
+err_fences_put:
+	while (count--)
+		dma_fence_put(fences[count]);
+	kfree(fences);
+	return -ENOMEM;
+}
+
 /**
  * amdgpu_gem_map_attach - &dma_buf_ops.attach implementation
  * @dma_buf: shared DMA buffer
@@ -219,16 +262,16 @@ static int amdgpu_gem_map_attach(struct dma_buf *dma_buf,
 
 	if (attach->dev->driver != adev->dev->driver) {
 		/*
-		 * Wait for all shared fences to complete before we switch to future
-		 * use of exclusive fence on this prime shared bo.
+		 * We only create shared fences for internal use, but importers
+		 * of the dmabuf rely on exclusive fences for implicitly
+		 * tracking write hazards. As any of the current fences may
+		 * correspond to a write, we need to convert all existing
+		 * fences on the reservation object into a single exclusive
+		 * fence.
 		 */
-		r = reservation_object_wait_timeout_rcu(bo->tbo.resv,
-							true, false,
-							MAX_SCHEDULE_TIMEOUT);
-		if (unlikely(r < 0)) {
-			DRM_DEBUG_PRIME("Fence wait failed: %li\n", r);
+		r = __reservation_object_make_exclusive(bo->tbo.resv);
+		if (r)
 			goto error_unreserve;
-		}
 	}
 
 	/* pin buffer into GTT */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 6a84526e20e0..49fe5084c53d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -3011,14 +3011,15 @@ void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
 			 struct amdgpu_task_info *task_info)
 {
 	struct amdgpu_vm *vm;
+	unsigned long flags;
 
-	spin_lock(&adev->vm_manager.pasid_lock);
+	spin_lock_irqsave(&adev->vm_manager.pasid_lock, flags);
 
 	vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
 	if (vm)
 		*task_info = vm->task_info;
 
-	spin_unlock(&adev->vm_manager.pasid_lock);
+	spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index d587779a80b4..a97294ac96d5 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -5676,7 +5676,7 @@ int ci_dpm_init(struct radeon_device *rdev)
 	u16 data_offset, size;
 	u8 frev, crev;
 	struct ci_power_info *pi;
-	enum pci_bus_speed speed_cap;
+	enum pci_bus_speed speed_cap = PCI_SPEED_UNKNOWN;
 	struct pci_dev *root = rdev->pdev->bus->self;
 	int ret;
 
@@ -5685,7 +5685,8 @@ int ci_dpm_init(struct radeon_device *rdev)
 		return -ENOMEM;
 	rdev->pm.dpm.priv = pi;
 
-	speed_cap = pcie_get_speed_cap(root);
+	if (!pci_is_root_bus(rdev->pdev->bus))
+		speed_cap = pcie_get_speed_cap(root);
 	if (speed_cap == PCI_SPEED_UNKNOWN) {
 		pi->sys_pcie_mask = 0;
 	} else {
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 8fb60b3af015..0a785ef0ab66 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -6899,7 +6899,7 @@ int si_dpm_init(struct radeon_device *rdev)
 	struct ni_power_info *ni_pi;
 	struct si_power_info *si_pi;
 	struct atom_clock_dividers dividers;
-	enum pci_bus_speed speed_cap;
+	enum pci_bus_speed speed_cap = PCI_SPEED_UNKNOWN;
 	struct pci_dev *root = rdev->pdev->bus->self;
 	int ret;
 
@@ -6911,7 +6911,8 @@ int si_dpm_init(struct radeon_device *rdev)
 	eg_pi = &ni_pi->eg;
 	pi = &eg_pi->rv7xx;
 
-	speed_cap = pcie_get_speed_cap(root);
+	if (!pci_is_root_bus(rdev->pdev->bus))
+		speed_cap = pcie_get_speed_cap(root);
 	if (speed_cap == PCI_SPEED_UNKNOWN) {
 		si_pi->sys_pcie_mask = 0;
 	} else {
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index 3fb084f802e2..8c31c9ab06f8 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -672,6 +672,7 @@ static int sun4i_tcon_init_clocks(struct device *dev,
 			return PTR_ERR(tcon->sclk0);
 		}
 	}
+	clk_prepare_enable(tcon->sclk0);
 
 	if (tcon->quirks->has_channel_1) {
 		tcon->sclk1 = devm_clk_get(dev, "tcon-ch1");
@@ -686,6 +687,7 @@ static int sun4i_tcon_init_clocks(struct device *dev,
 
 static void sun4i_tcon_free_clocks(struct sun4i_tcon *tcon)
 {
+	clk_disable_unprepare(tcon->sclk0);
 	clk_disable_unprepare(tcon->clk);
 }