Re: [PATCH 1/5] drm/xe/svm: Remap and provide memmap backing for GPU vram

["Welty, Brian" <brian.welty@intel.com>]

Hi Oak,

On 3/13/2024 8:35 PM, 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.
> 
> Signed-off-by: Oak Zeng <oak.zeng@intel.com>
> Co-developed-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
> Signed-off-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: Thomas Hellström <thomas.hellstrom@intel.com>
> Cc: Brian Welty <brian.welty@intel.com>
> ---
>   drivers/gpu/drm/xe/Makefile          |  3 +-
>   drivers/gpu/drm/xe/xe_device_types.h |  9 +++
>   drivers/gpu/drm/xe/xe_mmio.c         |  8 +++
>   drivers/gpu/drm/xe/xe_svm.h          | 14 +++++
>   drivers/gpu/drm/xe/xe_svm_devmem.c   | 91 ++++++++++++++++++++++++++++
>   5 files changed, 124 insertions(+), 1 deletion(-)
>   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 c531210695db..840467080e59 100644
> --- a/drivers/gpu/drm/xe/Makefile
> +++ b/drivers/gpu/drm/xe/Makefile
> @@ -142,7 +142,8 @@ xe-y += xe_bb.o \
>   	xe_vram_freq.o \
>   	xe_wait_user_fence.o \
>   	xe_wa.o \
> -	xe_wopcm.o
> +	xe_wopcm.o \
> +	xe_svm_devmem.o

Minor, but maintainers want above alphabetically sorted.

>   
>   # graphics hardware monitoring (HWMON) support
>   xe-$(CONFIG_HWMON) += xe_hwmon.o
> diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
> index 9785eef2e5a4..f27c3bee8ce7 100644
> --- a/drivers/gpu/drm/xe/xe_device_types.h
> +++ b/drivers/gpu/drm/xe/xe_device_types.h
> @@ -99,6 +99,15 @@ 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 e3db3a178760..0d795394bc4c 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)
> @@ -286,6 +287,7 @@ int xe_mmio_probe_vram(struct xe_device *xe)
>   		}
>   
>   		io_size -= min_t(u64, tile_size, io_size);
> +		xe_svm_devm_add(tile, &tile->mem.vram);

I think slightly more appropriate call site for this might be 
xe_tile_init_noalloc(), as that function states it is preparing tile
for VRAM allocations.
Also, I mention because we might like the flexiblity in future to call 
this once for xe_device.mem.vram, instead of calling for each tile,
and easier to handle that in xe_tile.c instead of xe_mmio.c.

Related comment below.


>   	}
>   
>   	xe->mem.vram.actual_physical_size = total_size;
> @@ -354,10 +356,16 @@ 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;
>   
>   	pci_iounmap(to_pci_dev(xe->drm.dev), xe->mmio.regs);
>   	if (xe->mem.vram.mapping)
>   		iounmap(xe->mem.vram.mapping);
> +
> +	for_each_tile(tile, xe, id)
> +		xe_svm_devm_remove(xe, &tile->mem.vram);
> +
>   }
>   
>   static int xe_verify_lmem_ready(struct xe_device *xe)
> diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h
> new file mode 100644
> index 000000000000..09f9afb0e7d4
> --- /dev/null
> +++ b/drivers/gpu/drm/xe/xe_svm.h
> @@ -0,0 +1,14 @@
> +// SPDX-License-Identifier: MIT
> +/*
> + * Copyright © 2023 Intel Corporation
> + */
> +
> +#ifndef __XE_SVM_H
> +#define __XE_SVM_H
> +
> +#include "xe_device_types.h"
> +
> +int xe_svm_devm_add(struct xe_tile *tile, struct xe_mem_region *mem);
> +void xe_svm_devm_remove(struct xe_device *xe, struct xe_mem_region *mem);
> +
> +#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..63b7a1961cc6
> --- /dev/null
> +++ b/drivers/gpu/drm/xe/xe_svm_devmem.c
> @@ -0,0 +1,91 @@
> +// 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_trace.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_svm_devm_add: Remap and provide memmap backing for device memory

Do we really need 'svm' in function name?

> + * @tile: tile that the memory region blongs to

We might like flexibility in future to call this once for 
xe_device.mem.vram, instead of calling for each tile.
So can we remove the tile argument, and just pass the xe_device pointer
and tile->id ?


> + * @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_svm_devm_add(struct xe_tile *tile, struct xe_mem_region *mr)
> +{
> +	struct device *dev = &to_pci_dev(tile->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 = tile->xe->drm.dev;
> +	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(&tile->xe->drm, "Failed to remap tile %d memory, errno %d\n",
> +				tile->id, ret);
> +		return ret;
> +	}
> +	mr->hpa_base = res->start;
> +
> +	drm_info(&tile->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_svm_devm_remove: Unmap device memory and free resources
> + * @xe: xe device
> + * @mr: memory region to remove
> + */
> +void xe_svm_devm_remove(struct xe_device *xe, struct xe_mem_region *mr)
> +{
> +	/*FIXME: below cause a kernel hange during moduel remove*/
> +#if 0
> +	struct device *dev = &to_pci_dev(xe->drm.dev)->dev;
> +
> +	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);
> +	}
> +#endif
> +}
> +