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
|
/*
* Dynamic DMA mapping support.
*/
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/pci.h>
#include <linux/module.h>
#include <linux/dmar.h>
#include <linux/bootmem.h>
#include <asm/proto.h>
#include <asm/io.h>
#include <asm/gart.h>
#include <asm/calgary.h>
int iommu_merge __read_mostly = 0;
dma_addr_t bad_dma_address __read_mostly;
EXPORT_SYMBOL(bad_dma_address);
/* This tells the BIO block layer to assume merging. Default to off
because we cannot guarantee merging later. */
int iommu_bio_merge __read_mostly = 0;
EXPORT_SYMBOL(iommu_bio_merge);
extern int iommu_sac_force;
int no_iommu __read_mostly;
/* Set this to 1 if there is a HW IOMMU in the system */
int iommu_detected __read_mostly = 0;
/* 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,
};
/* Allocate DMA memory on node near device */
noinline static void *
dma_alloc_pages(struct device *dev, gfp_t gfp, unsigned order)
{
struct page *page;
int node;
node = dev_to_node(dev);
page = alloc_pages_node(node, gfp, order);
return page ? page_address(page) : NULL;
}
/*
* Allocate memory for a coherent mapping.
*/
void *
dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
gfp_t gfp)
{
void *memory;
unsigned long dma_mask = 0;
u64 bus;
if (!dev)
dev = &fallback_dev;
dma_mask = dev->coherent_dma_mask;
if (dma_mask == 0)
dma_mask = DMA_32BIT_MASK;
/* Device not DMA able */
if (dev->dma_mask == NULL)
return NULL;
/* Don't invoke OOM killer */
gfp |= __GFP_NORETRY;
/* Kludge to make it bug-to-bug compatible with i386. i386
uses the normal dma_mask for alloc_coherent. */
dma_mask &= *dev->dma_mask;
/* Why <=? Even when the mask is smaller than 4GB it is often
larger than 16MB and in this case we have a chance of
finding fitting memory in the next higher zone first. If
not retry with true GFP_DMA. -AK */
if (dma_mask <= DMA_32BIT_MASK)
gfp |= GFP_DMA32;
again:
memory = dma_alloc_pages(dev, gfp, get_order(size));
if (memory == NULL)
return NULL;
{
int high, mmu;
bus = virt_to_bus(memory);
high = (bus + size) >= dma_mask;
mmu = high;
if (force_iommu && !(gfp & GFP_DMA))
mmu = 1;
else if (high) {
free_pages((unsigned long)memory,
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;
}
/* Let low level make its own zone decisions */
gfp &= ~(GFP_DMA32|GFP_DMA);
if (dma_ops->alloc_coherent)
return dma_ops->alloc_coherent(dev, size,
dma_handle, gfp);
return NULL;
}
memset(memory, 0, size);
if (!mmu) {
*dma_handle = virt_to_bus(memory);
return memory;
}
}
if (dma_ops->alloc_coherent) {
free_pages((unsigned long)memory, get_order(size));
gfp &= ~(GFP_DMA|GFP_DMA32);
return dma_ops->alloc_coherent(dev, size, dma_handle, gfp);
}
if (dma_ops->map_simple) {
*dma_handle = dma_ops->map_simple(dev, virt_to_phys(memory),
size,
PCI_DMA_BIDIRECTIONAL);
if (*dma_handle != bad_dma_address)
return memory;
}
if (panic_on_overflow)
panic("dma_alloc_coherent: IOMMU overflow by %lu bytes\n",size);
free_pages((unsigned long)memory, get_order(size));
return NULL;
}
EXPORT_SYMBOL(dma_alloc_coherent);
/*
* Unmap coherent memory.
* The caller must ensure that the device has finished accessing the mapping.
*/
void dma_free_coherent(struct device *dev, size_t size,
void *vaddr, dma_addr_t bus)
{
WARN_ON(irqs_disabled()); /* for portability */
if (dma_ops->unmap_single)
dma_ops->unmap_single(dev, bus, size, 0);
free_pages((unsigned long)vaddr, get_order(size));
}
EXPORT_SYMBOL(dma_free_coherent);
/*
* See <Documentation/x86_64/boot-options.txt> for the iommu kernel parameter
* documentation.
*/
static __init int iommu_setup(char *p)
{
iommu_merge = 1;
if (!p)
return -EINVAL;
while (*p) {
if (!strncmp(p, "off", 3))
no_iommu = 1;
/* gart_parse_options has more force support */
if (!strncmp(p, "force", 5))
force_iommu = 1;
if (!strncmp(p, "noforce", 7)) {
iommu_merge = 0;
force_iommu = 0;
}
if (!strncmp(p, "biomerge", 8)) {
iommu_bio_merge = 4096;
iommu_merge = 1;
force_iommu = 1;
}
if (!strncmp(p, "panic", 5))
panic_on_overflow = 1;
if (!strncmp(p, "nopanic", 7))
panic_on_overflow = 0;
if (!strncmp(p, "merge", 5)) {
iommu_merge = 1;
force_iommu = 1;
}
if (!strncmp(p, "nomerge", 7))
iommu_merge = 0;
if (!strncmp(p, "forcesac", 8))
iommu_sac_force = 1;
if (!strncmp(p, "allowdac", 8))
forbid_dac = 0;
if (!strncmp(p, "nodac", 5))
forbid_dac = -1;
#ifdef CONFIG_SWIOTLB
if (!strncmp(p, "soft", 4))
swiotlb = 1;
#endif
#ifdef CONFIG_GART_IOMMU
gart_parse_options(p);
#endif
#ifdef CONFIG_CALGARY_IOMMU
if (!strncmp(p, "calgary", 7))
use_calgary = 1;
#endif /* CONFIG_CALGARY_IOMMU */
p += strcspn(p, ",");
if (*p == ',')
++p;
}
return 0;
}
early_param("iommu", iommu_setup);
|
