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
|
/*
* Copyright (c) 2015, 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.
*/
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/tcp.h>
#include <net/busy_poll.h>
#include "en.h"
#include "en_tc.h"
#include "eswitch.h"
static inline bool mlx5e_rx_hw_stamp(struct mlx5e_tstamp *tstamp)
{
return tstamp->hwtstamp_config.rx_filter == HWTSTAMP_FILTER_ALL;
}
static inline void mlx5e_read_cqe_slot(struct mlx5e_cq *cq, u32 cqcc,
void *data)
{
u32 ci = cqcc & cq->wq.sz_m1;
memcpy(data, mlx5_cqwq_get_wqe(&cq->wq, ci), sizeof(struct mlx5_cqe64));
}
static inline void mlx5e_read_title_slot(struct mlx5e_rq *rq,
struct mlx5e_cq *cq, u32 cqcc)
{
mlx5e_read_cqe_slot(cq, cqcc, &cq->title);
cq->decmprs_left = be32_to_cpu(cq->title.byte_cnt);
cq->decmprs_wqe_counter = be16_to_cpu(cq->title.wqe_counter);
rq->stats.cqe_compress_blks++;
}
static inline void mlx5e_read_mini_arr_slot(struct mlx5e_cq *cq, u32 cqcc)
{
mlx5e_read_cqe_slot(cq, cqcc, cq->mini_arr);
cq->mini_arr_idx = 0;
}
static inline void mlx5e_cqes_update_owner(struct mlx5e_cq *cq, u32 cqcc, int n)
{
u8 op_own = (cqcc >> cq->wq.log_sz) & 1;
u32 wq_sz = 1 << cq->wq.log_sz;
u32 ci = cqcc & cq->wq.sz_m1;
u32 ci_top = min_t(u32, wq_sz, ci + n);
for (; ci < ci_top; ci++, n--) {
struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(&cq->wq, ci);
cqe->op_own = op_own;
}
if (unlikely(ci == wq_sz)) {
op_own = !op_own;
for (ci = 0; ci < n; ci++) {
struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(&cq->wq, ci);
cqe->op_own = op_own;
}
}
}
static inline void mlx5e_decompress_cqe(struct mlx5e_rq *rq,
struct mlx5e_cq *cq, u32 cqcc)
{
u16 wqe_cnt_step;
cq->title.byte_cnt = cq->mini_arr[cq->mini_arr_idx].byte_cnt;
cq->title.check_sum = cq->mini_arr[cq->mini_arr_idx].checksum;
cq->title.op_own &= 0xf0;
cq->title.op_own |= 0x01 & (cqcc >> cq->wq.log_sz);
cq->title.wqe_counter = cpu_to_be16(cq->decmprs_wqe_counter);
wqe_cnt_step =
rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ ?
mpwrq_get_cqe_consumed_strides(&cq->title) : 1;
cq->decmprs_wqe_counter =
(cq->decmprs_wqe_counter + wqe_cnt_step) & rq->wq.sz_m1;
}
static inline void mlx5e_decompress_cqe_no_hash(struct mlx5e_rq *rq,
struct mlx5e_cq *cq, u32 cqcc)
{
mlx5e_decompress_cqe(rq, cq, cqcc);
cq->title.rss_hash_type = 0;
cq->title.rss_hash_result = 0;
}
static inline u32 mlx5e_decompress_cqes_cont(struct mlx5e_rq *rq,
struct mlx5e_cq *cq,
int update_owner_only,
int budget_rem)
{
u32 cqcc = cq->wq.cc + update_owner_only;
u32 cqe_count;
u32 i;
cqe_count = min_t(u32, cq->decmprs_left, budget_rem);
for (i = update_owner_only; i < cqe_count;
i++, cq->mini_arr_idx++, cqcc++) {
if (cq->mini_arr_idx == MLX5_MINI_CQE_ARRAY_SIZE)
mlx5e_read_mini_arr_slot(cq, cqcc);
mlx5e_decompress_cqe_no_hash(rq, cq, cqcc);
rq->handle_rx_cqe(rq, &cq->title);
}
mlx5e_cqes_update_owner(cq, cq->wq.cc, cqcc - cq->wq.cc);
cq->wq.cc = cqcc;
cq->decmprs_left -= cqe_count;
rq->stats.cqe_compress_pkts += cqe_count;
return cqe_count;
}
static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq,
struct mlx5e_cq *cq,
int budget_rem)
{
mlx5e_read_title_slot(rq, cq, cq->wq.cc);
mlx5e_read_mini_arr_slot(cq, cq->wq.cc + 1);
mlx5e_decompress_cqe(rq, cq, cq->wq.cc);
rq->handle_rx_cqe(rq, &cq->title);
cq->mini_arr_idx++;
return mlx5e_decompress_cqes_cont(rq, cq, 1, budget_rem) - 1;
}
void mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val)
{
bool was_opened;
if (!MLX5_CAP_GEN(priv->mdev, cqe_compression))
return;
if (MLX5E_GET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS) == val)
return;
was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
if (was_opened)
mlx5e_close_locked(priv->netdev);
MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS, val);
if (was_opened)
mlx5e_open_locked(priv->netdev);
}
#define RQ_PAGE_SIZE(rq) ((1 << rq->buff.page_order) << PAGE_SHIFT)
static inline bool mlx5e_rx_cache_put(struct mlx5e_rq *rq,
struct mlx5e_dma_info *dma_info)
{
struct mlx5e_page_cache *cache = &rq->page_cache;
u32 tail_next = (cache->tail + 1) & (MLX5E_CACHE_SIZE - 1);
if (tail_next == cache->head) {
rq->stats.cache_full++;
return false;
}
cache->page_cache[cache->tail] = *dma_info;
cache->tail = tail_next;
return true;
}
static inline bool mlx5e_rx_cache_get(struct mlx5e_rq *rq,
struct mlx5e_dma_info *dma_info)
{
struct mlx5e_page_cache *cache = &rq->page_cache;
if (unlikely(cache->head == cache->tail)) {
rq->stats.cache_empty++;
return false;
}
if (page_ref_count(cache->page_cache[cache->head].page) != 1) {
rq->stats.cache_busy++;
return false;
}
*dma_info = cache->page_cache[cache->head];
cache->head = (cache->head + 1) & (MLX5E_CACHE_SIZE - 1);
rq->stats.cache_reuse++;
dma_sync_single_for_device(rq->pdev, dma_info->addr,
RQ_PAGE_SIZE(rq),
DMA_FROM_DEVICE);
return true;
}
static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq,
struct mlx5e_dma_info *dma_info)
{
struct page *page;
if (mlx5e_rx_cache_get(rq, dma_info))
return 0;
page = dev_alloc_pages(rq->buff.page_order);
if (unlikely(!page))
return -ENOMEM;
dma_info->page = page;
dma_info->addr = dma_map_page(rq->pdev, page, 0,
RQ_PAGE_SIZE(rq), rq->buff.map_dir);
if (unlikely(dma_mapping_error(rq->pdev, dma_info->addr))) {
put_page(page);
return -ENOMEM;
}
return 0;
}
void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info,
bool recycle)
{
if (likely(recycle) && mlx5e_rx_cache_put(rq, dma_info))
return;
dma_unmap_page(rq->pdev, dma_info->addr, RQ_PAGE_SIZE(rq),
rq->buff.map_dir);
put_page(dma_info->page);
}
int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix)
{
struct mlx5e_dma_info *di = &rq->dma_info[ix];
if (unlikely(mlx5e_page_alloc_mapped(rq, di)))
return -ENOMEM;
wqe->data.addr = cpu_to_be64(di->addr + rq->rx_headroom);
return 0;
}
void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix)
{
struct mlx5e_dma_info *di = &rq->dma_info[ix];
mlx5e_page_release(rq, di, true);
}
static inline int mlx5e_mpwqe_strides_per_page(struct mlx5e_rq *rq)
{
return rq->mpwqe_num_strides >> MLX5_MPWRQ_WQE_PAGE_ORDER;
}
static inline void mlx5e_add_skb_frag_mpwqe(struct mlx5e_rq *rq,
struct sk_buff *skb,
struct mlx5e_mpw_info *wi,
u32 page_idx, u32 frag_offset,
u32 len)
{
unsigned int truesize = ALIGN(len, rq->mpwqe_stride_sz);
dma_sync_single_for_cpu(rq->pdev,
wi->umr.dma_info[page_idx].addr + frag_offset,
len, DMA_FROM_DEVICE);
wi->skbs_frags[page_idx]++;
skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
wi->umr.dma_info[page_idx].page, frag_offset,
len, truesize);
}
static inline void
mlx5e_copy_skb_header_mpwqe(struct device *pdev,
struct sk_buff *skb,
struct mlx5e_mpw_info *wi,
u32 page_idx, u32 offset,
u32 headlen)
{
u16 headlen_pg = min_t(u32, headlen, PAGE_SIZE - offset);
struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[page_idx];
unsigned int len;
/* Aligning len to sizeof(long) optimizes memcpy performance */
len = ALIGN(headlen_pg, sizeof(long));
dma_sync_single_for_cpu(pdev, dma_info->addr + offset, len,
DMA_FROM_DEVICE);
skb_copy_to_linear_data_offset(skb, 0,
page_address(dma_info->page) + offset,
len);
if (unlikely(offset + headlen > PAGE_SIZE)) {
dma_info++;
headlen_pg = len;
len = ALIGN(headlen - headlen_pg, sizeof(long));
dma_sync_single_for_cpu(pdev, dma_info->addr, len,
DMA_FROM_DEVICE);
skb_copy_to_linear_data_offset(skb, headlen_pg,
page_address(dma_info->page),
len);
}
}
static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix)
{
struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
struct mlx5e_sq *sq = &rq->channel->icosq;
struct mlx5_wq_cyc *wq = &sq->wq;
struct mlx5e_umr_wqe *wqe;
u8 num_wqebbs = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_BB);
u16 pi;
/* fill sq edge with nops to avoid wqe wrap around */
while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) {
sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP;
sq->db.ico_wqe[pi].num_wqebbs = 1;
mlx5e_send_nop(sq, false);
}
wqe = mlx5_wq_cyc_get_wqe(wq, pi);
memcpy(wqe, &wi->umr.wqe, sizeof(*wqe));
wqe->ctrl.opmod_idx_opcode =
cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
MLX5_OPCODE_UMR);
sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
sq->db.ico_wqe[pi].num_wqebbs = num_wqebbs;
sq->pc += num_wqebbs;
mlx5e_tx_notify_hw(sq, &wqe->ctrl, 0);
}
static int mlx5e_alloc_rx_umr_mpwqe(struct mlx5e_rq *rq,
struct mlx5e_rx_wqe *wqe,
u16 ix)
{
struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
u64 dma_offset = (u64)mlx5e_get_wqe_mtt_offset(rq, ix) << PAGE_SHIFT;
int pg_strides = mlx5e_mpwqe_strides_per_page(rq);
int err;
int i;
for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++) {
struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[i];
err = mlx5e_page_alloc_mapped(rq, dma_info);
if (unlikely(err))
goto err_unmap;
wi->umr.mtt[i] = cpu_to_be64(dma_info->addr | MLX5_EN_WR);
page_ref_add(dma_info->page, pg_strides);
wi->skbs_frags[i] = 0;
}
wi->consumed_strides = 0;
wqe->data.addr = cpu_to_be64(dma_offset);
return 0;
err_unmap:
while (--i >= 0) {
struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[i];
page_ref_sub(dma_info->page, pg_strides);
mlx5e_page_release(rq, dma_info, true);
}
return err;
}
void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
{
int pg_strides = mlx5e_mpwqe_strides_per_page(rq);
int i;
for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++) {
struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[i];
page_ref_sub(dma_info->page, pg_strides - wi->skbs_frags[i]);
mlx5e_page_release(rq, dma_info, true);
}
}
void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq)
{
struct mlx5_wq_ll *wq = &rq->wq;
struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head);
clear_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state);
if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) {
mlx5e_free_rx_mpwqe(rq, &rq->mpwqe.info[wq->head]);
return;
}
mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index));
/* ensure wqes are visible to device before updating doorbell record */
dma_wmb();
mlx5_wq_ll_update_db_record(wq);
}
int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix)
{
int err;
err = mlx5e_alloc_rx_umr_mpwqe(rq, wqe, ix);
if (unlikely(err))
return err;
set_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state);
mlx5e_post_umr_wqe(rq, ix);
return -EBUSY;
}
void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
{
struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
mlx5e_free_rx_mpwqe(rq, wi);
}
#define RQ_CANNOT_POST(rq) \
(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state) || \
test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state))
bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
{
struct mlx5_wq_ll *wq = &rq->wq;
if (unlikely(RQ_CANNOT_POST(rq)))
return false;
while (!mlx5_wq_ll_is_full(wq)) {
struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head);
int err;
err = rq->alloc_wqe(rq, wqe, wq->head);
if (err == -EBUSY)
return true;
if (unlikely(err)) {
rq->stats.buff_alloc_err++;
break;
}
mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index));
}
/* ensure wqes are visible to device before updating doorbell record */
dma_wmb();
mlx5_wq_ll_update_db_record(wq);
return !mlx5_wq_ll_is_full(wq);
}
static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
u32 cqe_bcnt)
{
struct ethhdr *eth = (struct ethhdr *)(skb->data);
struct iphdr *ipv4;
struct ipv6hdr *ipv6;
struct tcphdr *tcp;
int network_depth = 0;
__be16 proto;
u16 tot_len;
u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe);
int tcp_ack = ((CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA == l4_hdr_type) ||
(CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA == l4_hdr_type));
skb->mac_len = ETH_HLEN;
proto = __vlan_get_protocol(skb, eth->h_proto, &network_depth);
ipv4 = (struct iphdr *)(skb->data + network_depth);
ipv6 = (struct ipv6hdr *)(skb->data + network_depth);
tot_len = cqe_bcnt - network_depth;
if (proto == htons(ETH_P_IP)) {
tcp = (struct tcphdr *)(skb->data + network_depth +
sizeof(struct iphdr));
ipv6 = NULL;
skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
} else {
tcp = (struct tcphdr *)(skb->data + network_depth +
sizeof(struct ipv6hdr));
ipv4 = NULL;
skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
}
if (get_cqe_lro_tcppsh(cqe))
tcp->psh = 1;
if (tcp_ack) {
tcp->ack = 1;
tcp->ack_seq = cqe->lro_ack_seq_num;
tcp->window = cqe->lro_tcp_win;
}
if (ipv4) {
ipv4->ttl = cqe->lro_min_ttl;
ipv4->tot_len = cpu_to_be16(tot_len);
ipv4->check = 0;
ipv4->check = ip_fast_csum((unsigned char *)ipv4,
ipv4->ihl);
} else {
ipv6->hop_limit = cqe->lro_min_ttl;
ipv6->payload_len = cpu_to_be16(tot_len -
sizeof(struct ipv6hdr));
}
}
static inline void mlx5e_skb_set_hash(struct mlx5_cqe64 *cqe,
struct sk_buff *skb)
{
u8 cht = cqe->rss_hash_type;
int ht = (cht & CQE_RSS_HTYPE_L4) ? PKT_HASH_TYPE_L4 :
(cht & CQE_RSS_HTYPE_IP) ? PKT_HASH_TYPE_L3 :
PKT_HASH_TYPE_NONE;
skb_set_hash(skb, be32_to_cpu(cqe->rss_hash_result), ht);
}
static inline bool is_first_ethertype_ip(struct sk_buff *skb)
{
__be16 ethertype = ((struct ethhdr *)skb->data)->h_proto;
return (ethertype == htons(ETH_P_IP) || ethertype == htons(ETH_P_IPV6));
}
static inline void mlx5e_handle_csum(struct net_device *netdev,
struct mlx5_cqe64 *cqe,
struct mlx5e_rq *rq,
struct sk_buff *skb,
bool lro)
{
if (unlikely(!(netdev->features & NETIF_F_RXCSUM)))
goto csum_none;
if (lro) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
return;
}
if (is_first_ethertype_ip(skb)) {
skb->ip_summed = CHECKSUM_COMPLETE;
skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
rq->stats.csum_complete++;
return;
}
if (likely((cqe->hds_ip_ext & CQE_L3_OK) &&
(cqe->hds_ip_ext & CQE_L4_OK))) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
if (cqe_is_tunneled(cqe)) {
skb->csum_level = 1;
skb->encapsulation = 1;
rq->stats.csum_unnecessary_inner++;
}
return;
}
csum_none:
skb->ip_summed = CHECKSUM_NONE;
rq->stats.csum_none++;
}
static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
u32 cqe_bcnt,
struct mlx5e_rq *rq,
struct sk_buff *skb)
{
struct net_device *netdev = rq->netdev;
struct mlx5e_tstamp *tstamp = rq->tstamp;
int lro_num_seg;
lro_num_seg = be32_to_cpu(cqe->srqn) >> 24;
if (lro_num_seg > 1) {
mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt);
skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt, lro_num_seg);
rq->stats.lro_packets++;
rq->stats.lro_bytes += cqe_bcnt;
}
if (unlikely(mlx5e_rx_hw_stamp(tstamp)))
mlx5e_fill_hwstamp(tstamp, get_cqe_ts(cqe), skb_hwtstamps(skb));
skb_record_rx_queue(skb, rq->ix);
if (likely(netdev->features & NETIF_F_RXHASH))
mlx5e_skb_set_hash(cqe, skb);
if (cqe_has_vlan(cqe))
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
be16_to_cpu(cqe->vlan_info));
skb->mark = be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK;
mlx5e_handle_csum(netdev, cqe, rq, skb, !!lro_num_seg);
skb->protocol = eth_type_trans(skb, netdev);
}
static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq,
struct mlx5_cqe64 *cqe,
u32 cqe_bcnt,
struct sk_buff *skb)
{
rq->stats.packets++;
rq->stats.bytes += cqe_bcnt;
mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb);
}
static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_sq *sq)
{
struct mlx5_wq_cyc *wq = &sq->wq;
struct mlx5e_tx_wqe *wqe;
u16 pi = (sq->pc - MLX5E_XDP_TX_WQEBBS) & wq->sz_m1; /* last pi */
wqe = mlx5_wq_cyc_get_wqe(wq, pi);
wqe->ctrl.fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE;
mlx5e_tx_notify_hw(sq, &wqe->ctrl, 0);
}
static inline void mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq,
struct mlx5e_dma_info *di,
const struct xdp_buff *xdp)
{
struct mlx5e_sq *sq = &rq->channel->xdp_sq;
struct mlx5_wq_cyc *wq = &sq->wq;
u16 pi = sq->pc & wq->sz_m1;
struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi);
struct mlx5e_sq_wqe_info *wi = &sq->db.xdp.wqe_info[pi];
struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
struct mlx5_wqe_eth_seg *eseg = &wqe->eth;
struct mlx5_wqe_data_seg *dseg;
ptrdiff_t data_offset = xdp->data - xdp->data_hard_start;
dma_addr_t dma_addr = di->addr + data_offset + MLX5E_XDP_MIN_INLINE;
unsigned int dma_len = xdp->data_end - xdp->data;
if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE ||
MLX5E_SW2HW_MTU(rq->netdev->mtu) < dma_len)) {
rq->stats.xdp_drop++;
mlx5e_page_release(rq, di, true);
return;
}
if (unlikely(!mlx5e_sq_has_room_for(sq, MLX5E_XDP_TX_WQEBBS))) {
if (sq->db.xdp.doorbell) {
/* SQ is full, ring doorbell */
mlx5e_xmit_xdp_doorbell(sq);
sq->db.xdp.doorbell = false;
}
rq->stats.xdp_tx_full++;
mlx5e_page_release(rq, di, true);
return;
}
dma_len -= MLX5E_XDP_MIN_INLINE;
dma_sync_single_for_device(sq->pdev, dma_addr, dma_len,
PCI_DMA_TODEVICE);
memset(wqe, 0, sizeof(*wqe));
/* copy the inline part */
memcpy(eseg->inline_hdr_start, xdp->data, MLX5E_XDP_MIN_INLINE);
eseg->inline_hdr_sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE);
dseg = (struct mlx5_wqe_data_seg *)cseg + (MLX5E_XDP_TX_DS_COUNT - 1);
/* write the dma part */
dseg->addr = cpu_to_be64(dma_addr);
dseg->byte_count = cpu_to_be32(dma_len);
dseg->lkey = sq->mkey_be;
cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_SEND);
cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | MLX5E_XDP_TX_DS_COUNT);
sq->db.xdp.di[pi] = *di;
wi->opcode = MLX5_OPCODE_SEND;
wi->num_wqebbs = MLX5E_XDP_TX_WQEBBS;
sq->pc += MLX5E_XDP_TX_WQEBBS;
sq->db.xdp.doorbell = true;
rq->stats.xdp_tx++;
}
/* returns true if packet was consumed by xdp */
static inline int mlx5e_xdp_handle(struct mlx5e_rq *rq,
struct mlx5e_dma_info *di,
void *va, u16 *rx_headroom, u32 *len)
{
const struct bpf_prog *prog = READ_ONCE(rq->xdp_prog);
struct xdp_buff xdp;
u32 act;
if (!prog)
return false;
xdp.data = va + *rx_headroom;
xdp.data_end = xdp.data + *len;
xdp.data_hard_start = va;
act = bpf_prog_run_xdp(prog, &xdp);
switch (act) {
case XDP_PASS:
*rx_headroom = xdp.data - xdp.data_hard_start;
*len = xdp.data_end - xdp.data;
return false;
case XDP_TX:
mlx5e_xmit_xdp_frame(rq, di, &xdp);
return true;
default:
bpf_warn_invalid_xdp_action(act);
case XDP_ABORTED:
case XDP_DROP:
rq->stats.xdp_drop++;
mlx5e_page_release(rq, di, true);
return true;
}
}
static inline
struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
u16 wqe_counter, u32 cqe_bcnt)
{
struct mlx5e_dma_info *di;
struct sk_buff *skb;
void *va, *data;
u16 rx_headroom = rq->rx_headroom;
bool consumed;
di = &rq->dma_info[wqe_counter];
va = page_address(di->page);
data = va + rx_headroom;
dma_sync_single_range_for_cpu(rq->pdev,
di->addr,
rx_headroom,
rq->buff.wqe_sz,
DMA_FROM_DEVICE);
prefetch(data);
if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) {
rq->stats.wqe_err++;
mlx5e_page_release(rq, di, true);
return NULL;
}
rcu_read_lock();
consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt);
rcu_read_unlock();
if (consumed)
return NULL; /* page/packet was consumed by XDP */
skb = build_skb(va, RQ_PAGE_SIZE(rq));
if (unlikely(!skb)) {
rq->stats.buff_alloc_err++;
mlx5e_page_release(rq, di, true);
return NULL;
}
/* queue up for recycling ..*/
page_ref_inc(di->page);
mlx5e_page_release(rq, di, true);
skb_reserve(skb, rx_headroom);
skb_put(skb, cqe_bcnt);
return skb;
}
void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
{
struct mlx5e_rx_wqe *wqe;
__be16 wqe_counter_be;
struct sk_buff *skb;
u16 wqe_counter;
u32 cqe_bcnt;
wqe_counter_be = cqe->wqe_counter;
wqe_counter = be16_to_cpu(wqe_counter_be);
wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter);
cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
skb = skb_from_cqe(rq, cqe, wqe_counter, cqe_bcnt);
if (!skb)
goto wq_ll_pop;
mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
napi_gro_receive(rq->cq.napi, skb);
wq_ll_pop:
mlx5_wq_ll_pop(&rq->wq, wqe_counter_be,
&wqe->next.next_wqe_index);
}
void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
{
struct net_device *netdev = rq->netdev;
struct mlx5e_priv *priv = netdev_priv(netdev);
struct mlx5_eswitch_rep *rep = priv->ppriv;
struct mlx5e_rx_wqe *wqe;
struct sk_buff *skb;
__be16 wqe_counter_be;
u16 wqe_counter;
u32 cqe_bcnt;
wqe_counter_be = cqe->wqe_counter;
wqe_counter = be16_to_cpu(wqe_counter_be);
wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter);
cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
skb = skb_from_cqe(rq, cqe, wqe_counter, cqe_bcnt);
if (!skb)
goto wq_ll_pop;
mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
if (rep->vlan && skb_vlan_tag_present(skb))
skb_vlan_pop(skb);
napi_gro_receive(rq->cq.napi, skb);
wq_ll_pop:
mlx5_wq_ll_pop(&rq->wq, wqe_counter_be,
&wqe->next.next_wqe_index);
}
static inline void mlx5e_mpwqe_fill_rx_skb(struct mlx5e_rq *rq,
struct mlx5_cqe64 *cqe,
struct mlx5e_mpw_info *wi,
u32 cqe_bcnt,
struct sk_buff *skb)
{
u16 stride_ix = mpwrq_get_cqe_stride_index(cqe);
u32 wqe_offset = stride_ix * rq->mpwqe_stride_sz;
u32 head_offset = wqe_offset & (PAGE_SIZE - 1);
u32 page_idx = wqe_offset >> PAGE_SHIFT;
u32 head_page_idx = page_idx;
u16 headlen = min_t(u16, MLX5_MPWRQ_SMALL_PACKET_THRESHOLD, cqe_bcnt);
u32 frag_offset = head_offset + headlen;
u16 byte_cnt = cqe_bcnt - headlen;
if (unlikely(frag_offset >= PAGE_SIZE)) {
page_idx++;
frag_offset -= PAGE_SIZE;
}
while (byte_cnt) {
u32 pg_consumed_bytes =
min_t(u32, PAGE_SIZE - frag_offset, byte_cnt);
mlx5e_add_skb_frag_mpwqe(rq, skb, wi, page_idx, frag_offset,
pg_consumed_bytes);
byte_cnt -= pg_consumed_bytes;
frag_offset = 0;
page_idx++;
}
/* copy header */
mlx5e_copy_skb_header_mpwqe(rq->pdev, skb, wi, head_page_idx,
head_offset, headlen);
/* skb linear part was allocated with headlen and aligned to long */
skb->tail += headlen;
skb->len += headlen;
}
void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
{
u16 cstrides = mpwrq_get_cqe_consumed_strides(cqe);
u16 wqe_id = be16_to_cpu(cqe->wqe_id);
struct mlx5e_mpw_info *wi = &rq->mpwqe.info[wqe_id];
struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_id);
struct sk_buff *skb;
u16 cqe_bcnt;
wi->consumed_strides += cstrides;
if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) {
rq->stats.wqe_err++;
goto mpwrq_cqe_out;
}
if (unlikely(mpwrq_is_filler_cqe(cqe))) {
rq->stats.mpwqe_filler++;
goto mpwrq_cqe_out;
}
skb = napi_alloc_skb(rq->cq.napi,
ALIGN(MLX5_MPWRQ_SMALL_PACKET_THRESHOLD,
sizeof(long)));
if (unlikely(!skb)) {
rq->stats.buff_alloc_err++;
goto mpwrq_cqe_out;
}
prefetch(skb->data);
cqe_bcnt = mpwrq_get_cqe_byte_cnt(cqe);
mlx5e_mpwqe_fill_rx_skb(rq, cqe, wi, cqe_bcnt, skb);
mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
napi_gro_receive(rq->cq.napi, skb);
mpwrq_cqe_out:
if (likely(wi->consumed_strides < rq->mpwqe_num_strides))
return;
mlx5e_free_rx_mpwqe(rq, wi);
mlx5_wq_ll_pop(&rq->wq, cqe->wqe_id, &wqe->next.next_wqe_index);
}
int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
{
struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
struct mlx5e_sq *xdp_sq = &rq->channel->xdp_sq;
int work_done = 0;
if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
return 0;
if (cq->decmprs_left)
work_done += mlx5e_decompress_cqes_cont(rq, cq, 0, budget);
for (; work_done < budget; work_done++) {
struct mlx5_cqe64 *cqe = mlx5e_get_cqe(cq);
if (!cqe)
break;
if (mlx5_get_cqe_format(cqe) == MLX5_COMPRESSED) {
work_done +=
mlx5e_decompress_cqes_start(rq, cq,
budget - work_done);
continue;
}
mlx5_cqwq_pop(&cq->wq);
rq->handle_rx_cqe(rq, cqe);
}
if (xdp_sq->db.xdp.doorbell) {
mlx5e_xmit_xdp_doorbell(xdp_sq);
xdp_sq->db.xdp.doorbell = false;
}
mlx5_cqwq_update_db_record(&cq->wq);
/* ensure cq space is freed before enabling more cqes */
wmb();
return work_done;
}
|