Am 2021-08-24 um 11:48 p.m. schrieb Alex Sierra:
> 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_PUBLIC to create the device
> page map region.
>
> Signed-off-by: Alex Sierra <alex.sie...@amd.com>
> Reviewed-by: Felix Kuehling <felix.kuehl...@amd.com>
> ---
> v7:
> Remove lookup_resource call, so export symbol for this function
> is not longer required. Patch dropped "kernel: resource:
> lookup_resource as exported symbol"
> ---
> drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 29 +++++++++++++++---------
> 1 file changed, 18 insertions(+), 11 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> index 47ee9a895cd2..dd245699479f 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
> @@ -865,7 +865,7 @@ 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;
>
> @@ -880,19 +880,25 @@ 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_PUBLIC;
> + } 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;
> r = devm_memremap_pages(adev->dev, pgmap);
> - if (IS_ERR(r)) {
> + if (res && IS_ERR(r)) {
I think the (res && ...) condition means you only detect failures for
DEVICE_PRIVATE memory. Why are you ignoring failures for DEVICE_PUBLIC?
For DEVICE_PUBLIC you can skip devm_release_mem_region, but you still
need to detect and return the error. Also, using res as an indicator is
a bit obscure. I'd put an if (pgmap->type == MEMORY_DEVICE_PRIVATE)
before the devm_release_mem_region call.
Regards,
Felix
> pr_err("failed to register HMM device memory\n");
> devm_release_mem_region(adev->dev, res->start,
> res->end - res->start + 1);
> @@ -914,6 +920,7 @@ void svm_migrate_fini(struct amdgpu_device *adev)
> struct dev_pagemap *pgmap = &adev->kfd.dev->pgmap;
>
> devm_memunmap_pages(adev->dev, pgmap);
> - devm_release_mem_region(adev->dev, pgmap->range.start,
> - pgmap->range.end - pgmap->range.start + 1);
> + if (pgmap->type == MEMORY_DEVICE_PRIVATE)
> + devm_release_mem_region(adev->dev, pgmap->range.start,
> + pgmap->range.end - pgmap->range.start +
> 1);
> }
