-
Notifications
You must be signed in to change notification settings - Fork 166
/
ena_netdev.c
5219 lines (4289 loc) · 143 KB
/
ena_netdev.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
// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
/*
* Copyright 2015-2020 Amazon.com, Inc. or its affiliates. All rights reserved.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#ifdef CONFIG_RFS_ACCEL
#include <linux/cpu_rmap.h>
#endif /* CONFIG_RFS_ACCEL */
#include <linux/ethtool.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/numa.h>
#include <linux/pci.h>
#include <linux/utsname.h>
#include <linux/version.h>
#include <linux/vmalloc.h>
#if defined(CONFIG_NET_RX_BUSY_POLL) && (LINUX_VERSION_CODE < KERNEL_VERSION(4,5,0))
#include <net/busy_poll.h>
#endif
#include <net/ip.h>
#include "ena_netdev.h"
#include "ena_pci_id_tbl.h"
#include "ena_sysfs.h"
#include "ena_xdp.h"
#include "ena_lpc.h"
#include "ena_phc.h"
static char version[] = DEVICE_NAME " v" DRV_MODULE_GENERATION "\n";
MODULE_AUTHOR("Amazon.com, Inc. or its affiliates");
MODULE_DESCRIPTION(DEVICE_NAME);
MODULE_LICENSE("GPL");
MODULE_VERSION(DRV_MODULE_GENERATION);
/* Time in jiffies before concluding the transmitter is hung. */
#define TX_TIMEOUT (5 * HZ)
#define ENA_MAX_RINGS min_t(unsigned int, ENA_MAX_NUM_IO_QUEUES, num_possible_cpus())
#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_IFUP | \
NETIF_MSG_IFDOWN | NETIF_MSG_TX_ERR | NETIF_MSG_RX_ERR)
#define ENA_HIGH_LOW_TO_U64(high, low) ((((u64)(high)) << 32) | (low))
#ifndef ENA_LINEAR_FRAG_SUPPORTED
#define ENA_SKB_PULL_MIN_LEN 64
#endif
static int debug = -1;
module_param(debug, int, 0444);
MODULE_PARM_DESC(debug, "Debug level (-1=default,0=none,...,16=all)");
static int rx_queue_size = ENA_DEFAULT_RING_SIZE;
module_param(rx_queue_size, int, 0444);
MODULE_PARM_DESC(rx_queue_size, "Rx queue size. The size should be a power of 2. Depending on instance type, max value can be up to 16K\n");
#define FORCE_LARGE_LLQ_HEADER_UNINIT_VALUE 0xFFFF
static int force_large_llq_header = FORCE_LARGE_LLQ_HEADER_UNINIT_VALUE;
module_param(force_large_llq_header, int, 0444);
MODULE_PARM_DESC(force_large_llq_header, "Increases maximum supported header size in LLQ mode to 224 bytes, while reducing the maximum TX queue size by half.\n");
static int num_io_queues = ENA_MAX_NUM_IO_QUEUES;
module_param(num_io_queues, int, 0444);
MODULE_PARM_DESC(num_io_queues, "Sets number of RX/TX queues to allocate to device. The maximum value depends on the device and number of online CPUs.\n");
static int enable_bql = 0;
module_param(enable_bql, int, 0444);
MODULE_PARM_DESC(enable_bql, "Enable BQL.\n");
static int lpc_size = ENA_LPC_DEFAULT_MULTIPLIER;
module_param(lpc_size, uint, 0444);
MODULE_PARM_DESC(lpc_size, "Each local page cache (lpc) holds N * 1024 pages. This parameter sets N which is rounded up to a multiplier of 2. If zero, the page cache is disabled. Max: 32\n");
#ifdef ENA_PHC_SUPPORT
static int phc_enable = 0;
module_param(phc_enable, uint, 0444);
MODULE_PARM_DESC(phc_enable, "Enable PHC.\n");
#endif /* ENA_PHC_SUPPORT */
static struct ena_aenq_handlers aenq_handlers;
static struct workqueue_struct *ena_wq;
MODULE_DEVICE_TABLE(pci, ena_pci_tbl);
static int ena_rss_init_default(struct ena_adapter *adapter);
static void check_for_admin_com_state(struct ena_adapter *adapter);
static void ena_set_dev_offloads(struct ena_com_dev_get_features_ctx *feat,
struct net_device *netdev);
static void ena_tx_timeout(struct net_device *dev, unsigned int txqueue)
{
enum ena_regs_reset_reason_types reset_reason = ENA_REGS_RESET_OS_NETDEV_WD;
struct ena_adapter *adapter = netdev_priv(dev);
unsigned int time_since_last_napi, threshold;
unsigned long jiffies_since_last_intr;
struct ena_ring *tx_ring;
int napi_scheduled;
if (txqueue >= adapter->num_io_queues) {
netdev_err(dev, "TX timeout on invalid queue %u\n", txqueue);
goto schedule_reset;
}
threshold = jiffies_to_usecs(dev->watchdog_timeo);
tx_ring = &adapter->tx_ring[txqueue];
time_since_last_napi = jiffies_to_usecs(jiffies - tx_ring->tx_stats.last_napi_jiffies);
napi_scheduled = !!(tx_ring->napi->state & NAPIF_STATE_SCHED);
jiffies_since_last_intr = jiffies - READ_ONCE(adapter->ena_napi[txqueue].last_intr_jiffies);
netdev_err(dev,
"TX q %d is paused for too long (threshold %u). Time since last napi %u usec. napi scheduled: %d. msecs since last interrupt: %u\n",
txqueue,
threshold,
time_since_last_napi,
napi_scheduled,
jiffies_to_msecs(jiffies_since_last_intr));
if (threshold < time_since_last_napi && napi_scheduled) {
netdev_err(dev,
"napi handler hasn't been called for a long time but is scheduled\n");
reset_reason = ENA_REGS_RESET_SUSPECTED_POLL_STARVATION;
}
schedule_reset:
/* Change the state of the device to trigger reset
* Check that we are not in the middle or a trigger already
*/
if (test_and_set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))
return;
ena_reset_device(adapter, reset_reason);
ena_increase_stat(&adapter->dev_stats.tx_timeout, 1, &adapter->syncp);
}
#ifndef HAVE_NDO_TX_TIMEOUT_STUCK_QUEUE_PARAMETER
/* This function is called by the kernel's watchdog and indicates that the queue
* has been closed longer than dev->watchdog_timeo value allows.
* In older kernels the called function doesn't contain the id of the queue
* that's been closed for too long. This helper function retrieves this
* information
*/
static void ena_find_and_timeout_queue(struct net_device *dev)
{
struct ena_adapter *adapter = netdev_priv(dev);
unsigned long trans_start;
struct netdev_queue *txq;
unsigned int i;
for (i = 0; i < dev->num_tx_queues; i++) {
txq = netdev_get_tx_queue(dev, i);
trans_start = txq->trans_start;
if (netif_xmit_stopped(txq) &&
time_after(jiffies, (trans_start + dev->watchdog_timeo))) {
ena_tx_timeout(dev, i);
return;
}
}
netdev_warn(dev, "timeout was called, but no offending queue was found\n");
/* Change the state of the device to trigger reset
* Check that we are not in the middle or a trigger already
*/
if (test_and_set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))
return;
ena_reset_device(adapter, ENA_REGS_RESET_OS_NETDEV_WD);
ena_increase_stat(&adapter->dev_stats.tx_timeout, 1, &adapter->syncp);
}
#endif
static void update_rx_ring_mtu(struct ena_adapter *adapter, int mtu)
{
int i;
for (i = 0; i < adapter->num_io_queues; i++)
adapter->rx_ring[i].mtu = mtu;
}
static int ena_change_mtu(struct net_device *dev, int new_mtu)
{
struct ena_adapter *adapter = netdev_priv(dev);
int ret;
#ifndef HAVE_MTU_MIN_MAX_IN_NET_DEVICE
if ((new_mtu > adapter->max_mtu) || (new_mtu < ENA_MIN_MTU)) {
netif_err(adapter, drv, dev,
"Invalid MTU setting. new_mtu: %d max mtu: %d min mtu: %d\n",
new_mtu, adapter->max_mtu, ENA_MIN_MTU);
return -EINVAL;
}
#endif
ret = ena_com_set_dev_mtu(adapter->ena_dev, new_mtu);
if (!ret) {
netif_dbg(adapter, drv, dev, "Set MTU to %d\n", new_mtu);
update_rx_ring_mtu(adapter, new_mtu);
dev->mtu = new_mtu;
} else {
netif_err(adapter, drv, dev, "Failed to set MTU to %d\n",
new_mtu);
}
return ret;
}
int ena_xmit_common(struct ena_adapter *adapter,
struct ena_ring *ring,
struct ena_tx_buffer *tx_info,
struct ena_com_tx_ctx *ena_tx_ctx,
u16 next_to_use,
u32 bytes)
{
int rc, nb_hw_desc;
if (unlikely(ena_com_is_doorbell_needed(ring->ena_com_io_sq,
ena_tx_ctx))) {
netif_dbg(adapter, tx_queued, adapter->netdev,
"llq tx max burst size of queue %d achieved, writing doorbell to send burst\n",
ring->qid);
ena_ring_tx_doorbell(ring);
}
/* prepare the packet's descriptors to dma engine */
rc = ena_com_prepare_tx(ring->ena_com_io_sq, ena_tx_ctx,
&nb_hw_desc);
/* In case there isn't enough space in the queue for the packet,
* we simply drop it. All other failure reasons of
* ena_com_prepare_tx() are fatal and therefore require a device reset.
*/
if (unlikely(rc)) {
netif_err(adapter, tx_queued, adapter->netdev,
"Failed to prepare tx bufs\n");
ena_increase_stat(&ring->tx_stats.prepare_ctx_err, 1, &ring->syncp);
if (rc != -ENOMEM)
ena_reset_device(adapter, ENA_REGS_RESET_DRIVER_INVALID_STATE);
return rc;
}
u64_stats_update_begin(&ring->syncp);
ring->tx_stats.cnt++;
ring->tx_stats.bytes += bytes;
u64_stats_update_end(&ring->syncp);
tx_info->tx_descs = nb_hw_desc;
tx_info->total_tx_size = bytes;
tx_info->tx_sent_jiffies = jiffies;
tx_info->print_once = 0;
ring->next_to_use = ENA_TX_RING_IDX_NEXT(next_to_use,
ring->ring_size);
return 0;
}
static int ena_init_rx_cpu_rmap(struct ena_adapter *adapter)
{
#ifdef CONFIG_RFS_ACCEL
u32 i;
int rc;
adapter->netdev->rx_cpu_rmap = alloc_irq_cpu_rmap(adapter->num_io_queues);
if (!adapter->netdev->rx_cpu_rmap)
return -ENOMEM;
for (i = 0; i < adapter->num_io_queues; i++) {
int irq_idx = ENA_IO_IRQ_IDX(i);
rc = irq_cpu_rmap_add(adapter->netdev->rx_cpu_rmap,
#if LINUX_VERSION_CODE < KERNEL_VERSION(4, 8, 0)
adapter->msix_entries[irq_idx].vector);
#else
pci_irq_vector(adapter->pdev, irq_idx));
#endif
if (rc) {
free_irq_cpu_rmap(adapter->netdev->rx_cpu_rmap);
adapter->netdev->rx_cpu_rmap = NULL;
return rc;
}
}
#endif /* CONFIG_RFS_ACCEL */
return 0;
}
static void ena_init_io_rings_common(struct ena_adapter *adapter,
struct ena_ring *ring, u16 qid)
{
ring->qid = qid;
ring->pdev = adapter->pdev;
ring->dev = &adapter->pdev->dev;
ring->netdev = adapter->netdev;
ring->napi = &adapter->ena_napi[qid].napi;
ring->adapter = adapter;
ring->ena_dev = adapter->ena_dev;
ring->per_napi_packets = 0;
ring->cpu = 0;
ring->numa_node = 0;
ring->no_interrupt_event_cnt = 0;
u64_stats_init(&ring->syncp);
}
void ena_init_io_rings(struct ena_adapter *adapter,
int first_index, int count)
{
struct ena_com_dev *ena_dev;
struct ena_ring *txr, *rxr;
int i;
ena_dev = adapter->ena_dev;
for (i = first_index; i < first_index + count; i++) {
txr = &adapter->tx_ring[i];
rxr = &adapter->rx_ring[i];
/* TX common ring state */
ena_init_io_rings_common(adapter, txr, i);
/* TX specific ring state */
txr->ring_size = adapter->requested_tx_ring_size;
txr->tx_max_header_size = ena_dev->tx_max_header_size;
txr->tx_mem_queue_type = ena_dev->tx_mem_queue_type;
txr->sgl_size = adapter->max_tx_sgl_size;
txr->enable_bql = enable_bql;
txr->interrupt_interval =
ena_com_get_nonadaptive_moderation_interval_tx(ena_dev);
/* Initial value, mark as true */
txr->interrupt_interval_changed = true;
txr->disable_meta_caching = adapter->disable_meta_caching;
#ifdef ENA_XDP_SUPPORT
spin_lock_init(&txr->xdp_tx_lock);
#endif
/* Don't init RX queues for xdp queues */
if (!ENA_IS_XDP_INDEX(adapter, i)) {
/* RX common ring state */
ena_init_io_rings_common(adapter, rxr, i);
/* RX specific ring state */
rxr->ring_size = adapter->requested_rx_ring_size;
rxr->rx_copybreak = adapter->rx_copybreak;
rxr->sgl_size = adapter->max_rx_sgl_size;
rxr->interrupt_interval =
ena_com_get_nonadaptive_moderation_interval_rx(ena_dev);
/* Initial value, mark as true */
rxr->interrupt_interval_changed = true;
rxr->empty_rx_queue = 0;
rxr->rx_headroom = NET_SKB_PAD;
adapter->ena_napi[i].dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
#ifdef ENA_XDP_SUPPORT
rxr->xdp_ring = &adapter->tx_ring[i + adapter->num_io_queues];
#endif
}
}
}
/* ena_setup_tx_resources - allocate I/O Tx resources (Descriptors)
* @adapter: network interface device structure
* @qid: queue index
*
* Return 0 on success, negative on failure
*/
static int ena_setup_tx_resources(struct ena_adapter *adapter, int qid)
{
struct ena_ring *tx_ring = &adapter->tx_ring[qid];
struct ena_irq *ena_irq = &adapter->irq_tbl[ENA_IO_IRQ_IDX(qid)];
int size, i, node;
if (tx_ring->tx_buffer_info) {
netif_err(adapter, ifup,
adapter->netdev, "tx_buffer_info info is not NULL");
return -EEXIST;
}
size = sizeof(struct ena_tx_buffer) * tx_ring->ring_size;
node = cpu_to_node(ena_irq->cpu);
tx_ring->tx_buffer_info = vzalloc_node(size, node);
if (!tx_ring->tx_buffer_info) {
tx_ring->tx_buffer_info = vzalloc(size);
if (!tx_ring->tx_buffer_info)
goto err_tx_buffer_info;
}
size = sizeof(u16) * tx_ring->ring_size;
tx_ring->free_ids = vzalloc_node(size, node);
if (!tx_ring->free_ids) {
tx_ring->free_ids = vzalloc(size);
if (!tx_ring->free_ids)
goto err_tx_free_ids;
}
size = tx_ring->tx_max_header_size;
tx_ring->push_buf_intermediate_buf = vzalloc_node(size, node);
if (!tx_ring->push_buf_intermediate_buf) {
tx_ring->push_buf_intermediate_buf = vzalloc(size);
if (!tx_ring->push_buf_intermediate_buf)
goto err_push_buf_intermediate_buf;
}
/* Req id ring for TX out of order completions */
for (i = 0; i < tx_ring->ring_size; i++)
tx_ring->free_ids[i] = i;
/* Reset tx statistics */
memset(&tx_ring->tx_stats, 0x0, sizeof(tx_ring->tx_stats));
tx_ring->next_to_use = 0;
tx_ring->next_to_clean = 0;
tx_ring->cpu = ena_irq->cpu;
tx_ring->numa_node = node;
return 0;
err_push_buf_intermediate_buf:
vfree(tx_ring->free_ids);
tx_ring->free_ids = NULL;
err_tx_free_ids:
vfree(tx_ring->tx_buffer_info);
tx_ring->tx_buffer_info = NULL;
err_tx_buffer_info:
return -ENOMEM;
}
/* ena_free_tx_resources - Free I/O Tx Resources per Queue
* @adapter: network interface device structure
* @qid: queue index
*
* Free all transmit software resources
*/
static void ena_free_tx_resources(struct ena_adapter *adapter, int qid)
{
struct ena_ring *tx_ring = &adapter->tx_ring[qid];
vfree(tx_ring->tx_buffer_info);
tx_ring->tx_buffer_info = NULL;
vfree(tx_ring->free_ids);
tx_ring->free_ids = NULL;
vfree(tx_ring->push_buf_intermediate_buf);
tx_ring->push_buf_intermediate_buf = NULL;
}
int ena_setup_tx_resources_in_range(struct ena_adapter *adapter,
int first_index, int count)
{
int i, rc = 0;
for (i = first_index; i < first_index + count; i++) {
rc = ena_setup_tx_resources(adapter, i);
if (rc)
goto err_setup_tx;
}
return 0;
err_setup_tx:
netif_err(adapter, ifup, adapter->netdev,
"Tx queue %d: allocation failed\n", i);
/* rewind the index freeing the rings as we go */
while (first_index < i--)
ena_free_tx_resources(adapter, i);
return rc;
}
void ena_free_all_io_tx_resources_in_range(struct ena_adapter *adapter,
int first_index, int count)
{
int i;
for (i = first_index; i < first_index + count; i++)
ena_free_tx_resources(adapter, i);
}
/* ena_free_all_io_tx_resources - Free I/O Tx Resources for All Queues
* @adapter: board private structure
*
* Free all transmit software resources
*/
void ena_free_all_io_tx_resources(struct ena_adapter *adapter)
{
ena_free_all_io_tx_resources_in_range(adapter,
0,
adapter->xdp_num_queues +
adapter->num_io_queues);
}
/* ena_setup_rx_resources - allocate I/O Rx resources (Descriptors)
* @adapter: network interface device structure
* @qid: queue index
*
* Returns 0 on success, negative on failure
*/
static int ena_setup_rx_resources(struct ena_adapter *adapter,
u32 qid)
{
struct ena_ring *rx_ring = &adapter->rx_ring[qid];
struct ena_irq *ena_irq = &adapter->irq_tbl[ENA_IO_IRQ_IDX(qid)];
int size, node, i;
if (rx_ring->rx_buffer_info) {
netif_err(adapter, ifup, adapter->netdev,
"rx_buffer_info is not NULL");
return -EEXIST;
}
/* alloc extra element so in rx path
* we can always prefetch rx_info + 1
*/
size = sizeof(struct ena_rx_buffer) * (rx_ring->ring_size + 1);
node = cpu_to_node(ena_irq->cpu);
rx_ring->rx_buffer_info = vzalloc_node(size, node);
if (!rx_ring->rx_buffer_info) {
rx_ring->rx_buffer_info = vzalloc(size);
if (!rx_ring->rx_buffer_info)
return -ENOMEM;
}
size = sizeof(u16) * rx_ring->ring_size;
rx_ring->free_ids = vzalloc_node(size, node);
if (!rx_ring->free_ids) {
rx_ring->free_ids = vzalloc(size);
if (!rx_ring->free_ids) {
vfree(rx_ring->rx_buffer_info);
rx_ring->rx_buffer_info = NULL;
return -ENOMEM;
}
}
/* Req id ring for receiving RX pkts out of order */
for (i = 0; i < rx_ring->ring_size; i++)
rx_ring->free_ids[i] = i;
/* Reset rx statistics */
memset(&rx_ring->rx_stats, 0x0, sizeof(rx_ring->rx_stats));
#ifdef ENA_BUSY_POLL_SUPPORT
ena_bp_init_lock(rx_ring);
#endif
rx_ring->next_to_clean = 0;
rx_ring->next_to_use = 0;
rx_ring->cpu = ena_irq->cpu;
rx_ring->numa_node = node;
return 0;
}
/* ena_free_rx_resources - Free I/O Rx Resources
* @adapter: network interface device structure
* @qid: queue index
*
* Free all receive software resources
*/
static void ena_free_rx_resources(struct ena_adapter *adapter,
u32 qid)
{
struct ena_ring *rx_ring = &adapter->rx_ring[qid];
vfree(rx_ring->rx_buffer_info);
rx_ring->rx_buffer_info = NULL;
vfree(rx_ring->free_ids);
rx_ring->free_ids = NULL;
}
/* ena_setup_all_rx_resources - allocate I/O Rx queues resources for all queues
* @adapter: board private structure
*
* Return 0 on success, negative on failure
*/
static int ena_setup_all_rx_resources(struct ena_adapter *adapter)
{
int i, rc = 0;
for (i = 0; i < adapter->num_io_queues; i++) {
rc = ena_setup_rx_resources(adapter, i);
if (rc)
goto err_setup_rx;
}
return 0;
err_setup_rx:
netif_err(adapter, ifup, adapter->netdev,
"Rx queue %d: allocation failed\n", i);
/* rewind the index freeing the rings as we go */
while (i--)
ena_free_rx_resources(adapter, i);
return rc;
}
/* ena_free_all_io_rx_resources - Free I/O Rx Resources for All Queues
* @adapter: board private structure
*
* Free all receive software resources
*/
static void ena_free_all_io_rx_resources(struct ena_adapter *adapter)
{
int i;
for (i = 0; i < adapter->num_io_queues; i++)
ena_free_rx_resources(adapter, i);
}
struct page *ena_alloc_map_page(struct ena_ring *rx_ring,
dma_addr_t *dma)
{
struct page *page;
/* This would allocate the page on the same NUMA node the executing code
* is running on.
*/
page = dev_alloc_page();
if (!page) {
ena_increase_stat(&rx_ring->rx_stats.page_alloc_fail, 1, &rx_ring->syncp);
return ERR_PTR(-ENOSPC);
}
/* To enable NIC-side port-mirroring, AKA SPAN port,
* we make the buffer readable from the nic as well
*/
*dma = dma_map_page(rx_ring->dev, page, 0, ENA_PAGE_SIZE,
DMA_BIDIRECTIONAL);
if (unlikely(dma_mapping_error(rx_ring->dev, *dma))) {
ena_increase_stat(&rx_ring->rx_stats.dma_mapping_err, 1,
&rx_ring->syncp);
__free_page(page);
return ERR_PTR(-EIO);
}
return page;
}
static int ena_alloc_rx_buffer(struct ena_ring *rx_ring,
struct ena_rx_buffer *rx_info)
{
int headroom = rx_ring->rx_headroom;
struct ena_com_buf *ena_buf;
struct page *page;
dma_addr_t dma;
int tailroom;
/* restore page offset value in case it has been changed by device */
rx_info->buf_offset = headroom;
/* if previous allocated page is not used */
if (unlikely(rx_info->page))
return 0;
#ifdef ENA_AF_XDP_SUPPORT
if (unlikely(ENA_IS_XSK_RING(rx_ring))) {
struct xdp_buff *xdp;
xdp = xsk_buff_alloc(rx_ring->xsk_pool);
if (!xdp)
return -ENOMEM;
ena_buf = &rx_info->ena_buf;
ena_buf->paddr = xsk_buff_xdp_get_dma(xdp);
ena_buf->len = xsk_pool_get_rx_frame_size(rx_ring->xsk_pool);
rx_info->xdp = xdp;
return 0;
}
#endif /* ENA_AF_XDP_SUPPORT */
/* We handle DMA here */
page = ena_lpc_get_page(rx_ring, &dma, &rx_info->is_lpc_page);
if (unlikely(IS_ERR(page)))
return PTR_ERR(page);
netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev,
"Allocate page %p, rx_info %p\n", page, rx_info);
tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
rx_info->page = page;
rx_info->dma_addr = dma;
rx_info->page_offset = 0;
ena_buf = &rx_info->ena_buf;
ena_buf->paddr = dma + headroom;
ena_buf->len = ENA_PAGE_SIZE - headroom - tailroom;
return 0;
}
static void ena_unmap_rx_buff_attrs(struct ena_ring *rx_ring,
struct ena_rx_buffer *rx_info,
unsigned long attrs)
{
/* LPC pages are unmapped at cache destruction */
if (rx_info->is_lpc_page)
return;
ena_dma_unmap_page_attrs(rx_ring->dev, rx_info->dma_addr, ENA_PAGE_SIZE,
DMA_BIDIRECTIONAL, attrs);
}
static void ena_free_rx_page(struct ena_ring *rx_ring,
struct ena_rx_buffer *rx_info)
{
struct page *page = rx_info->page;
if (unlikely(!page)) {
netif_warn(rx_ring->adapter, rx_err, rx_ring->netdev,
"Trying to free unallocated buffer\n");
return;
}
ena_unmap_rx_buff_attrs(rx_ring, rx_info, 0);
__free_page(page);
rx_info->page = NULL;
}
int ena_refill_rx_bufs(struct ena_ring *rx_ring, u32 num)
{
u16 next_to_use, req_id;
u32 i;
int rc;
next_to_use = rx_ring->next_to_use;
for (i = 0; i < num; i++) {
struct ena_rx_buffer *rx_info;
req_id = rx_ring->free_ids[next_to_use];
rx_info = &rx_ring->rx_buffer_info[req_id];
rc = ena_alloc_rx_buffer(rx_ring, rx_info);
if (unlikely(rc < 0)) {
#ifdef ENA_AF_XDP_SUPPORT
if (ENA_IS_XSK_RING(rx_ring))
break;
#endif /* ENA_AF_XDP_SUPPORT */
netif_warn(rx_ring->adapter, rx_err, rx_ring->netdev,
"Failed to allocate buffer for rx queue %d\n",
rx_ring->qid);
break;
}
rc = ena_com_add_single_rx_desc(rx_ring->ena_com_io_sq,
&rx_info->ena_buf,
req_id);
if (unlikely(rc)) {
netif_warn(rx_ring->adapter, rx_status, rx_ring->netdev,
"Failed to add buffer for rx queue %d\n",
rx_ring->qid);
break;
}
next_to_use = ENA_RX_RING_IDX_NEXT(next_to_use,
rx_ring->ring_size);
}
if (unlikely(i < num)) {
ena_increase_stat(&rx_ring->rx_stats.refil_partial, 1,
&rx_ring->syncp);
#ifdef ENA_AF_XDP_SUPPORT
if (ENA_IS_XSK_RING(rx_ring))
goto ring_doorbell;
#endif /* ENA_AF_XDP_SUPPORT */
netif_warn(rx_ring->adapter, rx_err, rx_ring->netdev,
"Refilled rx qid %d with only %d buffers (from %d)\n",
rx_ring->qid, i, num);
}
#ifdef ENA_AF_XDP_SUPPORT
ring_doorbell:
#endif /* ENA_AF_XDP_SUPPORT */
/* ena_com_write_sq_doorbell issues a wmb() */
if (likely(i))
ena_com_write_sq_doorbell(rx_ring->ena_com_io_sq);
rx_ring->next_to_use = next_to_use;
return i;
}
static void ena_free_rx_bufs(struct ena_adapter *adapter,
u32 qid)
{
struct ena_ring *rx_ring = &adapter->rx_ring[qid];
u32 i;
#ifdef ENA_AF_XDP_SUPPORT
if (ENA_IS_XSK_RING(rx_ring)) {
ena_xdp_free_rx_bufs_zc(rx_ring);
return;
}
#endif /* ENA_AF_XDP_SUPPORT */
for (i = 0; i < rx_ring->ring_size; i++) {
struct ena_rx_buffer *rx_info = &rx_ring->rx_buffer_info[i];
if (rx_info->page)
ena_free_rx_page(rx_ring, rx_info);
}
}
/* ena_refill_all_rx_bufs - allocate all queues Rx buffers
* @adapter: board private structure
*/
static void ena_refill_all_rx_bufs(struct ena_adapter *adapter)
{
struct ena_ring *rx_ring;
int i, rc, bufs_num;
for (i = 0; i < adapter->num_io_queues; i++) {
rx_ring = &adapter->rx_ring[i];
bufs_num = rx_ring->ring_size - 1;
rc = ena_refill_rx_bufs(rx_ring, bufs_num);
if (unlikely(rc != bufs_num))
netif_warn(rx_ring->adapter, rx_status, rx_ring->netdev,
"Refilling Queue %d failed. allocated %d buffers from: %d\n",
i, rc, bufs_num);
}
}
static void ena_free_all_rx_bufs(struct ena_adapter *adapter)
{
int i;
for (i = 0; i < adapter->num_io_queues; i++)
ena_free_rx_bufs(adapter, i);
}
void ena_unmap_tx_buff(struct ena_ring *tx_ring,
struct ena_tx_buffer *tx_info)
{
struct ena_com_buf *ena_buf;
u32 cnt;
int i;
ena_buf = tx_info->bufs;
cnt = tx_info->num_of_bufs;
if (unlikely(!cnt))
return;
if (tx_info->map_linear_data) {
dma_unmap_single(tx_ring->dev,
dma_unmap_addr(ena_buf, paddr),
dma_unmap_len(ena_buf, len),
DMA_TO_DEVICE);
ena_buf++;
cnt--;
}
/* unmap remaining mapped pages */
for (i = 0; i < cnt; i++) {
dma_unmap_page(tx_ring->dev, dma_unmap_addr(ena_buf, paddr),
dma_unmap_len(ena_buf, len), DMA_TO_DEVICE);
ena_buf++;
}
}
/* ena_free_tx_bufs - Free Tx Buffers per Queue
* @tx_ring: TX ring for which buffers be freed
*/
static void ena_free_tx_bufs(struct ena_ring *tx_ring)
{
bool print_once = true;
bool is_xdp_ring;
u32 i;
is_xdp_ring = ENA_IS_XDP_INDEX(tx_ring->adapter, tx_ring->qid);
for (i = 0; i < tx_ring->ring_size; i++) {
struct ena_tx_buffer *tx_info = &tx_ring->tx_buffer_info[i];
unsigned long jiffies_since_submitted;
if (!tx_info->skb)
continue;
jiffies_since_submitted = jiffies - tx_info->tx_sent_jiffies;
if (print_once) {
netif_notice(tx_ring->adapter, ifdown, tx_ring->netdev,
"Free uncompleted tx skb qid %d, idx 0x%x, %u msecs since submission\n",
tx_ring->qid, i, jiffies_to_msecs(jiffies_since_submitted));
print_once = false;
} else {
netif_dbg(tx_ring->adapter, ifdown, tx_ring->netdev,
"Free uncompleted tx skb qid %d, idx 0x%x, %u msecs since submission\n",
tx_ring->qid, i, jiffies_to_msecs(jiffies_since_submitted));
}
ena_unmap_tx_buff(tx_ring, tx_info);
if (is_xdp_ring)
xdp_return_frame(tx_info->xdpf);
else
dev_kfree_skb_any(tx_info->skb);
}
if (!is_xdp_ring)
netdev_tx_reset_queue(netdev_get_tx_queue(tx_ring->netdev,
tx_ring->qid));
}
static void ena_free_all_tx_bufs(struct ena_adapter *adapter)
{
struct ena_ring *tx_ring;
int i;
for (i = 0; i < adapter->num_io_queues + adapter->xdp_num_queues; i++) {
tx_ring = &adapter->tx_ring[i];
#ifdef ENA_AF_XDP_SUPPORT
if (ENA_IS_XSK_RING(tx_ring)) {
ena_xdp_free_tx_bufs_zc(tx_ring);
continue;
}
#endif /* ENA_AF_XDP_SUPPORT */
ena_free_tx_bufs(tx_ring);
}
}
static void ena_destroy_all_tx_queues(struct ena_adapter *adapter)
{
u16 ena_qid;
int i;
for (i = 0; i < adapter->num_io_queues + adapter->xdp_num_queues; i++) {
ena_qid = ENA_IO_TXQ_IDX(i);
ena_com_destroy_io_queue(adapter->ena_dev, ena_qid);
}
}
static void ena_destroy_all_rx_queues(struct ena_adapter *adapter)
{
u16 ena_qid;
int i;
for (i = 0; i < adapter->num_io_queues; i++) {
ena_qid = ENA_IO_RXQ_IDX(i);
cancel_work_sync(&adapter->ena_napi[i].dim.work);
ena_xdp_unregister_rxq_info(&adapter->rx_ring[i]);
ena_com_destroy_io_queue(adapter->ena_dev, ena_qid);
}
}
static void ena_destroy_all_io_queues(struct ena_adapter *adapter)
{
ena_destroy_all_tx_queues(adapter);
ena_destroy_all_rx_queues(adapter);
}
int handle_invalid_req_id(struct ena_ring *ring, u16 req_id,
struct ena_tx_buffer *tx_info, bool is_xdp)
{
if (tx_info)
netif_err(ring->adapter,
tx_done,
ring->netdev,
"tx_info doesn't have valid %s. qid %u req_id %u",
is_xdp ? "xdp frame" : "skb", ring->qid, req_id);
else
netif_err(ring->adapter,
tx_done,
ring->netdev,
"Invalid req_id %u in qid %u\n",
req_id, ring->qid);
ena_increase_stat(&ring->tx_stats.bad_req_id, 1, &ring->syncp);
ena_reset_device(ring->adapter, ENA_REGS_RESET_INV_TX_REQ_ID);
return -EFAULT;
}
static int validate_tx_req_id(struct ena_ring *tx_ring, u16 req_id)
{
struct ena_tx_buffer *tx_info;
tx_info = &tx_ring->tx_buffer_info[req_id];
if (likely(tx_info->skb))
return 0;
return handle_invalid_req_id(tx_ring, req_id, tx_info, false);
}
static int ena_clean_tx_irq(struct ena_ring *tx_ring, u32 budget)
{
struct netdev_queue *txq;
bool above_thresh;
u32 tx_bytes = 0;
u32 total_done = 0;
u16 next_to_clean;
u16 req_id;