aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel/pci-dma_32.c
blob: 5450bd142cb0a568ba0df5e9ff832f834bfb8b9f (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
/*
 * Dynamic DMA mapping support.
 *
 * On i386 there is no hardware dynamic DMA address translation,
 * so consistent alloc/free are merely page allocation/freeing.
 * The rest of the dynamic DMA mapping interface is implemented
 * in asm/pci.h.
 */

#include <linux/types.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/pci.h>
#include <linux/module.h>
#include <asm/io.h>

/* Dummy device used for NULL arguments (normally ISA). Better would
   be probably a smaller DMA mask, but this is bug-to-bug compatible
   to i386. */
struct device fallback_dev = {
	.bus_id = "fallback device",
	.coherent_dma_mask = DMA_32BIT_MASK,
	.dma_mask = &fallback_dev.coherent_dma_mask,
};


static int dma_alloc_from_coherent_mem(struct device *dev, ssize_t size,
				       dma_addr_t *dma_handle, void **ret)
{
	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
	int order = get_order(size);

	if (mem) {
		int page = bitmap_find_free_region(mem->bitmap, mem->size,
						     order);
		if (page >= 0) {
			*dma_handle = mem->device_base + (page << PAGE_SHIFT);
			*ret = mem->virt_base + (page << PAGE_SHIFT);
			memset(*ret, 0, size);
		}
		if (mem->flags & DMA_MEMORY_EXCLUSIVE)
			*ret = NULL;
	}
	return (mem != NULL);
}

static int dma_release_coherent(struct device *dev, int order, void *vaddr)
{
	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;

	if (mem && vaddr >= mem->virt_base && vaddr <
		   (mem->virt_base + (mem->size << PAGE_SHIFT))) {
		int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;

		bitmap_release_region(mem->bitmap, page, order);
		return 1;
	}
	return 0;
}

/* Allocate DMA memory on node near device */
noinline struct page *
dma_alloc_pages(struct device *dev, gfp_t gfp, unsigned order)
{
	int node;

	node = dev_to_node(dev);

	return alloc_pages_node(node, gfp, order);
}

void *dma_alloc_coherent(struct device *dev, size_t size,
			   dma_addr_t *dma_handle, gfp_t gfp)
{
	void *ret = NULL;
	struct page *page;
	dma_addr_t bus;
	int order = get_order(size);
	unsigned long dma_mask = 0;

	/* ignore region specifiers */
	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);

	if (dma_alloc_from_coherent_mem(dev, size, dma_handle, &ret))
		return ret;

	if (!dev)
		dev = &fallback_dev;

	dma_mask = dev->coherent_dma_mask;
	if (dma_mask == 0)
		dma_mask = DMA_32BIT_MASK;

	/* Don't invoke OOM killer */
	gfp |= __GFP_NORETRY;
again:
	page = dma_alloc_pages(dev, gfp, order);
	if (page == NULL)
		return NULL;

	{
		int high, mmu;
		bus = page_to_phys(page);
		ret = page_address(page);
		high = (bus + size) >= dma_mask;
		mmu = high;
		if (force_iommu && !(gfp & GFP_DMA))
			mmu = 1;
		else if (high) {
			free_pages((unsigned long)ret,
				   get_order(size));

			/* Don't use the 16MB ZONE_DMA unless absolutely
			   needed. It's better to use remapping first. */
			if (dma_mask < DMA_32BIT_MASK && !(gfp & GFP_DMA)) {
				gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
				goto again;
			}
		}
		memset(ret, 0, size);
		*dma_handle = bus;
	}

	return ret;
}
EXPORT_SYMBOL(dma_alloc_coherent);

void dma_free_coherent(struct device *dev, size_t size,
			 void *vaddr, dma_addr_t dma_handle)
{
	int order = get_order(size);

	WARN_ON(irqs_disabled());	/* for portability */
	if (dma_release_coherent(dev, order, vaddr))
		return;
	if (dma_ops->unmap_single)
		dma_ops->unmap_single(dev, dma_handle, size, 0);
	free_pages((unsigned long)vaddr, order);
}
EXPORT_SYMBOL(dma_free_coherent);