drm/msm: Add PRR support

Add PRR (Partial Resident Region) is a bypass address which make GPU
writes go to /dev/null and reads return zero.  This is used to implement
vulkan sparse residency.

To support PRR/NULL mappings, we allocate a page to reserve a physical
address which we know will not be used as part of a GEM object, and
configure the SMMU to use this address for PRR/NULL mappings.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Tested-by: Antonino Maniscalco <antomani103@gmail.com>
Reviewed-by: Antonino Maniscalco <antomani103@gmail.com>
Patchwork: https://patchwork.freedesktop.org/patch/661486/

Author: robclark

drivers/gpu/drm/msm/adreno/adreno_gpu.c

@@ -357,6 +357,13 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags,
 	return 0;
 }
 
+static bool
+adreno_smmu_has_prr(struct msm_gpu *gpu)
+{
+	struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(&gpu->pdev->dev);
+	return adreno_smmu && adreno_smmu->set_prr_addr;
+}
+
 int adreno_get_param(struct msm_gpu *gpu, struct msm_context *ctx,
 		     uint32_t param, uint64_t *value, uint32_t *len)
 {
@@ -440,6 +447,9 @@ int adreno_get_param(struct msm_gpu *gpu, struct msm_context *ctx,
 	case MSM_PARAM_UCHE_TRAP_BASE:
 		*value = adreno_gpu->uche_trap_base;
 		return 0;
+	case MSM_PARAM_HAS_PRR:
+		*value = adreno_smmu_has_prr(gpu);
+		return 0;
 	default:
 		return UERR(EINVAL, drm, "%s: invalid param: %u", gpu->name, param);
 	}

drivers/gpu/drm/msm/msm_iommu.c

@@ -13,6 +13,7 @@ struct msm_iommu {
 	struct msm_mmu base;
 	struct iommu_domain *domain;
 	atomic_t pagetables;
+	struct page *prr_page;
 };
 
 #define to_msm_iommu(x) container_of(x, struct msm_iommu, base)
@@ -112,6 +113,36 @@ static int msm_iommu_pagetable_unmap(struct msm_mmu *mmu, u64 iova,
 	return (size == 0) ? 0 : -EINVAL;
 }
 
+static int msm_iommu_pagetable_map_prr(struct msm_mmu *mmu, u64 iova, size_t len, int prot)
+{
+	struct msm_iommu_pagetable *pagetable = to_pagetable(mmu);
+	struct io_pgtable_ops *ops = pagetable->pgtbl_ops;
+	struct msm_iommu *iommu = to_msm_iommu(pagetable->parent);
+	phys_addr_t phys = page_to_phys(iommu->prr_page);
+	u64 addr = iova;
+
+	while (len) {
+		size_t mapped = 0;
+		size_t size = PAGE_SIZE;
+		int ret;
+
+		ret = ops->map_pages(ops, addr, phys, size, 1, prot, GFP_KERNEL, &mapped);
+
+		/* map_pages could fail after mapping some of the pages,
+		 * so update the counters before error handling.
+		 */
+		addr += mapped;
+		len  -= mapped;
+
+		if (ret) {
+			msm_iommu_pagetable_unmap(mmu, iova, addr - iova);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 static int msm_iommu_pagetable_map(struct msm_mmu *mmu, u64 iova,
 				   struct sg_table *sgt, size_t off, size_t len,
 				   int prot)
@@ -122,6 +153,9 @@ static int msm_iommu_pagetable_map(struct msm_mmu *mmu, u64 iova,
 	u64 addr = iova;
 	unsigned int i;
 
+	if (!sgt)
+		return msm_iommu_pagetable_map_prr(mmu, iova, len, prot);
+
 	for_each_sgtable_sg(sgt, sg, i) {
 		size_t size = sg->length;
 		phys_addr_t phys = sg_phys(sg);
@@ -177,9 +211,16 @@ static void msm_iommu_pagetable_destroy(struct msm_mmu *mmu)
 	 * If this is the last attached pagetable for the parent,
 	 * disable TTBR0 in the arm-smmu driver
 	 */
-	if (atomic_dec_return(&iommu->pagetables) == 0)
+	if (atomic_dec_return(&iommu->pagetables) == 0) {
 		adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, NULL);
 
+		if (adreno_smmu->set_prr_bit) {
+			adreno_smmu->set_prr_bit(adreno_smmu->cookie, false);
+			__free_page(iommu->prr_page);
+			iommu->prr_page = NULL;
+		}
+	}
+
 	free_io_pgtable_ops(pagetable->pgtbl_ops);
 	kfree(pagetable);
 }
@@ -336,6 +377,25 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent)
 			kfree(pagetable);
 			return ERR_PTR(ret);
 		}
+
+		BUG_ON(iommu->prr_page);
+		if (adreno_smmu->set_prr_bit) {
+			/*
+			 * We need a zero'd page for two reasons:
+			 *
+			 * 1) Reserve a known physical address to use when
+			 *    mapping NULL / sparsely resident regions
+			 * 2) Read back zero
+			 *
+			 * It appears the hw drops writes to the PRR region
+			 * on the floor, but reads actually return whatever
+			 * is in the PRR page.
+			 */
+			iommu->prr_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+			adreno_smmu->set_prr_addr(adreno_smmu->cookie,
+						  page_to_phys(iommu->prr_page));
+			adreno_smmu->set_prr_bit(adreno_smmu->cookie, true);
+		}
 	}
 
 	/* Needed later for TLB flush */

include/uapi/drm/msm_drm.h

@@ -91,6 +91,8 @@ struct drm_msm_timespec {
 #define MSM_PARAM_UBWC_SWIZZLE 0x12 /* RO */
 #define MSM_PARAM_MACROTILE_MODE 0x13 /* RO */
 #define MSM_PARAM_UCHE_TRAP_BASE 0x14 /* RO */
+/* PRR (Partially Resident Region) is required for sparse residency: */
+#define MSM_PARAM_HAS_PRR    0x15  /* RO */
 
 /* For backwards compat.  The original support for preemption was based on
  * a single ring per priority level so # of priority levels equals the #