summaryrefslogtreecommitdiffstats
path: root/drivers/net/ethernet/netronome/nfp/nfp_net.h
blob: da33f09facb916db18966cf457fabf202135979e (plain)
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-only OR BSD-2-Clause) */
/* Copyright (C) 2015-2018 Netronome Systems, Inc. */

/*
 * nfp_net.h
 * Declarations for Netronome network device driver.
 * Authors: Jakub Kicinski <jakub.kicinski@netronome.com>
 *          Jason McMullan <jason.mcmullan@netronome.com>
 *          Rolf Neugebauer <rolf.neugebauer@netronome.com>
 */

#ifndef _NFP_NET_H_
#define _NFP_NET_H_

#include <linux/atomic.h>
#include <linux/interrupt.h>
#include <linux/list.h>
#include <linux/netdevice.h>
#include <linux/pci.h>
#include <linux/dim.h>
#include <linux/io-64-nonatomic-hi-lo.h>
#include <linux/semaphore.h>
#include <linux/workqueue.h>
#include <net/xdp.h>

#include "nfp_net_ctrl.h"

#define nn_pr(nn, lvl, fmt, args...)					\
	({								\
		struct nfp_net *__nn = (nn);				\
									\
		if (__nn->dp.netdev)					\
			netdev_printk(lvl, __nn->dp.netdev, fmt, ## args); \
		else							\
			dev_printk(lvl, __nn->dp.dev, "ctrl: " fmt, ## args); \
	})

#define nn_err(nn, fmt, args...)	nn_pr(nn, KERN_ERR, fmt, ## args)
#define nn_warn(nn, fmt, args...)	nn_pr(nn, KERN_WARNING, fmt, ## args)
#define nn_info(nn, fmt, args...)	nn_pr(nn, KERN_INFO, fmt, ## args)
#define nn_dbg(nn, fmt, args...)	nn_pr(nn, KERN_DEBUG, fmt, ## args)

#define nn_dp_warn(dp, fmt, args...)					\
	({								\
		struct nfp_net_dp *__dp = (dp);				\
									\
		if (unlikely(net_ratelimit())) {			\
			if (__dp->netdev)				\
				netdev_warn(__dp->netdev, fmt, ## args); \
			else						\
				dev_warn(__dp->dev, fmt, ## args);	\
		}							\
	})

/* Max time to wait for NFP to respond on updates (in seconds) */
#define NFP_NET_POLL_TIMEOUT	5

/* Interval for reading offloaded filter stats */
#define NFP_NET_STAT_POLL_IVL	msecs_to_jiffies(100)

/* Bar allocation */
#define NFP_NET_CTRL_BAR	0
#define NFP_NET_Q0_BAR		2
#define NFP_NET_Q1_BAR		4	/* OBSOLETE */

/* Default size for MTU and freelist buffer sizes */
#define NFP_NET_DEFAULT_MTU		1500U

/* Maximum number of bytes prepended to a packet */
#define NFP_NET_MAX_PREPEND		64

/* Interrupt definitions */
#define NFP_NET_NON_Q_VECTORS		2
#define NFP_NET_IRQ_LSC_IDX		0
#define NFP_NET_IRQ_EXN_IDX		1
#define NFP_NET_MIN_VNIC_IRQS		(NFP_NET_NON_Q_VECTORS + 1)

/* Queue/Ring definitions */
#define NFP_NET_MAX_TX_RINGS	64	/* Max. # of Tx rings per device */
#define NFP_NET_MAX_RX_RINGS	64	/* Max. # of Rx rings per device */
#define NFP_NET_MAX_R_VECS	(NFP_NET_MAX_TX_RINGS > NFP_NET_MAX_RX_RINGS ? \
				 NFP_NET_MAX_TX_RINGS : NFP_NET_MAX_RX_RINGS)
#define NFP_NET_MAX_IRQS	(NFP_NET_NON_Q_VECTORS + NFP_NET_MAX_R_VECS)

#define NFP_NET_TX_DESCS_DEFAULT 4096	/* Default # of Tx descs per ring */
#define NFP_NET_RX_DESCS_DEFAULT 4096	/* Default # of Rx descs per ring */

#define NFP_NET_FL_BATCH	16	/* Add freelist in this Batch size */
#define NFP_NET_XDP_MAX_COMPLETE 2048	/* XDP bufs to reclaim in NAPI poll */

/* MC definitions */
#define NFP_NET_CFG_MAC_MC_MAX	1024	/* The maximum number of MC address per port*/

/* Offload definitions */
#define NFP_NET_N_VXLAN_PORTS	(NFP_NET_CFG_VXLAN_SZ / sizeof(__be16))

#define NFP_NET_RX_BUF_HEADROOM	(NET_SKB_PAD + NET_IP_ALIGN)
#define NFP_NET_RX_BUF_NON_DATA	(NFP_NET_RX_BUF_HEADROOM +		\
				 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))

/* Forward declarations */
struct nfp_cpp;
struct nfp_dev_info;
struct nfp_dp_ops;
struct nfp_eth_table_port;
struct nfp_net;
struct nfp_net_r_vector;
struct nfp_port;
struct xsk_buff_pool;

struct nfp_nfd3_tx_desc;
struct nfp_nfd3_tx_buf;

struct nfp_nfdk_tx_desc;
struct nfp_nfdk_tx_buf;

/* Convenience macro for wrapping descriptor index on ring size */
#define D_IDX(ring, idx)	((idx) & ((ring)->cnt - 1))

/* Convenience macro for writing dma address into RX/TX descriptors */
#define nfp_desc_set_dma_addr_40b(desc, dma_addr)			\
	do {								\
		__typeof__(desc) __d = (desc);				\
		dma_addr_t __addr = (dma_addr);				\
									\
		__d->dma_addr_lo = cpu_to_le32(lower_32_bits(__addr));	\
		__d->dma_addr_hi = upper_32_bits(__addr) & 0xff;	\
	} while (0)

#define nfp_desc_set_dma_addr_48b(desc, dma_addr)			\
	do {								\
		__typeof__(desc) __d = (desc);				\
		dma_addr_t __addr = (dma_addr);				\
									\
		__d->dma_addr_hi = cpu_to_le16(upper_32_bits(__addr));	\
		__d->dma_addr_lo = cpu_to_le32(lower_32_bits(__addr));	\
	} while (0)

/**
 * struct nfp_net_tx_ring - TX ring structure
 * @r_vec:      Back pointer to ring vector structure
 * @idx:        Ring index from Linux's perspective
 * @data_pending: number of bytes added to current block (NFDK only)
 * @qcp_q:      Pointer to base of the QCP TX queue
 * @txrwb:	TX pointer write back area
 * @cnt:        Size of the queue in number of descriptors
 * @wr_p:       TX ring write pointer (free running)
 * @rd_p:       TX ring read pointer (free running)
 * @qcp_rd_p:   Local copy of QCP TX queue read pointer
 * @wr_ptr_add:	Accumulated number of buffers to add to QCP write pointer
 *		(used for .xmit_more delayed kick)
 * @txbufs:	Array of transmitted TX buffers, to free on transmit (NFD3)
 * @ktxbufs:	Array of transmitted TX buffers, to free on transmit (NFDK)
 * @txds:	Virtual address of TX ring in host memory (NFD3)
 * @ktxds:	Virtual address of TX ring in host memory (NFDK)
 *
 * @qcidx:      Queue Controller Peripheral (QCP) queue index for the TX queue
 * @dma:        DMA address of the TX ring
 * @size:       Size, in bytes, of the TX ring (needed to free)
 * @is_xdp:	Is this a XDP TX ring?
 */
struct nfp_net_tx_ring {
	struct nfp_net_r_vector *r_vec;

	u16 idx;
	u16 data_pending;
	u8 __iomem *qcp_q;
	u64 *txrwb;

	u32 cnt;
	u32 wr_p;
	u32 rd_p;
	u32 qcp_rd_p;

	u32 wr_ptr_add;

	union {
		struct nfp_nfd3_tx_buf *txbufs;
		struct nfp_nfdk_tx_buf *ktxbufs;
	};
	union {
		struct nfp_nfd3_tx_desc *txds;
		struct nfp_nfdk_tx_desc *ktxds;
	};

	/* Cold data follows */
	int qcidx;

	dma_addr_t dma;
	size_t size;
	bool is_xdp;
} ____cacheline_aligned;

/* RX and freelist descriptor format */

#define PCIE_DESC_RX_DD			BIT(7)
#define PCIE_DESC_RX_META_LEN_MASK	GENMASK(6, 0)

/* Flags in the RX descriptor */
#define PCIE_DESC_RX_RSS		cpu_to_le16(BIT(15))
#define PCIE_DESC_RX_I_IP4_CSUM		cpu_to_le16(BIT(14))
#define PCIE_DESC_RX_I_IP4_CSUM_OK	cpu_to_le16(BIT(13))
#define PCIE_DESC_RX_I_TCP_CSUM		cpu_to_le16(BIT(12))
#define PCIE_DESC_RX_I_TCP_CSUM_OK	cpu_to_le16(BIT(11))
#define PCIE_DESC_RX_I_UDP_CSUM		cpu_to_le16(BIT(10))
#define PCIE_DESC_RX_I_UDP_CSUM_OK	cpu_to_le16(BIT(9))
#define PCIE_DESC_RX_DECRYPTED		cpu_to_le16(BIT(8))
#define PCIE_DESC_RX_EOP		cpu_to_le16(BIT(7))
#define PCIE_DESC_RX_IP4_CSUM		cpu_to_le16(BIT(6))
#define PCIE_DESC_RX_IP4_CSUM_OK	cpu_to_le16(BIT(5))
#define PCIE_DESC_RX_TCP_CSUM		cpu_to_le16(BIT(4))
#define PCIE_DESC_RX_TCP_CSUM_OK	cpu_to_le16(BIT(3))
#define PCIE_DESC_RX_UDP_CSUM		cpu_to_le16(BIT(2))
#define PCIE_DESC_RX_UDP_CSUM_OK	cpu_to_le16(BIT(1))
#define PCIE_DESC_RX_VLAN		cpu_to_le16(BIT(0))

#define PCIE_DESC_RX_CSUM_ALL		(PCIE_DESC_RX_IP4_CSUM |	\
					 PCIE_DESC_RX_TCP_CSUM |	\
					 PCIE_DESC_RX_UDP_CSUM |	\
					 PCIE_DESC_RX_I_IP4_CSUM |	\
					 PCIE_DESC_RX_I_TCP_CSUM |	\
					 PCIE_DESC_RX_I_UDP_CSUM)
#define PCIE_DESC_RX_CSUM_OK_SHIFT	1
#define __PCIE_DESC_RX_CSUM_ALL		le16_to_cpu(PCIE_DESC_RX_CSUM_ALL)
#define __PCIE_DESC_RX_CSUM_ALL_OK	(__PCIE_DESC_RX_CSUM_ALL >>	\
					 PCIE_DESC_RX_CSUM_OK_SHIFT)

struct nfp_net_rx_desc {
	union {
		struct {
			__le16 dma_addr_hi; /* High bits of the buf address */
			u8 reserved; /* Must be zero */
			u8 meta_len_dd; /* Must be zero */

			__le32 dma_addr_lo; /* Low bits of the buffer address */
		} __packed fld;

		struct {
			__le16 data_len; /* Length of the frame + meta data */
			u8 reserved;
			u8 meta_len_dd;	/* Length of meta data prepended +
					 * descriptor done flag.
					 */

			__le16 flags;	/* RX flags. See @PCIE_DESC_RX_* */
			__le16 vlan;	/* VLAN if stripped */
		} __packed rxd;

		__le32 vals[2];
	};
};

#define NFP_NET_META_FIELD_MASK GENMASK(NFP_NET_META_FIELD_SIZE - 1, 0)
#define NFP_NET_VLAN_CTAG	0
#define NFP_NET_VLAN_STAG	1

struct nfp_meta_parsed {
	u8 hash_type;
	u8 csum_type;
	u32 hash;
	u32 mark;
	u32 portid;
	__wsum csum;
	struct {
		bool stripped;
		u8 tpid;
		u16 tci;
	} vlan;

#ifdef CONFIG_NFP_NET_IPSEC
	u32 ipsec_saidx;
#endif
};

struct nfp_net_rx_hash {
	__be32 hash_type;
	__be32 hash;
};

/**
 * struct nfp_net_rx_buf - software RX buffer descriptor
 * @frag:	page fragment buffer
 * @dma_addr:	DMA mapping address of the buffer
 */
struct nfp_net_rx_buf {
	void *frag;
	dma_addr_t dma_addr;
};

/**
 * struct nfp_net_xsk_rx_buf - software RX XSK buffer descriptor
 * @dma_addr:	DMA mapping address of the buffer
 * @xdp:	XSK buffer pool handle (for AF_XDP)
 */
struct nfp_net_xsk_rx_buf {
	dma_addr_t dma_addr;
	struct xdp_buff *xdp;
};

/**
 * struct nfp_net_rx_ring - RX ring structure
 * @r_vec:      Back pointer to ring vector structure
 * @cnt:        Size of the queue in number of descriptors
 * @wr_p:       FL/RX ring write pointer (free running)
 * @rd_p:       FL/RX ring read pointer (free running)
 * @idx:        Ring index from Linux's perspective
 * @fl_qcidx:   Queue Controller Peripheral (QCP) queue index for the freelist
 * @qcp_fl:     Pointer to base of the QCP freelist queue
 * @rxbufs:     Array of transmitted FL/RX buffers
 * @xsk_rxbufs: Array of transmitted FL/RX buffers (for AF_XDP)
 * @rxds:       Virtual address of FL/RX ring in host memory
 * @xdp_rxq:    RX-ring info avail for XDP
 * @dma:        DMA address of the FL/RX ring
 * @size:       Size, in bytes, of the FL/RX ring (needed to free)
 */
struct nfp_net_rx_ring {
	struct nfp_net_r_vector *r_vec;

	u32 cnt;
	u32 wr_p;
	u32 rd_p;

	u32 idx;

	int fl_qcidx;
	u8 __iomem *qcp_fl;

	struct nfp_net_rx_buf *rxbufs;
	struct nfp_net_xsk_rx_buf *xsk_rxbufs;
	struct nfp_net_rx_desc *rxds;

	struct xdp_rxq_info xdp_rxq;

	dma_addr_t dma;
	size_t size;
} ____cacheline_aligned;

/**
 * struct nfp_net_r_vector - Per ring interrupt vector configuration
 * @nfp_net:        Backpointer to nfp_net structure
 * @napi:           NAPI structure for this ring vec
 * @tasklet:        ctrl vNIC, tasklet for servicing the r_vec
 * @queue:          ctrl vNIC, send queue
 * @lock:           ctrl vNIC, r_vec lock protects @queue
 * @tx_ring:        Pointer to TX ring
 * @rx_ring:        Pointer to RX ring
 * @xdp_ring:	    Pointer to an extra TX ring for XDP
 * @xsk_pool:	    XSK buffer pool active on vector queue pair (for AF_XDP)
 * @irq_entry:      MSI-X table entry (use for talking to the device)
 * @event_ctr:	    Number of interrupt
 * @rx_dim:	    Dynamic interrupt moderation structure for RX
 * @tx_dim:	    Dynamic interrupt moderation structure for TX
 * @rx_sync:	    Seqlock for atomic updates of RX stats
 * @rx_pkts:        Number of received packets
 * @rx_bytes:	    Number of received bytes
 * @rx_drops:	    Number of packets dropped on RX due to lack of resources
 * @hw_csum_rx_ok:  Counter of packets where the HW checksum was OK
 * @hw_csum_rx_inner_ok: Counter of packets where the inner HW checksum was OK
 * @hw_csum_rx_complete: Counter of packets with CHECKSUM_COMPLETE reported
 * @hw_csum_rx_error:	 Counter of packets with bad checksums
 * @hw_tls_rx:	    Number of packets with TLS decrypted by hardware
 * @tx_sync:	    Seqlock for atomic updates of TX stats
 * @tx_pkts:	    Number of Transmitted packets
 * @tx_bytes:	    Number of Transmitted bytes
 * @hw_csum_tx:	    Counter of packets with TX checksum offload requested
 * @hw_csum_tx_inner:	 Counter of inner TX checksum offload requests
 * @tx_gather:	    Counter of packets with Gather DMA
 * @tx_lso:	    Counter of LSO packets sent
 * @hw_tls_tx:	    Counter of TLS packets sent with crypto offloaded to HW
 * @tls_tx_fallback:	Counter of TLS packets sent which had to be encrypted
 *			by the fallback path because packets came out of order
 * @tls_tx_no_fallback:	Counter of TLS packets not sent because the fallback
 *			path could not encrypt them
 * @tx_errors:	    How many TX errors were encountered
 * @tx_busy:        How often was TX busy (no space)?
 * @rx_replace_buf_alloc_fail:	Counter of RX buffer allocation failures
 * @irq_vector:     Interrupt vector number (use for talking to the OS)
 * @handler:        Interrupt handler for this ring vector
 * @name:           Name of the interrupt vector
 * @affinity_mask:  SMP affinity mask for this vector
 *
 * This structure ties RX and TX rings to interrupt vectors and a NAPI
 * context. This currently only supports one RX and TX ring per
 * interrupt vector but might be extended in the future to allow
 * association of multiple rings per vector.
 */
struct nfp_net_r_vector {
	struct nfp_net *nfp_net;
	union {
		struct napi_struct napi;
		struct {
			struct tasklet_struct tasklet;
			struct sk_buff_head queue;
			spinlock_t lock;
		};
	};

	struct nfp_net_tx_ring *tx_ring;
	struct nfp_net_rx_ring *rx_ring;

	u16 irq_entry;

	u16 event_ctr;
	struct dim rx_dim;
	struct dim tx_dim;

	struct u64_stats_sync rx_sync;
	u64 rx_pkts;
	u64 rx_bytes;
	u64 rx_drops;
	u64 hw_csum_rx_ok;
	u64 hw_csum_rx_inner_ok;
	u64 hw_csum_rx_complete;
	u64 hw_tls_rx;

	u64 hw_csum_rx_error;
	u64 rx_replace_buf_alloc_fail;

	struct nfp_net_tx_ring *xdp_ring;
	struct xsk_buff_pool *xsk_pool;

	struct u64_stats_sync tx_sync;
	u64 tx_pkts;
	u64 tx_bytes;

	u64 ____cacheline_aligned_in_smp hw_csum_tx;
	u64 hw_csum_tx_inner;
	u64 tx_gather;
	u64 tx_lso;
	u64 hw_tls_tx;

	u64 tls_tx_fallback;
	u64 tls_tx_no_fallback;
	u64 tx_errors;
	u64 tx_busy;

	/* Cold data follows */

	u32 irq_vector;
	irq_handler_t handler;
	char name[IFNAMSIZ + 8];
	cpumask_t affinity_mask;
} ____cacheline_aligned;

/* Firmware version as it is written in the 32bit value in the BAR */
struct nfp_net_fw_version {
	u8 minor;
	u8 major;
	u8 class;

	/* This byte can be exploited for more use, currently,
	 * BIT0: dp type, BIT[7:1]: reserved
	 */
	u8 extend;
} __packed;

static inline bool nfp_net_fw_ver_eq(struct nfp_net_fw_version *fw_ver,
				     u8 extend, u8 class, u8 major, u8 minor)
{
	return fw_ver->extend == extend &&
	       fw_ver->class == class &&
	       fw_ver->major == major &&
	       fw_ver->minor == minor;
}

struct nfp_stat_pair {
	u64 pkts;
	u64 bytes;
};

/**
 * struct nfp_net_dp - NFP network device datapath data structure
 * @dev:		Backpointer to struct device
 * @netdev:		Backpointer to net_device structure
 * @is_vf:		Is the driver attached to a VF?
 * @chained_metadata_format:  Firemware will use new metadata format
 * @ktls_tx:		Is kTLS TX enabled?
 * @rx_dma_dir:		Mapping direction for RX buffers
 * @rx_dma_off:		Offset at which DMA packets (for XDP headroom)
 * @rx_offset:		Offset in the RX buffers where packet data starts
 * @ctrl:		Local copy of the control register/word.
 * @ctrl_w1:		Local copy of the control register/word1.
 * @fl_bufsz:		Currently configured size of the freelist buffers
 * @xdp_prog:		Installed XDP program
 * @tx_rings:		Array of pre-allocated TX ring structures
 * @rx_rings:		Array of pre-allocated RX ring structures
 * @ctrl_bar:		Pointer to mapped control BAR
 *
 * @ops:		Callbacks and parameters for this vNIC's NFD version
 * @txrwb:		TX pointer write back area (indexed by queue id)
 * @txrwb_dma:		TX pointer write back area DMA address
 * @txd_cnt:		Size of the TX ring in number of min size packets
 * @rxd_cnt:		Size of the RX ring in number of min size packets
 * @num_r_vecs:		Number of used ring vectors
 * @num_tx_rings:	Currently configured number of TX rings
 * @num_stack_tx_rings:	Number of TX rings used by the stack (not XDP)
 * @num_rx_rings:	Currently configured number of RX rings
 * @mtu:		Device MTU
 * @xsk_pools:		XSK buffer pools, @max_r_vecs in size (for AF_XDP).
 */
struct nfp_net_dp {
	struct device *dev;
	struct net_device *netdev;

	u8 is_vf:1;
	u8 chained_metadata_format:1;
	u8 ktls_tx:1;

	u8 rx_dma_dir;
	u8 rx_offset;

	u32 rx_dma_off;

	u32 ctrl;
	u32 ctrl_w1;
	u32 fl_bufsz;

	struct bpf_prog *xdp_prog;

	struct nfp_net_tx_ring *tx_rings;
	struct nfp_net_rx_ring *rx_rings;

	u8 __iomem *ctrl_bar;

	/* Cold data follows */

	const struct nfp_dp_ops *ops;

	u64 *txrwb;
	dma_addr_t txrwb_dma;

	unsigned int txd_cnt;
	unsigned int rxd_cnt;

	unsigned int num_r_vecs;

	unsigned int num_tx_rings;
	unsigned int num_stack_tx_rings;
	unsigned int num_rx_rings;

	unsigned int mtu;

	struct xsk_buff_pool **xsk_pools;
};

/**
 * struct nfp_net - NFP network device structure
 * @dp:			Datapath structure
 * @dev_info:		NFP ASIC params
 * @id:			vNIC id within the PF (0 for VFs)
 * @fw_ver:		Firmware version
 * @cap:                Capabilities advertised by the Firmware
 * @cap_w1:             Extended capabilities word advertised by the Firmware
 * @max_mtu:            Maximum support MTU advertised by the Firmware
 * @rss_hfunc:		RSS selected hash function
 * @rss_cfg:            RSS configuration
 * @rss_key:            RSS secret key
 * @rss_itbl:           RSS indirection table
 * @xdp:		Information about the driver XDP program
 * @xdp_hw:		Information about the HW XDP program
 * @max_r_vecs:		Number of allocated interrupt vectors for RX/TX
 * @max_tx_rings:       Maximum number of TX rings supported by the Firmware
 * @max_rx_rings:       Maximum number of RX rings supported by the Firmware
 * @stride_rx:		Queue controller RX queue spacing
 * @stride_tx:		Queue controller TX queue spacing
 * @r_vecs:             Pre-allocated array of ring vectors
 * @irq_entries:        Pre-allocated array of MSI-X entries
 * @lsc_handler:        Handler for Link State Change interrupt
 * @lsc_name:           Name for Link State Change interrupt
 * @exn_handler:        Handler for Exception interrupt
 * @exn_name:           Name for Exception interrupt
 * @shared_handler:     Handler for shared interrupts
 * @shared_name:        Name for shared interrupt
 * @reconfig_lock:	Protects @reconfig_posted, @reconfig_timer_active,
 *			@reconfig_sync_present and HW reconfiguration request
 *			regs/machinery from async requests (sync must take
 *			@bar_lock)
 * @reconfig_posted:	Pending reconfig bits coming from async sources
 * @reconfig_timer_active:  Timer for reading reconfiguration results is pending
 * @reconfig_sync_present:  Some thread is performing synchronous reconfig
 * @reconfig_timer:	Timer for async reading of reconfig results
 * @reconfig_in_progress_update:	Update FW is processing now (debug only)
 * @bar_lock:		vNIC config BAR access lock, protects: update,
 *			mailbox area, crypto TLV
 * @link_up:            Is the link up?
 * @link_status_lock:	Protects @link_* and ensures atomicity with BAR reading
 * @rx_coalesce_adapt_on:   Is RX interrupt moderation adaptive?
 * @tx_coalesce_adapt_on:   Is TX interrupt moderation adaptive?
 * @rx_coalesce_usecs:      RX interrupt moderation usecs delay parameter
 * @rx_coalesce_max_frames: RX interrupt moderation frame count parameter
 * @tx_coalesce_usecs:      TX interrupt moderation usecs delay parameter
 * @tx_coalesce_max_frames: TX interrupt moderation frame count parameter
 * @qcp_cfg:            Pointer to QCP queue used for configuration notification
 * @tx_bar:             Pointer to mapped TX queues
 * @rx_bar:             Pointer to mapped FL/RX queues
 * @xa_ipsec:           IPsec xarray SA data
 * @tlv_caps:		Parsed TLV capabilities
 * @ktls_tx_conn_cnt:	Number of offloaded kTLS TX connections
 * @ktls_rx_conn_cnt:	Number of offloaded kTLS RX connections
 * @ktls_conn_id_gen:	Trivial generator for kTLS connection ids (for TX)
 * @ktls_no_space:	Counter of firmware rejecting kTLS connection due to
 *			lack of space
 * @ktls_rx_resync_req:	Counter of TLS RX resync requested
 * @ktls_rx_resync_ign:	Counter of TLS RX resync requests ignored
 * @ktls_rx_resync_sent:    Counter of TLS RX resync completed
 * @mbox_cmsg:		Common Control Message via vNIC mailbox state
 * @mbox_cmsg.queue:	CCM mbox queue of pending messages
 * @mbox_cmsg.wq:	CCM mbox wait queue of waiting processes
 * @mbox_cmsg.workq:	CCM mbox work queue for @wait_work and @runq_work
 * @mbox_cmsg.wait_work:    CCM mbox posted msg reconfig wait work
 * @mbox_cmsg.runq_work:    CCM mbox posted msg queue runner work
 * @mbox_cmsg.tag:	CCM mbox message tag allocator
 * @debugfs_dir:	Device directory in debugfs
 * @vnic_list:		Entry on device vNIC list
 * @pdev:		Backpointer to PCI device
 * @app:		APP handle if available
 * @vnic_no_name:	For non-port PF vNIC make ndo_get_phys_port_name return
 *			-EOPNOTSUPP to keep backwards compatibility (set by app)
 * @port:		Pointer to nfp_port structure if vNIC is a port
 * @app_priv:		APP private data for this vNIC
 */
struct nfp_net {
	struct nfp_net_dp dp;

	const struct nfp_dev_info *dev_info;
	struct nfp_net_fw_version fw_ver;

	u32 id;

	u32 cap;
	u32 cap_w1;
	u32 max_mtu;

	u8 rss_hfunc;
	u32 rss_cfg;
	u8 rss_key[NFP_NET_CFG_RSS_KEY_SZ];
	u8 rss_itbl[NFP_NET_CFG_RSS_ITBL_SZ];

	struct xdp_attachment_info xdp;
	struct xdp_attachment_info xdp_hw;

	unsigned int max_tx_rings;
	unsigned int max_rx_rings;

	int stride_tx;
	int stride_rx;

	unsigned int max_r_vecs;
	struct nfp_net_r_vector r_vecs[NFP_NET_MAX_R_VECS];
	struct msix_entry irq_entries[NFP_NET_MAX_IRQS];

	irq_handler_t lsc_handler;
	char lsc_name[IFNAMSIZ + 8];

	irq_handler_t exn_handler;
	char exn_name[IFNAMSIZ + 8];

	irq_handler_t shared_handler;
	char shared_name[IFNAMSIZ + 8];

	bool link_up;
	spinlock_t link_status_lock;

	spinlock_t reconfig_lock;
	u32 reconfig_posted;
	bool reconfig_timer_active;
	bool reconfig_sync_present;
	struct timer_list reconfig_timer;
	u32 reconfig_in_progress_update;

	struct semaphore bar_lock;

	bool rx_coalesce_adapt_on;
	bool tx_coalesce_adapt_on;
	u32 rx_coalesce_usecs;
	u32 rx_coalesce_max_frames;
	u32 tx_coalesce_usecs;
	u32 tx_coalesce_max_frames;

	u8 __iomem *qcp_cfg;

	u8 __iomem *tx_bar;
	u8 __iomem *rx_bar;

#ifdef CONFIG_NFP_NET_IPSEC
	struct xarray xa_ipsec;
#endif

	struct nfp_net_tlv_caps tlv_caps;

	unsigned int ktls_tx_conn_cnt;
	unsigned int ktls_rx_conn_cnt;

	atomic64_t ktls_conn_id_gen;

	atomic_t ktls_no_space;
	atomic_t ktls_rx_resync_req;
	atomic_t ktls_rx_resync_ign;
	atomic_t ktls_rx_resync_sent;

	struct {
		struct sk_buff_head queue;
		wait_queue_head_t wq;
		struct workqueue_struct *workq;
		struct work_struct wait_work;
		struct work_struct runq_work;
		u16 tag;
	} mbox_cmsg;

	struct dentry *debugfs_dir;

	struct list_head vnic_list;

	struct pci_dev *pdev;
	struct nfp_app *app;

	bool vnic_no_name;

	struct nfp_port *port;

	void *app_priv;
};

/* Functions to read/write from/to a BAR
 * Performs any endian conversion necessary.
 */
static inline u16 nn_readb(struct nfp_net *nn, int off)
{
	return readb(nn->dp.ctrl_bar + off);
}

static inline void nn_writeb(struct nfp_net *nn, int off, u8 val)
{
	writeb(val, nn->dp.ctrl_bar + off);
}

static inline u16 nn_readw(struct nfp_net *nn, int off)
{
	return readw(nn->dp.ctrl_bar + off);
}

static inline void nn_writew(struct nfp_net *nn, int off, u16 val)
{
	writew(val, nn->dp.ctrl_bar + off);
}

static inline u32 nn_readl(struct nfp_net *nn, int off)
{
	return readl(nn->dp.ctrl_bar + off);
}

static inline void nn_writel(struct nfp_net *nn, int off, u32 val)
{
	writel(val, nn->dp.ctrl_bar + off);
}

static inline u64 nn_readq(struct nfp_net *nn, int off)
{
	return readq(nn->dp.ctrl_bar + off);
}

static inline void nn_writeq(struct nfp_net *nn, int off, u64 val)
{
	writeq(val, nn->dp.ctrl_bar + off);
}

/* Flush posted PCI writes by reading something without side effects */
static inline void nn_pci_flush(struct nfp_net *nn)
{
	nn_readl(nn, NFP_NET_CFG_VERSION);
}

/* Queue Controller Peripheral access functions and definitions.
 *
 * Some of the BARs of the NFP are mapped to portions of the Queue
 * Controller Peripheral (QCP) address space on the NFP.  A QCP queue
 * has a read and a write pointer (as well as a size and flags,
 * indicating overflow etc).  The QCP offers a number of different
 * operation on queue pointers, but here we only offer function to
 * either add to a pointer or to read the pointer value.
 */
#define NFP_QCP_QUEUE_ADDR_SZ			0x800
#define NFP_QCP_QUEUE_OFF(_x)			((_x) * NFP_QCP_QUEUE_ADDR_SZ)
#define NFP_QCP_QUEUE_ADD_RPTR			0x0000
#define NFP_QCP_QUEUE_ADD_WPTR			0x0004
#define NFP_QCP_QUEUE_STS_LO			0x0008
#define NFP_QCP_QUEUE_STS_LO_READPTR_mask	0x3ffff
#define NFP_QCP_QUEUE_STS_HI			0x000c
#define NFP_QCP_QUEUE_STS_HI_WRITEPTR_mask	0x3ffff

/* nfp_qcp_ptr - Read or Write Pointer of a queue */
enum nfp_qcp_ptr {
	NFP_QCP_READ_PTR = 0,
	NFP_QCP_WRITE_PTR
};

/**
 * nfp_qcp_rd_ptr_add() - Add the value to the read pointer of a queue
 *
 * @q:   Base address for queue structure
 * @val: Value to add to the queue pointer
 */
static inline void nfp_qcp_rd_ptr_add(u8 __iomem *q, u32 val)
{
	writel(val, q + NFP_QCP_QUEUE_ADD_RPTR);
}

/**
 * nfp_qcp_wr_ptr_add() - Add the value to the write pointer of a queue
 *
 * @q:   Base address for queue structure
 * @val: Value to add to the queue pointer
 */
static inline void nfp_qcp_wr_ptr_add(u8 __iomem *q, u32 val)
{
	writel(val, q + NFP_QCP_QUEUE_ADD_WPTR);
}

static inline u32 _nfp_qcp_read(u8 __iomem *q, enum nfp_qcp_ptr ptr)
{
	u32 off;
	u32 val;

	if (ptr == NFP_QCP_READ_PTR)
		off = NFP_QCP_QUEUE_STS_LO;
	else
		off = NFP_QCP_QUEUE_STS_HI;

	val = readl(q + off);

	if (ptr == NFP_QCP_READ_PTR)
		return val & NFP_QCP_QUEUE_STS_LO_READPTR_mask;
	else
		return val & NFP_QCP_QUEUE_STS_HI_WRITEPTR_mask;
}

/**
 * nfp_qcp_rd_ptr_read() - Read the current read pointer value for a queue
 * @q:  Base address for queue structure
 *
 * Return: Value read.
 */
static inline u32 nfp_qcp_rd_ptr_read(u8 __iomem *q)
{
	return _nfp_qcp_read(q, NFP_QCP_READ_PTR);
}

/**
 * nfp_qcp_wr_ptr_read() - Read the current write pointer value for a queue
 * @q:  Base address for queue structure
 *
 * Return: Value read.
 */
static inline u32 nfp_qcp_wr_ptr_read(u8 __iomem *q)
{
	return _nfp_qcp_read(q, NFP_QCP_WRITE_PTR);
}

u32 nfp_qcp_queue_offset(const struct nfp_dev_info *dev_info, u16 queue);

static inline bool nfp_net_is_data_vnic(struct nfp_net *nn)
{
	WARN_ON_ONCE(!nn->dp.netdev && nn->port);
	return !!nn->dp.netdev;
}

static inline bool nfp_net_running(struct nfp_net *nn)
{
	return nn->dp.ctrl & NFP_NET_CFG_CTRL_ENABLE;
}

static inline const char *nfp_net_name(struct nfp_net *nn)
{
	return nn->dp.netdev ? nn->dp.netdev->name : "ctrl";
}

static inline void nfp_ctrl_lock(struct nfp_net *nn)
	__acquires(&nn->r_vecs[0].lock)
{
	spin_lock_bh(&nn->r_vecs[0].lock);
}

static inline void nfp_ctrl_unlock(struct nfp_net *nn)
	__releases(&nn->r_vecs[0].lock)
{
	spin_unlock_bh(&nn->r_vecs[0].lock);
}

static inline void nn_ctrl_bar_lock(struct nfp_net *nn)
{
	down(&nn->bar_lock);
}

static inline bool nn_ctrl_bar_trylock(struct nfp_net *nn)
{
	return !down_trylock(&nn->bar_lock);
}

static inline void nn_ctrl_bar_unlock(struct nfp_net *nn)
{
	up(&nn->bar_lock);
}

/* Globals */
extern const char nfp_driver_version[];

extern const struct net_device_ops nfp_nfd3_netdev_ops;
extern const struct net_device_ops nfp_nfdk_netdev_ops;

static inline bool nfp_netdev_is_nfp_net(struct net_device *netdev)
{
	return netdev->netdev_ops == &nfp_nfd3_netdev_ops ||
	       netdev->netdev_ops == &nfp_nfdk_netdev_ops;
}

static inline int nfp_net_coalesce_para_check(u32 usecs, u32 pkts)
{
	if ((usecs >= ((1 << 16) - 1)) || (pkts >= ((1 << 16) - 1)))
		return -EINVAL;

	return 0;
}

/* Prototypes */
void nfp_net_get_fw_version(struct nfp_net_fw_version *fw_ver,
			    void __iomem *ctrl_bar);

struct nfp_net *
nfp_net_alloc(struct pci_dev *pdev, const struct nfp_dev_info *dev_info,
	      void __iomem *ctrl_bar, bool needs_netdev,
	      unsigned int max_tx_rings, unsigned int max_rx_rings);
void nfp_net_free(struct nfp_net *nn);

int nfp_net_init(struct nfp_net *nn);
void nfp_net_clean(struct nfp_net *nn);

int nfp_ctrl_open(struct nfp_net *nn);
void nfp_ctrl_close(struct nfp_net *nn);

void nfp_net_set_ethtool_ops(struct net_device *netdev);
void nfp_net_info(struct nfp_net *nn);
int __nfp_net_reconfig(struct nfp_net *nn, u32 update);
int nfp_net_reconfig(struct nfp_net *nn, u32 update);
unsigned int nfp_net_rss_key_sz(struct nfp_net *nn);
void nfp_net_rss_write_itbl(struct nfp_net *nn);
void nfp_net_rss_write_key(struct nfp_net *nn);
void nfp_net_coalesce_write_cfg(struct nfp_net *nn);
int nfp_net_mbox_lock(struct nfp_net *nn, unsigned int data_size);
int nfp_net_mbox_reconfig(struct nfp_net *nn, u32 mbox_cmd);
int nfp_net_mbox_reconfig_and_unlock(struct nfp_net *nn, u32 mbox_cmd);
void nfp_net_mbox_reconfig_post(struct nfp_net *nn, u32 update);
int nfp_net_mbox_reconfig_wait_posted(struct nfp_net *nn);

unsigned int
nfp_net_irqs_alloc(struct pci_dev *pdev, struct msix_entry *irq_entries,
		   unsigned int min_irqs, unsigned int want_irqs);
void nfp_net_irqs_disable(struct pci_dev *pdev);
void
nfp_net_irqs_assign(struct nfp_net *nn, struct msix_entry *irq_entries,
		    unsigned int n);
struct sk_buff *
nfp_net_tls_tx(struct nfp_net_dp *dp, struct nfp_net_r_vector *r_vec,
	       struct sk_buff *skb, u64 *tls_handle, int *nr_frags);
void nfp_net_tls_tx_undo(struct sk_buff *skb, u64 tls_handle);

struct nfp_net_dp *nfp_net_clone_dp(struct nfp_net *nn);
int nfp_net_ring_reconfig(struct nfp_net *nn, struct nfp_net_dp *new,
			  struct netlink_ext_ack *extack);

#ifdef CONFIG_NFP_DEBUG
void nfp_net_debugfs_create(void);
void nfp_net_debugfs_destroy(void);
struct dentry *nfp_net_debugfs_device_add(struct pci_dev *pdev);
void nfp_net_debugfs_vnic_add(struct nfp_net *nn, struct dentry *ddir);
void nfp_net_debugfs_dir_clean(struct dentry **dir);
#else
static inline void nfp_net_debugfs_create(void)
{
}

static inline void nfp_net_debugfs_destroy(void)
{
}

static inline struct dentry *nfp_net_debugfs_device_add(struct pci_dev *pdev)
{
	return NULL;
}

static inline void
nfp_net_debugfs_vnic_add(struct nfp_net *nn, struct dentry *ddir)
{
}

static inline void nfp_net_debugfs_dir_clean(struct dentry **dir)
{
}
#endif /* CONFIG_NFP_DEBUG */

#endif /* _NFP_NET_H_ */