summaryrefslogtreecommitdiffstats
path: root/arch/openrisc/kernel/dma.c
blob: a945f00011b426e501bf2ac1e2bce398a78a7487 (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
254
255
256
257
258
259
260
/*
 * OpenRISC Linux
 *
 * Linux architectural port borrowing liberally from similar works of
 * others.  All original copyrights apply as per the original source
 * declaration.
 *
 * Modifications for the OpenRISC architecture:
 * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com>
 * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se>
 *
 *      This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 *
 * DMA mapping callbacks...
 * As alloc_coherent is the only DMA callback being used currently, that's
 * the only thing implemented properly.  The rest need looking into...
 */

#include <linux/dma-mapping.h>
#include <linux/dma-debug.h>
#include <linux/export.h>

#include <asm/cpuinfo.h>
#include <asm/spr_defs.h>
#include <asm/tlbflush.h>

static int
page_set_nocache(pte_t *pte, unsigned long addr,
		 unsigned long next, struct mm_walk *walk)
{
	unsigned long cl;
	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];

	pte_val(*pte) |= _PAGE_CI;

	/*
	 * Flush the page out of the TLB so that the new page flags get
	 * picked up next time there's an access
	 */
	flush_tlb_page(NULL, addr);

	/* Flush page out of dcache */
	for (cl = __pa(addr); cl < __pa(next); cl += cpuinfo->dcache_block_size)
		mtspr(SPR_DCBFR, cl);

	return 0;
}

static int
page_clear_nocache(pte_t *pte, unsigned long addr,
		   unsigned long next, struct mm_walk *walk)
{
	pte_val(*pte) &= ~_PAGE_CI;

	/*
	 * Flush the page out of the TLB so that the new page flags get
	 * picked up next time there's an access
	 */
	flush_tlb_page(NULL, addr);

	return 0;
}

/*
 * Alloc "coherent" memory, which for OpenRISC means simply uncached.
 *
 * This function effectively just calls __get_free_pages, sets the
 * cache-inhibit bit on those pages, and makes sure that the pages are
 * flushed out of the cache before they are used.
 *
 * If the NON_CONSISTENT attribute is set, then this function just
 * returns "normal", cachable memory.
 *
 * There are additional flags WEAK_ORDERING and WRITE_COMBINE to take
 * into consideration here, too.  All current known implementations of
 * the OR1K support only strongly ordered memory accesses, so that flag
 * is being ignored for now; uncached but write-combined memory is a
 * missing feature of the OR1K.
 */
static void *
or1k_dma_alloc(struct device *dev, size_t size,
	       dma_addr_t *dma_handle, gfp_t gfp,
	       unsigned long attrs)
{
	unsigned long va;
	void *page;
	struct mm_walk walk = {
		.pte_entry = page_set_nocache,
		.mm = &init_mm
	};

	page = alloc_pages_exact(size, gfp);
	if (!page)
		return NULL;

	/* This gives us the real physical address of the first page. */
	*dma_handle = __pa(page);

	va = (unsigned long)page;

	if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0) {
		/*
		 * We need to iterate through the pages, clearing the dcache for
		 * them and setting the cache-inhibit bit.
		 */
		if (walk_page_range(va, va + size, &walk)) {
			free_pages_exact(page, size);
			return NULL;
		}
	}

	return (void *)va;
}

static void
or1k_dma_free(struct device *dev, size_t size, void *vaddr,
	      dma_addr_t dma_handle, unsigned long attrs)
{
	unsigned long va = (unsigned long)vaddr;
	struct mm_walk walk = {
		.pte_entry = page_clear_nocache,
		.mm = &init_mm
	};

	if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0) {
		/* walk_page_range shouldn't be able to fail here */
		WARN_ON(walk_page_range(va, va + size, &walk));
	}

	free_pages_exact(vaddr, size);
}

static dma_addr_t
or1k_map_page(struct device *dev, struct page *page,
	      unsigned long offset, size_t size,
	      enum dma_data_direction dir,
	      unsigned long attrs)
{
	unsigned long cl;
	dma_addr_t addr = page_to_phys(page) + offset;
	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];

	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
		return addr;

	switch (dir) {
	case DMA_TO_DEVICE:
		/* Flush the dcache for the requested range */
		for (cl = addr; cl < addr + size;
		     cl += cpuinfo->dcache_block_size)
			mtspr(SPR_DCBFR, cl);
		break;
	case DMA_FROM_DEVICE:
		/* Invalidate the dcache for the requested range */
		for (cl = addr; cl < addr + size;
		     cl += cpuinfo->dcache_block_size)
			mtspr(SPR_DCBIR, cl);
		break;
	default:
		/*
		 * NOTE: If dir == DMA_BIDIRECTIONAL then there's no need to
		 * flush nor invalidate the cache here as the area will need
		 * to be manually synced anyway.
		 */
		break;
	}

	return addr;
}

static void
or1k_unmap_page(struct device *dev, dma_addr_t dma_handle,
		size_t size, enum dma_data_direction dir,
		unsigned long attrs)
{
	/* Nothing special to do here... */
}

static int
or1k_map_sg(struct device *dev, struct scatterlist *sg,
	    int nents, enum dma_data_direction dir,
	    unsigned long attrs)
{
	struct scatterlist *s;
	int i;

	for_each_sg(sg, s, nents, i) {
		s->dma_address = or1k_map_page(dev, sg_page(s), s->offset,
					       s->length, dir, 0);
	}

	return nents;
}

static void
or1k_unmap_sg(struct device *dev, struct scatterlist *sg,
	      int nents, enum dma_data_direction dir,
	      unsigned long attrs)
{
	struct scatterlist *s;
	int i;

	for_each_sg(sg, s, nents, i) {
		or1k_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, 0);
	}
}

static void
or1k_sync_single_for_cpu(struct device *dev,
			 dma_addr_t dma_handle, size_t size,
			 enum dma_data_direction dir)
{
	unsigned long cl;
	dma_addr_t addr = dma_handle;
	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];

	/* Invalidate the dcache for the requested range */
	for (cl = addr; cl < addr + size; cl += cpuinfo->dcache_block_size)
		mtspr(SPR_DCBIR, cl);
}

static void
or1k_sync_single_for_device(struct device *dev,
			    dma_addr_t dma_handle, size_t size,
			    enum dma_data_direction dir)
{
	unsigned long cl;
	dma_addr_t addr = dma_handle;
	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];

	/* Flush the dcache for the requested range */
	for (cl = addr; cl < addr + size; cl += cpuinfo->dcache_block_size)
		mtspr(SPR_DCBFR, cl);
}

const struct dma_map_ops or1k_dma_map_ops = {
	.alloc = or1k_dma_alloc,
	.free = or1k_dma_free,
	.map_page = or1k_map_page,
	.unmap_page = or1k_unmap_page,
	.map_sg = or1k_map_sg,
	.unmap_sg = or1k_unmap_sg,
	.sync_single_for_cpu = or1k_sync_single_for_cpu,
	.sync_single_for_device = or1k_sync_single_for_device,
};
EXPORT_SYMBOL(or1k_dma_map_ops);

/* Number of entries preallocated for DMA-API debugging */
#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)

static int __init dma_init(void)
{
	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);

	return 0;
}
fs_initcall(dma_init);