aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/i915/gem/i915_gem_internal.c
blob: 9cfb0e41ff06d1562837b2aec9552d73537c93cd (plain) (blame)
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
/*
 * SPDX-License-Identifier: MIT
 *
 * Copyright © 2014-2016 Intel Corporation
 */

#include <linux/scatterlist.h>
#include <linux/slab.h>
#include <linux/swiotlb.h>

#include <drm/i915_drm.h>

#include "i915_drv.h"
#include "i915_gem.h"
#include "i915_gem_object.h"
#include "i915_scatterlist.h"
#include "i915_utils.h"

#define QUIET (__GFP_NORETRY | __GFP_NOWARN)
#define MAYFAIL (__GFP_RETRY_MAYFAIL | __GFP_NOWARN)

static void internal_free_pages(struct sg_table *st)
{
	struct scatterlist *sg;

	for (sg = st->sgl; sg; sg = __sg_next(sg)) {
		if (sg_page(sg))
			__free_pages(sg_page(sg), get_order(sg->length));
	}

	sg_free_table(st);
	kfree(st);
}

static int i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj)
{
	struct drm_i915_private *i915 = to_i915(obj->base.dev);
	struct sg_table *st;
	struct scatterlist *sg;
	unsigned int sg_page_sizes;
	unsigned int npages;
	int max_order;
	gfp_t gfp;

	max_order = MAX_ORDER;
#ifdef CONFIG_SWIOTLB
	if (swiotlb_nr_tbl()) {
		unsigned int max_segment;

		max_segment = swiotlb_max_segment();
		if (max_segment) {
			max_segment = max_t(unsigned int, max_segment,
					    PAGE_SIZE) >> PAGE_SHIFT;
			max_order = min(max_order, ilog2(max_segment));
		}
	}
#endif

	gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_RECLAIMABLE;
	if (IS_I965GM(i915) || IS_I965G(i915)) {
		/* 965gm cannot relocate objects above 4GiB. */
		gfp &= ~__GFP_HIGHMEM;
		gfp |= __GFP_DMA32;
	}

create_st:
	st = kmalloc(sizeof(*st), GFP_KERNEL);
	if (!st)
		return -ENOMEM;

	npages = obj->base.size / PAGE_SIZE;
	if (sg_alloc_table(st, npages, GFP_KERNEL)) {
		kfree(st);
		return -ENOMEM;
	}

	sg = st->sgl;
	st->nents = 0;
	sg_page_sizes = 0;

	do {
		int order = min(fls(npages) - 1, max_order);
		struct page *page;

		do {
			page = alloc_pages(gfp | (order ? QUIET : MAYFAIL),
					   order);
			if (page)
				break;
			if (!order--)
				goto err;

			/* Limit subsequent allocations as well */
			max_order = order;
		} while (1);

		sg_set_page(sg, page, PAGE_SIZE << order, 0);
		sg_page_sizes |= PAGE_SIZE << order;
		st->nents++;

		npages -= 1 << order;
		if (!npages) {
			sg_mark_end(sg);
			break;
		}

		sg = __sg_next(sg);
	} while (1);

	if (i915_gem_gtt_prepare_pages(obj, st)) {
		/* Failed to dma-map try again with single page sg segments */
		if (get_order(st->sgl->length)) {
			internal_free_pages(st);
			max_order = 0;
			goto create_st;
		}
		goto err;
	}

	__i915_gem_object_set_pages(obj, st, sg_page_sizes);

	return 0;

err:
	sg_set_page(sg, NULL, 0, 0);
	sg_mark_end(sg);
	internal_free_pages(st);

	return -ENOMEM;
}

static void i915_gem_object_put_pages_internal(struct drm_i915_gem_object *obj,
					       struct sg_table *pages)
{
	i915_gem_gtt_finish_pages(obj, pages);
	internal_free_pages(pages);

	obj->mm.dirty = false;
}

static const struct drm_i915_gem_object_ops i915_gem_object_internal_ops = {
	.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE |
		 I915_GEM_OBJECT_IS_SHRINKABLE,
	.get_pages = i915_gem_object_get_pages_internal,
	.put_pages = i915_gem_object_put_pages_internal,
};

/**
 * i915_gem_object_create_internal: create an object with volatile pages
 * @i915: the i915 device
 * @size: the size in bytes of backing storage to allocate for the object
 *
 * Creates a new object that wraps some internal memory for private use.
 * This object is not backed by swappable storage, and as such its contents
 * are volatile and only valid whilst pinned. If the object is reaped by the
 * shrinker, its pages and data will be discarded. Equally, it is not a full
 * GEM object and so not valid for access from userspace. This makes it useful
 * for hardware interfaces like ringbuffers (which are pinned from the time
 * the request is written to the time the hardware stops accessing it), but
 * not for contexts (which need to be preserved when not active for later
 * reuse). Note that it is not cleared upon allocation.
 */
struct drm_i915_gem_object *
i915_gem_object_create_internal(struct drm_i915_private *i915,
				phys_addr_t size)
{
	static struct lock_class_key lock_class;
	struct drm_i915_gem_object *obj;
	unsigned int cache_level;

	GEM_BUG_ON(!size);
	GEM_BUG_ON(!IS_ALIGNED(size, PAGE_SIZE));

	if (overflows_type(size, obj->base.size))
		return ERR_PTR(-E2BIG);

	obj = i915_gem_object_alloc();
	if (!obj)
		return ERR_PTR(-ENOMEM);

	drm_gem_private_object_init(&i915->drm, &obj->base, size);
	i915_gem_object_init(obj, &i915_gem_object_internal_ops, &lock_class);

	/*
	 * Mark the object as volatile, such that the pages are marked as
	 * dontneed whilst they are still pinned. As soon as they are unpinned
	 * they are allowed to be reaped by the shrinker, and the caller is
	 * expected to repopulate - the contents of this object are only valid
	 * whilst active and pinned.
	 */
	i915_gem_object_set_volatile(obj);

	obj->read_domains = I915_GEM_DOMAIN_CPU;
	obj->write_domain = I915_GEM_DOMAIN_CPU;

	cache_level = HAS_LLC(i915) ? I915_CACHE_LLC : I915_CACHE_NONE;
	i915_gem_object_set_cache_coherency(obj, cache_level);

	return obj;
}