[v2 12/31] drm/xe/svm: Remap and provide memmap backing for GPU vram

Matthew Brost matthew.brost at intel.com
Tue Apr 16 19:01:54 UTC 2024


On Tue, Apr 09, 2024 at 04:17:23PM -0400, Oak Zeng wrote:
> Memory remap GPU vram using devm_memremap_pages, so each GPU vram
> page is backed by a struct page.
> 
> Those struct pages are created to allow hmm migrate buffer b/t
> GPU vram and CPU system memory using existing Linux migration
> mechanism (i.e., migrating b/t CPU system memory and hard disk).
> 
> This is prepare work to enable svm (shared virtual memory) through
> Linux kernel hmm framework. The memory remap's page map type is set
> to MEMORY_DEVICE_PRIVATE for now. This means even though each GPU
> vram page get a struct page and can be mapped in CPU page table,
> but such pages are treated as GPU's private resource, so CPU can't
> access them. If CPU access such page, a page fault is triggered
> and page will be migrate to system memory.
> 
> For GPU device which supports coherent memory protocol b/t CPU and
> GPU (such as CXL and CAPI protocol), we can remap device memory as
> MEMORY_DEVICE_COHERENT. This is TBD.
> 
> v1:
> Changes per code review feedback from Matt:
>     change .o order in Makefile
>     fix indentation
>     change code order in mmio_fini
>     remove unnecessary header file
>     uniform xe_svm_devm_add/_remove parameter
>     use tile (vs dev) as pagemap.owner during memremap
>     only remap vram for platform that support usm
> Changes per review feedback from Brian:
>     s/xe_svm_devm_add/xe_devm_add
>     s/xe_svm_devm_remove/xe_devm_remove
>     move calling of xe_devm_add to xe_tile.c
> 
> Signed-off-by: Oak Zeng <oak.zeng at intel.com>
> Co-developed-by: Niranjana Vishwanathapura <niranjana.vishwanathapura at intel.com>
> Signed-off-by: Niranjana Vishwanathapura <niranjana.vishwanathapura at intel.com>
> Cc: Matthew Brost <matthew.brost at intel.com>
> Cc: Thomas Hellström <thomas.hellstrom at intel.com>
> Cc: Brian Welty <brian.welty at intel.com>
> ---
>  drivers/gpu/drm/xe/Makefile          |  1 +
>  drivers/gpu/drm/xe/xe_device_types.h |  8 +++
>  drivers/gpu/drm/xe/xe_mmio.c         |  6 ++
>  drivers/gpu/drm/xe/xe_svm.h          | 15 +++++
>  drivers/gpu/drm/xe/xe_svm_devmem.c   | 89 ++++++++++++++++++++++++++++
>  drivers/gpu/drm/xe/xe_tile.c         |  4 ++
>  6 files changed, 123 insertions(+)
>  create mode 100644 drivers/gpu/drm/xe/xe_svm.h
>  create mode 100644 drivers/gpu/drm/xe/xe_svm_devmem.c
> 
> diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
> index fff70fc9a09e..cd5213ba182b 100644
> --- a/drivers/gpu/drm/xe/Makefile
> +++ b/drivers/gpu/drm/xe/Makefile
> @@ -129,6 +129,7 @@ xe-y += xe_bb.o \
>  	xe_sa.o \
>  	xe_sched_job.o \
>  	xe_step.o \
> +	xe_svm_devmem.o \
>  	xe_sync.o \
>  	xe_tile.o \
>  	xe_tile_sysfs.o \
> diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
> index e73b9a086718..d6a14327986b 100644
> --- a/drivers/gpu/drm/xe/xe_device_types.h
> +++ b/drivers/gpu/drm/xe/xe_device_types.h
> @@ -103,6 +103,14 @@ 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_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c
> index 7ba2477452d7..12923fe6abae 100644
> --- a/drivers/gpu/drm/xe/xe_mmio.c
> +++ b/drivers/gpu/drm/xe/xe_mmio.c
> @@ -22,6 +22,7 @@
>  #include "xe_module.h"
>  #include "xe_sriov.h"
>  #include "xe_tile.h"
> +#include "xe_svm.h"
>  
>  #define XEHP_MTCFG_ADDR		XE_REG(0x101800)
>  #define TILE_COUNT		REG_GENMASK(15, 8)
> @@ -354,6 +355,11 @@ void xe_mmio_probe_tiles(struct xe_device *xe)
>  static void mmio_fini(struct drm_device *drm, void *arg)
>  {
>  	struct xe_device *xe = arg;
> +	struct xe_tile *tile;
> +	u8 id;
> +
> +	for_each_tile(tile, xe, id)
> +		xe_devm_remove(tile, &tile->mem.vram);
>  
>  	pci_iounmap(to_pci_dev(xe->drm.dev), xe->mmio.regs);
>  	if (xe->mem.vram.mapping)
> diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h
> new file mode 100644
> index 000000000000..e944971cfc6d
> --- /dev/null
> +++ b/drivers/gpu/drm/xe/xe_svm.h
> @@ -0,0 +1,15 @@
> +// SPDX-License-Identifier: MIT
> +/*
> + * Copyright © 2023 Intel Corporation
> + */
> +
> +#ifndef __XE_SVM_H
> +#define __XE_SVM_H
> +
> +struct xe_tile;
> +struct xe_mem_region;
> +
> +int xe_devm_add(struct xe_tile *tile, struct xe_mem_region *mr);
> +void xe_devm_remove(struct xe_tile *tile, struct xe_mem_region *mr);
> +
> +#endif
> diff --git a/drivers/gpu/drm/xe/xe_svm_devmem.c b/drivers/gpu/drm/xe/xe_svm_devmem.c
> new file mode 100644
> index 000000000000..31af56e8285a
> --- /dev/null
> +++ b/drivers/gpu/drm/xe/xe_svm_devmem.c
> @@ -0,0 +1,89 @@
> +// SPDX-License-Identifier: MIT
> +/*
> + * Copyright © 2023 Intel Corporation
> + */
> +
> +#include <linux/mm_types.h>
> +#include <linux/sched/mm.h>
> +
> +#include "xe_device_types.h"
> +#include "xe_svm.h"
> +
> +
> +static vm_fault_t xe_devm_migrate_to_ram(struct vm_fault *vmf)
> +{
> +	return 0;
> +}
> +
> +static void xe_devm_page_free(struct page *page)
> +{
> +}
> +
> +static const struct dev_pagemap_ops xe_devm_pagemap_ops = {
> +	.page_free = xe_devm_page_free,
> +	.migrate_to_ram = xe_devm_migrate_to_ram,
> +};
> +
> +/**
> + * xe_devm_add: Remap and provide memmap backing for device memory
> + * @tile: tile that the memory region blongs 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 = &xe_devm_pagemap_ops;
> +	mr->pagemap.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;
> +}
> +
> +/**
> + * xe_devm_remove: Unmap device memory and free resources
> + * @tile: xe tile
> + * @mr: memory region to remove
> + */
> +void xe_devm_remove(struct xe_tile *tile, struct xe_mem_region *mr)

Also I don't think function is not needed...

devm_memremap_pages registers devm_memremap_pages_release via
evm_add_action_or_reset...

And if it was we'd want to register a devm_fini function rather than
exporting a function and call it from the mmio layer.

Matt

> +{
> +	struct device *dev = &to_pci_dev(tile->xe->drm.dev)->dev;
> +
> +	/*FIXME: Does below cause a kernel hange during moduel remove?*/
> +	if (mr->hpa_base) {
> +		devm_memunmap_pages(dev, &mr->pagemap);
> +		devm_release_mem_region(dev, mr->pagemap.range.start,
> +			mr->pagemap.range.end - mr->pagemap.range.start + 1);
> +	}
> +}
> +
> diff --git a/drivers/gpu/drm/xe/xe_tile.c b/drivers/gpu/drm/xe/xe_tile.c
> index 0650b2fa75ef..f1c4f9de51df 100644
> --- a/drivers/gpu/drm/xe/xe_tile.c
> +++ b/drivers/gpu/drm/xe/xe_tile.c
> @@ -14,6 +14,7 @@
>  #include "xe_tile_sysfs.h"
>  #include "xe_ttm_vram_mgr.h"
>  #include "xe_wa.h"
> +#include "xe_svm.h"
>  
>  /**
>   * DOC: Multi-tile Design
> @@ -158,6 +159,7 @@ 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;
>  
>  	xe_device_mem_access_get(tile_to_xe(tile));
> @@ -175,6 +177,8 @@ int xe_tile_init_noalloc(struct xe_tile *tile)
>  
>  	xe_tile_sysfs_init(tile);
>  
> +	if (xe->info.has_usm)
> +		xe_devm_add(tile, &tile->mem.vram);
>  err_mem_access:
>  	xe_device_mem_access_put(tile_to_xe(tile));
>  	return err;
> -- 
> 2.26.3
> 


More information about the Intel-xe mailing list