drm/radeon: use gart memory for DMA ring tests

Avoids HDP cache flush issues when using vram which can
cause ring test failures on certain boards.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: Alexander Fyodorov <halcy@yandex.ru>
Cc: stable@vger.kernel.org

drivers/gpu/drm/radeon/cik_sdma.c

@@ -618,16 +618,19 @@ int cik_sdma_ring_test(struct radeon_device *rdev,
 {
 	unsigned i;
 	int r;
-	void __iomem *ptr = (void *)rdev->vram_scratch.ptr;
+	unsigned index;
 	u32 tmp;
+	u64 gpu_addr;
 
-	if (!ptr) {
-		DRM_ERROR("invalid vram scratch pointer\n");
-		return -EINVAL;
-	}
+	if (ring->idx == R600_RING_TYPE_DMA_INDEX)
+		index = R600_WB_DMA_RING_TEST_OFFSET;
+	else
+		index = CAYMAN_WB_DMA1_RING_TEST_OFFSET;
+
+	gpu_addr = rdev->wb.gpu_addr + index;
 
 	tmp = 0xCAFEDEAD;
-	writel(tmp, ptr);
+	rdev->wb.wb[index/4] = cpu_to_le32(tmp);
 
 	r = radeon_ring_lock(rdev, ring, 5);
 	if (r) {
@@ -635,14 +638,14 @@ int cik_sdma_ring_test(struct radeon_device *rdev,
 		return r;
 	}
 	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_WRITE, SDMA_WRITE_SUB_OPCODE_LINEAR, 0));
-	radeon_ring_write(ring, rdev->vram_scratch.gpu_addr & 0xfffffffc);
-	radeon_ring_write(ring, upper_32_bits(rdev->vram_scratch.gpu_addr));
+	radeon_ring_write(ring, lower_32_bits(gpu_addr));
+	radeon_ring_write(ring, upper_32_bits(gpu_addr));
 	radeon_ring_write(ring, 1); /* number of DWs to follow */
 	radeon_ring_write(ring, 0xDEADBEEF);
 	radeon_ring_unlock_commit(rdev, ring, false);
 
 	for (i = 0; i < rdev->usec_timeout; i++) {
-		tmp = readl(ptr);
+		tmp = le32_to_cpu(rdev->wb.wb[index/4]);
 		if (tmp == 0xDEADBEEF)
 			break;
 		DRM_UDELAY(1);

drivers/gpu/drm/radeon/r600_dma.c

@@ -241,16 +241,19 @@ int r600_dma_ring_test(struct radeon_device *rdev,
 {
 	unsigned i;
 	int r;
-	void __iomem *ptr = (void *)rdev->vram_scratch.ptr;
+	unsigned index;
 	u32 tmp;
+	u64 gpu_addr;
 
-	if (!ptr) {
-		DRM_ERROR("invalid vram scratch pointer\n");
-		return -EINVAL;
-	}
+	if (ring->idx == R600_RING_TYPE_DMA_INDEX)
+		index = R600_WB_DMA_RING_TEST_OFFSET;
+	else
+		index = CAYMAN_WB_DMA1_RING_TEST_OFFSET;
+
+	gpu_addr = rdev->wb.gpu_addr + index;
 
 	tmp = 0xCAFEDEAD;
-	writel(tmp, ptr);
+	rdev->wb.wb[index/4] = cpu_to_le32(tmp);
 
 	r = radeon_ring_lock(rdev, ring, 4);
 	if (r) {
@@ -258,13 +261,13 @@ int r600_dma_ring_test(struct radeon_device *rdev,
 		return r;
 	}
 	radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_WRITE, 0, 0, 1));
-	radeon_ring_write(ring, rdev->vram_scratch.gpu_addr & 0xfffffffc);
-	radeon_ring_write(ring, upper_32_bits(rdev->vram_scratch.gpu_addr) & 0xff);
+	radeon_ring_write(ring, lower_32_bits(gpu_addr));
+	radeon_ring_write(ring, upper_32_bits(gpu_addr) & 0xff);
 	radeon_ring_write(ring, 0xDEADBEEF);
 	radeon_ring_unlock_commit(rdev, ring, false);
 
 	for (i = 0; i < rdev->usec_timeout; i++) {
-		tmp = readl(ptr);
+		tmp = le32_to_cpu(rdev->wb.wb[index/4]);
 		if (tmp == 0xDEADBEEF)
 			break;
 		DRM_UDELAY(1);

drivers/gpu/drm/radeon/radeon.h

@@ -1132,6 +1132,8 @@ struct radeon_wb {
 #define R600_WB_EVENT_OFFSET     3072
 #define CIK_WB_CP1_WPTR_OFFSET     3328
 #define CIK_WB_CP2_WPTR_OFFSET     3584
+#define R600_WB_DMA_RING_TEST_OFFSET 3588
+#define CAYMAN_WB_DMA1_RING_TEST_OFFSET 3592
 
 /**
  * struct radeon_pm - power management datas