On Sat, Dec 21, 2024 at 12:09:55AM +0530, Ghimiray, Himal Prasad wrote:
>
>
> On 18-12-2024 05:03, Matthew Brost wrote:
> > Add SVM device memory mirroring which enables device pages for
> > migration. Enabled via CONFIG_XE_DEVMEM_MIRROR Kconfig. Kconfig option
> > defaults to enabled. If not enabled, SVM will work sans migration and
> > KMD memory footprint will be less.
> >
> > v3:
> > - Add CONFIG_XE_DEVMEM_MIRROR
> >
> > Signed-off-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@xxxxxxxxx>
> > Signed-off-by: Oak Zeng <oak.zeng@xxxxxxxxx>
> > Signed-off-by: Matthew Brost <matthew.brost@xxxxxxxxx>
> > ---
> > drivers/gpu/drm/xe/Kconfig | 9 ++++
> > drivers/gpu/drm/xe/xe_device_types.h | 8 ++++
> > drivers/gpu/drm/xe/xe_svm.c | 62 +++++++++++++++++++++++++++-
> > drivers/gpu/drm/xe/xe_svm.h | 3 ++
> > drivers/gpu/drm/xe/xe_tile.c | 5 +++
> > 5 files changed, 85 insertions(+), 2 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/xe/Kconfig b/drivers/gpu/drm/xe/Kconfig
> > index 3a08e16bfada..1989c99a9f5a 100644
> > --- a/drivers/gpu/drm/xe/Kconfig
> > +++ b/drivers/gpu/drm/xe/Kconfig
> > @@ -60,6 +60,15 @@ config DRM_XE_DISPLAY
> > help
> > Disable this option only if you want to compile out display support.
> > +config CONFIG_XE_DEVMEM_MIRROR
>
>
> %s/CONFIG_XE_DEVMEM_MIRROR/XE_DEVMEM_MIRROR
>
Yep, missed this. This version is broken with proper Kconfig enabled
too. Working on fixing this up now.
Matt
>
> > + bool "Enable device memory mirror"
> > + depends on DRM_XE
> > + select CONFIG_GET_FREE_REGION
> > + default y
> > + help
> > + Disable this option only if you want to compile out without device
> > + memory mirror. Will reduce KMD memory footprint when disabled.
> > +
> > config DRM_XE_FORCE_PROBE
> > string "Force probe xe for selected Intel hardware IDs"
> > depends on DRM_XE
> > diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
> > index 8a7b15972413..b949a960cebb 100644
> > --- a/drivers/gpu/drm/xe/xe_device_types.h
> > +++ b/drivers/gpu/drm/xe/xe_device_types.h
> > @@ -102,6 +102,14 @@ struct xe_mem_region {
> > resource_size_t actual_physical_size;
> > /** @mapping: pointer to VRAM mappable space */
> > void __iomem *mapping;
> > + /** @pagemap: Used to remap device memory as ZONE_DEVICE */
> > + struct dev_pagemap pagemap;
> > + /**
> > + * @hpa_base: base host physical address
> > + *
> > + * This is generated when remap device memory as ZONE_DEVICE
> > + */
> > + resource_size_t hpa_base;
> > };
> > /**
> > diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
> > index 3cbf29732249..2860e54bb035 100644
> > --- a/drivers/gpu/drm/xe/xe_svm.c
> > +++ b/drivers/gpu/drm/xe/xe_svm.c
> > @@ -19,6 +19,11 @@ static struct xe_vm *range_to_vm(struct drm_gpusvm_range *r)
> > return gpusvm_to_vm(r->gpusvm);
> > }
> > +static void *xe_svm_devm_owner(struct xe_device *xe)
> > +{
> > + return xe;
> > +}
> > +
> > static struct drm_gpusvm_range *
> > xe_svm_range_alloc(struct drm_gpusvm *gpusvm)
> > {
> > @@ -306,8 +311,8 @@ int xe_svm_init(struct xe_vm *vm)
> > xe_svm_garbage_collector_work_func);
> > err = drm_gpusvm_init(&vm->svm.gpusvm, "Xe SVM", &vm->xe->drm,
> > - current->mm, NULL, 0, vm->size,
> > - SZ_512M, &gpusvm_ops, fault_chunk_sizes,
> > + current->mm, xe_svm_devm_owner(vm->xe), 0,
> > + vm->size, SZ_512M, &gpusvm_ops, fault_chunk_sizes,
> > ARRAY_SIZE(fault_chunk_sizes));
> > if (err)
> > return err;
> > @@ -442,3 +447,56 @@ bool xe_svm_has_mapping(struct xe_vm *vm, u64 start, u64 end)
> > {
> > return drm_gpusvm_has_mapping(&vm->svm.gpusvm, start, end);
> > }
> > +
> > +#if IS_ENABLED(CONFIG_XE_DEVMEM_MIRROR)
> > +/**
> > + * xe_devm_add: Remap and provide memmap backing for device memory
> > + * @tile: tile that the memory region belongs to
> > + * @mr: memory region to remap
> > + *
> > + * This remap device memory to host physical address space and create
> > + * struct page to back device memory
> > + *
> > + * Return: 0 on success standard error code otherwise
> > + */
> > +int xe_devm_add(struct xe_tile *tile, struct xe_mem_region *mr)
> > +{
> > + struct xe_device *xe = tile_to_xe(tile);
> > + struct device *dev = &to_pci_dev(xe->drm.dev)->dev;
> > + struct resource *res;
> > + void *addr;
> > + int ret;
> > +
> > + res = devm_request_free_mem_region(dev, &iomem_resource,
> > + mr->usable_size);
> > + if (IS_ERR(res)) {
> > + ret = PTR_ERR(res);
> > + return ret;
> > + }
> > +
> > + mr->pagemap.type = MEMORY_DEVICE_PRIVATE;
> > + mr->pagemap.range.start = res->start;
> > + mr->pagemap.range.end = res->end;
> > + mr->pagemap.nr_range = 1;
> > + mr->pagemap.ops = drm_gpusvm_pagemap_ops_get();
> > + mr->pagemap.owner = xe_svm_devm_owner(xe);
> > + addr = devm_memremap_pages(dev, &mr->pagemap);
> > + if (IS_ERR(addr)) {
> > + devm_release_mem_region(dev, res->start, resource_size(res));
> > + ret = PTR_ERR(addr);
> > + drm_err(&xe->drm, "Failed to remap tile %d memory, errno %d\n",
> > + tile->id, ret);
> > + return ret;
> > + }
> > + mr->hpa_base = res->start;
> > +
> > + drm_info(&xe->drm, "Added tile %d memory [%llx-%llx] to devm, remapped to %pr\n",
> > + tile->id, mr->io_start, mr->io_start + mr->usable_size, res);
> > + return 0;
> > +}
> > +#else
> > +int xe_devm_add(struct xe_tile *tile, struct xe_mem_region *mr)
> > +{
> > + return 0;
> > +}
> > +#endif
> > diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h
> > index ddce1069ba1e..85832e6ed3f5 100644
> > --- a/drivers/gpu/drm/xe/xe_svm.h
> > +++ b/drivers/gpu/drm/xe/xe_svm.h
> > @@ -11,6 +11,7 @@
> > #define XE_INTERCONNECT_VRAM DRM_INTERCONNECT_DRIVER
> > +struct xe_mem_region;
> > struct xe_tile;
> > struct xe_vm;
> > struct xe_vma;
> > @@ -36,6 +37,8 @@ struct xe_svm_range {
> > u8 tile_invalidated;
> > };
> > +int xe_devm_add(struct xe_tile *tile, struct xe_mem_region *mr);
> > +
> > int xe_svm_init(struct xe_vm *vm);
> > void xe_svm_fini(struct xe_vm *vm);
> > diff --git a/drivers/gpu/drm/xe/xe_tile.c b/drivers/gpu/drm/xe/xe_tile.c
> > index 07cf7cfe4abd..bbb430392dfb 100644
> > --- a/drivers/gpu/drm/xe/xe_tile.c
> > +++ b/drivers/gpu/drm/xe/xe_tile.c
> > @@ -13,6 +13,7 @@
> > #include "xe_migrate.h"
> > #include "xe_pcode.h"
> > #include "xe_sa.h"
> > +#include "xe_svm.h"
> > #include "xe_tile.h"
> > #include "xe_tile_sysfs.h"
> > #include "xe_ttm_vram_mgr.h"
> > @@ -164,6 +165,7 @@ static int tile_ttm_mgr_init(struct xe_tile *tile)
> > */
> > int xe_tile_init_noalloc(struct xe_tile *tile)
> > {
> > + struct xe_device *xe = tile_to_xe(tile);
> > int err;
> > err = tile_ttm_mgr_init(tile);
> > @@ -176,6 +178,9 @@ int xe_tile_init_noalloc(struct xe_tile *tile)
> > xe_wa_apply_tile_workarounds(tile);
> > + if (xe->info.has_usm && IS_DGFX(xe))
> > + xe_devm_add(tile, &tile->mem.vram);
> > +
> > err = xe_tile_sysfs_init(tile);
> > return 0;
>
