forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathntb_transport.c
1933 lines (1562 loc) · 48.1 KB
/
ntb_transport.c
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
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
*
* GPL LICENSE SUMMARY
*
* Copyright(c) 2012 Intel Corporation. All rights reserved.
* Copyright (C) 2015 EMC Corporation. All Rights Reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* published by the Free Software Foundation.
*
* BSD LICENSE
*
* Copyright(c) 2012 Intel Corporation. All rights reserved.
* Copyright (C) 2015 EMC Corporation. All Rights Reserved.
*
* 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 copy
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
* * Neither the name of Intel Corporation nor the names of its
* contributors may be used to endorse or promote products derived
* from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
* PCIe NTB Transport Linux driver
*
* Contact Information:
* Jon Mason <[email protected]>
*/
#include <linux/debugfs.h>
#include <linux/delay.h>
#include <linux/dmaengine.h>
#include <linux/dma-mapping.h>
#include <linux/errno.h>
#include <linux/export.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/slab.h>
#include <linux/types.h>
#include "linux/ntb.h"
#include "linux/ntb_transport.h"
#define NTB_TRANSPORT_VERSION 4
#define NTB_TRANSPORT_VER "4"
#define NTB_TRANSPORT_NAME "ntb_transport"
#define NTB_TRANSPORT_DESC "Software Queue-Pair Transport over NTB"
MODULE_DESCRIPTION(NTB_TRANSPORT_DESC);
MODULE_VERSION(NTB_TRANSPORT_VER);
MODULE_LICENSE("Dual BSD/GPL");
MODULE_AUTHOR("Intel Corporation");
static unsigned long max_mw_size;
module_param(max_mw_size, ulong, 0644);
MODULE_PARM_DESC(max_mw_size, "Limit size of large memory windows");
static unsigned int transport_mtu = 0x401E;
module_param(transport_mtu, uint, 0644);
MODULE_PARM_DESC(transport_mtu, "Maximum size of NTB transport packets");
static unsigned char max_num_clients;
module_param(max_num_clients, byte, 0644);
MODULE_PARM_DESC(max_num_clients, "Maximum number of NTB transport clients");
static unsigned int copy_bytes = 1024;
module_param(copy_bytes, uint, 0644);
MODULE_PARM_DESC(copy_bytes, "Threshold under which NTB will use the CPU to copy instead of DMA");
static struct dentry *nt_debugfs_dir;
struct ntb_queue_entry {
/* ntb_queue list reference */
struct list_head entry;
/* pointers to data to be transferred */
void *cb_data;
void *buf;
unsigned int len;
unsigned int flags;
struct ntb_transport_qp *qp;
union {
struct ntb_payload_header __iomem *tx_hdr;
struct ntb_payload_header *rx_hdr;
};
unsigned int index;
};
struct ntb_rx_info {
unsigned int entry;
};
struct ntb_transport_qp {
struct ntb_transport_ctx *transport;
struct ntb_dev *ndev;
void *cb_data;
struct dma_chan *dma_chan;
bool client_ready;
bool link_is_up;
u8 qp_num; /* Only 64 QP's are allowed. 0-63 */
u64 qp_bit;
struct ntb_rx_info __iomem *rx_info;
struct ntb_rx_info *remote_rx_info;
void (*tx_handler)(struct ntb_transport_qp *qp, void *qp_data,
void *data, int len);
struct list_head tx_free_q;
spinlock_t ntb_tx_free_q_lock;
void __iomem *tx_mw;
dma_addr_t tx_mw_phys;
unsigned int tx_index;
unsigned int tx_max_entry;
unsigned int tx_max_frame;
void (*rx_handler)(struct ntb_transport_qp *qp, void *qp_data,
void *data, int len);
struct list_head rx_pend_q;
struct list_head rx_free_q;
spinlock_t ntb_rx_pend_q_lock;
spinlock_t ntb_rx_free_q_lock;
void *rx_buff;
unsigned int rx_index;
unsigned int rx_max_entry;
unsigned int rx_max_frame;
dma_cookie_t last_cookie;
struct tasklet_struct rxc_db_work;
void (*event_handler)(void *data, int status);
struct delayed_work link_work;
struct work_struct link_cleanup;
struct dentry *debugfs_dir;
struct dentry *debugfs_stats;
/* Stats */
u64 rx_bytes;
u64 rx_pkts;
u64 rx_ring_empty;
u64 rx_err_no_buf;
u64 rx_err_oflow;
u64 rx_err_ver;
u64 rx_memcpy;
u64 rx_async;
u64 tx_bytes;
u64 tx_pkts;
u64 tx_ring_full;
u64 tx_err_no_buf;
u64 tx_memcpy;
u64 tx_async;
};
struct ntb_transport_mw {
phys_addr_t phys_addr;
resource_size_t phys_size;
resource_size_t xlat_align;
resource_size_t xlat_align_size;
void __iomem *vbase;
size_t xlat_size;
size_t buff_size;
void *virt_addr;
dma_addr_t dma_addr;
};
struct ntb_transport_client_dev {
struct list_head entry;
struct ntb_transport_ctx *nt;
struct device dev;
};
struct ntb_transport_ctx {
struct list_head entry;
struct list_head client_devs;
struct ntb_dev *ndev;
struct ntb_transport_mw *mw_vec;
struct ntb_transport_qp *qp_vec;
unsigned int mw_count;
unsigned int qp_count;
u64 qp_bitmap;
u64 qp_bitmap_free;
bool link_is_up;
struct delayed_work link_work;
struct work_struct link_cleanup;
};
enum {
DESC_DONE_FLAG = BIT(0),
LINK_DOWN_FLAG = BIT(1),
};
struct ntb_payload_header {
unsigned int ver;
unsigned int len;
unsigned int flags;
};
enum {
VERSION = 0,
QP_LINKS,
NUM_QPS,
NUM_MWS,
MW0_SZ_HIGH,
MW0_SZ_LOW,
MW1_SZ_HIGH,
MW1_SZ_LOW,
MAX_SPAD,
};
#define dev_client_dev(__dev) \
container_of((__dev), struct ntb_transport_client_dev, dev)
#define drv_client(__drv) \
container_of((__drv), struct ntb_transport_client, driver)
#define QP_TO_MW(nt, qp) ((qp) % nt->mw_count)
#define NTB_QP_DEF_NUM_ENTRIES 100
#define NTB_LINK_DOWN_TIMEOUT 10
static void ntb_transport_rxc_db(unsigned long data);
static const struct ntb_ctx_ops ntb_transport_ops;
static struct ntb_client ntb_transport_client;
static int ntb_transport_bus_match(struct device *dev,
struct device_driver *drv)
{
return !strncmp(dev_name(dev), drv->name, strlen(drv->name));
}
static int ntb_transport_bus_probe(struct device *dev)
{
const struct ntb_transport_client *client;
int rc = -EINVAL;
get_device(dev);
client = drv_client(dev->driver);
rc = client->probe(dev);
if (rc)
put_device(dev);
return rc;
}
static int ntb_transport_bus_remove(struct device *dev)
{
const struct ntb_transport_client *client;
client = drv_client(dev->driver);
client->remove(dev);
put_device(dev);
return 0;
}
static struct bus_type ntb_transport_bus = {
.name = "ntb_transport",
.match = ntb_transport_bus_match,
.probe = ntb_transport_bus_probe,
.remove = ntb_transport_bus_remove,
};
static LIST_HEAD(ntb_transport_list);
static int ntb_bus_init(struct ntb_transport_ctx *nt)
{
list_add(&nt->entry, &ntb_transport_list);
return 0;
}
static void ntb_bus_remove(struct ntb_transport_ctx *nt)
{
struct ntb_transport_client_dev *client_dev, *cd;
list_for_each_entry_safe(client_dev, cd, &nt->client_devs, entry) {
dev_err(client_dev->dev.parent, "%s still attached to bus, removing\n",
dev_name(&client_dev->dev));
list_del(&client_dev->entry);
device_unregister(&client_dev->dev);
}
list_del(&nt->entry);
}
static void ntb_transport_client_release(struct device *dev)
{
struct ntb_transport_client_dev *client_dev;
client_dev = dev_client_dev(dev);
kfree(client_dev);
}
/**
* ntb_transport_unregister_client_dev - Unregister NTB client device
* @device_name: Name of NTB client device
*
* Unregister an NTB client device with the NTB transport layer
*/
void ntb_transport_unregister_client_dev(char *device_name)
{
struct ntb_transport_client_dev *client, *cd;
struct ntb_transport_ctx *nt;
list_for_each_entry(nt, &ntb_transport_list, entry)
list_for_each_entry_safe(client, cd, &nt->client_devs, entry)
if (!strncmp(dev_name(&client->dev), device_name,
strlen(device_name))) {
list_del(&client->entry);
device_unregister(&client->dev);
}
}
EXPORT_SYMBOL_GPL(ntb_transport_unregister_client_dev);
/**
* ntb_transport_register_client_dev - Register NTB client device
* @device_name: Name of NTB client device
*
* Register an NTB client device with the NTB transport layer
*/
int ntb_transport_register_client_dev(char *device_name)
{
struct ntb_transport_client_dev *client_dev;
struct ntb_transport_ctx *nt;
int rc, i = 0;
if (list_empty(&ntb_transport_list))
return -ENODEV;
list_for_each_entry(nt, &ntb_transport_list, entry) {
struct device *dev;
client_dev = kzalloc(sizeof(*client_dev),
GFP_KERNEL);
if (!client_dev) {
rc = -ENOMEM;
goto err;
}
dev = &client_dev->dev;
/* setup and register client devices */
dev_set_name(dev, "%s%d", device_name, i);
dev->bus = &ntb_transport_bus;
dev->release = ntb_transport_client_release;
dev->parent = &nt->ndev->dev;
rc = device_register(dev);
if (rc) {
kfree(client_dev);
goto err;
}
list_add_tail(&client_dev->entry, &nt->client_devs);
i++;
}
return 0;
err:
ntb_transport_unregister_client_dev(device_name);
return rc;
}
EXPORT_SYMBOL_GPL(ntb_transport_register_client_dev);
/**
* ntb_transport_register_client - Register NTB client driver
* @drv: NTB client driver to be registered
*
* Register an NTB client driver with the NTB transport layer
*
* RETURNS: An appropriate -ERRNO error value on error, or zero for success.
*/
int ntb_transport_register_client(struct ntb_transport_client *drv)
{
drv->driver.bus = &ntb_transport_bus;
if (list_empty(&ntb_transport_list))
return -ENODEV;
return driver_register(&drv->driver);
}
EXPORT_SYMBOL_GPL(ntb_transport_register_client);
/**
* ntb_transport_unregister_client - Unregister NTB client driver
* @drv: NTB client driver to be unregistered
*
* Unregister an NTB client driver with the NTB transport layer
*
* RETURNS: An appropriate -ERRNO error value on error, or zero for success.
*/
void ntb_transport_unregister_client(struct ntb_transport_client *drv)
{
driver_unregister(&drv->driver);
}
EXPORT_SYMBOL_GPL(ntb_transport_unregister_client);
static ssize_t debugfs_read(struct file *filp, char __user *ubuf, size_t count,
loff_t *offp)
{
struct ntb_transport_qp *qp;
char *buf;
ssize_t ret, out_offset, out_count;
out_count = 1000;
buf = kmalloc(out_count, GFP_KERNEL);
if (!buf)
return -ENOMEM;
qp = filp->private_data;
out_offset = 0;
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"NTB QP stats\n");
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"rx_bytes - \t%llu\n", qp->rx_bytes);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"rx_pkts - \t%llu\n", qp->rx_pkts);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"rx_memcpy - \t%llu\n", qp->rx_memcpy);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"rx_async - \t%llu\n", qp->rx_async);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"rx_ring_empty - %llu\n", qp->rx_ring_empty);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"rx_err_no_buf - %llu\n", qp->rx_err_no_buf);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"rx_err_oflow - \t%llu\n", qp->rx_err_oflow);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"rx_err_ver - \t%llu\n", qp->rx_err_ver);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"rx_buff - \t%p\n", qp->rx_buff);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"rx_index - \t%u\n", qp->rx_index);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"rx_max_entry - \t%u\n", qp->rx_max_entry);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"tx_bytes - \t%llu\n", qp->tx_bytes);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"tx_pkts - \t%llu\n", qp->tx_pkts);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"tx_memcpy - \t%llu\n", qp->tx_memcpy);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"tx_async - \t%llu\n", qp->tx_async);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"tx_ring_full - \t%llu\n", qp->tx_ring_full);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"tx_err_no_buf - %llu\n", qp->tx_err_no_buf);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"tx_mw - \t%p\n", qp->tx_mw);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"tx_index - \t%u\n", qp->tx_index);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"tx_max_entry - \t%u\n", qp->tx_max_entry);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"\nQP Link %s\n",
qp->link_is_up ? "Up" : "Down");
if (out_offset > out_count)
out_offset = out_count;
ret = simple_read_from_buffer(ubuf, count, offp, buf, out_offset);
kfree(buf);
return ret;
}
static const struct file_operations ntb_qp_debugfs_stats = {
.owner = THIS_MODULE,
.open = simple_open,
.read = debugfs_read,
};
static void ntb_list_add(spinlock_t *lock, struct list_head *entry,
struct list_head *list)
{
unsigned long flags;
spin_lock_irqsave(lock, flags);
list_add_tail(entry, list);
spin_unlock_irqrestore(lock, flags);
}
static struct ntb_queue_entry *ntb_list_rm(spinlock_t *lock,
struct list_head *list)
{
struct ntb_queue_entry *entry;
unsigned long flags;
spin_lock_irqsave(lock, flags);
if (list_empty(list)) {
entry = NULL;
goto out;
}
entry = list_first_entry(list, struct ntb_queue_entry, entry);
list_del(&entry->entry);
out:
spin_unlock_irqrestore(lock, flags);
return entry;
}
static int ntb_transport_setup_qp_mw(struct ntb_transport_ctx *nt,
unsigned int qp_num)
{
struct ntb_transport_qp *qp = &nt->qp_vec[qp_num];
struct ntb_transport_mw *mw;
unsigned int rx_size, num_qps_mw;
unsigned int mw_num, mw_count, qp_count;
unsigned int i;
mw_count = nt->mw_count;
qp_count = nt->qp_count;
mw_num = QP_TO_MW(nt, qp_num);
mw = &nt->mw_vec[mw_num];
if (!mw->virt_addr)
return -ENOMEM;
if (qp_count % mw_count && mw_num + 1 < qp_count / mw_count)
num_qps_mw = qp_count / mw_count + 1;
else
num_qps_mw = qp_count / mw_count;
rx_size = (unsigned int)mw->xlat_size / num_qps_mw;
qp->rx_buff = mw->virt_addr + rx_size * qp_num / mw_count;
rx_size -= sizeof(struct ntb_rx_info);
qp->remote_rx_info = qp->rx_buff + rx_size;
/* Due to housekeeping, there must be atleast 2 buffs */
qp->rx_max_frame = min(transport_mtu, rx_size / 2);
qp->rx_max_entry = rx_size / qp->rx_max_frame;
qp->rx_index = 0;
qp->remote_rx_info->entry = qp->rx_max_entry - 1;
/* setup the hdr offsets with 0's */
for (i = 0; i < qp->rx_max_entry; i++) {
void *offset = (qp->rx_buff + qp->rx_max_frame * (i + 1) -
sizeof(struct ntb_payload_header));
memset(offset, 0, sizeof(struct ntb_payload_header));
}
qp->rx_pkts = 0;
qp->tx_pkts = 0;
qp->tx_index = 0;
return 0;
}
static void ntb_free_mw(struct ntb_transport_ctx *nt, int num_mw)
{
struct ntb_transport_mw *mw = &nt->mw_vec[num_mw];
struct pci_dev *pdev = nt->ndev->pdev;
if (!mw->virt_addr)
return;
ntb_mw_clear_trans(nt->ndev, num_mw);
dma_free_coherent(&pdev->dev, mw->buff_size,
mw->virt_addr, mw->dma_addr);
mw->xlat_size = 0;
mw->buff_size = 0;
mw->virt_addr = NULL;
}
static int ntb_set_mw(struct ntb_transport_ctx *nt, int num_mw,
unsigned int size)
{
struct ntb_transport_mw *mw = &nt->mw_vec[num_mw];
struct pci_dev *pdev = nt->ndev->pdev;
unsigned int xlat_size, buff_size;
int rc;
xlat_size = round_up(size, mw->xlat_align_size);
buff_size = round_up(size, mw->xlat_align);
/* No need to re-setup */
if (mw->xlat_size == xlat_size)
return 0;
if (mw->buff_size)
ntb_free_mw(nt, num_mw);
/* Alloc memory for receiving data. Must be aligned */
mw->xlat_size = xlat_size;
mw->buff_size = buff_size;
mw->virt_addr = dma_alloc_coherent(&pdev->dev, buff_size,
&mw->dma_addr, GFP_KERNEL);
if (!mw->virt_addr) {
mw->xlat_size = 0;
mw->buff_size = 0;
dev_err(&pdev->dev, "Unable to alloc MW buff of size %d\n",
buff_size);
return -ENOMEM;
}
/*
* we must ensure that the memory address allocated is BAR size
* aligned in order for the XLAT register to take the value. This
* is a requirement of the hardware. It is recommended to setup CMA
* for BAR sizes equal or greater than 4MB.
*/
if (!IS_ALIGNED(mw->dma_addr, mw->xlat_align)) {
dev_err(&pdev->dev, "DMA memory %pad is not aligned\n",
&mw->dma_addr);
ntb_free_mw(nt, num_mw);
return -ENOMEM;
}
/* Notify HW the memory location of the receive buffer */
rc = ntb_mw_set_trans(nt->ndev, num_mw, mw->dma_addr, mw->xlat_size);
if (rc) {
dev_err(&pdev->dev, "Unable to set mw%d translation", num_mw);
ntb_free_mw(nt, num_mw);
return -EIO;
}
return 0;
}
static void ntb_qp_link_cleanup(struct ntb_transport_qp *qp)
{
struct ntb_transport_ctx *nt = qp->transport;
struct pci_dev *pdev = nt->ndev->pdev;
if (qp->link_is_up) {
cancel_delayed_work_sync(&qp->link_work);
return;
}
dev_info(&pdev->dev, "qp %d: Link Cleanup\n", qp->qp_num);
qp->link_is_up = false;
if (qp->event_handler)
qp->event_handler(qp->cb_data, qp->link_is_up);
}
static void ntb_qp_link_cleanup_work(struct work_struct *work)
{
struct ntb_transport_qp *qp = container_of(work,
struct ntb_transport_qp,
link_cleanup);
struct ntb_transport_ctx *nt = qp->transport;
ntb_qp_link_cleanup(qp);
if (nt->link_is_up)
schedule_delayed_work(&qp->link_work,
msecs_to_jiffies(NTB_LINK_DOWN_TIMEOUT));
}
static void ntb_qp_link_down(struct ntb_transport_qp *qp)
{
schedule_work(&qp->link_cleanup);
}
static void ntb_transport_link_cleanup(struct ntb_transport_ctx *nt)
{
struct ntb_transport_qp *qp;
u64 qp_bitmap_alloc;
int i;
qp_bitmap_alloc = nt->qp_bitmap & ~nt->qp_bitmap_free;
/* Pass along the info to any clients */
for (i = 0; i < nt->qp_count; i++)
if (qp_bitmap_alloc & BIT_ULL(i)) {
qp = &nt->qp_vec[i];
ntb_qp_link_cleanup(qp);
cancel_work_sync(&qp->link_cleanup);
cancel_delayed_work_sync(&qp->link_work);
}
if (!nt->link_is_up)
cancel_delayed_work_sync(&nt->link_work);
/* The scratchpad registers keep the values if the remote side
* goes down, blast them now to give them a sane value the next
* time they are accessed
*/
for (i = 0; i < MAX_SPAD; i++)
ntb_spad_write(nt->ndev, i, 0);
}
static void ntb_transport_link_cleanup_work(struct work_struct *work)
{
struct ntb_transport_ctx *nt =
container_of(work, struct ntb_transport_ctx, link_cleanup);
ntb_transport_link_cleanup(nt);
}
static void ntb_transport_event_callback(void *data)
{
struct ntb_transport_ctx *nt = data;
if (ntb_link_is_up(nt->ndev, NULL, NULL) == 1)
schedule_delayed_work(&nt->link_work, 0);
else
schedule_work(&nt->link_cleanup);
}
static void ntb_transport_link_work(struct work_struct *work)
{
struct ntb_transport_ctx *nt =
container_of(work, struct ntb_transport_ctx, link_work.work);
struct ntb_dev *ndev = nt->ndev;
struct pci_dev *pdev = ndev->pdev;
resource_size_t size;
u32 val;
int rc, i, spad;
/* send the local info, in the opposite order of the way we read it */
for (i = 0; i < nt->mw_count; i++) {
size = nt->mw_vec[i].phys_size;
if (max_mw_size && size > max_mw_size)
size = max_mw_size;
spad = MW0_SZ_HIGH + (i * 2);
ntb_peer_spad_write(ndev, spad, (u32)(size >> 32));
spad = MW0_SZ_LOW + (i * 2);
ntb_peer_spad_write(ndev, spad, (u32)size);
}
ntb_peer_spad_write(ndev, NUM_MWS, nt->mw_count);
ntb_peer_spad_write(ndev, NUM_QPS, nt->qp_count);
ntb_peer_spad_write(ndev, VERSION, NTB_TRANSPORT_VERSION);
/* Query the remote side for its info */
val = ntb_spad_read(ndev, VERSION);
dev_dbg(&pdev->dev, "Remote version = %d\n", val);
if (val != NTB_TRANSPORT_VERSION)
goto out;
val = ntb_spad_read(ndev, NUM_QPS);
dev_dbg(&pdev->dev, "Remote max number of qps = %d\n", val);
if (val != nt->qp_count)
goto out;
val = ntb_spad_read(ndev, NUM_MWS);
dev_dbg(&pdev->dev, "Remote number of mws = %d\n", val);
if (val != nt->mw_count)
goto out;
for (i = 0; i < nt->mw_count; i++) {
u64 val64;
val = ntb_spad_read(ndev, MW0_SZ_HIGH + (i * 2));
val64 = (u64)val << 32;
val = ntb_spad_read(ndev, MW0_SZ_LOW + (i * 2));
val64 |= val;
dev_dbg(&pdev->dev, "Remote MW%d size = %#llx\n", i, val64);
rc = ntb_set_mw(nt, i, val64);
if (rc)
goto out1;
}
nt->link_is_up = true;
for (i = 0; i < nt->qp_count; i++) {
struct ntb_transport_qp *qp = &nt->qp_vec[i];
ntb_transport_setup_qp_mw(nt, i);
if (qp->client_ready)
schedule_delayed_work(&qp->link_work, 0);
}
return;
out1:
for (i = 0; i < nt->mw_count; i++)
ntb_free_mw(nt, i);
out:
if (ntb_link_is_up(ndev, NULL, NULL) == 1)
schedule_delayed_work(&nt->link_work,
msecs_to_jiffies(NTB_LINK_DOWN_TIMEOUT));
}
static void ntb_qp_link_work(struct work_struct *work)
{
struct ntb_transport_qp *qp = container_of(work,
struct ntb_transport_qp,
link_work.work);
struct pci_dev *pdev = qp->ndev->pdev;
struct ntb_transport_ctx *nt = qp->transport;
int val;
WARN_ON(!nt->link_is_up);
val = ntb_spad_read(nt->ndev, QP_LINKS);
ntb_peer_spad_write(nt->ndev, QP_LINKS, val | BIT(qp->qp_num));
/* query remote spad for qp ready bits */
ntb_peer_spad_read(nt->ndev, QP_LINKS);
dev_dbg(&pdev->dev, "Remote QP link status = %x\n", val);
/* See if the remote side is up */
if (val & BIT(qp->qp_num)) {
dev_info(&pdev->dev, "qp %d: Link Up\n", qp->qp_num);
qp->link_is_up = true;
if (qp->event_handler)
qp->event_handler(qp->cb_data, qp->link_is_up);
} else if (nt->link_is_up)
schedule_delayed_work(&qp->link_work,
msecs_to_jiffies(NTB_LINK_DOWN_TIMEOUT));
}
static int ntb_transport_init_queue(struct ntb_transport_ctx *nt,
unsigned int qp_num)
{
struct ntb_transport_qp *qp;
struct ntb_transport_mw *mw;
phys_addr_t mw_base;
resource_size_t mw_size;
unsigned int num_qps_mw, tx_size;
unsigned int mw_num, mw_count, qp_count;
u64 qp_offset;
mw_count = nt->mw_count;
qp_count = nt->qp_count;
mw_num = QP_TO_MW(nt, qp_num);
mw = &nt->mw_vec[mw_num];
qp = &nt->qp_vec[qp_num];
qp->qp_num = qp_num;
qp->transport = nt;
qp->ndev = nt->ndev;
qp->link_is_up = false;
qp->client_ready = false;
qp->event_handler = NULL;
if (qp_count % mw_count && mw_num + 1 < qp_count / mw_count)
num_qps_mw = qp_count / mw_count + 1;
else
num_qps_mw = qp_count / mw_count;
mw_base = nt->mw_vec[mw_num].phys_addr;
mw_size = nt->mw_vec[mw_num].phys_size;
tx_size = (unsigned int)mw_size / num_qps_mw;
qp_offset = tx_size * qp_num / mw_count;
qp->tx_mw = nt->mw_vec[mw_num].vbase + qp_offset;
if (!qp->tx_mw)
return -EINVAL;
qp->tx_mw_phys = mw_base + qp_offset;
if (!qp->tx_mw_phys)
return -EINVAL;
tx_size -= sizeof(struct ntb_rx_info);
qp->rx_info = qp->tx_mw + tx_size;
/* Due to housekeeping, there must be atleast 2 buffs */
qp->tx_max_frame = min(transport_mtu, tx_size / 2);
qp->tx_max_entry = tx_size / qp->tx_max_frame;
if (nt_debugfs_dir) {
char debugfs_name[4];
snprintf(debugfs_name, 4, "qp%d", qp_num);
qp->debugfs_dir = debugfs_create_dir(debugfs_name,
nt_debugfs_dir);
qp->debugfs_stats = debugfs_create_file("stats", S_IRUSR,
qp->debugfs_dir, qp,
&ntb_qp_debugfs_stats);
} else {
qp->debugfs_dir = NULL;
qp->debugfs_stats = NULL;
}
INIT_DELAYED_WORK(&qp->link_work, ntb_qp_link_work);
INIT_WORK(&qp->link_cleanup, ntb_qp_link_cleanup_work);
spin_lock_init(&qp->ntb_rx_pend_q_lock);
spin_lock_init(&qp->ntb_rx_free_q_lock);
spin_lock_init(&qp->ntb_tx_free_q_lock);
INIT_LIST_HEAD(&qp->rx_pend_q);
INIT_LIST_HEAD(&qp->rx_free_q);
INIT_LIST_HEAD(&qp->tx_free_q);
tasklet_init(&qp->rxc_db_work, ntb_transport_rxc_db,
(unsigned long)qp);
return 0;
}
static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev)
{
struct ntb_transport_ctx *nt;
struct ntb_transport_mw *mw;
unsigned int mw_count, qp_count;
u64 qp_bitmap;
int rc, i;
if (ntb_db_is_unsafe(ndev))
dev_dbg(&ndev->dev,
"doorbell is unsafe, proceed anyway...\n");
if (ntb_spad_is_unsafe(ndev))
dev_dbg(&ndev->dev,
"scratchpad is unsafe, proceed anyway...\n");
nt = kzalloc(sizeof(*nt), GFP_KERNEL);
if (!nt)
return -ENOMEM;
nt->ndev = ndev;
mw_count = ntb_mw_count(ndev);
nt->mw_count = mw_count;
nt->mw_vec = kcalloc(mw_count, sizeof(*nt->mw_vec), GFP_KERNEL);
if (!nt->mw_vec) {
rc = -ENOMEM;
goto err;
}
for (i = 0; i < mw_count; i++) {
mw = &nt->mw_vec[i];
rc = ntb_mw_get_range(ndev, i, &mw->phys_addr, &mw->phys_size,
&mw->xlat_align, &mw->xlat_align_size);
if (rc)
goto err1;
mw->vbase = ioremap(mw->phys_addr, mw->phys_size);
if (!mw->vbase) {
rc = -ENOMEM;
goto err1;
}
mw->buff_size = 0;
mw->xlat_size = 0;
mw->virt_addr = NULL;
mw->dma_addr = 0;
}
qp_bitmap = ntb_db_valid_mask(ndev);
qp_count = ilog2(qp_bitmap);
if (max_num_clients && max_num_clients < qp_count)
qp_count = max_num_clients;
else if (mw_count < qp_count)
qp_count = mw_count;
qp_bitmap &= BIT_ULL(qp_count) - 1;
nt->qp_count = qp_count;
nt->qp_bitmap = qp_bitmap;
nt->qp_bitmap_free = qp_bitmap;
nt->qp_vec = kcalloc(qp_count, sizeof(*nt->qp_vec), GFP_KERNEL);
if (!nt->qp_vec) {
rc = -ENOMEM;
goto err2;
}