drm/amdkfd: add SPM support for SVM

When CPU is connected throug XGMI, it has coherent access to VRAM
resource.  In this case that resource is taken from a table in the device
gmc aperture base.  This resource is used along with the device type,
which could be DEVICE_PRIVATE or DEVICE_COHERENT to create the device page
map region.

Also, MIGRATE_VMA_SELECT_DEVICE_COHERENT flag is selected for coherent
type case during migration to device.

Link: https://lkml.kernel.org/r/20220715150521.18165-8-alex.sierra@amd.com
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 21 insertions, 13 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index e44376c2ecdc..f73e3e340413 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -671,13 +671,15 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 	migrate.vma = vma;
 	migrate.start = start;
 	migrate.end = end;
-	migrate.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
 	migrate.pgmap_owner = SVM_ADEV_PGMAP_OWNER(adev);
+	if (adev->gmc.xgmi.connected_to_cpu)
+		migrate.flags = MIGRATE_VMA_SELECT_DEVICE_COHERENT;
+	else
+		migrate.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
 
 	buf = kvcalloc(npages,
 		       2 * sizeof(*migrate.src) + sizeof(uint64_t) + sizeof(dma_addr_t),
 		       GFP_KERNEL);
-
 	if (!buf)
 		goto out;
 
@@ -947,7 +949,7 @@ int svm_migrate_init(struct amdgpu_device *adev)
 {
 	struct kfd_dev *kfddev = adev->kfd.dev;
 	struct dev_pagemap *pgmap;
-	struct resource *res;
+	struct resource *res = NULL;
 	unsigned long size;
 	void *r;
 
@@ -962,28 +964,34 @@ int svm_migrate_init(struct amdgpu_device *adev)
 	 * should remove reserved size
 	 */
 	size = ALIGN(adev->gmc.real_vram_size, 2ULL << 20);
-	res = devm_request_free_mem_region(adev->dev, &iomem_resource, size);
-	if (IS_ERR(res))
-		return -ENOMEM;
+	if (adev->gmc.xgmi.connected_to_cpu) {
+		pgmap->range.start = adev->gmc.aper_base;
+		pgmap->range.end = adev->gmc.aper_base + adev->gmc.aper_size - 1;
+		pgmap->type = MEMORY_DEVICE_COHERENT;
+	} else {
+		res = devm_request_free_mem_region(adev->dev, &iomem_resource, size);
+		if (IS_ERR(res))
+			return -ENOMEM;
+		pgmap->range.start = res->start;
+		pgmap->range.end = res->end;
+		pgmap->type = MEMORY_DEVICE_PRIVATE;
+	}
 
-	pgmap->type = MEMORY_DEVICE_PRIVATE;
 	pgmap->nr_range = 1;
-	pgmap->range.start = res->start;
-	pgmap->range.end = res->end;
 	pgmap->ops = &svm_migrate_pgmap_ops;
 	pgmap->owner = SVM_ADEV_PGMAP_OWNER(adev);
-	pgmap->flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
-
+	pgmap->flags = 0;
 	/* Device manager releases device-specific resources, memory region and
 	 * pgmap when driver disconnects from device.
 	 */
 	r = devm_memremap_pages(adev->dev, pgmap);
 	if (IS_ERR(r)) {
 		pr_err("failed to register HMM device memory\n");
-
 		/* Disable SVM support capability */
 		pgmap->type = 0;
-		devm_release_mem_region(adev->dev, res->start, resource_size(res));
+		if (pgmap->type == MEMORY_DEVICE_PRIVATE)
+			devm_release_mem_region(adev->dev, res->start,
+						res->end - res->start + 1);
 		return PTR_ERR(r);
 	}