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
|
/*
* Copyright (c) 2014 Mellanox Technologies. All rights reserved.
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
* General Public License (GPL) Version 2, available from the file
* COPYING in the main directory of this source tree, or the
* OpenIB.org BSD license below:
*
* Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met:
*
* - Redistributions of source code must retain the above
* copyright notice, this list of conditions and the following
* disclaimer.
*
* - Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following
* disclaimer in the documentation and/or other materials
* provided with the distribution.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#ifndef IB_UMEM_ODP_H
#define IB_UMEM_ODP_H
#include <rdma/ib_umem.h>
#include <rdma/ib_verbs.h>
#include <linux/interval_tree.h>
struct ib_umem_odp {
struct ib_umem umem;
struct ib_ucontext_per_mm *per_mm;
/*
* An array of the pages included in the on-demand paging umem.
* Indices of pages that are currently not mapped into the device will
* contain NULL.
*/
struct page **page_list;
/*
* An array of the same size as page_list, with DMA addresses mapped
* for pages the pages in page_list. The lower two bits designate
* access permissions. See ODP_READ_ALLOWED_BIT and
* ODP_WRITE_ALLOWED_BIT.
*/
dma_addr_t *dma_list;
/*
* The umem_mutex protects the page_list and dma_list fields of an ODP
* umem, allowing only a single thread to map/unmap pages. The mutex
* also protects access to the mmu notifier counters.
*/
struct mutex umem_mutex;
void *private; /* for the HW driver to use. */
int notifiers_seq;
int notifiers_count;
int npages;
/* Tree tracking */
struct interval_tree_node interval_tree;
/*
* An implicit odp umem cannot be DMA mapped, has 0 length, and serves
* only as an anchor for the driver to hold onto the per_mm. FIXME:
* This should be removed and drivers should work with the per_mm
* directly.
*/
bool is_implicit_odp;
struct completion notifier_completion;
int dying;
unsigned int page_shift;
struct work_struct work;
};
static inline struct ib_umem_odp *to_ib_umem_odp(struct ib_umem *umem)
{
return container_of(umem, struct ib_umem_odp, umem);
}
/* Returns the first page of an ODP umem. */
static inline unsigned long ib_umem_start(struct ib_umem_odp *umem_odp)
{
return umem_odp->interval_tree.start;
}
/* Returns the address of the page after the last one of an ODP umem. */
static inline unsigned long ib_umem_end(struct ib_umem_odp *umem_odp)
{
return umem_odp->interval_tree.last + 1;
}
static inline size_t ib_umem_odp_num_pages(struct ib_umem_odp *umem_odp)
{
return (ib_umem_end(umem_odp) - ib_umem_start(umem_odp)) >>
umem_odp->page_shift;
}
/*
* The lower 2 bits of the DMA address signal the R/W permissions for
* the entry. To upgrade the permissions, provide the appropriate
* bitmask to the map_dma_pages function.
*
* Be aware that upgrading a mapped address might result in change of
* the DMA address for the page.
*/
#define ODP_READ_ALLOWED_BIT (1<<0ULL)
#define ODP_WRITE_ALLOWED_BIT (1<<1ULL)
#define ODP_DMA_ADDR_MASK (~(ODP_READ_ALLOWED_BIT | ODP_WRITE_ALLOWED_BIT))
#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
struct ib_ucontext_per_mm {
struct ib_ucontext *context;
struct mm_struct *mm;
struct pid *tgid;
bool active;
struct rb_root_cached umem_tree;
/* Protects umem_tree */
struct rw_semaphore umem_rwsem;
struct mmu_notifier mn;
unsigned int odp_mrs_count;
struct list_head ucontext_list;
struct rcu_head rcu;
};
struct ib_umem_odp *ib_umem_odp_get(struct ib_udata *udata, unsigned long addr,
size_t size, int access);
struct ib_umem_odp *ib_umem_odp_alloc_implicit(struct ib_udata *udata,
int access);
struct ib_umem_odp *ib_umem_odp_alloc_child(struct ib_umem_odp *root_umem,
unsigned long addr, size_t size);
void ib_umem_odp_release(struct ib_umem_odp *umem_odp);
int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 start_offset,
u64 bcnt, u64 access_mask,
unsigned long current_seq);
void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 start_offset,
u64 bound);
typedef int (*umem_call_back)(struct ib_umem_odp *item, u64 start, u64 end,
void *cookie);
/*
* Call the callback on each ib_umem in the range. Returns the logical or of
* the return values of the functions called.
*/
int rbt_ib_umem_for_each_in_range(struct rb_root_cached *root,
u64 start, u64 end,
umem_call_back cb,
bool blockable, void *cookie);
/*
* Find first region intersecting with address range.
* Return NULL if not found
*/
static inline struct ib_umem_odp *
rbt_ib_umem_lookup(struct rb_root_cached *root, u64 addr, u64 length)
{
struct interval_tree_node *node;
node = interval_tree_iter_first(root, addr, addr + length - 1);
if (!node)
return NULL;
return container_of(node, struct ib_umem_odp, interval_tree);
}
static inline int ib_umem_mmu_notifier_retry(struct ib_umem_odp *umem_odp,
unsigned long mmu_seq)
{
/*
* This code is strongly based on the KVM code from
* mmu_notifier_retry. Should be called with
* the relevant locks taken (umem_odp->umem_mutex
* and the ucontext umem_mutex semaphore locked for read).
*/
if (unlikely(umem_odp->notifiers_count))
return 1;
if (umem_odp->notifiers_seq != mmu_seq)
return 1;
return 0;
}
#else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
static inline struct ib_umem_odp *ib_umem_odp_get(struct ib_udata *udata,
unsigned long addr,
size_t size, int access)
{
return ERR_PTR(-EINVAL);
}
static inline void ib_umem_odp_release(struct ib_umem_odp *umem_odp) {}
#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
#endif /* IB_UMEM_ODP_H */
|
