summaryrefslogtreecommitdiff
path: root/include/linux/memremap.h
blob: c3b4cc84877b5611576b44b04ed2bdaea7e0646f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_MEMREMAP_H_
#define _LINUX_MEMREMAP_H_

#include <linux/mmzone.h>
#include <linux/range.h>
#include <linux/ioport.h>
#include <linux/percpu-refcount.h>

struct resource;
struct device;

/**
 * struct vmem_altmap - pre-allocated storage for vmemmap_populate
 * @base_pfn: base of the entire dev_pagemap mapping
 * @reserve: pages mapped, but reserved for driver use (relative to @base)
 * @free: free pages set aside in the mapping for memmap storage
 * @align: pages reserved to meet allocation alignments
 * @alloc: track pages consumed, private to vmemmap_populate()
 */
struct vmem_altmap {
	unsigned long base_pfn;
	const unsigned long end_pfn;
	const unsigned long reserve;
	unsigned long free;
	unsigned long align;
	unsigned long alloc;
};

/*
 * Specialize ZONE_DEVICE memory into multiple types each has a different
 * usage.
 *
 * MEMORY_DEVICE_PRIVATE:
 * Device memory that is not directly addressable by the CPU: CPU can neither
 * read nor write private memory. In this case, we do still have struct pages
 * backing the device memory. Doing so simplifies the implementation, but it is
 * important to remember that there are certain points at which the struct page
 * must be treated as an opaque object, rather than a "normal" struct page.
 *
 * A more complete discussion of unaddressable memory may be found in
 * include/linux/hmm.h and Documentation/mm/hmm.rst.
 *
 * MEMORY_DEVICE_COHERENT:
 * Device memory that is cache coherent from device and CPU point of view. This
 * is used on platforms that have an advanced system bus (like CAPI or CXL). A
 * driver can hotplug the device memory using ZONE_DEVICE and with that memory
 * type. Any page of a process can be migrated to such memory. However no one
 * should be allowed to pin such memory so that it can always be evicted.
 *
 * MEMORY_DEVICE_FS_DAX:
 * Host memory that has similar access semantics as System RAM i.e. DMA
 * coherent and supports page pinning. In support of coordinating page
 * pinning vs other operations MEMORY_DEVICE_FS_DAX arranges for a
 * wakeup event whenever a page is unpinned and becomes idle. This
 * wakeup is used to coordinate physical address space management (ex:
 * fs truncate/hole punch) vs pinned pages (ex: device dma).
 *
 * MEMORY_DEVICE_GENERIC:
 * Host memory that has similar access semantics as System RAM i.e. DMA
 * coherent and supports page pinning. This is for example used by DAX devices
 * that expose memory using a character device.
 *
 * MEMORY_DEVICE_PCI_P2PDMA:
 * Device memory residing in a PCI BAR intended for use with Peer-to-Peer
 * transactions.
 */
enum memory_type {
	/* 0 is reserved to catch uninitialized type fields */
	MEMORY_DEVICE_PRIVATE = 1,
	MEMORY_DEVICE_COHERENT,
	MEMORY_DEVICE_FS_DAX,
	MEMORY_DEVICE_GENERIC,
	MEMORY_DEVICE_PCI_P2PDMA,
};

struct dev_pagemap_ops {
	/*
	 * Called once the page refcount reaches 0.  The reference count will be
	 * reset to one by the core code after the method is called to prepare
	 * for handing out the page again.
	 */
	void (*page_free)(struct page *page);

	/*
	 * Used for private (un-addressable) device memory only.  Must migrate
	 * the page back to a CPU accessible page.
	 */
	vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf);

	/*
	 * Handle the memory failure happens on a range of pfns.  Notify the
	 * processes who are using these pfns, and try to recover the data on
	 * them if necessary.  The mf_flags is finally passed to the recover
	 * function through the whole notify routine.
	 *
	 * When this is not implemented, or it returns -EOPNOTSUPP, the caller
	 * will fall back to a common handler called mf_generic_kill_procs().
	 */
	int (*memory_failure)(struct dev_pagemap *pgmap, unsigned long pfn,
			      unsigned long nr_pages, int mf_flags);
};

#define PGMAP_ALTMAP_VALID	(1 << 0)

/**
 * struct dev_pagemap - metadata for ZONE_DEVICE mappings
 * @altmap: pre-allocated/reserved memory for vmemmap allocations
 * @ref: reference count that pins the devm_memremap_pages() mapping
 * @done: completion for @ref
 * @type: memory type: see MEMORY_* in memory_hotplug.h
 * @flags: PGMAP_* flags to specify defailed behavior
 * @vmemmap_shift: structural definition of how the vmemmap page metadata
 *      is populated, specifically the metadata page order.
 *	A zero value (default) uses base pages as the vmemmap metadata
 *	representation. A bigger value will set up compound struct pages
 *	of the requested order value.
 * @ops: method table
 * @owner: an opaque pointer identifying the entity that manages this
 *	instance.  Used by various helpers to make sure that no
 *	foreign ZONE_DEVICE memory is accessed.
 * @nr_range: number of ranges to be mapped
 * @range: range to be mapped when nr_range == 1
 * @ranges: array of ranges to be mapped when nr_range > 1
 */
struct dev_pagemap {
	struct vmem_altmap altmap;
	struct percpu_ref ref;
	struct completion done;
	enum memory_type type;
	unsigned int flags;
	unsigned long vmemmap_shift;
	const struct dev_pagemap_ops *ops;
	void *owner;
	int nr_range;
	union {
		struct range range;
		struct range ranges[0];
	};
};

static inline bool pgmap_has_memory_failure(struct dev_pagemap *pgmap)
{
	return pgmap->ops && pgmap->ops->memory_failure;
}

static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap)
{
	if (pgmap->flags & PGMAP_ALTMAP_VALID)
		return &pgmap->altmap;
	return NULL;
}

static inline unsigned long pgmap_vmemmap_nr(struct dev_pagemap *pgmap)
{
	return 1 << pgmap->vmemmap_shift;
}

static inline bool is_device_private_page(const struct page *page)
{
	return IS_ENABLED(CONFIG_DEVICE_PRIVATE) &&
		is_zone_device_page(page) &&
		page->pgmap->type == MEMORY_DEVICE_PRIVATE;
}

static inline bool folio_is_device_private(const struct folio *folio)
{
	return is_device_private_page(&folio->page);
}

static inline bool is_pci_p2pdma_page(const struct page *page)
{
	return IS_ENABLED(CONFIG_PCI_P2PDMA) &&
		is_zone_device_page(page) &&
		page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA;
}

static inline bool is_device_coherent_page(const struct page *page)
{
	return is_zone_device_page(page) &&
		page->pgmap->type == MEMORY_DEVICE_COHERENT;
}

static inline bool folio_is_device_coherent(const struct folio *folio)
{
	return is_device_coherent_page(&folio->page);
}

#ifdef CONFIG_ZONE_DEVICE
void *memremap_pages(struct dev_pagemap *pgmap, int nid);
void memunmap_pages(struct dev_pagemap *pgmap);
void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap);
void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap);
struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
		struct dev_pagemap *pgmap);
bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn);

unsigned long vmem_altmap_offset(struct vmem_altmap *altmap);
void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns);
unsigned long memremap_compat_align(void);
#else
static inline void *devm_memremap_pages(struct device *dev,
		struct dev_pagemap *pgmap)
{
	/*
	 * Fail attempts to call devm_memremap_pages() without
	 * ZONE_DEVICE support enabled, this requires callers to fall
	 * back to plain devm_memremap() based on config
	 */
	WARN_ON_ONCE(1);
	return ERR_PTR(-ENXIO);
}

static inline void devm_memunmap_pages(struct device *dev,
		struct dev_pagemap *pgmap)
{
}

static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
		struct dev_pagemap *pgmap)
{
	return NULL;
}

static inline bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn)
{
	return false;
}

static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
{
	return 0;
}

static inline void vmem_altmap_free(struct vmem_altmap *altmap,
		unsigned long nr_pfns)
{
}

/* when memremap_pages() is disabled all archs can remap a single page */
static inline unsigned long memremap_compat_align(void)
{
	return PAGE_SIZE;
}
#endif /* CONFIG_ZONE_DEVICE */

static inline void put_dev_pagemap(struct dev_pagemap *pgmap)
{
	if (pgmap)
		percpu_ref_put(&pgmap->ref);
}

#endif /* _LINUX_MEMREMAP_H_ */