gpu: host1x: Allocate gather copy for host1x

Currently when the gather buffers are copied, they are copied to a
buffer that is allocated for the host1x client that wants to execute the
command streams in the buffers. However, the gather buffers will be read
by the host1x device, which causes SMMU faults if the DMA API is backed
by an IOMMU.

Fix this by allocating the gather buffer copy for the host1x device,
which makes sure that it will be mapped into the host1x's IOVA space if
the DMA API is backed by an IOMMU.

Signed-off-by: Thierry Reding <[e-mail]>

drivers/gpu/host1x/job.c

···
 	return err;
 }
 
-static inline int copy_gathers(struct host1x_job *job, struct device *dev)
+static inline int copy_gathers(struct device *host, struct host1x_job *job,
+			       struct device *dev)
 {
 	struct host1x_firewall fw;
 	size_t size = 0;
···
 	 * Try a non-blocking allocation from a higher priority pools first,
 	 * as awaiting for the allocation here is a major performance hit.
 	 */
-	job->gather_copy_mapped = dma_alloc_wc(dev, size, &job->gather_copy,
+	job->gather_copy_mapped = dma_alloc_wc(host, size, &job->gather_copy,
 					       GFP_NOWAIT);
 
 	/* the higher priority allocation failed, try the generic-blocking */
 	if (!job->gather_copy_mapped)
-		job->gather_copy_mapped = dma_alloc_wc(dev, size,
+		job->gather_copy_mapped = dma_alloc_wc(host, size,
 						       &job->gather_copy,
 						       GFP_KERNEL);
 	if (!job->gather_copy_mapped)
···
 		goto out;
 
 	if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) {
-		err = copy_gathers(job, dev);
+		err = copy_gathers(host->dev, job, dev);
 		if (err)
 			goto out;
 	}
···
 	job->num_unpins = 0;
 
 	if (job->gather_copy_size)
-		dma_free_wc(job->channel->dev, job->gather_copy_size,
+		dma_free_wc(host->dev, job->gather_copy_size,
 			    job->gather_copy_mapped, job->gather_copy);
 }
 EXPORT_SYMBOL(host1x_job_unpin);