summaryrefslogtreecommitdiff
path: root/mm/page_frag_cache.c
blob: 3f7a203d35c6409193df5b64adb5301193b4141b (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
// SPDX-License-Identifier: GPL-2.0-only
/* Page fragment allocator
 *
 * Page Fragment:
 *  An arbitrary-length arbitrary-offset area of memory which resides within a
 *  0 or higher order page.  Multiple fragments within that page are
 *  individually refcounted, in the page's reference counter.
 *
 * The page_frag functions provide a simple allocation framework for page
 * fragments.  This is used by the network stack and network device drivers to
 * provide a backing region of memory for use as either an sk_buff->head, or to
 * be used in the "frags" portion of skb_shared_info.
 */

#include <linux/build_bug.h>
#include <linux/export.h>
#include <linux/gfp_types.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/page_frag_cache.h>
#include "internal.h"

static unsigned long encoded_page_create(struct page *page, unsigned int order,
					 bool pfmemalloc)
{
	BUILD_BUG_ON(PAGE_FRAG_CACHE_MAX_ORDER > PAGE_FRAG_CACHE_ORDER_MASK);
	BUILD_BUG_ON(PAGE_FRAG_CACHE_PFMEMALLOC_BIT >= PAGE_SIZE);

	return (unsigned long)page_address(page) |
		(order & PAGE_FRAG_CACHE_ORDER_MASK) |
		((unsigned long)pfmemalloc * PAGE_FRAG_CACHE_PFMEMALLOC_BIT);
}

static unsigned long encoded_page_decode_order(unsigned long encoded_page)
{
	return encoded_page & PAGE_FRAG_CACHE_ORDER_MASK;
}

static void *encoded_page_decode_virt(unsigned long encoded_page)
{
	return (void *)(encoded_page & PAGE_MASK);
}

static struct page *encoded_page_decode_page(unsigned long encoded_page)
{
	return virt_to_page((void *)encoded_page);
}

static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
					     gfp_t gfp_mask)
{
	unsigned long order = PAGE_FRAG_CACHE_MAX_ORDER;
	struct page *page = NULL;
	gfp_t gfp = gfp_mask;

#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
	gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) |  __GFP_COMP |
		   __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC;
	page = __alloc_pages(gfp_mask, PAGE_FRAG_CACHE_MAX_ORDER,
			     numa_mem_id(), NULL);
#endif
	if (unlikely(!page)) {
		page = __alloc_pages(gfp, 0, numa_mem_id(), NULL);
		order = 0;
	}

	nc->encoded_page = page ?
		encoded_page_create(page, order, page_is_pfmemalloc(page)) : 0;

	return page;
}

void page_frag_cache_drain(struct page_frag_cache *nc)
{
	if (!nc->encoded_page)
		return;

	__page_frag_cache_drain(encoded_page_decode_page(nc->encoded_page),
				nc->pagecnt_bias);
	nc->encoded_page = 0;
}
EXPORT_SYMBOL(page_frag_cache_drain);

void __page_frag_cache_drain(struct page *page, unsigned int count)
{
	VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);

	if (page_ref_sub_and_test(page, count))
		free_unref_page(page, compound_order(page));
}
EXPORT_SYMBOL(__page_frag_cache_drain);

void *__page_frag_alloc_align(struct page_frag_cache *nc,
			      unsigned int fragsz, gfp_t gfp_mask,
			      unsigned int align_mask)
{
	unsigned long encoded_page = nc->encoded_page;
	unsigned int size, offset;
	struct page *page;

	if (unlikely(!encoded_page)) {
refill:
		page = __page_frag_cache_refill(nc, gfp_mask);
		if (!page)
			return NULL;

		encoded_page = nc->encoded_page;

		/* Even if we own the page, we do not use atomic_set().
		 * This would break get_page_unless_zero() users.
		 */
		page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE);

		/* reset page count bias and offset to start of new frag */
		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
		nc->offset = 0;
	}

	size = PAGE_SIZE << encoded_page_decode_order(encoded_page);
	offset = __ALIGN_KERNEL_MASK(nc->offset, ~align_mask);
	if (unlikely(offset + fragsz > size)) {
		if (unlikely(fragsz > PAGE_SIZE)) {
			/*
			 * The caller is trying to allocate a fragment
			 * with fragsz > PAGE_SIZE but the cache isn't big
			 * enough to satisfy the request, this may
			 * happen in low memory conditions.
			 * We don't release the cache page because
			 * it could make memory pressure worse
			 * so we simply return NULL here.
			 */
			return NULL;
		}

		page = encoded_page_decode_page(encoded_page);

		if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
			goto refill;

		if (unlikely(encoded_page_decode_pfmemalloc(encoded_page))) {
			free_unref_page(page,
					encoded_page_decode_order(encoded_page));
			goto refill;
		}

		/* OK, page count is 0, we can safely set it */
		set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1);

		/* reset page count bias and offset to start of new frag */
		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
		offset = 0;
	}

	nc->pagecnt_bias--;
	nc->offset = offset + fragsz;

	return encoded_page_decode_virt(encoded_page) + offset;
}
EXPORT_SYMBOL(__page_frag_alloc_align);

/*
 * Frees a page fragment allocated out of either a compound or order 0 page.
 */
void page_frag_free(void *addr)
{
	struct page *page = virt_to_head_page(addr);

	if (unlikely(put_page_testzero(page)))
		free_unref_page(page, compound_order(page));
}
EXPORT_SYMBOL(page_frag_free);