summaryrefslogtreecommitdiffstats
path: root/arch/csky/mm/dma-mapping.c
blob: ad4046939713af8794bafb10c82ebe5e77d8be88 (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
// SPDX-License-Identifier: GPL-2.0
// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.

#include <linux/cache.h>
#include <linux/dma-mapping.h>
#include <linux/dma-contiguous.h>
#include <linux/dma-noncoherent.h>
#include <linux/genalloc.h>
#include <linux/highmem.h>
#include <linux/io.h>
#include <linux/mm.h>
#include <linux/scatterlist.h>
#include <linux/types.h>
#include <linux/version.h>
#include <asm/cache.h>

static struct gen_pool *atomic_pool;
static size_t atomic_pool_size __initdata = SZ_256K;

static int __init early_coherent_pool(char *p)
{
	atomic_pool_size = memparse(p, &p);
	return 0;
}
early_param("coherent_pool", early_coherent_pool);

static int __init atomic_pool_init(void)
{
	struct page *page;
	size_t size = atomic_pool_size;
	void *ptr;
	int ret;

	atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
	if (!atomic_pool)
		BUG();

	page = alloc_pages(GFP_KERNEL, get_order(size));
	if (!page)
		BUG();

	ptr = dma_common_contiguous_remap(page, size, VM_ALLOC,
					  pgprot_noncached(PAGE_KERNEL),
					  __builtin_return_address(0));
	if (!ptr)
		BUG();

	ret = gen_pool_add_virt(atomic_pool, (unsigned long)ptr,
				page_to_phys(page), atomic_pool_size, -1);
	if (ret)
		BUG();

	gen_pool_set_algo(atomic_pool, gen_pool_first_fit_order_align, NULL);

	pr_info("DMA: preallocated %zu KiB pool for atomic coherent pool\n",
		atomic_pool_size / 1024);

	pr_info("DMA: vaddr: 0x%x phy: 0x%lx,\n", (unsigned int)ptr,
		page_to_phys(page));

	return 0;
}
postcore_initcall(atomic_pool_init);

static void *csky_dma_alloc_atomic(struct device *dev, size_t size,
				   dma_addr_t *dma_handle)
{
	unsigned long addr;

	addr = gen_pool_alloc(atomic_pool, size);
	if (addr)
		*dma_handle = gen_pool_virt_to_phys(atomic_pool, addr);

	return (void *)addr;
}

static void csky_dma_free_atomic(struct device *dev, size_t size, void *vaddr,
				 dma_addr_t dma_handle, unsigned long attrs)
{
	gen_pool_free(atomic_pool, (unsigned long)vaddr, size);
}

static void __dma_clear_buffer(struct page *page, size_t size)
{
	if (PageHighMem(page)) {
		unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;

		do {
			void *ptr = kmap_atomic(page);
			size_t _size = (size < PAGE_SIZE) ? size : PAGE_SIZE;

			memset(ptr, 0, _size);
			dma_wbinv_range((unsigned long)ptr,
					(unsigned long)ptr + _size);

			kunmap_atomic(ptr);

			page++;
			size -= PAGE_SIZE;
			count--;
		} while (count);
	} else {
		void *ptr = page_address(page);

		memset(ptr, 0, size);
		dma_wbinv_range((unsigned long)ptr, (unsigned long)ptr + size);
	}
}

static void *csky_dma_alloc_nonatomic(struct device *dev, size_t size,
				      dma_addr_t *dma_handle, gfp_t gfp,
				      unsigned long attrs)
{
	void  *vaddr;
	struct page *page;
	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;

	if (DMA_ATTR_NON_CONSISTENT & attrs) {
		pr_err("csky %s can't support DMA_ATTR_NON_CONSISTENT.\n", __func__);
		return NULL;
	}

	if (IS_ENABLED(CONFIG_DMA_CMA))
		page = dma_alloc_from_contiguous(dev, count, get_order(size),
						 gfp);
	else
		page = alloc_pages(gfp, get_order(size));

	if (!page) {
		pr_err("csky %s no more free pages.\n", __func__);
		return NULL;
	}

	*dma_handle = page_to_phys(page);

	__dma_clear_buffer(page, size);

	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
		return page;

	vaddr = dma_common_contiguous_remap(page, PAGE_ALIGN(size), VM_USERMAP,
		pgprot_noncached(PAGE_KERNEL), __builtin_return_address(0));
	if (!vaddr)
		BUG();

	return vaddr;
}

static void csky_dma_free_nonatomic(
	struct device *dev,
	size_t size,
	void *vaddr,
	dma_addr_t dma_handle,
	unsigned long attrs
	)
{
	struct page *page = phys_to_page(dma_handle);
	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;

	if ((unsigned int)vaddr >= VMALLOC_START)
		dma_common_free_remap(vaddr, size, VM_USERMAP);

	if (IS_ENABLED(CONFIG_DMA_CMA))
		dma_release_from_contiguous(dev, page, count);
	else
		__free_pages(page, get_order(size));
}

void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
		     gfp_t gfp, unsigned long attrs)
{
	if (gfpflags_allow_blocking(gfp))
		return csky_dma_alloc_nonatomic(dev, size, dma_handle, gfp,
						attrs);
	else
		return csky_dma_alloc_atomic(dev, size, dma_handle);
}

void arch_dma_free(struct device *dev, size_t size, void *vaddr,
		   dma_addr_t dma_handle, unsigned long attrs)
{
	if (!addr_in_gen_pool(atomic_pool, (unsigned int) vaddr, size))
		csky_dma_free_nonatomic(dev, size, vaddr, dma_handle, attrs);
	else
		csky_dma_free_atomic(dev, size, vaddr, dma_handle, attrs);
}

static inline void cache_op(phys_addr_t paddr, size_t size,
			    void (*fn)(unsigned long start, unsigned long end))
{
	struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
	unsigned int offset = paddr & ~PAGE_MASK;
	size_t left = size;
	unsigned long start;

	do {
		size_t len = left;

		if (PageHighMem(page)) {
			void *addr;

			if (offset + len > PAGE_SIZE) {
				if (offset >= PAGE_SIZE) {
					page += offset >> PAGE_SHIFT;
					offset &= ~PAGE_MASK;
				}
				len = PAGE_SIZE - offset;
			}

			addr = kmap_atomic(page);
			start = (unsigned long)(addr + offset);
			fn(start, start + len);
			kunmap_atomic(addr);
		} else {
			start = (unsigned long)phys_to_virt(paddr);
			fn(start, start + size);
		}
		offset = 0;
		page++;
		left -= len;
	} while (left);
}

void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
			      size_t size, enum dma_data_direction dir)
{
	switch (dir) {
	case DMA_TO_DEVICE:
		cache_op(paddr, size, dma_wb_range);
		break;
	case DMA_FROM_DEVICE:
	case DMA_BIDIRECTIONAL:
		cache_op(paddr, size, dma_wbinv_range);
		break;
	default:
		BUG();
	}
}

void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
			   size_t size, enum dma_data_direction dir)
{
	switch (dir) {
	case DMA_TO_DEVICE:
		cache_op(paddr, size, dma_wb_range);
		break;
	case DMA_FROM_DEVICE:
	case DMA_BIDIRECTIONAL:
		cache_op(paddr, size, dma_wbinv_range);
		break;
	default:
		BUG();
	}
}