Merge v5.0-rc7 into drm-next

Backmerging for nouveau and imx that needed some fixes for next pulls.

Signed-off-by: Dave Airlie <airlied@redhat.com>

6 files changed, 94 insertions, 26 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index 71913a18d142..a38e0fb4a6fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -38,6 +38,7 @@
 #include "amdgpu_gem.h"
 #include <drm/amdgpu_drm.h>
 #include <linux/dma-buf.h>
+#include <linux/dma-fence-array.h>
 
 /**
  * amdgpu_gem_prime_get_sg_table - &drm_driver.gem_prime_get_sg_table
@@ -187,6 +188,48 @@ 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
@@ -218,16 +261,16 @@ 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_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index d87f165e3a23..3091488cd8cc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -84,8 +84,10 @@ static int psp_sw_fini(void *handle)
 	adev->psp.sos_fw = NULL;
 	release_firmware(adev->psp.asd_fw);
 	adev->psp.asd_fw = NULL;
-	release_firmware(adev->psp.ta_fw);
-	adev->psp.ta_fw = NULL;
+	if (adev->psp.ta_fw) {
+		release_firmware(adev->psp.ta_fw);
+		adev->psp.ta_fw = NULL;
+	}
 	return 0;
 }
 
@@ -440,6 +442,9 @@ static int psp_xgmi_initialize(struct psp_context *psp)
 	struct ta_xgmi_shared_memory *xgmi_cmd;
 	int ret;
 
+	if (!psp->adev->psp.ta_fw)
+		return -ENOENT;
+
 	if (!psp->xgmi_context.initialized) {
 		ret = psp_xgmi_init_shared_buf(psp);
 		if (ret)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 75481cf3348f..7cd2336e29ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -3398,14 +3398,15 @@ 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/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index e347b407bd03..221f26e50322 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -90,7 +90,20 @@ static void nbio_v7_4_enable_doorbell_aperture(struct amdgpu_device *adev,
 static void nbio_v7_4_enable_doorbell_selfring_aperture(struct amdgpu_device *adev,
 							bool enable)
 {
+	u32 tmp = 0;
 
+	if (enable) {
+		tmp = REG_SET_FIELD(tmp, DOORBELL_SELFRING_GPA_APER_CNTL, DOORBELL_SELFRING_GPA_APER_EN, 1) |
+		      REG_SET_FIELD(tmp, DOORBELL_SELFRING_GPA_APER_CNTL, DOORBELL_SELFRING_GPA_APER_MODE, 1) |
+		      REG_SET_FIELD(tmp, DOORBELL_SELFRING_GPA_APER_CNTL, DOORBELL_SELFRING_GPA_APER_SIZE, 0);
+
+		WREG32_SOC15(NBIO, 0, mmDOORBELL_SELFRING_GPA_APER_BASE_LOW,
+			     lower_32_bits(adev->doorbell.base));
+		WREG32_SOC15(NBIO, 0, mmDOORBELL_SELFRING_GPA_APER_BASE_HIGH,
+			     upper_32_bits(adev->doorbell.base));
+	}
+
+	WREG32_SOC15(NBIO, 0, mmDOORBELL_SELFRING_GPA_APER_CNTL, tmp);
 }
 
 static void nbio_v7_4_ih_doorbell_range(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index f71384be1f97..860b70d80d3c 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -98,18 +98,22 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name);
 	err = request_firmware(&adev->psp.ta_fw, fw_name, adev->dev);
-	if (err)
-		goto out2;
-
-	err = amdgpu_ucode_validate(adev->psp.ta_fw);
-	if (err)
-		goto out2;
-
-	ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data;
-	adev->psp.ta_xgmi_ucode_version = le32_to_cpu(ta_hdr->ta_xgmi_ucode_version);
-	adev->psp.ta_xgmi_ucode_size = le32_to_cpu(ta_hdr->ta_xgmi_size_bytes);
-	adev->psp.ta_xgmi_start_addr = (uint8_t *)ta_hdr +
-		le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes);
+	if (err) {
+		release_firmware(adev->psp.ta_fw);
+		adev->psp.ta_fw = NULL;
+		dev_info(adev->dev,
+			 "psp v11.0: Failed to load firmware \"%s\"\n", fw_name);
+	} else {
+		err = amdgpu_ucode_validate(adev->psp.ta_fw);
+		if (err)
+			goto out2;
+
+		ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data;
+		adev->psp.ta_xgmi_ucode_version = le32_to_cpu(ta_hdr->ta_xgmi_ucode_version);
+		adev->psp.ta_xgmi_ucode_size = le32_to_cpu(ta_hdr->ta_xgmi_size_bytes);
+		adev->psp.ta_xgmi_start_addr = (uint8_t *)ta_hdr +
+			le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes);
+	}
 
 	return 0;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 62d272b4be19..99ebcf29dcb0 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -858,11 +858,13 @@ static int soc15_common_early_init(void *handle)
 	case CHIP_RAVEN:
 		adev->asic_funcs = &soc15_asic_funcs;
 		if (adev->rev_id >= 0x8)
-			adev->external_rev_id = adev->rev_id + 0x81;
+			adev->external_rev_id = adev->rev_id + 0x79;
 		else if (adev->pdev->device == 0x15d8)
 			adev->external_rev_id = adev->rev_id + 0x41;
+		else if (adev->rev_id == 1)
+			adev->external_rev_id = adev->rev_id + 0x20;
 		else
-			adev->external_rev_id = 0x1;
+			adev->external_rev_id = adev->rev_id + 0x01;
 
 		if (adev->rev_id >= 0x8) {
 			adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |