summaryrefslogtreecommitdiff
path: root/include/net/page_pool.h
blob: b5b1953053468e5d627d122030ad77f50db51be7 (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
/* SPDX-License-Identifier: GPL-2.0
 *
 * page_pool.h
 *	Author:	Jesper Dangaard Brouer <netoptimizer@brouer.com>
 *	Copyright (C) 2016 Red Hat, Inc.
 */

/**
 * DOC: page_pool allocator
 *
 * This page_pool allocator is optimized for the XDP mode that
 * uses one-frame-per-page, but have fallbacks that act like the
 * regular page allocator APIs.
 *
 * Basic use involve replacing alloc_pages() calls with the
 * page_pool_alloc_pages() call.  Drivers should likely use
 * page_pool_dev_alloc_pages() replacing dev_alloc_pages().
 *
 * API keeps track of in-flight pages, in-order to let API user know
 * when it is safe to dealloactor page_pool object.  Thus, API users
 * must make sure to call page_pool_release_page() when a page is
 * "leaving" the page_pool.  Or call page_pool_put_page() where
 * appropiate.  For maintaining correct accounting.
 *
 * API user must only call page_pool_put_page() once on a page, as it
 * will either recycle the page, or in case of elevated refcnt, it
 * will release the DMA mapping and in-flight state accounting.  We
 * hope to lift this requirement in the future.
 */
#ifndef _NET_PAGE_POOL_H
#define _NET_PAGE_POOL_H

#include <linux/mm.h> /* Needed by ptr_ring */
#include <linux/ptr_ring.h>
#include <linux/dma-direction.h>

#define PP_FLAG_DMA_MAP		BIT(0) /* Should page_pool do the DMA
					* map/unmap
					*/
#define PP_FLAG_DMA_SYNC_DEV	BIT(1) /* If set all pages that the driver gets
					* from page_pool will be
					* DMA-synced-for-device according to
					* the length provided by the device
					* driver.
					* Please note DMA-sync-for-CPU is still
					* device driver responsibility
					*/
#define PP_FLAG_ALL		(PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV)

/*
 * Fast allocation side cache array/stack
 *
 * The cache size and refill watermark is related to the network
 * use-case.  The NAPI budget is 64 packets.  After a NAPI poll the RX
 * ring is usually refilled and the max consumed elements will be 64,
 * thus a natural max size of objects needed in the cache.
 *
 * Keeping room for more objects, is due to XDP_DROP use-case.  As
 * XDP_DROP allows the opportunity to recycle objects directly into
 * this array, as it shares the same softirq/NAPI protection.  If
 * cache is already full (or partly full) then the XDP_DROP recycles
 * would have to take a slower code path.
 */
#define PP_ALLOC_CACHE_SIZE	128
#define PP_ALLOC_CACHE_REFILL	64
struct pp_alloc_cache {
	u32 count;
	void *cache[PP_ALLOC_CACHE_SIZE];
};

struct page_pool_params {
	unsigned int	flags;
	unsigned int	order;
	unsigned int	pool_size;
	int		nid;  /* Numa node id to allocate from pages from */
	struct device	*dev; /* device, for DMA pre-mapping purposes */
	enum dma_data_direction dma_dir; /* DMA mapping direction */
	unsigned int	max_len; /* max DMA sync memory size */
	unsigned int	offset;  /* DMA addr offset */
};

struct page_pool {
	struct page_pool_params p;

	struct delayed_work release_dw;
	void (*disconnect)(void *);
	unsigned long defer_start;
	unsigned long defer_warn;

	u32 pages_state_hold_cnt;

	/*
	 * Data structure for allocation side
	 *
	 * Drivers allocation side usually already perform some kind
	 * of resource protection.  Piggyback on this protection, and
	 * require driver to protect allocation side.
	 *
	 * For NIC drivers this means, allocate a page_pool per
	 * RX-queue. As the RX-queue is already protected by
	 * Softirq/BH scheduling and napi_schedule. NAPI schedule
	 * guarantee that a single napi_struct will only be scheduled
	 * on a single CPU (see napi_schedule).
	 */
	struct pp_alloc_cache alloc ____cacheline_aligned_in_smp;

	/* Data structure for storing recycled pages.
	 *
	 * Returning/freeing pages is more complicated synchronization
	 * wise, because free's can happen on remote CPUs, with no
	 * association with allocation resource.
	 *
	 * Use ptr_ring, as it separates consumer and producer
	 * effeciently, it a way that doesn't bounce cache-lines.
	 *
	 * TODO: Implement bulk return pages into this structure.
	 */
	struct ptr_ring ring;

	atomic_t pages_state_release_cnt;

	/* A page_pool is strictly tied to a single RX-queue being
	 * protected by NAPI, due to above pp_alloc_cache. This
	 * refcnt serves purpose is to simplify drivers error handling.
	 */
	refcount_t user_cnt;

	u64 destroy_cnt;
};

struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp);

static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool)
{
	gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN);

	return page_pool_alloc_pages(pool, gfp);
}

/* get the stored dma direction. A driver might decide to treat this locally and
 * avoid the extra cache line from page_pool to determine the direction
 */
static
inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool)
{
	return pool->p.dma_dir;
}

struct page_pool *page_pool_create(const struct page_pool_params *params);

#ifdef CONFIG_PAGE_POOL
void page_pool_destroy(struct page_pool *pool);
void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *));
void page_pool_release_page(struct page_pool *pool, struct page *page);
void page_pool_put_page_bulk(struct page_pool *pool, void **data,
			     int count);
#else
static inline void page_pool_destroy(struct page_pool *pool)
{
}

static inline void page_pool_use_xdp_mem(struct page_pool *pool,
					 void (*disconnect)(void *))
{
}
static inline void page_pool_release_page(struct page_pool *pool,
					  struct page *page)
{
}

static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data,
					   int count)
{
}
#endif

void page_pool_put_page(struct page_pool *pool, struct page *page,
			unsigned int dma_sync_size, bool allow_direct);

/* Same as above but will try to sync the entire area pool->max_len */
static inline void page_pool_put_full_page(struct page_pool *pool,
					   struct page *page, bool allow_direct)
{
	/* When page_pool isn't compiled-in, net/core/xdp.c doesn't
	 * allow registering MEM_TYPE_PAGE_POOL, but shield linker.
	 */
#ifdef CONFIG_PAGE_POOL
	page_pool_put_page(pool, page, -1, allow_direct);
#endif
}

/* Same as above but the caller must guarantee safe context. e.g NAPI */
static inline void page_pool_recycle_direct(struct page_pool *pool,
					    struct page *page)
{
	page_pool_put_full_page(pool, page, true);
}

static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
{
	return page->dma_addr;
}

static inline bool is_page_pool_compiled_in(void)
{
#ifdef CONFIG_PAGE_POOL
	return true;
#else
	return false;
#endif
}

static inline bool page_pool_put(struct page_pool *pool)
{
	return refcount_dec_and_test(&pool->user_cnt);
}

/* Caller must provide appropriate safe context, e.g. NAPI. */
void page_pool_update_nid(struct page_pool *pool, int new_nid);
static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid)
{
	if (unlikely(pool->p.nid != new_nid))
		page_pool_update_nid(pool, new_nid);
}

static inline void page_pool_ring_lock(struct page_pool *pool)
	__acquires(&pool->ring.producer_lock)
{
	if (in_serving_softirq())
		spin_lock(&pool->ring.producer_lock);
	else
		spin_lock_bh(&pool->ring.producer_lock);
}

static inline void page_pool_ring_unlock(struct page_pool *pool)
	__releases(&pool->ring.producer_lock)
{
	if (in_serving_softirq())
		spin_unlock(&pool->ring.producer_lock);
	else
		spin_unlock_bh(&pool->ring.producer_lock);
}

#endif /* _NET_PAGE_POOL_H */