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
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* AMD Passthrough DMA device driver
* -- Based on the CCP driver
*
* Copyright (C) 2016,2021 Advanced Micro Devices, Inc.
*
* Author: Sanjay R Mehta <sanju.mehta@amd.com>
* Author: Gary R Hook <gary.hook@amd.com>
*/
#include "ptdma.h"
#include "../dmaengine.h"
#include "../virt-dma.h"
static inline struct pt_dma_chan *to_pt_chan(struct dma_chan *dma_chan)
{
return container_of(dma_chan, struct pt_dma_chan, vc.chan);
}
static inline struct pt_dma_desc *to_pt_desc(struct virt_dma_desc *vd)
{
return container_of(vd, struct pt_dma_desc, vd);
}
static void pt_free_chan_resources(struct dma_chan *dma_chan)
{
struct pt_dma_chan *chan = to_pt_chan(dma_chan);
vchan_free_chan_resources(&chan->vc);
}
static void pt_synchronize(struct dma_chan *dma_chan)
{
struct pt_dma_chan *chan = to_pt_chan(dma_chan);
vchan_synchronize(&chan->vc);
}
static void pt_do_cleanup(struct virt_dma_desc *vd)
{
struct pt_dma_desc *desc = to_pt_desc(vd);
struct pt_device *pt = desc->pt;
kmem_cache_free(pt->dma_desc_cache, desc);
}
static int pt_dma_start_desc(struct pt_dma_desc *desc)
{
struct pt_passthru_engine *pt_engine;
struct pt_device *pt;
struct pt_cmd *pt_cmd;
struct pt_cmd_queue *cmd_q;
desc->issued_to_hw = 1;
pt_cmd = &desc->pt_cmd;
pt = pt_cmd->pt;
cmd_q = &pt->cmd_q;
pt_engine = &pt_cmd->passthru;
pt->tdata.cmd = pt_cmd;
/* Execute the command */
pt_cmd->ret = pt_core_perform_passthru(cmd_q, pt_engine);
return 0;
}
static struct pt_dma_desc *pt_next_dma_desc(struct pt_dma_chan *chan)
{
/* Get the next DMA descriptor on the active list */
struct virt_dma_desc *vd = vchan_next_desc(&chan->vc);
return vd ? to_pt_desc(vd) : NULL;
}
static struct pt_dma_desc *pt_handle_active_desc(struct pt_dma_chan *chan,
struct pt_dma_desc *desc)
{
struct dma_async_tx_descriptor *tx_desc;
struct virt_dma_desc *vd;
unsigned long flags;
/* Loop over descriptors until one is found with commands */
do {
if (desc) {
if (!desc->issued_to_hw) {
/* No errors, keep going */
if (desc->status != DMA_ERROR)
return desc;
}
tx_desc = &desc->vd.tx;
vd = &desc->vd;
} else {
tx_desc = NULL;
}
spin_lock_irqsave(&chan->vc.lock, flags);
if (desc) {
if (desc->status != DMA_ERROR)
desc->status = DMA_COMPLETE;
dma_cookie_complete(tx_desc);
dma_descriptor_unmap(tx_desc);
list_del(&desc->vd.node);
}
desc = pt_next_dma_desc(chan);
spin_unlock_irqrestore(&chan->vc.lock, flags);
if (tx_desc) {
dmaengine_desc_get_callback_invoke(tx_desc, NULL);
dma_run_dependencies(tx_desc);
vchan_vdesc_fini(vd);
}
} while (desc);
return NULL;
}
static void pt_cmd_callback(void *data, int err)
{
struct pt_dma_desc *desc = data;
struct dma_chan *dma_chan;
struct pt_dma_chan *chan;
int ret;
if (err == -EINPROGRESS)
return;
dma_chan = desc->vd.tx.chan;
chan = to_pt_chan(dma_chan);
if (err)
desc->status = DMA_ERROR;
while (true) {
/* Check for DMA descriptor completion */
desc = pt_handle_active_desc(chan, desc);
/* Don't submit cmd if no descriptor or DMA is paused */
if (!desc)
break;
ret = pt_dma_start_desc(desc);
if (!ret)
break;
desc->status = DMA_ERROR;
}
}
static struct pt_dma_desc *pt_alloc_dma_desc(struct pt_dma_chan *chan,
unsigned long flags)
{
struct pt_dma_desc *desc;
desc = kmem_cache_zalloc(chan->pt->dma_desc_cache, GFP_NOWAIT);
if (!desc)
return NULL;
vchan_tx_prep(&chan->vc, &desc->vd, flags);
desc->pt = chan->pt;
desc->issued_to_hw = 0;
desc->status = DMA_IN_PROGRESS;
return desc;
}
static struct pt_dma_desc *pt_create_desc(struct dma_chan *dma_chan,
dma_addr_t dst,
dma_addr_t src,
unsigned int len,
unsigned long flags)
{
struct pt_dma_chan *chan = to_pt_chan(dma_chan);
struct pt_passthru_engine *pt_engine;
struct pt_dma_desc *desc;
struct pt_cmd *pt_cmd;
desc = pt_alloc_dma_desc(chan, flags);
if (!desc)
return NULL;
pt_cmd = &desc->pt_cmd;
pt_cmd->pt = chan->pt;
pt_engine = &pt_cmd->passthru;
pt_cmd->engine = PT_ENGINE_PASSTHRU;
pt_engine->src_dma = src;
pt_engine->dst_dma = dst;
pt_engine->src_len = len;
pt_cmd->pt_cmd_callback = pt_cmd_callback;
pt_cmd->data = desc;
desc->len = len;
return desc;
}
static struct dma_async_tx_descriptor *
pt_prep_dma_memcpy(struct dma_chan *dma_chan, dma_addr_t dst,
dma_addr_t src, size_t len, unsigned long flags)
{
struct pt_dma_desc *desc;
desc = pt_create_desc(dma_chan, dst, src, len, flags);
if (!desc)
return NULL;
return &desc->vd.tx;
}
static struct dma_async_tx_descriptor *
pt_prep_dma_interrupt(struct dma_chan *dma_chan, unsigned long flags)
{
struct pt_dma_chan *chan = to_pt_chan(dma_chan);
struct pt_dma_desc *desc;
desc = pt_alloc_dma_desc(chan, flags);
if (!desc)
return NULL;
return &desc->vd.tx;
}
static void pt_issue_pending(struct dma_chan *dma_chan)
{
struct pt_dma_chan *chan = to_pt_chan(dma_chan);
struct pt_dma_desc *desc;
unsigned long flags;
bool engine_is_idle = true;
spin_lock_irqsave(&chan->vc.lock, flags);
desc = pt_next_dma_desc(chan);
if (desc)
engine_is_idle = false;
vchan_issue_pending(&chan->vc);
desc = pt_next_dma_desc(chan);
spin_unlock_irqrestore(&chan->vc.lock, flags);
/* If there was nothing active, start processing */
if (engine_is_idle)
pt_cmd_callback(desc, 0);
}
static int pt_pause(struct dma_chan *dma_chan)
{
struct pt_dma_chan *chan = to_pt_chan(dma_chan);
unsigned long flags;
spin_lock_irqsave(&chan->vc.lock, flags);
pt_stop_queue(&chan->pt->cmd_q);
spin_unlock_irqrestore(&chan->vc.lock, flags);
return 0;
}
static int pt_resume(struct dma_chan *dma_chan)
{
struct pt_dma_chan *chan = to_pt_chan(dma_chan);
struct pt_dma_desc *desc = NULL;
unsigned long flags;
spin_lock_irqsave(&chan->vc.lock, flags);
pt_start_queue(&chan->pt->cmd_q);
desc = pt_next_dma_desc(chan);
spin_unlock_irqrestore(&chan->vc.lock, flags);
/* If there was something active, re-start */
if (desc)
pt_cmd_callback(desc, 0);
return 0;
}
static int pt_terminate_all(struct dma_chan *dma_chan)
{
struct pt_dma_chan *chan = to_pt_chan(dma_chan);
unsigned long flags;
LIST_HEAD(head);
spin_lock_irqsave(&chan->vc.lock, flags);
vchan_get_all_descriptors(&chan->vc, &head);
spin_unlock_irqrestore(&chan->vc.lock, flags);
vchan_dma_desc_free_list(&chan->vc, &head);
vchan_free_chan_resources(&chan->vc);
return 0;
}
int pt_dmaengine_register(struct pt_device *pt)
{
struct pt_dma_chan *chan;
struct dma_device *dma_dev = &pt->dma_dev;
char *cmd_cache_name;
char *desc_cache_name;
int ret;
pt->pt_dma_chan = devm_kzalloc(pt->dev, sizeof(*pt->pt_dma_chan),
GFP_KERNEL);
if (!pt->pt_dma_chan)
return -ENOMEM;
cmd_cache_name = devm_kasprintf(pt->dev, GFP_KERNEL,
"%s-dmaengine-cmd-cache",
dev_name(pt->dev));
if (!cmd_cache_name)
return -ENOMEM;
desc_cache_name = devm_kasprintf(pt->dev, GFP_KERNEL,
"%s-dmaengine-desc-cache",
dev_name(pt->dev));
if (!desc_cache_name) {
ret = -ENOMEM;
goto err_cache;
}
pt->dma_desc_cache = kmem_cache_create(desc_cache_name,
sizeof(struct pt_dma_desc), 0,
SLAB_HWCACHE_ALIGN, NULL);
if (!pt->dma_desc_cache) {
ret = -ENOMEM;
goto err_cache;
}
dma_dev->dev = pt->dev;
dma_dev->src_addr_widths = DMA_SLAVE_BUSWIDTH_64_BYTES;
dma_dev->dst_addr_widths = DMA_SLAVE_BUSWIDTH_64_BYTES;
dma_dev->directions = DMA_MEM_TO_MEM;
dma_dev->residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask);
dma_cap_set(DMA_INTERRUPT, dma_dev->cap_mask);
/*
* PTDMA is intended to be used with the AMD NTB devices, hence
* marking it as DMA_PRIVATE.
*/
dma_cap_set(DMA_PRIVATE, dma_dev->cap_mask);
INIT_LIST_HEAD(&dma_dev->channels);
chan = pt->pt_dma_chan;
chan->pt = pt;
/* Set base and prep routines */
dma_dev->device_free_chan_resources = pt_free_chan_resources;
dma_dev->device_prep_dma_memcpy = pt_prep_dma_memcpy;
dma_dev->device_prep_dma_interrupt = pt_prep_dma_interrupt;
dma_dev->device_issue_pending = pt_issue_pending;
dma_dev->device_tx_status = dma_cookie_status;
dma_dev->device_pause = pt_pause;
dma_dev->device_resume = pt_resume;
dma_dev->device_terminate_all = pt_terminate_all;
dma_dev->device_synchronize = pt_synchronize;
chan->vc.desc_free = pt_do_cleanup;
vchan_init(&chan->vc, dma_dev);
dma_set_mask_and_coherent(pt->dev, DMA_BIT_MASK(64));
ret = dma_async_device_register(dma_dev);
if (ret)
goto err_reg;
return 0;
err_reg:
kmem_cache_destroy(pt->dma_desc_cache);
err_cache:
kmem_cache_destroy(pt->dma_cmd_cache);
return ret;
}
void pt_dmaengine_unregister(struct pt_device *pt)
{
struct dma_device *dma_dev = &pt->dma_dev;
dma_async_device_unregister(dma_dev);
kmem_cache_destroy(pt->dma_desc_cache);
kmem_cache_destroy(pt->dma_cmd_cache);
}
|