summaryrefslogtreecommitdiff
path: root/arch/arm/xen/mm.c
blob: 7c34f7126b046abe9d61637a1716a2ae5139bfe5 (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
#include <linux/cpu.h>
#include <linux/dma-mapping.h>
#include <linux/bootmem.h>
#include <linux/gfp.h>
#include <linux/highmem.h>
#include <linux/export.h>
#include <linux/memblock.h>
#include <linux/of_address.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/dma-mapping.h>
#include <linux/vmalloc.h>
#include <linux/swiotlb.h>

#include <xen/xen.h>
#include <xen/interface/grant_table.h>
#include <xen/interface/memory.h>
#include <xen/page.h>
#include <xen/swiotlb-xen.h>

#include <asm/cacheflush.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/interface.h>

unsigned long xen_get_swiotlb_free_pages(unsigned int order)
{
	struct memblock_region *reg;
	gfp_t flags = __GFP_NOWARN;

	for_each_memblock(memory, reg) {
		if (reg->base < (phys_addr_t)0xffffffff) {
			flags |= __GFP_DMA;
			break;
		}
	}
	return __get_free_pages(flags, order);
}

enum dma_cache_op {
       DMA_UNMAP,
       DMA_MAP,
};
static bool hypercall_cflush = false;

/* functions called by SWIOTLB */

static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
	size_t size, enum dma_data_direction dir, enum dma_cache_op op)
{
	struct gnttab_cache_flush cflush;
	unsigned long xen_pfn;
	size_t left = size;

	xen_pfn = (handle >> XEN_PAGE_SHIFT) + offset / XEN_PAGE_SIZE;
	offset %= XEN_PAGE_SIZE;

	do {
		size_t len = left;
	
		/* buffers in highmem or foreign pages cannot cross page
		 * boundaries */
		if (len + offset > XEN_PAGE_SIZE)
			len = XEN_PAGE_SIZE - offset;

		cflush.op = 0;
		cflush.a.dev_bus_addr = xen_pfn << XEN_PAGE_SHIFT;
		cflush.offset = offset;
		cflush.length = len;

		if (op == DMA_UNMAP && dir != DMA_TO_DEVICE)
			cflush.op = GNTTAB_CACHE_INVAL;
		if (op == DMA_MAP) {
			if (dir == DMA_FROM_DEVICE)
				cflush.op = GNTTAB_CACHE_INVAL;
			else
				cflush.op = GNTTAB_CACHE_CLEAN;
		}
		if (cflush.op)
			HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1);

		offset = 0;
		xen_pfn++;
		left -= len;
	} while (left);
}

static void __xen_dma_page_dev_to_cpu(struct device *hwdev, dma_addr_t handle,
		size_t size, enum dma_data_direction dir)
{
	dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_UNMAP);
}

static void __xen_dma_page_cpu_to_dev(struct device *hwdev, dma_addr_t handle,
		size_t size, enum dma_data_direction dir)
{
	dma_cache_maint(handle & PAGE_MASK, handle & ~PAGE_MASK, size, dir, DMA_MAP);
}

void __xen_dma_map_page(struct device *hwdev, struct page *page,
	     dma_addr_t dev_addr, unsigned long offset, size_t size,
	     enum dma_data_direction dir, struct dma_attrs *attrs)
{
	if (is_device_dma_coherent(hwdev))
		return;
	if (dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
		return;

	__xen_dma_page_cpu_to_dev(hwdev, dev_addr, size, dir);
}

void __xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
		size_t size, enum dma_data_direction dir,
		struct dma_attrs *attrs)

{
	if (is_device_dma_coherent(hwdev))
		return;
	if (dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
		return;

	__xen_dma_page_dev_to_cpu(hwdev, handle, size, dir);
}

void __xen_dma_sync_single_for_cpu(struct device *hwdev,
		dma_addr_t handle, size_t size, enum dma_data_direction dir)
{
	if (is_device_dma_coherent(hwdev))
		return;
	__xen_dma_page_dev_to_cpu(hwdev, handle, size, dir);
}

void __xen_dma_sync_single_for_device(struct device *hwdev,
		dma_addr_t handle, size_t size, enum dma_data_direction dir)
{
	if (is_device_dma_coherent(hwdev))
		return;
	__xen_dma_page_cpu_to_dev(hwdev, handle, size, dir);
}

bool xen_arch_need_swiotlb(struct device *dev,
			   phys_addr_t phys,
			   dma_addr_t dev_addr)
{
	unsigned int xen_pfn = XEN_PFN_DOWN(phys);
	unsigned int bfn = XEN_PFN_DOWN(dev_addr);

	/*
	 * The swiotlb buffer should be used if
	 *	- Xen doesn't have the cache flush hypercall
	 *	- The Linux page refers to foreign memory
	 *	- The device doesn't support coherent DMA request
	 *
	 * The Linux page may be spanned acrros multiple Xen page, although
	 * it's not possible to have a mix of local and foreign Xen page.
	 * Furthermore, range_straddles_page_boundary is already checking
	 * if buffer is physically contiguous in the host RAM.
	 *
	 * Therefore we only need to check the first Xen page to know if we
	 * require a bounce buffer because the device doesn't support coherent
	 * memory and we are not able to flush the cache.
	 */
	return (!hypercall_cflush && (xen_pfn != bfn) &&
		!is_device_dma_coherent(dev));
}

int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
				 unsigned int address_bits,
				 dma_addr_t *dma_handle)
{
	if (!xen_initial_domain())
		return -EINVAL;

	/* we assume that dom0 is mapped 1:1 for now */
	*dma_handle = pstart;
	return 0;
}
EXPORT_SYMBOL_GPL(xen_create_contiguous_region);

void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
{
	return;
}
EXPORT_SYMBOL_GPL(xen_destroy_contiguous_region);

struct dma_map_ops *xen_dma_ops;
EXPORT_SYMBOL(xen_dma_ops);

static struct dma_map_ops xen_swiotlb_dma_ops = {
	.mapping_error = xen_swiotlb_dma_mapping_error,
	.alloc = xen_swiotlb_alloc_coherent,
	.free = xen_swiotlb_free_coherent,
	.sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu,
	.sync_single_for_device = xen_swiotlb_sync_single_for_device,
	.sync_sg_for_cpu = xen_swiotlb_sync_sg_for_cpu,
	.sync_sg_for_device = xen_swiotlb_sync_sg_for_device,
	.map_sg = xen_swiotlb_map_sg_attrs,
	.unmap_sg = xen_swiotlb_unmap_sg_attrs,
	.map_page = xen_swiotlb_map_page,
	.unmap_page = xen_swiotlb_unmap_page,
	.dma_supported = xen_swiotlb_dma_supported,
	.set_dma_mask = xen_swiotlb_set_dma_mask,
};

int __init xen_mm_init(void)
{
	struct gnttab_cache_flush cflush;
	if (!xen_initial_domain())
		return 0;
	xen_swiotlb_init(1, false);
	xen_dma_ops = &xen_swiotlb_dma_ops;

	cflush.op = 0;
	cflush.a.dev_bus_addr = 0;
	cflush.offset = 0;
	cflush.length = 0;
	if (HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1) != -ENOSYS)
		hypercall_cflush = true;
	return 0;
}
arch_initcall(xen_mm_init);