[RFC,2/6] mm/gmem: add arch-independent abstraction to track address mapping status

Commit Message

zhuweixi Nov. 28, 2023, 12:50 p.m. UTC

This patch adds an abstraction layer, struct vm_object, that maintains
per-process virtual-to-physical mapping status stored in struct gm_mapping.
For example, a virtual page may be mapped to a CPU physical page or to a
device physical page. Struct vm_object effectively maintains an
arch-independent page table, which is defined as a "logical page table".
While arch-dependent page table used by a real MMU is named a "physical
page table". The logical page table is useful if Linux core MM is extended
to handle a unified virtual address space with external accelerators using
customized MMUs.

In this patch, struct vm_object utilizes a radix
tree (xarray) to track where a virtual page is mapped to. This adds extra
memory consumption from xarray, but provides a nice abstraction to isolate
mapping status from the machine-dependent layer (PTEs). Besides supporting
accelerators with external MMUs, struct vm_object is planned to further
union with i_pages in struct address_mapping for file-backed memory.

The idea of struct vm_object is originated from FreeBSD VM design, which
provides a unified abstraction for anonymous memory, file-backed memory,
page cache and etc[1].

Currently, Linux utilizes a set of hierarchical page walk functions to
abstract page table manipulations of different CPU architecture. The
problem happens when a device wants to reuse Linux MM code to manage its
page table -- the device page table may not be accessible to the CPU.
Existing solution like Linux HMM utilizes the MMU notifier mechanisms to
invoke device-specific MMU functions, but relies on encoding the mapping
status on the CPU page table entries. This entangles machine-independent
code with machine-dependent code, and also brings unnecessary restrictions.
The PTE size and format vary arch by arch, which harms the extensibility.

[1] https://docs.freebsd.org/en/articles/vm-design/

Signed-off-by: Weixi Zhu <[e-mail]>
---
 include/linux/gmem.h     | 120 +++++++++++++++++++++++++
 include/linux/mm_types.h |   4 +
 mm/Makefile              |   2 +-
 mm/vm_object.c           | 184 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 309 insertions(+), 1 deletion(-)
 create mode 100644 mm/vm_object.c

Comments

emily Nov. 29, 2023, 8:33 a.m. UTC | #1

On 11/28/23 07:50, Weixi Zhu wrote:
> This patch adds an abstraction layer, struct vm_object, that maintains
> per-process virtual-to-physical mapping status stored in struct gm_mapping.
> For example, a virtual page may be mapped to a CPU physical page or to a
> device physical page. Struct vm_object effectively maintains an
> arch-independent page table, which is defined as a "logical page table".
> While arch-dependent page table used by a real MMU is named a "physical
> page table". The logical page table is useful if Linux core MM is extended
> to handle a unified virtual address space with external accelerators using
> customized MMUs.
>
> In this patch, struct vm_object utilizes a radix
> tree (xarray) to track where a virtual page is mapped to. This adds extra
> memory consumption from xarray, but provides a nice abstraction to isolate
> mapping status from the machine-dependent layer (PTEs). Besides supporting
> accelerators with external MMUs, struct vm_object is planned to further
> union with i_pages in struct address_mapping for file-backed memory.
>
> The idea of struct vm_object is originated from FreeBSD VM design, which
> provides a unified abstraction for anonymous memory, file-backed memory,
> page cache and etc[1].
>
> Currently, Linux utilizes a set of hierarchical page walk functions to
> abstract page table manipulations of different CPU architecture. The
> problem happens when a device wants to reuse Linux MM code to manage its
> page table -- the device page table may not be accessible to the CPU.
> Existing solution like Linux HMM utilizes the MMU notifier mechanisms to
> invoke device-specific MMU functions, but relies on encoding the mapping
> status on the CPU page table entries. This entangles machine-independent
> code with machine-dependent code, and also brings unnecessary restrictions.
> The PTE size and format vary arch by arch, which harms the extensibility.
>
> [1] https://docs.freebsd.org/en/articles/vm-design/
>
> Signed-off-by: Weixi Zhu <[e-mail]>
> ---
>   include/linux/gmem.h     | 120 +++++++++++++++++++++++++
>   include/linux/mm_types.h |   4 +
>   mm/Makefile              |   2 +-
>   mm/vm_object.c           | 184 +++++++++++++++++++++++++++++++++++++++
>   4 files changed, 309 insertions(+), 1 deletion(-)
>   create mode 100644 mm/vm_object.c
>
> diff --git a/include/linux/gmem.h b/include/linux/gmem.h
> index fff877873557..529ff6755a99 100644
> --- a/include/linux/gmem.h
> +++ b/include/linux/gmem.h
> @@ -9,11 +9,131 @@
>   #ifndef _GMEM_H
>   #define _GMEM_H
>   
> +#include <linux/mm_types.h>
> +
>   #ifdef CONFIG_GMEM
> +
> +#define GM_PAGE_CPU	0x10 /* Determines whether page is a pointer or a pfn number. */
> +#define GM_PAGE_DEVICE	0x20
> +#define GM_PAGE_NOMAP	0x40
> +#define GM_PAGE_WILLNEED	0x80
> +
> +#define GM_PAGE_TYPE_MASK	(GM_PAGE_CPU | GM_PAGE_DEVICE | GM_PAGE_NOMAP)
> +
> +struct gm_mapping {
> +	unsigned int flag;
> +
> +	union {
> +		struct page *page;	/* CPU node */
> +		struct gm_dev *dev;	/* hetero-node. TODO: support multiple devices */
> +		unsigned long pfn;
> +	};
> +
> +	struct mutex lock;
> +};
> +
> +static inline void gm_mapping_flags_set(struct gm_mapping *gm_mapping, int flags)
> +{
> +	if (flags & GM_PAGE_TYPE_MASK)
> +		gm_mapping->flag &= ~GM_PAGE_TYPE_MASK;
> +
> +	gm_mapping->flag |= flags;
> +}
> +
> +static inline void gm_mapping_flags_clear(struct gm_mapping *gm_mapping, int flags)
> +{
> +	gm_mapping->flag &= ~flags;
> +}
> +
> +static inline bool gm_mapping_cpu(struct gm_mapping *gm_mapping)
> +{
> +	return !!(gm_mapping->flag & GM_PAGE_CPU);
> +}
> +
> +static inline bool gm_mapping_device(struct gm_mapping *gm_mapping)
> +{
> +	return !!(gm_mapping->flag & GM_PAGE_DEVICE);
> +}
> +
> +static inline bool gm_mapping_nomap(struct gm_mapping *gm_mapping)
> +{
> +	return !!(gm_mapping->flag & GM_PAGE_NOMAP);
> +}
> +
> +static inline bool gm_mapping_willneed(struct gm_mapping *gm_mapping)
> +{
> +	return !!(gm_mapping->flag & GM_PAGE_WILLNEED);
> +}
> +
>   /* h-NUMA topology */
>   void __init hnuma_init(void);
> +
> +/* vm object */
> +/*
> + * Each per-process vm_object tracks the mapping status of virtual pages from
> + * all VMAs mmap()-ed with MAP_PRIVATE | MAP_PEER_SHARED.
> + */
> +struct vm_object {
> +	spinlock_t lock;
> +
> +	/*
> +	 * The logical_page_table is a container that holds the mapping
> +	 * information between a VA and a struct page.
> +	 */
> +	struct xarray *logical_page_table;
> +	atomic_t nr_pages;
> +};
> +
> +int __init vm_object_init(void);
> +struct vm_object *vm_object_create(struct mm_struct *mm);
> +void vm_object_drop_locked(struct mm_struct *mm);
> +
> +struct gm_mapping *alloc_gm_mapping(void);
> +void free_gm_mappings(struct vm_area_struct *vma);
> +struct gm_mapping *vm_object_lookup(struct vm_object *obj, unsigned long va);
> +void vm_object_mapping_create(struct vm_object *obj, unsigned long start);
> +void unmap_gm_mappings_range(struct vm_area_struct *vma, unsigned long start,
> +			     unsigned long end);
> +void munmap_in_peer_devices(struct mm_struct *mm, unsigned long start,
> +			    unsigned long end);
>   #else
>   static inline void hnuma_init(void) {}
> +static inline void __init vm_object_init(void)
> +{
> +}
> +static inline struct vm_object *vm_object_create(struct vm_area_struct *vma)
> +{
> +	return NULL;
> +}
> +static inline void vm_object_drop_locked(struct vm_area_struct *vma)
> +{
> +}
> +static inline struct gm_mapping *alloc_gm_mapping(void)
> +{
> +	return NULL;
> +}
> +static inline void free_gm_mappings(struct vm_area_struct *vma)
> +{
> +}
> +static inline struct gm_mapping *vm_object_lookup(struct vm_object *obj,
> +						  unsigned long va)
> +{
> +	return NULL;
> +}
> +static inline void vm_object_mapping_create(struct vm_object *obj,
> +					    unsigned long start)
> +{
> +}
> +static inline void unmap_gm_mappings_range(struct vm_area_struct *vma,
> +					   unsigned long start,
> +					   unsigned long end)
> +{
> +}
> +static inline void munmap_in_peer_devices(struct mm_struct *mm,
> +					  unsigned long start,
> +					  unsigned long end)
> +{
> +}
>   #endif
>   
>   #endif /* _GMEM_H */
> diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
> index 957ce38768b2..4e50dc019d75 100644
> --- a/include/linux/mm_types.h
> +++ b/include/linux/mm_types.h
> @@ -31,6 +31,7 @@
>   
>   struct address_space;
>   struct mem_cgroup;
> +struct vm_object;
>   
>   /*
>    * Each physical page in the system has a struct page associated with
> @@ -974,6 +975,9 @@ struct mm_struct {
>   #endif
>   		} lru_gen;
>   #endif /* CONFIG_LRU_GEN */
> +#ifdef CONFIG_GMEM
> +		struct vm_object *vm_obj;
> +#endif
>   	} __randomize_layout;
>   
>   	/*
> diff --git a/mm/Makefile b/mm/Makefile
> index f48ea2eb4a44..d2dfab012c96 100644
> --- a/mm/Makefile
> +++ b/mm/Makefile
> @@ -138,4 +138,4 @@ obj-$(CONFIG_IO_MAPPING) += io-mapping.o
>   obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o
>   obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o
>   obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o
> -obj-$(CONFIG_GMEM) += gmem.o
> +obj-$(CONFIG_GMEM) += gmem.o vm_object.o
> diff --git a/mm/vm_object.c b/mm/vm_object.c
> new file mode 100644
> index 000000000000..4e76737e0ca1
> --- /dev/null
> +++ b/mm/vm_object.c
> @@ -0,0 +1,184 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * arch/alpha/boot/bootp.c
> + *
> + * Copyright (C) 1997 Jay Estabrook
> + *
> + * This file is used for creating a bootp file for the Linux/AXP kernel
> + *
> + * based significantly on the arch/alpha/boot/main.c of Linus Torvalds
> + */


i believe you have made a mistake here. you will likely want to correct 
the information in this comment.

> +#include <linux/mm.h>
> +#include <linux/gmem.h>
> +
> +/*
> + * Sine VM_OBJECT maintains the logical page table under each VMA, and each VMA
> + * points to a VM_OBJECT. Ultimately VM_OBJECTs must be maintained as long as VMA
> + * gets changed: merge, split, adjust
> + */
> +static struct kmem_cache *vm_object_cachep;
> +static struct kmem_cache *gm_mapping_cachep;
> +
> +static inline void release_gm_mapping(struct gm_mapping *mapping)
> +{
> +	kmem_cache_free(gm_mapping_cachep, mapping);
> +}
> +
> +static inline struct gm_mapping *lookup_gm_mapping(struct vm_object *obj,
> +						   unsigned long pindex)
> +{
> +	return xa_load(obj->logical_page_table, pindex);
> +}
> +
> +int __init vm_object_init(void)
> +{
> +	vm_object_cachep = KMEM_CACHE(vm_object, 0);
> +	if (!vm_object_cachep)
> +		goto out;
> +
> +	gm_mapping_cachep = KMEM_CACHE(gm_mapping, 0);
> +	if (!gm_mapping_cachep)
> +		goto free_vm_object;
> +
> +	return 0;
> +free_vm_object:
> +	kmem_cache_destroy(vm_object_cachep);
> +out:
> +	return -ENOMEM;
> +}
> +
> +/*
> + * Create a VM_OBJECT and attach it to a mm_struct
> + * This should be called when a task_struct is created.
> + */
> +struct vm_object *vm_object_create(struct mm_struct *mm)
> +{
> +	struct vm_object *obj = kmem_cache_alloc(vm_object_cachep, GFP_KERNEL);
> +
> +	if (!obj)
> +		return NULL;
> +
> +	spin_lock_init(&obj->lock);
> +
> +	/*
> +	 * The logical page table maps va >> PAGE_SHIFT
> +	 * to pointers of struct gm_mapping.
> +	 */
> +	obj->logical_page_table = kmalloc(sizeof(struct xarray), GFP_KERNEL);
> +	if (!obj->logical_page_table) {
> +		kmem_cache_free(vm_object_cachep, obj);
> +		return NULL;
> +	}
> +
> +	xa_init(obj->logical_page_table);
> +	atomic_set(&obj->nr_pages, 0);
> +
> +	return obj;
> +}
> +
> +/* This should be called when a mm no longer refers to a VM_OBJECT */
> +void vm_object_drop_locked(struct mm_struct *mm)
> +{
> +	struct vm_object *obj = mm->vm_obj;
> +
> +	if (!obj)
> +		return;
> +
> +	/*
> +	 * We must enter this with VMA write-locked, which is unfortunately a
> +	 * giant lock.
> +	 */
> +	mmap_assert_write_locked(mm);
> +	mm->vm_obj = NULL;
> +
> +	xa_destroy(obj->logical_page_table);
> +	kfree(obj->logical_page_table);
> +	kmem_cache_free(vm_object_cachep, obj);
> +}
> +
> +/*
> + * Given a VA, the page_index is computed by
> + * page_index = address >> PAGE_SHIFT
> + */
> +struct gm_mapping *vm_object_lookup(struct vm_object *obj, unsigned long va)
> +{
> +	return lookup_gm_mapping(obj, va >> PAGE_SHIFT);
> +}
> +EXPORT_SYMBOL_GPL(vm_object_lookup);
> +
> +void vm_object_mapping_create(struct vm_object *obj, unsigned long start)
> +{
> +
> +	unsigned long index = start >> PAGE_SHIFT;
> +	struct gm_mapping *gm_mapping;
> +
> +	if (!obj)
> +		return;
> +
> +	gm_mapping = alloc_gm_mapping();
> +	if (!gm_mapping)
> +		return;
> +
> +	__xa_store(obj->logical_page_table, index, gm_mapping, GFP_KERNEL);
> +}
> +
> +/* gm_mapping will not be release dynamically */
> +struct gm_mapping *alloc_gm_mapping(void)
> +{
> +	struct gm_mapping *gm_mapping = kmem_cache_zalloc(gm_mapping_cachep, GFP_KERNEL);
> +
> +	if (!gm_mapping)
> +		return NULL;
> +
> +	gm_mapping_flags_set(gm_mapping, GM_PAGE_NOMAP);
> +	mutex_init(&gm_mapping->lock);
> +
> +	return gm_mapping;
> +}
> +
> +/* This should be called when a PEER_SHAERD vma is freed */
> +void free_gm_mappings(struct vm_area_struct *vma)
> +{
> +	struct gm_mapping *gm_mapping;
> +	struct vm_object *obj;
> +
> +	obj = vma->vm_mm->vm_obj;
> +	if (!obj)
> +		return;
> +
> +	XA_STATE(xas, obj->logical_page_table, vma->vm_start >> PAGE_SHIFT);
> +
> +	xa_lock(obj->logical_page_table);
> +		xas_for_each(&xas, gm_mapping, vma->vm_end >> PAGE_SHIFT) {
> +		release_gm_mapping(gm_mapping);
> +		xas_store(&xas, NULL);
> +	}
> +	xa_unlock(obj->logical_page_table);
> +}
> +
> +void unmap_gm_mappings_range(struct vm_area_struct *vma, unsigned long start,
> +			    unsigned long end)
> +{
> +	struct xarray *logical_page_table;
> +	struct gm_mapping *gm_mapping;
> +	struct page *page = NULL;
> +
> +	if (!vma->vm_mm->vm_obj)
> +		return;
> +
> +	logical_page_table = vma->vm_mm->vm_obj->logical_page_table;
> +	if (!logical_page_table)
> +		return;
> +
> +	XA_STATE(xas, logical_page_table, start >> PAGE_SHIFT);
> +
> +	xa_lock(logical_page_table);
> +	xas_for_each(&xas, gm_mapping, end >> PAGE_SHIFT) {
> +		page = gm_mapping->page;
> +		if (page && (page_ref_count(page) != 0)) {
> +			put_page(page);
> +			gm_mapping->page = NULL;
> +		}
> +	}
> +	xa_unlock(logical_page_table);
> +}

zhuweixi Nov. 29, 2023, 8:49 a.m. UTC | #2

Oops, that should be changed to the following:

/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * Generalized Memory Management.
 *
 * Copyright (C) 2023- Huawei, Inc.
 * Author: Weixi Zhu
 *
 */

Thanks for pointing it out.
-Weixi

-----Original Message-----
From: emily <[e-mail]> 
Sent: Wednesday, November 29, 2023 4:33 PM
To: zhuweixi <[e-mail]>; [e-mail]; [e-mail]; [e-mail]
Cc: [e-mail]; [e-mail]; [e-mail]; [e-mail]; [e-mail]; [e-mail]; [e-mail]; [e-mail]; [e-mail]; [e-mail]; [e-mail]; [e-mail]; [e-mail]; [e-mail]; [e-mail]; [e-mail]; [e-mail]; [e-mail]; [e-mail]; [e-mail]; [e-mail]
Subject: Re: [RFC PATCH 2/6] mm/gmem: add arch-independent abstraction to track address mapping status


On 11/28/23 07:50, Weixi Zhu wrote:
> This patch adds an abstraction layer, struct vm_object, that maintains 
> per-process virtual-to-physical mapping status stored in struct gm_mapping.
> For example, a virtual page may be mapped to a CPU physical page or to 
> a device physical page. Struct vm_object effectively maintains an 
> arch-independent page table, which is defined as a "logical page table".
> While arch-dependent page table used by a real MMU is named a 
> "physical page table". The logical page table is useful if Linux core 
> MM is extended to handle a unified virtual address space with external 
> accelerators using customized MMUs.
>
> In this patch, struct vm_object utilizes a radix tree (xarray) to 
> track where a virtual page is mapped to. This adds extra memory 
> consumption from xarray, but provides a nice abstraction to isolate 
> mapping status from the machine-dependent layer (PTEs). Besides 
> supporting accelerators with external MMUs, struct vm_object is 
> planned to further union with i_pages in struct address_mapping for file-backed memory.
>
> The idea of struct vm_object is originated from FreeBSD VM design, 
> which provides a unified abstraction for anonymous memory, file-backed 
> memory, page cache and etc[1].
>
> Currently, Linux utilizes a set of hierarchical page walk functions to 
> abstract page table manipulations of different CPU architecture. The 
> problem happens when a device wants to reuse Linux MM code to manage 
> its page table -- the device page table may not be accessible to the CPU.
> Existing solution like Linux HMM utilizes the MMU notifier mechanisms 
> to invoke device-specific MMU functions, but relies on encoding the 
> mapping status on the CPU page table entries. This entangles 
> machine-independent code with machine-dependent code, and also brings unnecessary restrictions.
> The PTE size and format vary arch by arch, which harms the extensibility.
>
> [1] https://docs.freebsd.org/en/articles/vm-design/
>
> Signed-off-by: Weixi Zhu <[e-mail]>
> ---
>   include/linux/gmem.h     | 120 +++++++++++++++++++++++++
>   include/linux/mm_types.h |   4 +
>   mm/Makefile              |   2 +-
>   mm/vm_object.c           | 184 +++++++++++++++++++++++++++++++++++++++
>   4 files changed, 309 insertions(+), 1 deletion(-)
>   create mode 100644 mm/vm_object.c
>
> diff --git a/include/linux/gmem.h b/include/linux/gmem.h index 
> fff877873557..529ff6755a99 100644
> --- a/include/linux/gmem.h
> +++ b/include/linux/gmem.h
> @@ -9,11 +9,131 @@
>   #ifndef _GMEM_H
>   #define _GMEM_H
>   
> +#include <linux/mm_types.h>
> +
>   #ifdef CONFIG_GMEM
> +
> +#define GM_PAGE_CPU	0x10 /* Determines whether page is a pointer or a pfn number. */
> +#define GM_PAGE_DEVICE	0x20
> +#define GM_PAGE_NOMAP	0x40
> +#define GM_PAGE_WILLNEED	0x80
> +
> +#define GM_PAGE_TYPE_MASK	(GM_PAGE_CPU | GM_PAGE_DEVICE | GM_PAGE_NOMAP)
> +
> +struct gm_mapping {
> +	unsigned int flag;
> +
> +	union {
> +		struct page *page;	/* CPU node */
> +		struct gm_dev *dev;	/* hetero-node. TODO: support multiple devices */
> +		unsigned long pfn;
> +	};
> +
> +	struct mutex lock;
> +};
> +
> +static inline void gm_mapping_flags_set(struct gm_mapping 
> +*gm_mapping, int flags) {
> +	if (flags & GM_PAGE_TYPE_MASK)
> +		gm_mapping->flag &= ~GM_PAGE_TYPE_MASK;
> +
> +	gm_mapping->flag |= flags;
> +}
> +
> +static inline void gm_mapping_flags_clear(struct gm_mapping 
> +*gm_mapping, int flags) {
> +	gm_mapping->flag &= ~flags;
> +}
> +
> +static inline bool gm_mapping_cpu(struct gm_mapping *gm_mapping) {
> +	return !!(gm_mapping->flag & GM_PAGE_CPU); }
> +
> +static inline bool gm_mapping_device(struct gm_mapping *gm_mapping) {
> +	return !!(gm_mapping->flag & GM_PAGE_DEVICE); }
> +
> +static inline bool gm_mapping_nomap(struct gm_mapping *gm_mapping) {
> +	return !!(gm_mapping->flag & GM_PAGE_NOMAP); }
> +
> +static inline bool gm_mapping_willneed(struct gm_mapping *gm_mapping) 
> +{
> +	return !!(gm_mapping->flag & GM_PAGE_WILLNEED); }
> +
>   /* h-NUMA topology */
>   void __init hnuma_init(void);
> +
> +/* vm object */
> +/*
> + * Each per-process vm_object tracks the mapping status of virtual 
> +pages from
> + * all VMAs mmap()-ed with MAP_PRIVATE | MAP_PEER_SHARED.
> + */
> +struct vm_object {
> +	spinlock_t lock;
> +
> +	/*
> +	 * The logical_page_table is a container that holds the mapping
> +	 * information between a VA and a struct page.
> +	 */
> +	struct xarray *logical_page_table;
> +	atomic_t nr_pages;
> +};
> +
> +int __init vm_object_init(void);
> +struct vm_object *vm_object_create(struct mm_struct *mm); void 
> +vm_object_drop_locked(struct mm_struct *mm);
> +
> +struct gm_mapping *alloc_gm_mapping(void); void 
> +free_gm_mappings(struct vm_area_struct *vma); struct gm_mapping 
> +*vm_object_lookup(struct vm_object *obj, unsigned long va); void 
> +vm_object_mapping_create(struct vm_object *obj, unsigned long start); 
> +void unmap_gm_mappings_range(struct vm_area_struct *vma, unsigned long start,
> +			     unsigned long end);
> +void munmap_in_peer_devices(struct mm_struct *mm, unsigned long start,
> +			    unsigned long end);
>   #else
>   static inline void hnuma_init(void) {}
> +static inline void __init vm_object_init(void) { } static inline 
> +struct vm_object *vm_object_create(struct vm_area_struct *vma) {
> +	return NULL;
> +}
> +static inline void vm_object_drop_locked(struct vm_area_struct *vma) 
> +{ } static inline struct gm_mapping *alloc_gm_mapping(void) {
> +	return NULL;
> +}
> +static inline void free_gm_mappings(struct vm_area_struct *vma) { } 
> +static inline struct gm_mapping *vm_object_lookup(struct vm_object *obj,
> +						  unsigned long va)
> +{
> +	return NULL;
> +}
> +static inline void vm_object_mapping_create(struct vm_object *obj,
> +					    unsigned long start)
> +{
> +}
> +static inline void unmap_gm_mappings_range(struct vm_area_struct *vma,
> +					   unsigned long start,
> +					   unsigned long end)
> +{
> +}
> +static inline void munmap_in_peer_devices(struct mm_struct *mm,
> +					  unsigned long start,
> +					  unsigned long end)
> +{
> +}
>   #endif
>   
>   #endif /* _GMEM_H */
> diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 
> 957ce38768b2..4e50dc019d75 100644
> --- a/include/linux/mm_types.h
> +++ b/include/linux/mm_types.h
> @@ -31,6 +31,7 @@
>   
>   struct address_space;
>   struct mem_cgroup;
> +struct vm_object;
>   
>   /*
>    * Each physical page in the system has a struct page associated 
> with @@ -974,6 +975,9 @@ struct mm_struct {
>   #endif
>   		} lru_gen;
>   #endif /* CONFIG_LRU_GEN */
> +#ifdef CONFIG_GMEM
> +		struct vm_object *vm_obj;
> +#endif
>   	} __randomize_layout;
>   
>   	/*
> diff --git a/mm/Makefile b/mm/Makefile index 
> f48ea2eb4a44..d2dfab012c96 100644
> --- a/mm/Makefile
> +++ b/mm/Makefile
> @@ -138,4 +138,4 @@ obj-$(CONFIG_IO_MAPPING) += io-mapping.o
>   obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o
>   obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o
>   obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o
> -obj-$(CONFIG_GMEM) += gmem.o
> +obj-$(CONFIG_GMEM) += gmem.o vm_object.o
> diff --git a/mm/vm_object.c b/mm/vm_object.c new file mode 100644 
> index 000000000000..4e76737e0ca1
> --- /dev/null
> +++ b/mm/vm_object.c
> @@ -0,0 +1,184 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * arch/alpha/boot/bootp.c
> + *
> + * Copyright (C) 1997 Jay Estabrook
> + *
> + * This file is used for creating a bootp file for the Linux/AXP 
> +kernel
> + *
> + * based significantly on the arch/alpha/boot/main.c of Linus 
> +Torvalds  */


i believe you have made a mistake here. you will likely want to correct the information in this comment.

> +#include <linux/mm.h>
> +#include <linux/gmem.h>
> +
> +/*
> + * Sine VM_OBJECT maintains the logical page table under each VMA, 
> +and each VMA
> + * points to a VM_OBJECT. Ultimately VM_OBJECTs must be maintained as 
> +long as VMA
> + * gets changed: merge, split, adjust  */ static struct kmem_cache 
> +*vm_object_cachep; static struct kmem_cache *gm_mapping_cachep;
> +
> +static inline void release_gm_mapping(struct gm_mapping *mapping) {
> +	kmem_cache_free(gm_mapping_cachep, mapping); }
> +
> +static inline struct gm_mapping *lookup_gm_mapping(struct vm_object *obj,
> +						   unsigned long pindex)
> +{
> +	return xa_load(obj->logical_page_table, pindex); }
> +
> +int __init vm_object_init(void)
> +{
> +	vm_object_cachep = KMEM_CACHE(vm_object, 0);
> +	if (!vm_object_cachep)
> +		goto out;
> +
> +	gm_mapping_cachep = KMEM_CACHE(gm_mapping, 0);
> +	if (!gm_mapping_cachep)
> +		goto free_vm_object;
> +
> +	return 0;
> +free_vm_object:
> +	kmem_cache_destroy(vm_object_cachep);
> +out:
> +	return -ENOMEM;
> +}
> +
> +/*
> + * Create a VM_OBJECT and attach it to a mm_struct
> + * This should be called when a task_struct is created.
> + */
> +struct vm_object *vm_object_create(struct mm_struct *mm) {
> +	struct vm_object *obj = kmem_cache_alloc(vm_object_cachep, 
> +GFP_KERNEL);
> +
> +	if (!obj)
> +		return NULL;
> +
> +	spin_lock_init(&obj->lock);
> +
> +	/*
> +	 * The logical page table maps va >> PAGE_SHIFT
> +	 * to pointers of struct gm_mapping.
> +	 */
> +	obj->logical_page_table = kmalloc(sizeof(struct xarray), GFP_KERNEL);
> +	if (!obj->logical_page_table) {
> +		kmem_cache_free(vm_object_cachep, obj);
> +		return NULL;
> +	}
> +
> +	xa_init(obj->logical_page_table);
> +	atomic_set(&obj->nr_pages, 0);
> +
> +	return obj;
> +}
> +
> +/* This should be called when a mm no longer refers to a VM_OBJECT */ 
> +void vm_object_drop_locked(struct mm_struct *mm) {
> +	struct vm_object *obj = mm->vm_obj;
> +
> +	if (!obj)
> +		return;
> +
> +	/*
> +	 * We must enter this with VMA write-locked, which is unfortunately a
> +	 * giant lock.
> +	 */
> +	mmap_assert_write_locked(mm);
> +	mm->vm_obj = NULL;
> +
> +	xa_destroy(obj->logical_page_table);
> +	kfree(obj->logical_page_table);
> +	kmem_cache_free(vm_object_cachep, obj); }
> +
> +/*
> + * Given a VA, the page_index is computed by
> + * page_index = address >> PAGE_SHIFT  */ struct gm_mapping 
> +*vm_object_lookup(struct vm_object *obj, unsigned long va) {
> +	return lookup_gm_mapping(obj, va >> PAGE_SHIFT); } 
> +EXPORT_SYMBOL_GPL(vm_object_lookup);
> +
> +void vm_object_mapping_create(struct vm_object *obj, unsigned long 
> +start) {
> +
> +	unsigned long index = start >> PAGE_SHIFT;
> +	struct gm_mapping *gm_mapping;
> +
> +	if (!obj)
> +		return;
> +
> +	gm_mapping = alloc_gm_mapping();
> +	if (!gm_mapping)
> +		return;
> +
> +	__xa_store(obj->logical_page_table, index, gm_mapping, GFP_KERNEL); 
> +}
> +
> +/* gm_mapping will not be release dynamically */ struct gm_mapping 
> +*alloc_gm_mapping(void) {
> +	struct gm_mapping *gm_mapping = kmem_cache_zalloc(gm_mapping_cachep, 
> +GFP_KERNEL);
> +
> +	if (!gm_mapping)
> +		return NULL;
> +
> +	gm_mapping_flags_set(gm_mapping, GM_PAGE_NOMAP);
> +	mutex_init(&gm_mapping->lock);
> +
> +	return gm_mapping;
> +}
> +
> +/* This should be called when a PEER_SHAERD vma is freed */ void 
> +free_gm_mappings(struct vm_area_struct *vma) {
> +	struct gm_mapping *gm_mapping;
> +	struct vm_object *obj;
> +
> +	obj = vma->vm_mm->vm_obj;
> +	if (!obj)
> +		return;
> +
> +	XA_STATE(xas, obj->logical_page_table, vma->vm_start >> PAGE_SHIFT);
> +
> +	xa_lock(obj->logical_page_table);
> +		xas_for_each(&xas, gm_mapping, vma->vm_end >> PAGE_SHIFT) {
> +		release_gm_mapping(gm_mapping);
> +		xas_store(&xas, NULL);
> +	}
> +	xa_unlock(obj->logical_page_table);
> +}
> +
> +void unmap_gm_mappings_range(struct vm_area_struct *vma, unsigned long start,
> +			    unsigned long end)
> +{
> +	struct xarray *logical_page_table;
> +	struct gm_mapping *gm_mapping;
> +	struct page *page = NULL;
> +
> +	if (!vma->vm_mm->vm_obj)
> +		return;
> +
> +	logical_page_table = vma->vm_mm->vm_obj->logical_page_table;
> +	if (!logical_page_table)
> +		return;
> +
> +	XA_STATE(xas, logical_page_table, start >> PAGE_SHIFT);
> +
> +	xa_lock(logical_page_table);
> +	xas_for_each(&xas, gm_mapping, end >> PAGE_SHIFT) {
> +		page = gm_mapping->page;
> +		if (page && (page_ref_count(page) != 0)) {
> +			put_page(page);
> +			gm_mapping->page = NULL;
> +		}
> +	}
> +	xa_unlock(logical_page_table);
> +}

David Hildenbrand Dec. 1, 2023, 9:23 a.m. UTC | #3

On 28.11.23 13:50, Weixi Zhu wrote:
> This patch adds an abstraction layer, struct vm_object, that maintains
> per-process virtual-to-physical mapping status stored in struct gm_mapping.
> For example, a virtual page may be mapped to a CPU physical page or to a
> device physical page. Struct vm_object effectively maintains an
> arch-independent page table, which is defined as a "logical page table".
> While arch-dependent page table used by a real MMU is named a "physical
> page table". The logical page table is useful if Linux core MM is extended
> to handle a unified virtual address space with external accelerators using
> customized MMUs.

Which raises the question why we are dealing with anonymous memory at 
all? Why not go for shmem if you are already only special-casing VMAs 
with a MMAP flag right now?

That would maybe avoid having to introduce controversial BSD design 
concepts into Linux, that feel like going a step backwards in time to me 
and adding *more* MM complexity.

> 
> In this patch, struct vm_object utilizes a radix
> tree (xarray) to track where a virtual page is mapped to. This adds extra
> memory consumption from xarray, but provides a nice abstraction to isolate
> mapping status from the machine-dependent layer (PTEs). Besides supporting
> accelerators with external MMUs, struct vm_object is planned to further
> union with i_pages in struct address_mapping for file-backed memory.

A file already has a tree structure (pagecache) to manage the pages that 
are theoretically mapped. It's easy to translate from a VMA to a page 
inside that tree structure that is currently not present in page tables.

Why the need for that tree structure if you can just remove anon memory 
from the picture?

> 
> The idea of struct vm_object is originated from FreeBSD VM design, which
> provides a unified abstraction for anonymous memory, file-backed memory,
> page cache and etc[1].

:/

> Currently, Linux utilizes a set of hierarchical page walk functions to
> abstract page table manipulations of different CPU architecture. The
> problem happens when a device wants to reuse Linux MM code to manage its
> page table -- the device page table may not be accessible to the CPU.
> Existing solution like Linux HMM utilizes the MMU notifier mechanisms to
> invoke device-specific MMU functions, but relies on encoding the mapping
> status on the CPU page table entries. This entangles machine-independent
> code with machine-dependent code, and also brings unnecessary restrictions.

Why? we have primitives to walk arch page tables in a non-arch specific 
fashion and are using them all over the place.

We even have various mechanisms to map something into the page tables 
and get the CPU to fault on it, as if it is inaccessible (PROT_NONE as 
used for NUMA balancing, fake swap entries).

> The PTE size and format vary arch by arch, which harms the extensibility.

Not really.

We might have some features limited to some architectures because of the 
lack of PTE bits. And usually the problem is that people don't care 
enough about enabling these features on older architectures.

If we ever *really* need more space for sw-defined data, it would be 
possible to allocate auxiliary data for page tables only where required 
(where the features apply), instead of crafting a completely new, 
auxiliary datastructure with it's own locking.

So far it was not required to enable the feature we need on the 
architectures we care about.

> 
> [1] https://docs.freebsd.org/en/articles/vm-design/

In the cover letter you have:

"The future plan of logical page table is to provide a generic 
abstraction layer that support common anonymous memory (I am looking at 
you, transparent huge pages) and file-backed memory."

Which I doubt will happen; there is little interest in making anonymous 
memory management slower, more serialized, and wasting more memory on 
metadata.

Note that you won't make many friends around here with statements like 
"To be honest, not using a logical page table for anonymous memory is 
why Linux THP fails compared with FreeBSD's superpage".

I read one paper that makes such claims (I'm curious how you define 
"winning"), and am aware of some shortcomings. But I am not convinced 
that a second datastructure "is why Linux THP fails". It just requires 
some more work to get it sorted under Linux (e.g., allocate THP, PTE-map 
it and map inaccessible parts PROT_NONE, later collapse it in-place into 
a PMD), and so far, there was not a lot of interest that I am ware of to 
even start working on that.

So if there is not enough pain for companies to even work on that in 
Linux, maybe FreeBSD superpages are "winning" "on paper" only? Remember 
that the target audience here are Linux developers.


But yeah, this here is all designed around the idea "core MM is extended 
to handle a unified virtual address space with external accelerators 
using customized MMUs." and then trying to find other arguments why it's 
a good idea, without going too much into detail why it's all unsolvable 
without that.

The first thing to sort out if we even want that, and some discussions 
here already went into the direction of "likely not". Let's see.

Pedro Falcato Dec. 2, 2023, 2:50 p.m. UTC | #4

On Fri, Dec 1, 2023 at 9:23 AM David Hildenbrand <[e-mail]> wrote:
>
> On 28.11.23 13:50, Weixi Zhu wrote:
> > This patch adds an abstraction layer, struct vm_object, that maintains
> > per-process virtual-to-physical mapping status stored in struct gm_mapping.
> > For example, a virtual page may be mapped to a CPU physical page or to a
> > device physical page. Struct vm_object effectively maintains an
> > arch-independent page table, which is defined as a "logical page table".
> > While arch-dependent page table used by a real MMU is named a "physical
> > page table". The logical page table is useful if Linux core MM is extended
> > to handle a unified virtual address space with external accelerators using
> > customized MMUs.
>
> Which raises the question why we are dealing with anonymous memory at
> all? Why not go for shmem if you are already only special-casing VMAs
> with a MMAP flag right now?
>
> That would maybe avoid having to introduce controversial BSD design
> concepts into Linux, that feel like going a step backwards in time to me
> and adding *more* MM complexity.
>
> >
> > In this patch, struct vm_object utilizes a radix
> > tree (xarray) to track where a virtual page is mapped to. This adds extra
> > memory consumption from xarray, but provides a nice abstraction to isolate
> > mapping status from the machine-dependent layer (PTEs). Besides supporting
> > accelerators with external MMUs, struct vm_object is planned to further
> > union with i_pages in struct address_mapping for file-backed memory.
>
> A file already has a tree structure (pagecache) to manage the pages that
> are theoretically mapped. It's easy to translate from a VMA to a page
> inside that tree structure that is currently not present in page tables.
>
> Why the need for that tree structure if you can just remove anon memory
> from the picture?
>
> >
> > The idea of struct vm_object is originated from FreeBSD VM design, which
> > provides a unified abstraction for anonymous memory, file-backed memory,
> > page cache and etc[1].
>
> :/
>
> > Currently, Linux utilizes a set of hierarchical page walk functions to
> > abstract page table manipulations of different CPU architecture. The
> > problem happens when a device wants to reuse Linux MM code to manage its
> > page table -- the device page table may not be accessible to the CPU.
> > Existing solution like Linux HMM utilizes the MMU notifier mechanisms to
> > invoke device-specific MMU functions, but relies on encoding the mapping
> > status on the CPU page table entries. This entangles machine-independent
> > code with machine-dependent code, and also brings unnecessary restrictions.
>
> Why? we have primitives to walk arch page tables in a non-arch specific
> fashion and are using them all over the place.
>
> We even have various mechanisms to map something into the page tables
> and get the CPU to fault on it, as if it is inaccessible (PROT_NONE as
> used for NUMA balancing, fake swap entries).
>
> > The PTE size and format vary arch by arch, which harms the extensibility.
>
> Not really.
>
> We might have some features limited to some architectures because of the
> lack of PTE bits. And usually the problem is that people don't care
> enough about enabling these features on older architectures.
>
> If we ever *really* need more space for sw-defined data, it would be
> possible to allocate auxiliary data for page tables only where required
> (where the features apply), instead of crafting a completely new,
> auxiliary datastructure with it's own locking.
>
> So far it was not required to enable the feature we need on the
> architectures we care about.
>
> >
> > [1] https://docs.freebsd.org/en/articles/vm-design/
>
> In the cover letter you have:
>
> "The future plan of logical page table is to provide a generic
> abstraction layer that support common anonymous memory (I am looking at
> you, transparent huge pages) and file-backed memory."
>
> Which I doubt will happen; there is little interest in making anonymous
> memory management slower, more serialized, and wasting more memory on
> metadata.

Also worth noting that:

1) Mach VM (which FreeBSD inherited, from the old BSD) vm_objects
aren't quite what's being stated here, rather they are somewhat
replacements for both anon_vma and address_space[1]. Very similarly to
Linux, they take pages from vm_objects and map them in page tables
using pmap (the big difference is anon memory, which has its
bookkeeping in page tables, on Linux)

2) These vm_objects were a horrendous mistake (see CoW chaining) and
FreeBSD has to go to horrendous lengths to make them tolerable. The
UVM paper/dissertation (by Charles Cranor) talks about these issues at
length, and 20 years later it's still true.

3) Despite Linux MM having its warts, it's probably correct to
consider it a solid improvement over FreeBSD MM or NetBSD UVM

And, finally, randomly tacking on core MM concepts from other systems
is at best a *really weird* idea. Particularly when they aren't even
what was stated!

[1] If you really can't use PTEs, I don't see how you can't use file
mappings and/or some vm_operations_struct workarounds, when the
patch's vm_object is literally just an xarray with a different name

David Hildenbrand Dec. 4, 2023, 10:21 a.m. UTC | #5

On 02.12.23 15:50, Pedro Falcato wrote:
> On Fri, Dec 1, 2023 at 9:23 AM David Hildenbrand <[e-mail]> wrote:
>>
>> On 28.11.23 13:50, Weixi Zhu wrote:
>>> This patch adds an abstraction layer, struct vm_object, that maintains
>>> per-process virtual-to-physical mapping status stored in struct gm_mapping.
>>> For example, a virtual page may be mapped to a CPU physical page or to a
>>> device physical page. Struct vm_object effectively maintains an
>>> arch-independent page table, which is defined as a "logical page table".
>>> While arch-dependent page table used by a real MMU is named a "physical
>>> page table". The logical page table is useful if Linux core MM is extended
>>> to handle a unified virtual address space with external accelerators using
>>> customized MMUs.
>>
>> Which raises the question why we are dealing with anonymous memory at
>> all? Why not go for shmem if you are already only special-casing VMAs
>> with a MMAP flag right now?
>>
>> That would maybe avoid having to introduce controversial BSD design
>> concepts into Linux, that feel like going a step backwards in time to me
>> and adding *more* MM complexity.
>>
>>>
>>> In this patch, struct vm_object utilizes a radix
>>> tree (xarray) to track where a virtual page is mapped to. This adds extra
>>> memory consumption from xarray, but provides a nice abstraction to isolate
>>> mapping status from the machine-dependent layer (PTEs). Besides supporting
>>> accelerators with external MMUs, struct vm_object is planned to further
>>> union with i_pages in struct address_mapping for file-backed memory.
>>
>> A file already has a tree structure (pagecache) to manage the pages that
>> are theoretically mapped. It's easy to translate from a VMA to a page
>> inside that tree structure that is currently not present in page tables.
>>
>> Why the need for that tree structure if you can just remove anon memory
>> from the picture?
>>
>>>
>>> The idea of struct vm_object is originated from FreeBSD VM design, which
>>> provides a unified abstraction for anonymous memory, file-backed memory,
>>> page cache and etc[1].
>>
>> :/
>>
>>> Currently, Linux utilizes a set of hierarchical page walk functions to
>>> abstract page table manipulations of different CPU architecture. The
>>> problem happens when a device wants to reuse Linux MM code to manage its
>>> page table -- the device page table may not be accessible to the CPU.
>>> Existing solution like Linux HMM utilizes the MMU notifier mechanisms to
>>> invoke device-specific MMU functions, but relies on encoding the mapping
>>> status on the CPU page table entries. This entangles machine-independent
>>> code with machine-dependent code, and also brings unnecessary restrictions.
>>
>> Why? we have primitives to walk arch page tables in a non-arch specific
>> fashion and are using them all over the place.
>>
>> We even have various mechanisms to map something into the page tables
>> and get the CPU to fault on it, as if it is inaccessible (PROT_NONE as
>> used for NUMA balancing, fake swap entries).
>>
>>> The PTE size and format vary arch by arch, which harms the extensibility.
>>
>> Not really.
>>
>> We might have some features limited to some architectures because of the
>> lack of PTE bits. And usually the problem is that people don't care
>> enough about enabling these features on older architectures.
>>
>> If we ever *really* need more space for sw-defined data, it would be
>> possible to allocate auxiliary data for page tables only where required
>> (where the features apply), instead of crafting a completely new,
>> auxiliary datastructure with it's own locking.
>>
>> So far it was not required to enable the feature we need on the
>> architectures we care about.
>>
>>>
>>> [1] https://docs.freebsd.org/en/articles/vm-design/
>>
>> In the cover letter you have:
>>
>> "The future plan of logical page table is to provide a generic
>> abstraction layer that support common anonymous memory (I am looking at
>> you, transparent huge pages) and file-backed memory."
>>
>> Which I doubt will happen; there is little interest in making anonymous
>> memory management slower, more serialized, and wasting more memory on
>> metadata.
> 
> Also worth noting that:
> 
> 1) Mach VM (which FreeBSD inherited, from the old BSD) vm_objects
> aren't quite what's being stated here, rather they are somewhat
> replacements for both anon_vma and address_space[1]. Very similarly to
> Linux, they take pages from vm_objects and map them in page tables
> using pmap (the big difference is anon memory, which has its
> bookkeeping in page tables, on Linux)
> 
> 2) These vm_objects were a horrendous mistake (see CoW chaining) and
> FreeBSD has to go to horrendous lengths to make them tolerable. The
> UVM paper/dissertation (by Charles Cranor) talks about these issues at
> length, and 20 years later it's still true.
> 
> 3) Despite Linux MM having its warts, it's probably correct to
> consider it a solid improvement over FreeBSD MM or NetBSD UVM
> 
> And, finally, randomly tacking on core MM concepts from other systems
> is at best a *really weird* idea. Particularly when they aren't even
> what was stated!

Can you read my mind? :) thanks for noting all that, with which I 100% 
agree.

Patch

diff --git a/include/linux/gmem.h b/include/linux/gmem.h
index fff877873557..529ff6755a99 100644
--- a/include/linux/gmem.h
+++ b/include/linux/gmem.h
@@ -9,11 +9,131 @@ 
 #ifndef _GMEM_H
 #define _GMEM_H
 
+#include <linux/mm_types.h>
+
 #ifdef CONFIG_GMEM
+
+#define GM_PAGE_CPU	0x10 /* Determines whether page is a pointer or a pfn number. */
+#define GM_PAGE_DEVICE	0x20
+#define GM_PAGE_NOMAP	0x40
+#define GM_PAGE_WILLNEED	0x80
+
+#define GM_PAGE_TYPE_MASK	(GM_PAGE_CPU | GM_PAGE_DEVICE | GM_PAGE_NOMAP)
+
+struct gm_mapping {
+	unsigned int flag;
+
+	union {
+		struct page *page;	/* CPU node */
+		struct gm_dev *dev;	/* hetero-node. TODO: support multiple devices */
+		unsigned long pfn;
+	};
+
+	struct mutex lock;
+};
+
+static inline void gm_mapping_flags_set(struct gm_mapping *gm_mapping, int flags)
+{
+	if (flags & GM_PAGE_TYPE_MASK)
+		gm_mapping->flag &= ~GM_PAGE_TYPE_MASK;
+
+	gm_mapping->flag |= flags;
+}
+
+static inline void gm_mapping_flags_clear(struct gm_mapping *gm_mapping, int flags)
+{
+	gm_mapping->flag &= ~flags;
+}
+
+static inline bool gm_mapping_cpu(struct gm_mapping *gm_mapping)
+{
+	return !!(gm_mapping->flag & GM_PAGE_CPU);
+}
+
+static inline bool gm_mapping_device(struct gm_mapping *gm_mapping)
+{
+	return !!(gm_mapping->flag & GM_PAGE_DEVICE);
+}
+
+static inline bool gm_mapping_nomap(struct gm_mapping *gm_mapping)
+{
+	return !!(gm_mapping->flag & GM_PAGE_NOMAP);
+}
+
+static inline bool gm_mapping_willneed(struct gm_mapping *gm_mapping)
+{
+	return !!(gm_mapping->flag & GM_PAGE_WILLNEED);
+}
+
 /* h-NUMA topology */
 void __init hnuma_init(void);
+
+/* vm object */
+/*
+ * Each per-process vm_object tracks the mapping status of virtual pages from
+ * all VMAs mmap()-ed with MAP_PRIVATE | MAP_PEER_SHARED.
+ */
+struct vm_object {
+	spinlock_t lock;
+
+	/*
+	 * The logical_page_table is a container that holds the mapping
+	 * information between a VA and a struct page.
+	 */
+	struct xarray *logical_page_table;
+	atomic_t nr_pages;
+};
+
+int __init vm_object_init(void);
+struct vm_object *vm_object_create(struct mm_struct *mm);
+void vm_object_drop_locked(struct mm_struct *mm);
+
+struct gm_mapping *alloc_gm_mapping(void);
+void free_gm_mappings(struct vm_area_struct *vma);
+struct gm_mapping *vm_object_lookup(struct vm_object *obj, unsigned long va);
+void vm_object_mapping_create(struct vm_object *obj, unsigned long start);
+void unmap_gm_mappings_range(struct vm_area_struct *vma, unsigned long start,
+			     unsigned long end);
+void munmap_in_peer_devices(struct mm_struct *mm, unsigned long start,
+			    unsigned long end);
 #else
 static inline void hnuma_init(void) {}
+static inline void __init vm_object_init(void)
+{
+}
+static inline struct vm_object *vm_object_create(struct vm_area_struct *vma)
+{
+	return NULL;
+}
+static inline void vm_object_drop_locked(struct vm_area_struct *vma)
+{
+}
+static inline struct gm_mapping *alloc_gm_mapping(void)
+{
+	return NULL;
+}
+static inline void free_gm_mappings(struct vm_area_struct *vma)
+{
+}
+static inline struct gm_mapping *vm_object_lookup(struct vm_object *obj,
+						  unsigned long va)
+{
+	return NULL;
+}
+static inline void vm_object_mapping_create(struct vm_object *obj,
+					    unsigned long start)
+{
+}
+static inline void unmap_gm_mappings_range(struct vm_area_struct *vma,
+					   unsigned long start,
+					   unsigned long end)
+{
+}
+static inline void munmap_in_peer_devices(struct mm_struct *mm,
+					  unsigned long start,
+					  unsigned long end)
+{
+}
 #endif
 
 #endif /* _GMEM_H */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 957ce38768b2..4e50dc019d75 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -31,6 +31,7 @@ 
 
 struct address_space;
 struct mem_cgroup;
+struct vm_object;
 
 /*
  * Each physical page in the system has a struct page associated with
@@ -974,6 +975,9 @@  struct mm_struct {
 #endif
 		} lru_gen;
 #endif /* CONFIG_LRU_GEN */
+#ifdef CONFIG_GMEM
+		struct vm_object *vm_obj;
+#endif
 	} __randomize_layout;
 
 	/*
diff --git a/mm/Makefile b/mm/Makefile
index f48ea2eb4a44..d2dfab012c96 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -138,4 +138,4 @@  obj-$(CONFIG_IO_MAPPING) += io-mapping.o
 obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o
 obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o
 obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o
-obj-$(CONFIG_GMEM) += gmem.o
+obj-$(CONFIG_GMEM) += gmem.o vm_object.o
diff --git a/mm/vm_object.c b/mm/vm_object.c
new file mode 100644
index 000000000000..4e76737e0ca1
--- /dev/null
+++ b/mm/vm_object.c
@@ -0,0 +1,184 @@ 
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * arch/alpha/boot/bootp.c
+ *
+ * Copyright (C) 1997 Jay Estabrook
+ *
+ * This file is used for creating a bootp file for the Linux/AXP kernel
+ *
+ * based significantly on the arch/alpha/boot/main.c of Linus Torvalds
+ */
+#include <linux/mm.h>
+#include <linux/gmem.h>
+
+/*
+ * Sine VM_OBJECT maintains the logical page table under each VMA, and each VMA
+ * points to a VM_OBJECT. Ultimately VM_OBJECTs must be maintained as long as VMA
+ * gets changed: merge, split, adjust
+ */
+static struct kmem_cache *vm_object_cachep;
+static struct kmem_cache *gm_mapping_cachep;
+
+static inline void release_gm_mapping(struct gm_mapping *mapping)
+{
+	kmem_cache_free(gm_mapping_cachep, mapping);
+}
+
+static inline struct gm_mapping *lookup_gm_mapping(struct vm_object *obj,
+						   unsigned long pindex)
+{
+	return xa_load(obj->logical_page_table, pindex);
+}
+
+int __init vm_object_init(void)
+{
+	vm_object_cachep = KMEM_CACHE(vm_object, 0);
+	if (!vm_object_cachep)
+		goto out;
+
+	gm_mapping_cachep = KMEM_CACHE(gm_mapping, 0);
+	if (!gm_mapping_cachep)
+		goto free_vm_object;
+
+	return 0;
+free_vm_object:
+	kmem_cache_destroy(vm_object_cachep);
+out:
+	return -ENOMEM;
+}
+
+/*
+ * Create a VM_OBJECT and attach it to a mm_struct
+ * This should be called when a task_struct is created.
+ */
+struct vm_object *vm_object_create(struct mm_struct *mm)
+{
+	struct vm_object *obj = kmem_cache_alloc(vm_object_cachep, GFP_KERNEL);
+
+	if (!obj)
+		return NULL;
+
+	spin_lock_init(&obj->lock);
+
+	/*
+	 * The logical page table maps va >> PAGE_SHIFT
+	 * to pointers of struct gm_mapping.
+	 */
+	obj->logical_page_table = kmalloc(sizeof(struct xarray), GFP_KERNEL);
+	if (!obj->logical_page_table) {
+		kmem_cache_free(vm_object_cachep, obj);
+		return NULL;
+	}
+
+	xa_init(obj->logical_page_table);
+	atomic_set(&obj->nr_pages, 0);
+
+	return obj;
+}
+
+/* This should be called when a mm no longer refers to a VM_OBJECT */
+void vm_object_drop_locked(struct mm_struct *mm)
+{
+	struct vm_object *obj = mm->vm_obj;
+
+	if (!obj)
+		return;
+
+	/*
+	 * We must enter this with VMA write-locked, which is unfortunately a
+	 * giant lock.
+	 */
+	mmap_assert_write_locked(mm);
+	mm->vm_obj = NULL;
+
+	xa_destroy(obj->logical_page_table);
+	kfree(obj->logical_page_table);
+	kmem_cache_free(vm_object_cachep, obj);
+}
+
+/*
+ * Given a VA, the page_index is computed by
+ * page_index = address >> PAGE_SHIFT
+ */
+struct gm_mapping *vm_object_lookup(struct vm_object *obj, unsigned long va)
+{
+	return lookup_gm_mapping(obj, va >> PAGE_SHIFT);
+}
+EXPORT_SYMBOL_GPL(vm_object_lookup);
+
+void vm_object_mapping_create(struct vm_object *obj, unsigned long start)
+{
+
+	unsigned long index = start >> PAGE_SHIFT;
+	struct gm_mapping *gm_mapping;
+
+	if (!obj)
+		return;
+
+	gm_mapping = alloc_gm_mapping();
+	if (!gm_mapping)
+		return;
+
+	__xa_store(obj->logical_page_table, index, gm_mapping, GFP_KERNEL);
+}
+
+/* gm_mapping will not be release dynamically */
+struct gm_mapping *alloc_gm_mapping(void)
+{
+	struct gm_mapping *gm_mapping = kmem_cache_zalloc(gm_mapping_cachep, GFP_KERNEL);
+
+	if (!gm_mapping)
+		return NULL;
+
+	gm_mapping_flags_set(gm_mapping, GM_PAGE_NOMAP);
+	mutex_init(&gm_mapping->lock);
+
+	return gm_mapping;
+}
+
+/* This should be called when a PEER_SHAERD vma is freed */
+void free_gm_mappings(struct vm_area_struct *vma)
+{
+	struct gm_mapping *gm_mapping;
+	struct vm_object *obj;
+
+	obj = vma->vm_mm->vm_obj;
+	if (!obj)
+		return;
+
+	XA_STATE(xas, obj->logical_page_table, vma->vm_start >> PAGE_SHIFT);
+
+	xa_lock(obj->logical_page_table);
+		xas_for_each(&xas, gm_mapping, vma->vm_end >> PAGE_SHIFT) {
+		release_gm_mapping(gm_mapping);
+		xas_store(&xas, NULL);
+	}
+	xa_unlock(obj->logical_page_table);
+}
+
+void unmap_gm_mappings_range(struct vm_area_struct *vma, unsigned long start,
+			    unsigned long end)
+{
+	struct xarray *logical_page_table;
+	struct gm_mapping *gm_mapping;
+	struct page *page = NULL;
+
+	if (!vma->vm_mm->vm_obj)
+		return;
+
+	logical_page_table = vma->vm_mm->vm_obj->logical_page_table;
+	if (!logical_page_table)
+		return;
+
+	XA_STATE(xas, logical_page_table, start >> PAGE_SHIFT);
+
+	xa_lock(logical_page_table);
+	xas_for_each(&xas, gm_mapping, end >> PAGE_SHIFT) {
+		page = gm_mapping->page;
+		if (page && (page_ref_count(page) != 0)) {
+			put_page(page);
+			gm_mapping->page = NULL;
+		}
+	}
+	xa_unlock(logical_page_table);
+}