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
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
|
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/device.h>
#include <linux/sched/task.h>
#include <linux/intel-svm.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/cdev.h>
#include <linux/fs.h>
#include <linux/poll.h>
#include <uapi/linux/idxd.h>
#include "registers.h"
#include "idxd.h"
struct idxd_cdev_context {
const char *name;
dev_t devt;
struct ida minor_ida;
};
/*
* ictx is an array based off of accelerator types. enum idxd_type
* is used as index
*/
static struct idxd_cdev_context ictx[IDXD_TYPE_MAX] = {
{ .name = "dsa" },
};
struct idxd_user_context {
struct idxd_wq *wq;
struct task_struct *task;
unsigned int flags;
};
enum idxd_cdev_cleanup {
CDEV_NORMAL = 0,
CDEV_FAILED,
};
static void idxd_cdev_dev_release(struct device *dev)
{
dev_dbg(dev, "releasing cdev device\n");
kfree(dev);
}
static struct device_type idxd_cdev_device_type = {
.name = "idxd_cdev",
.release = idxd_cdev_dev_release,
};
static inline struct idxd_cdev *inode_idxd_cdev(struct inode *inode)
{
struct cdev *cdev = inode->i_cdev;
return container_of(cdev, struct idxd_cdev, cdev);
}
static inline struct idxd_wq *idxd_cdev_wq(struct idxd_cdev *idxd_cdev)
{
return container_of(idxd_cdev, struct idxd_wq, idxd_cdev);
}
static inline struct idxd_wq *inode_wq(struct inode *inode)
{
return idxd_cdev_wq(inode_idxd_cdev(inode));
}
static int idxd_cdev_open(struct inode *inode, struct file *filp)
{
struct idxd_user_context *ctx;
struct idxd_device *idxd;
struct idxd_wq *wq;
struct device *dev;
struct idxd_cdev *idxd_cdev;
wq = inode_wq(inode);
idxd = wq->idxd;
dev = &idxd->pdev->dev;
idxd_cdev = &wq->idxd_cdev;
dev_dbg(dev, "%s called\n", __func__);
if (idxd_wq_refcount(wq) > 1 && wq_dedicated(wq))
return -EBUSY;
ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return -ENOMEM;
ctx->wq = wq;
filp->private_data = ctx;
idxd_wq_get(wq);
return 0;
}
static int idxd_cdev_release(struct inode *node, struct file *filep)
{
struct idxd_user_context *ctx = filep->private_data;
struct idxd_wq *wq = ctx->wq;
struct idxd_device *idxd = wq->idxd;
struct device *dev = &idxd->pdev->dev;
dev_dbg(dev, "%s called\n", __func__);
filep->private_data = NULL;
kfree(ctx);
idxd_wq_put(wq);
return 0;
}
static int check_vma(struct idxd_wq *wq, struct vm_area_struct *vma,
const char *func)
{
struct device *dev = &wq->idxd->pdev->dev;
if ((vma->vm_end - vma->vm_start) > PAGE_SIZE) {
dev_info_ratelimited(dev,
"%s: %s: mapping too large: %lu\n",
current->comm, func,
vma->vm_end - vma->vm_start);
return -EINVAL;
}
return 0;
}
static int idxd_cdev_mmap(struct file *filp, struct vm_area_struct *vma)
{
struct idxd_user_context *ctx = filp->private_data;
struct idxd_wq *wq = ctx->wq;
struct idxd_device *idxd = wq->idxd;
struct pci_dev *pdev = idxd->pdev;
phys_addr_t base = pci_resource_start(pdev, IDXD_WQ_BAR);
unsigned long pfn;
int rc;
dev_dbg(&pdev->dev, "%s called\n", __func__);
rc = check_vma(wq, vma, __func__);
vma->vm_flags |= VM_DONTCOPY;
pfn = (base + idxd_get_wq_portal_full_offset(wq->id,
IDXD_PORTAL_LIMITED)) >> PAGE_SHIFT;
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
vma->vm_private_data = ctx;
return io_remap_pfn_range(vma, vma->vm_start, pfn, PAGE_SIZE,
vma->vm_page_prot);
}
static __poll_t idxd_cdev_poll(struct file *filp,
struct poll_table_struct *wait)
{
struct idxd_user_context *ctx = filp->private_data;
struct idxd_wq *wq = ctx->wq;
struct idxd_device *idxd = wq->idxd;
struct idxd_cdev *idxd_cdev = &wq->idxd_cdev;
unsigned long flags;
__poll_t out = 0;
poll_wait(filp, &idxd_cdev->err_queue, wait);
spin_lock_irqsave(&idxd->dev_lock, flags);
if (idxd->sw_err.valid)
out = EPOLLIN | EPOLLRDNORM;
spin_unlock_irqrestore(&idxd->dev_lock, flags);
return out;
}
static const struct file_operations idxd_cdev_fops = {
.owner = THIS_MODULE,
.open = idxd_cdev_open,
.release = idxd_cdev_release,
.mmap = idxd_cdev_mmap,
.poll = idxd_cdev_poll,
};
int idxd_cdev_get_major(struct idxd_device *idxd)
{
return MAJOR(ictx[idxd->type].devt);
}
static int idxd_wq_cdev_dev_setup(struct idxd_wq *wq)
{
struct idxd_device *idxd = wq->idxd;
struct idxd_cdev *idxd_cdev = &wq->idxd_cdev;
struct idxd_cdev_context *cdev_ctx;
struct device *dev;
int minor, rc;
idxd_cdev->dev = kzalloc(sizeof(*idxd_cdev->dev), GFP_KERNEL);
if (!idxd_cdev->dev)
return -ENOMEM;
dev = idxd_cdev->dev;
dev->parent = &idxd->pdev->dev;
dev_set_name(dev, "%s/wq%u.%u", idxd_get_dev_name(idxd),
idxd->id, wq->id);
dev->bus = idxd_get_bus_type(idxd);
cdev_ctx = &ictx[wq->idxd->type];
minor = ida_simple_get(&cdev_ctx->minor_ida, 0, MINORMASK, GFP_KERNEL);
if (minor < 0) {
rc = minor;
goto ida_err;
}
dev->devt = MKDEV(MAJOR(cdev_ctx->devt), minor);
dev->type = &idxd_cdev_device_type;
rc = device_register(dev);
if (rc < 0) {
dev_err(&idxd->pdev->dev, "device register failed\n");
put_device(dev);
goto dev_reg_err;
}
idxd_cdev->minor = minor;
return 0;
dev_reg_err:
ida_simple_remove(&cdev_ctx->minor_ida, MINOR(dev->devt));
ida_err:
kfree(dev);
idxd_cdev->dev = NULL;
return rc;
}
static void idxd_wq_cdev_cleanup(struct idxd_wq *wq,
enum idxd_cdev_cleanup cdev_state)
{
struct idxd_cdev *idxd_cdev = &wq->idxd_cdev;
struct idxd_cdev_context *cdev_ctx;
cdev_ctx = &ictx[wq->idxd->type];
if (cdev_state == CDEV_NORMAL)
cdev_del(&idxd_cdev->cdev);
device_unregister(idxd_cdev->dev);
/*
* The device_type->release() will be called on the device and free
* the allocated struct device. We can just forget it.
*/
ida_simple_remove(&cdev_ctx->minor_ida, idxd_cdev->minor);
idxd_cdev->dev = NULL;
idxd_cdev->minor = -1;
}
int idxd_wq_add_cdev(struct idxd_wq *wq)
{
struct idxd_cdev *idxd_cdev = &wq->idxd_cdev;
struct cdev *cdev = &idxd_cdev->cdev;
struct device *dev;
int rc;
rc = idxd_wq_cdev_dev_setup(wq);
if (rc < 0)
return rc;
dev = idxd_cdev->dev;
cdev_init(cdev, &idxd_cdev_fops);
cdev_set_parent(cdev, &dev->kobj);
rc = cdev_add(cdev, dev->devt, 1);
if (rc) {
dev_dbg(&wq->idxd->pdev->dev, "cdev_add failed: %d\n", rc);
idxd_wq_cdev_cleanup(wq, CDEV_FAILED);
return rc;
}
init_waitqueue_head(&idxd_cdev->err_queue);
return 0;
}
void idxd_wq_del_cdev(struct idxd_wq *wq)
{
idxd_wq_cdev_cleanup(wq, CDEV_NORMAL);
}
int idxd_cdev_register(void)
{
int rc, i;
for (i = 0; i < IDXD_TYPE_MAX; i++) {
ida_init(&ictx[i].minor_ida);
rc = alloc_chrdev_region(&ictx[i].devt, 0, MINORMASK,
ictx[i].name);
if (rc)
return rc;
}
return 0;
}
void idxd_cdev_remove(void)
{
int i;
for (i = 0; i < IDXD_TYPE_MAX; i++) {
unregister_chrdev_region(ictx[i].devt, MINORMASK);
ida_destroy(&ictx[i].minor_ida);
}
}
|