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
|
// SPDX-License-Identifier: GPL-2.0
/*
* channel program interfaces
*
* Copyright IBM Corp. 2017
*
* Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
* Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
*/
#include <linux/ratelimit.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/iommu.h>
#include <linux/vfio.h>
#include <asm/idals.h>
#include "vfio_ccw_cp.h"
#include "vfio_ccw_private.h"
struct page_array {
/* Array that stores pages need to pin. */
dma_addr_t *pa_iova;
/* Array that receives the pinned pages. */
struct page **pa_page;
/* Number of pages pinned from @pa_iova. */
int pa_nr;
};
struct ccwchain {
struct list_head next;
struct ccw1 *ch_ccw;
/* Guest physical address of the current chain. */
u64 ch_iova;
/* Count of the valid ccws in chain. */
int ch_len;
/* Pinned PAGEs for the original data. */
struct page_array *ch_pa;
};
/*
* page_array_alloc() - alloc memory for page array
* @pa: page_array on which to perform the operation
* @len: number of pages that should be pinned from @iova
*
* Attempt to allocate memory for page array.
*
* Usage of page_array:
* We expect (pa_nr == 0) and (pa_iova == NULL), any field in
* this structure will be filled in by this function.
*
* Returns:
* 0 if page array is allocated
* -EINVAL if pa->pa_nr is not initially zero, or pa->pa_iova is not NULL
* -ENOMEM if alloc failed
*/
static int page_array_alloc(struct page_array *pa, unsigned int len)
{
if (pa->pa_nr || pa->pa_iova)
return -EINVAL;
if (len == 0)
return -EINVAL;
pa->pa_nr = len;
pa->pa_iova = kcalloc(len, sizeof(*pa->pa_iova), GFP_KERNEL);
if (!pa->pa_iova)
return -ENOMEM;
pa->pa_page = kcalloc(len, sizeof(*pa->pa_page), GFP_KERNEL);
if (!pa->pa_page) {
kfree(pa->pa_iova);
return -ENOMEM;
}
return 0;
}
/*
* page_array_unpin() - Unpin user pages in memory
* @pa: page_array on which to perform the operation
* @vdev: the vfio device to perform the operation
* @pa_nr: number of user pages to unpin
* @unaligned: were pages unaligned on the pin request
*
* Only unpin if any pages were pinned to begin with, i.e. pa_nr > 0,
* otherwise only clear pa->pa_nr
*/
static void page_array_unpin(struct page_array *pa,
struct vfio_device *vdev, int pa_nr, bool unaligned)
{
int unpinned = 0, npage = 1;
while (unpinned < pa_nr) {
dma_addr_t *first = &pa->pa_iova[unpinned];
dma_addr_t *last = &first[npage];
if (unpinned + npage < pa_nr &&
*first + npage * PAGE_SIZE == *last &&
!unaligned) {
npage++;
continue;
}
vfio_unpin_pages(vdev, *first, npage);
unpinned += npage;
npage = 1;
}
pa->pa_nr = 0;
}
/*
* page_array_pin() - Pin user pages in memory
* @pa: page_array on which to perform the operation
* @vdev: the vfio device to perform pin operations
* @unaligned: are pages aligned to 4K boundary?
*
* Returns number of pages pinned upon success.
* If the pin request partially succeeds, or fails completely,
* all pages are left unpinned and a negative error value is returned.
*
* Requests to pin "aligned" pages can be coalesced into a single
* vfio_pin_pages request for the sake of efficiency, based on the
* expectation of 4K page requests. Unaligned requests are probably
* dealing with 2K "pages", and cannot be coalesced without
* reworking this logic to incorporate that math.
*/
static int page_array_pin(struct page_array *pa, struct vfio_device *vdev, bool unaligned)
{
int pinned = 0, npage = 1;
int ret = 0;
while (pinned < pa->pa_nr) {
dma_addr_t *first = &pa->pa_iova[pinned];
dma_addr_t *last = &first[npage];
if (pinned + npage < pa->pa_nr &&
*first + npage * PAGE_SIZE == *last &&
!unaligned) {
npage++;
continue;
}
ret = vfio_pin_pages(vdev, *first, npage,
IOMMU_READ | IOMMU_WRITE,
&pa->pa_page[pinned]);
if (ret < 0) {
goto err_out;
} else if (ret > 0 && ret != npage) {
pinned += ret;
ret = -EINVAL;
goto err_out;
}
pinned += npage;
npage = 1;
}
return ret;
err_out:
page_array_unpin(pa, vdev, pinned, unaligned);
return ret;
}
/* Unpin the pages before releasing the memory. */
static void page_array_unpin_free(struct page_array *pa, struct vfio_device *vdev, bool unaligned)
{
page_array_unpin(pa, vdev, pa->pa_nr, unaligned);
kfree(pa->pa_page);
kfree(pa->pa_iova);
}
static bool page_array_iova_pinned(struct page_array *pa, u64 iova, u64 length)
{
u64 iova_pfn_start = iova >> PAGE_SHIFT;
u64 iova_pfn_end = (iova + length - 1) >> PAGE_SHIFT;
u64 pfn;
int i;
for (i = 0; i < pa->pa_nr; i++) {
pfn = pa->pa_iova[i] >> PAGE_SHIFT;
if (pfn >= iova_pfn_start && pfn <= iova_pfn_end)
return true;
}
return false;
}
/* Create the list of IDAL words for a page_array. */
static inline void page_array_idal_create_words(struct page_array *pa,
unsigned long *idaws)
{
int i;
/*
* Idal words (execept the first one) rely on the memory being 4k
* aligned. If a user virtual address is 4K aligned, then it's
* corresponding kernel physical address will also be 4K aligned. Thus
* there will be no problem here to simply use the phys to create an
* idaw.
*/
for (i = 0; i < pa->pa_nr; i++) {
idaws[i] = page_to_phys(pa->pa_page[i]);
/* Incorporate any offset from each starting address */
idaws[i] += pa->pa_iova[i] & (PAGE_SIZE - 1);
}
}
static void convert_ccw0_to_ccw1(struct ccw1 *source, unsigned long len)
{
struct ccw0 ccw0;
struct ccw1 *pccw1 = source;
int i;
for (i = 0; i < len; i++) {
ccw0 = *(struct ccw0 *)pccw1;
if ((pccw1->cmd_code & 0x0f) == CCW_CMD_TIC) {
pccw1->cmd_code = CCW_CMD_TIC;
pccw1->flags = 0;
pccw1->count = 0;
} else {
pccw1->cmd_code = ccw0.cmd_code;
pccw1->flags = ccw0.flags;
pccw1->count = ccw0.count;
}
pccw1->cda = ccw0.cda;
pccw1++;
}
}
#define idal_is_2k(_cp) (!(_cp)->orb.cmd.c64 || (_cp)->orb.cmd.i2k)
/*
* Helpers to operate ccwchain.
*/
#define ccw_is_read(_ccw) (((_ccw)->cmd_code & 0x03) == 0x02)
#define ccw_is_read_backward(_ccw) (((_ccw)->cmd_code & 0x0F) == 0x0C)
#define ccw_is_sense(_ccw) (((_ccw)->cmd_code & 0x0F) == CCW_CMD_BASIC_SENSE)
#define ccw_is_noop(_ccw) ((_ccw)->cmd_code == CCW_CMD_NOOP)
#define ccw_is_tic(_ccw) ((_ccw)->cmd_code == CCW_CMD_TIC)
#define ccw_is_idal(_ccw) ((_ccw)->flags & CCW_FLAG_IDA)
#define ccw_is_skip(_ccw) ((_ccw)->flags & CCW_FLAG_SKIP)
#define ccw_is_chain(_ccw) ((_ccw)->flags & (CCW_FLAG_CC | CCW_FLAG_DC))
/*
* ccw_does_data_transfer()
*
* Determine whether a CCW will move any data, such that the guest pages
* would need to be pinned before performing the I/O.
*
* Returns 1 if yes, 0 if no.
*/
static inline int ccw_does_data_transfer(struct ccw1 *ccw)
{
/* If the count field is zero, then no data will be transferred */
if (ccw->count == 0)
return 0;
/* If the command is a NOP, then no data will be transferred */
if (ccw_is_noop(ccw))
return 0;
/* If the skip flag is off, then data will be transferred */
if (!ccw_is_skip(ccw))
return 1;
/*
* If the skip flag is on, it is only meaningful if the command
* code is a read, read backward, sense, or sense ID. In those
* cases, no data will be transferred.
*/
if (ccw_is_read(ccw) || ccw_is_read_backward(ccw))
return 0;
if (ccw_is_sense(ccw))
return 0;
/* The skip flag is on, but it is ignored for this command code. */
return 1;
}
/*
* is_cpa_within_range()
*
* @cpa: channel program address being questioned
* @head: address of the beginning of a CCW chain
* @len: number of CCWs within the chain
*
* Determine whether the address of a CCW (whether a new chain,
* or the target of a TIC) falls within a range (including the end points).
*
* Returns 1 if yes, 0 if no.
*/
static inline int is_cpa_within_range(u32 cpa, u32 head, int len)
{
u32 tail = head + (len - 1) * sizeof(struct ccw1);
return (head <= cpa && cpa <= tail);
}
static inline int is_tic_within_range(struct ccw1 *ccw, u32 head, int len)
{
if (!ccw_is_tic(ccw))
return 0;
return is_cpa_within_range(ccw->cda, head, len);
}
static struct ccwchain *ccwchain_alloc(struct channel_program *cp, int len)
{
struct ccwchain *chain;
chain = kzalloc(sizeof(*chain), GFP_KERNEL);
if (!chain)
return NULL;
chain->ch_ccw = kcalloc(len, sizeof(*chain->ch_ccw), GFP_DMA | GFP_KERNEL);
if (!chain->ch_ccw)
goto out_err;
chain->ch_pa = kcalloc(len, sizeof(*chain->ch_pa), GFP_KERNEL);
if (!chain->ch_pa)
goto out_err;
list_add_tail(&chain->next, &cp->ccwchain_list);
return chain;
out_err:
kfree(chain->ch_ccw);
kfree(chain);
return NULL;
}
static void ccwchain_free(struct ccwchain *chain)
{
list_del(&chain->next);
kfree(chain->ch_pa);
kfree(chain->ch_ccw);
kfree(chain);
}
/* Free resource for a ccw that allocated memory for its cda. */
static void ccwchain_cda_free(struct ccwchain *chain, int idx)
{
struct ccw1 *ccw = &chain->ch_ccw[idx];
if (ccw_is_tic(ccw))
return;
kfree(phys_to_virt(ccw->cda));
}
/**
* ccwchain_calc_length - calculate the length of the ccw chain.
* @iova: guest physical address of the target ccw chain
* @cp: channel_program on which to perform the operation
*
* This is the chain length not considering any TICs.
* You need to do a new round for each TIC target.
*
* The program is also validated for absence of not yet supported
* indirect data addressing scenarios.
*
* Returns: the length of the ccw chain or -errno.
*/
static int ccwchain_calc_length(u64 iova, struct channel_program *cp)
{
struct ccw1 *ccw = cp->guest_cp;
int cnt = 0;
do {
cnt++;
/*
* As we don't want to fail direct addressing even if the
* orb specified one of the unsupported formats, we defer
* checking for IDAWs in unsupported formats to here.
*/
if ((!cp->orb.cmd.c64 || cp->orb.cmd.i2k) && ccw_is_idal(ccw))
return -EOPNOTSUPP;
/*
* We want to keep counting if the current CCW has the
* command-chaining flag enabled, or if it is a TIC CCW
* that loops back into the current chain. The latter
* is used for device orientation, where the CCW PRIOR to
* the TIC can either jump to the TIC or a CCW immediately
* after the TIC, depending on the results of its operation.
*/
if (!ccw_is_chain(ccw) && !is_tic_within_range(ccw, iova, cnt))
break;
ccw++;
} while (cnt < CCWCHAIN_LEN_MAX + 1);
if (cnt == CCWCHAIN_LEN_MAX + 1)
cnt = -EINVAL;
return cnt;
}
static int tic_target_chain_exists(struct ccw1 *tic, struct channel_program *cp)
{
struct ccwchain *chain;
u32 ccw_head;
list_for_each_entry(chain, &cp->ccwchain_list, next) {
ccw_head = chain->ch_iova;
if (is_cpa_within_range(tic->cda, ccw_head, chain->ch_len))
return 1;
}
return 0;
}
static int ccwchain_loop_tic(struct ccwchain *chain,
struct channel_program *cp);
static int ccwchain_handle_ccw(u32 cda, struct channel_program *cp)
{
struct vfio_device *vdev =
&container_of(cp, struct vfio_ccw_private, cp)->vdev;
struct ccwchain *chain;
int len, ret;
/* Copy 2K (the most we support today) of possible CCWs */
ret = vfio_dma_rw(vdev, cda, cp->guest_cp, CCWCHAIN_LEN_MAX * sizeof(struct ccw1), false);
if (ret)
return ret;
/* Convert any Format-0 CCWs to Format-1 */
if (!cp->orb.cmd.fmt)
convert_ccw0_to_ccw1(cp->guest_cp, CCWCHAIN_LEN_MAX);
/* Count the CCWs in the current chain */
len = ccwchain_calc_length(cda, cp);
if (len < 0)
return len;
/* Need alloc a new chain for this one. */
chain = ccwchain_alloc(cp, len);
if (!chain)
return -ENOMEM;
chain->ch_len = len;
chain->ch_iova = cda;
/* Copy the actual CCWs into the new chain */
memcpy(chain->ch_ccw, cp->guest_cp, len * sizeof(struct ccw1));
/* Loop for tics on this new chain. */
ret = ccwchain_loop_tic(chain, cp);
if (ret)
ccwchain_free(chain);
return ret;
}
/* Loop for TICs. */
static int ccwchain_loop_tic(struct ccwchain *chain, struct channel_program *cp)
{
struct ccw1 *tic;
int i, ret;
for (i = 0; i < chain->ch_len; i++) {
tic = &chain->ch_ccw[i];
if (!ccw_is_tic(tic))
continue;
/* May transfer to an existing chain. */
if (tic_target_chain_exists(tic, cp))
continue;
/* Build a ccwchain for the next segment */
ret = ccwchain_handle_ccw(tic->cda, cp);
if (ret)
return ret;
}
return 0;
}
static int ccwchain_fetch_tic(struct ccw1 *ccw,
struct channel_program *cp)
{
struct ccwchain *iter;
u32 ccw_head;
list_for_each_entry(iter, &cp->ccwchain_list, next) {
ccw_head = iter->ch_iova;
if (is_cpa_within_range(ccw->cda, ccw_head, iter->ch_len)) {
ccw->cda = (__u32) (addr_t) (((char *)iter->ch_ccw) +
(ccw->cda - ccw_head));
return 0;
}
}
return -EFAULT;
}
static unsigned long *get_guest_idal(struct ccw1 *ccw,
struct channel_program *cp,
int idaw_nr)
{
struct vfio_device *vdev =
&container_of(cp, struct vfio_ccw_private, cp)->vdev;
unsigned long *idaws;
unsigned int *idaws_f1;
int idal_len = idaw_nr * sizeof(*idaws);
int idaw_size = idal_is_2k(cp) ? PAGE_SIZE / 2 : PAGE_SIZE;
int idaw_mask = ~(idaw_size - 1);
int i, ret;
idaws = kcalloc(idaw_nr, sizeof(*idaws), GFP_DMA | GFP_KERNEL);
if (!idaws)
return ERR_PTR(-ENOMEM);
if (ccw_is_idal(ccw)) {
/* Copy IDAL from guest */
ret = vfio_dma_rw(vdev, ccw->cda, idaws, idal_len, false);
if (ret) {
kfree(idaws);
return ERR_PTR(ret);
}
} else {
/* Fabricate an IDAL based off CCW data address */
if (cp->orb.cmd.c64) {
idaws[0] = ccw->cda;
for (i = 1; i < idaw_nr; i++)
idaws[i] = (idaws[i - 1] + idaw_size) & idaw_mask;
} else {
idaws_f1 = (unsigned int *)idaws;
idaws_f1[0] = ccw->cda;
for (i = 1; i < idaw_nr; i++)
idaws_f1[i] = (idaws_f1[i - 1] + idaw_size) & idaw_mask;
}
}
return idaws;
}
/*
* ccw_count_idaws() - Calculate the number of IDAWs needed to transfer
* a specified amount of data
*
* @ccw: The Channel Command Word being translated
* @cp: Channel Program being processed
*
* The ORB is examined, since it specifies what IDAWs could actually be
* used by any CCW in the channel program, regardless of whether or not
* the CCW actually does. An ORB that does not specify Format-2-IDAW
* Control could still contain a CCW with an IDAL, which would be
* Format-1 and thus only move 2K with each IDAW. Thus all CCWs within
* the channel program must follow the same size requirements.
*/
static int ccw_count_idaws(struct ccw1 *ccw,
struct channel_program *cp)
{
struct vfio_device *vdev =
&container_of(cp, struct vfio_ccw_private, cp)->vdev;
u64 iova;
int size = cp->orb.cmd.c64 ? sizeof(u64) : sizeof(u32);
int ret;
int bytes = 1;
if (ccw->count)
bytes = ccw->count;
if (ccw_is_idal(ccw)) {
/* Read first IDAW to check its starting address. */
/* All subsequent IDAWs will be 2K- or 4K-aligned. */
ret = vfio_dma_rw(vdev, ccw->cda, &iova, size, false);
if (ret)
return ret;
/*
* Format-1 IDAWs only occupy the first 32 bits,
* and bit 0 is always off.
*/
if (!cp->orb.cmd.c64)
iova = iova >> 32;
} else {
iova = ccw->cda;
}
/* Format-1 IDAWs operate on 2K each */
if (!cp->orb.cmd.c64)
return idal_2k_nr_words((void *)iova, bytes);
/* Using the 2K variant of Format-2 IDAWs? */
if (cp->orb.cmd.i2k)
return idal_2k_nr_words((void *)iova, bytes);
/* The 'usual' case is 4K Format-2 IDAWs */
return idal_nr_words((void *)iova, bytes);
}
static int ccwchain_fetch_ccw(struct ccw1 *ccw,
struct page_array *pa,
struct channel_program *cp)
{
struct vfio_device *vdev =
&container_of(cp, struct vfio_ccw_private, cp)->vdev;
unsigned long *idaws;
unsigned int *idaws_f1;
int ret;
int idaw_nr;
int i;
/* Calculate size of IDAL */
idaw_nr = ccw_count_idaws(ccw, cp);
if (idaw_nr < 0)
return idaw_nr;
/* Allocate an IDAL from host storage */
idaws = get_guest_idal(ccw, cp, idaw_nr);
if (IS_ERR(idaws)) {
ret = PTR_ERR(idaws);
goto out_init;
}
/*
* Allocate an array of pages to pin/translate.
* The number of pages is actually the count of the idaws
* required for the data transfer, since we only only support
* 4K IDAWs today.
*/
ret = page_array_alloc(pa, idaw_nr);
if (ret < 0)
goto out_free_idaws;
/*
* Copy guest IDAWs into page_array, in case the memory they
* occupy is not contiguous.
*/
idaws_f1 = (unsigned int *)idaws;
for (i = 0; i < idaw_nr; i++) {
if (cp->orb.cmd.c64)
pa->pa_iova[i] = idaws[i];
else
pa->pa_iova[i] = idaws_f1[i];
}
if (ccw_does_data_transfer(ccw)) {
ret = page_array_pin(pa, vdev, idal_is_2k(cp));
if (ret < 0)
goto out_unpin;
} else {
pa->pa_nr = 0;
}
ccw->cda = (__u32) virt_to_phys(idaws);
ccw->flags |= CCW_FLAG_IDA;
/* Populate the IDAL with pinned/translated addresses from page */
page_array_idal_create_words(pa, idaws);
return 0;
out_unpin:
page_array_unpin_free(pa, vdev, idal_is_2k(cp));
out_free_idaws:
kfree(idaws);
out_init:
ccw->cda = 0;
return ret;
}
/*
* Fetch one ccw.
* To reduce memory copy, we'll pin the cda page in memory,
* and to get rid of the cda 2G limitiaion of ccw1, we'll translate
* direct ccws to idal ccws.
*/
static int ccwchain_fetch_one(struct ccw1 *ccw,
struct page_array *pa,
struct channel_program *cp)
{
if (ccw_is_tic(ccw))
return ccwchain_fetch_tic(ccw, cp);
return ccwchain_fetch_ccw(ccw, pa, cp);
}
/**
* cp_init() - allocate ccwchains for a channel program.
* @cp: channel_program on which to perform the operation
* @orb: control block for the channel program from the guest
*
* This creates one or more ccwchain(s), and copies the raw data of
* the target channel program from @orb->cmd.iova to the new ccwchain(s).
*
* Limitations:
* 1. Supports idal(c64) ccw chaining.
* 2. Supports 4k idaw.
*
* Returns:
* %0 on success and a negative error value on failure.
*/
int cp_init(struct channel_program *cp, union orb *orb)
{
struct vfio_device *vdev =
&container_of(cp, struct vfio_ccw_private, cp)->vdev;
/* custom ratelimit used to avoid flood during guest IPL */
static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 1);
int ret;
/* this is an error in the caller */
if (cp->initialized)
return -EBUSY;
/*
* We only support prefetching the channel program. We assume all channel
* programs executed by supported guests likewise support prefetching.
* Executing a channel program that does not specify prefetching will
* typically not cause an error, but a warning is issued to help identify
* the problem if something does break.
*/
if (!orb->cmd.pfch && __ratelimit(&ratelimit_state))
dev_warn(
vdev->dev,
"Prefetching channel program even though prefetch not specified in ORB");
INIT_LIST_HEAD(&cp->ccwchain_list);
memcpy(&cp->orb, orb, sizeof(*orb));
/* Build a ccwchain for the first CCW segment */
ret = ccwchain_handle_ccw(orb->cmd.cpa, cp);
if (!ret)
cp->initialized = true;
return ret;
}
/**
* cp_free() - free resources for channel program.
* @cp: channel_program on which to perform the operation
*
* This unpins the memory pages and frees the memory space occupied by
* @cp, which must have been returned by a previous call to cp_init().
* Otherwise, undefined behavior occurs.
*/
void cp_free(struct channel_program *cp)
{
struct vfio_device *vdev =
&container_of(cp, struct vfio_ccw_private, cp)->vdev;
struct ccwchain *chain, *temp;
int i;
if (!cp->initialized)
return;
cp->initialized = false;
list_for_each_entry_safe(chain, temp, &cp->ccwchain_list, next) {
for (i = 0; i < chain->ch_len; i++) {
page_array_unpin_free(&chain->ch_pa[i], vdev, idal_is_2k(cp));
ccwchain_cda_free(chain, i);
}
ccwchain_free(chain);
}
}
/**
* cp_prefetch() - translate a guest physical address channel program to
* a real-device runnable channel program.
* @cp: channel_program on which to perform the operation
*
* This function translates the guest-physical-address channel program
* and stores the result to ccwchain list. @cp must have been
* initialized by a previous call with cp_init(). Otherwise, undefined
* behavior occurs.
* For each chain composing the channel program:
* - On entry ch_len holds the count of CCWs to be translated.
* - On exit ch_len is adjusted to the count of successfully translated CCWs.
* This allows cp_free to find in ch_len the count of CCWs to free in a chain.
*
* The S/390 CCW Translation APIS (prefixed by 'cp_') are introduced
* as helpers to do ccw chain translation inside the kernel. Basically
* they accept a channel program issued by a virtual machine, and
* translate the channel program to a real-device runnable channel
* program.
*
* These APIs will copy the ccws into kernel-space buffers, and update
* the guest phsical addresses with their corresponding host physical
* addresses. Then channel I/O device drivers could issue the
* translated channel program to real devices to perform an I/O
* operation.
*
* These interfaces are designed to support translation only for
* channel programs, which are generated and formatted by a
* guest. Thus this will make it possible for things like VFIO to
* leverage the interfaces to passthrough a channel I/O mediated
* device in QEMU.
*
* We support direct ccw chaining by translating them to idal ccws.
*
* Returns:
* %0 on success and a negative error value on failure.
*/
int cp_prefetch(struct channel_program *cp)
{
struct ccwchain *chain;
struct ccw1 *ccw;
struct page_array *pa;
int len, idx, ret;
/* this is an error in the caller */
if (!cp->initialized)
return -EINVAL;
list_for_each_entry(chain, &cp->ccwchain_list, next) {
len = chain->ch_len;
for (idx = 0; idx < len; idx++) {
ccw = &chain->ch_ccw[idx];
pa = &chain->ch_pa[idx];
ret = ccwchain_fetch_one(ccw, pa, cp);
if (ret)
goto out_err;
}
}
return 0;
out_err:
/* Only cleanup the chain elements that were actually translated. */
chain->ch_len = idx;
list_for_each_entry_continue(chain, &cp->ccwchain_list, next) {
chain->ch_len = 0;
}
return ret;
}
/**
* cp_get_orb() - get the orb of the channel program
* @cp: channel_program on which to perform the operation
* @sch: subchannel the operation will be performed against
*
* This function returns the address of the updated orb of the channel
* program. Channel I/O device drivers could use this orb to issue a
* ssch.
*/
union orb *cp_get_orb(struct channel_program *cp, struct subchannel *sch)
{
union orb *orb;
struct ccwchain *chain;
struct ccw1 *cpa;
/* this is an error in the caller */
if (!cp->initialized)
return NULL;
orb = &cp->orb;
orb->cmd.intparm = (u32)virt_to_phys(sch);
orb->cmd.fmt = 1;
/*
* Everything built by vfio-ccw is a Format-2 IDAL.
* If the input was a Format-1 IDAL, indicate that
* 2K Format-2 IDAWs were created here.
*/
if (!orb->cmd.c64)
orb->cmd.i2k = 1;
orb->cmd.c64 = 1;
if (orb->cmd.lpm == 0)
orb->cmd.lpm = sch->lpm;
chain = list_first_entry(&cp->ccwchain_list, struct ccwchain, next);
cpa = chain->ch_ccw;
orb->cmd.cpa = (__u32)virt_to_phys(cpa);
return orb;
}
/**
* cp_update_scsw() - update scsw for a channel program.
* @cp: channel_program on which to perform the operation
* @scsw: I/O results of the channel program and also the target to be
* updated
*
* @scsw contains the I/O results of the channel program that pointed
* to by @cp. However what @scsw->cpa stores is a host physical
* address, which is meaningless for the guest, which is waiting for
* the I/O results.
*
* This function updates @scsw->cpa to its coressponding guest physical
* address.
*/
void cp_update_scsw(struct channel_program *cp, union scsw *scsw)
{
struct ccwchain *chain;
u32 cpa = scsw->cmd.cpa;
u32 ccw_head;
if (!cp->initialized)
return;
/*
* LATER:
* For now, only update the cmd.cpa part. We may need to deal with
* other portions of the schib as well, even if we don't return them
* in the ioctl directly. Path status changes etc.
*/
list_for_each_entry(chain, &cp->ccwchain_list, next) {
ccw_head = (u32)(u64)chain->ch_ccw;
/*
* On successful execution, cpa points just beyond the end
* of the chain.
*/
if (is_cpa_within_range(cpa, ccw_head, chain->ch_len + 1)) {
/*
* (cpa - ccw_head) is the offset value of the host
* physical ccw to its chain head.
* Adding this value to the guest physical ccw chain
* head gets us the guest cpa.
*/
cpa = chain->ch_iova + (cpa - ccw_head);
break;
}
}
scsw->cmd.cpa = cpa;
}
/**
* cp_iova_pinned() - check if an iova is pinned for a ccw chain.
* @cp: channel_program on which to perform the operation
* @iova: the iova to check
* @length: the length to check from @iova
*
* If the @iova is currently pinned for the ccw chain, return true;
* else return false.
*/
bool cp_iova_pinned(struct channel_program *cp, u64 iova, u64 length)
{
struct ccwchain *chain;
int i;
if (!cp->initialized)
return false;
list_for_each_entry(chain, &cp->ccwchain_list, next) {
for (i = 0; i < chain->ch_len; i++)
if (page_array_iova_pinned(&chain->ch_pa[i], iova, length))
return true;
}
return false;
}
|