1// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause)
2/* QLogic qed NIC Driver
3 * Copyright (c) 2015-2017  QLogic Corporation
4 * Copyright (c) 2019-2020 Marvell International Ltd.
5 */
6
7#include <linux/types.h>
8#include <linux/bitops.h>
9#include <linux/dma-mapping.h>
10#include <linux/errno.h>
11#include <linux/kernel.h>
12#include <linux/list.h>
13#include <linux/log2.h>
14#include <linux/pci.h>
15#include <linux/slab.h>
16#include <linux/string.h>
17#include "qed.h"
18#include "qed_cxt.h"
19#include "qed_dev_api.h"
20#include "qed_hsi.h"
21#include "qed_hw.h"
22#include "qed_init_ops.h"
23#include "qed_rdma.h"
24#include "qed_reg_addr.h"
25#include "qed_sriov.h"
26
27/* QM constants */
28#define QM_PQ_ELEMENT_SIZE	4 /* in bytes */
29
30/* Doorbell-Queue constants */
31#define DQ_RANGE_SHIFT		4
32#define DQ_RANGE_ALIGN		BIT(DQ_RANGE_SHIFT)
33
34/* Searcher constants */
35#define SRC_MIN_NUM_ELEMS 256
36
37/* Timers constants */
38#define TM_SHIFT        7
39#define TM_ALIGN        BIT(TM_SHIFT)
40#define TM_ELEM_SIZE    4
41
42#define ILT_DEFAULT_HW_P_SIZE	4
43
44#define ILT_PAGE_IN_BYTES(hw_p_size)	(1U << ((hw_p_size) + 12))
45#define ILT_CFG_REG(cli, reg)	PSWRQ2_REG_ ## cli ## _ ## reg ## _RT_OFFSET
46
47/* ILT entry structure */
48#define ILT_ENTRY_PHY_ADDR_MASK		(~0ULL >> 12)
49#define ILT_ENTRY_PHY_ADDR_SHIFT	0
50#define ILT_ENTRY_VALID_MASK		0x1ULL
51#define ILT_ENTRY_VALID_SHIFT		52
52#define ILT_ENTRY_IN_REGS		2
53#define ILT_REG_SIZE_IN_BYTES		4
54
55/* connection context union */
56union conn_context {
57	struct e4_core_conn_context core_ctx;
58	struct e4_eth_conn_context eth_ctx;
59	struct e4_iscsi_conn_context iscsi_ctx;
60	struct e4_fcoe_conn_context fcoe_ctx;
61	struct e4_roce_conn_context roce_ctx;
62};
63
64/* TYPE-0 task context - iSCSI, FCOE */
65union type0_task_context {
66	struct e4_iscsi_task_context iscsi_ctx;
67	struct e4_fcoe_task_context fcoe_ctx;
68};
69
70/* TYPE-1 task context - ROCE */
71union type1_task_context {
72	struct e4_rdma_task_context roce_ctx;
73};
74
75struct src_ent {
76	__u8				opaque[56];
77	__be64				next;
78};
79
80#define CDUT_SEG_ALIGNMET		3 /* in 4k chunks */
81#define CDUT_SEG_ALIGNMET_IN_BYTES	BIT(CDUT_SEG_ALIGNMET + 12)
82
83#define CONN_CXT_SIZE(p_hwfn) \
84	ALIGNED_TYPE_SIZE(union conn_context, p_hwfn)
85
86#define SRQ_CXT_SIZE (sizeof(struct rdma_srq_context))
87#define XRC_SRQ_CXT_SIZE (sizeof(struct rdma_xrc_srq_context))
88
89#define TYPE0_TASK_CXT_SIZE(p_hwfn) \
90	ALIGNED_TYPE_SIZE(union type0_task_context, p_hwfn)
91
92/* Alignment is inherent to the type1_task_context structure */
93#define TYPE1_TASK_CXT_SIZE(p_hwfn) sizeof(union type1_task_context)
94
95static bool src_proto(enum protocol_type type)
96{
97	return type == PROTOCOLID_ISCSI ||
98	       type == PROTOCOLID_FCOE ||
99	       type == PROTOCOLID_IWARP;
100}
101
102static bool tm_cid_proto(enum protocol_type type)
103{
104	return type == PROTOCOLID_ISCSI ||
105	       type == PROTOCOLID_FCOE ||
106	       type == PROTOCOLID_ROCE ||
107	       type == PROTOCOLID_IWARP;
108}
109
110static bool tm_tid_proto(enum protocol_type type)
111{
112	return type == PROTOCOLID_FCOE;
113}
114
115/* counts the iids for the CDU/CDUC ILT client configuration */
116struct qed_cdu_iids {
117	u32 pf_cids;
118	u32 per_vf_cids;
119};
120
121static void qed_cxt_cdu_iids(struct qed_cxt_mngr *p_mngr,
122			     struct qed_cdu_iids *iids)
123{
124	u32 type;
125
126	for (type = 0; type < MAX_CONN_TYPES; type++) {
127		iids->pf_cids += p_mngr->conn_cfg[type].cid_count;
128		iids->per_vf_cids += p_mngr->conn_cfg[type].cids_per_vf;
129	}
130}
131
132/* counts the iids for the Searcher block configuration */
133struct qed_src_iids {
134	u32 pf_cids;
135	u32 per_vf_cids;
136};
137
138static void qed_cxt_src_iids(struct qed_cxt_mngr *p_mngr,
139			     struct qed_src_iids *iids)
140{
141	u32 i;
142
143	for (i = 0; i < MAX_CONN_TYPES; i++) {
144		if (!src_proto(i))
145			continue;
146
147		iids->pf_cids += p_mngr->conn_cfg[i].cid_count;
148		iids->per_vf_cids += p_mngr->conn_cfg[i].cids_per_vf;
149	}
150
151	/* Add L2 filtering filters in addition */
152	iids->pf_cids += p_mngr->arfs_count;
153}
154
155/* counts the iids for the Timers block configuration */
156struct qed_tm_iids {
157	u32 pf_cids;
158	u32 pf_tids[NUM_TASK_PF_SEGMENTS];	/* per segment */
159	u32 pf_tids_total;
160	u32 per_vf_cids;
161	u32 per_vf_tids;
162};
163
164static void qed_cxt_tm_iids(struct qed_hwfn *p_hwfn,
165			    struct qed_cxt_mngr *p_mngr,
166			    struct qed_tm_iids *iids)
167{
168	bool tm_vf_required = false;
169	bool tm_required = false;
170	int i, j;
171
172	/* Timers is a special case -> we don't count how many cids require
173	 * timers but what's the max cid that will be used by the timer block.
174	 * therefore we traverse in reverse order, and once we hit a protocol
175	 * that requires the timers memory, we'll sum all the protocols up
176	 * to that one.
177	 */
178	for (i = MAX_CONN_TYPES - 1; i >= 0; i--) {
179		struct qed_conn_type_cfg *p_cfg = &p_mngr->conn_cfg[i];
180
181		if (tm_cid_proto(i) || tm_required) {
182			if (p_cfg->cid_count)
183				tm_required = true;
184
185			iids->pf_cids += p_cfg->cid_count;
186		}
187
188		if (tm_cid_proto(i) || tm_vf_required) {
189			if (p_cfg->cids_per_vf)
190				tm_vf_required = true;
191
192			iids->per_vf_cids += p_cfg->cids_per_vf;
193		}
194
195		if (tm_tid_proto(i)) {
196			struct qed_tid_seg *segs = p_cfg->tid_seg;
197
198			/* for each segment there is at most one
199			 * protocol for which count is not 0.
200			 */
201			for (j = 0; j < NUM_TASK_PF_SEGMENTS; j++)
202				iids->pf_tids[j] += segs[j].count;
203
204			/* The last array elelment is for the VFs. As for PF
205			 * segments there can be only one protocol for
206			 * which this value is not 0.
207			 */
208			iids->per_vf_tids += segs[NUM_TASK_PF_SEGMENTS].count;
209		}
210	}
211
212	iids->pf_cids = roundup(iids->pf_cids, TM_ALIGN);
213	iids->per_vf_cids = roundup(iids->per_vf_cids, TM_ALIGN);
214	iids->per_vf_tids = roundup(iids->per_vf_tids, TM_ALIGN);
215
216	for (iids->pf_tids_total = 0, j = 0; j < NUM_TASK_PF_SEGMENTS; j++) {
217		iids->pf_tids[j] = roundup(iids->pf_tids[j], TM_ALIGN);
218		iids->pf_tids_total += iids->pf_tids[j];
219	}
220}
221
222static void qed_cxt_qm_iids(struct qed_hwfn *p_hwfn,
223			    struct qed_qm_iids *iids)
224{
225	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
226	struct qed_tid_seg *segs;
227	u32 vf_cids = 0, type, j;
228	u32 vf_tids = 0;
229
230	for (type = 0; type < MAX_CONN_TYPES; type++) {
231		iids->cids += p_mngr->conn_cfg[type].cid_count;
232		vf_cids += p_mngr->conn_cfg[type].cids_per_vf;
233
234		segs = p_mngr->conn_cfg[type].tid_seg;
235		/* for each segment there is at most one
236		 * protocol for which count is not 0.
237		 */
238		for (j = 0; j < NUM_TASK_PF_SEGMENTS; j++)
239			iids->tids += segs[j].count;
240
241		/* The last array elelment is for the VFs. As for PF
242		 * segments there can be only one protocol for
243		 * which this value is not 0.
244		 */
245		vf_tids += segs[NUM_TASK_PF_SEGMENTS].count;
246	}
247
248	iids->vf_cids = vf_cids;
249	iids->tids += vf_tids * p_mngr->vf_count;
250
251	DP_VERBOSE(p_hwfn, QED_MSG_ILT,
252		   "iids: CIDS %08x vf_cids %08x tids %08x vf_tids %08x\n",
253		   iids->cids, iids->vf_cids, iids->tids, vf_tids);
254}
255
256static struct qed_tid_seg *qed_cxt_tid_seg_info(struct qed_hwfn *p_hwfn,
257						u32 seg)
258{
259	struct qed_cxt_mngr *p_cfg = p_hwfn->p_cxt_mngr;
260	u32 i;
261
262	/* Find the protocol with tid count > 0 for this segment.
263	 * Note: there can only be one and this is already validated.
264	 */
265	for (i = 0; i < MAX_CONN_TYPES; i++)
266		if (p_cfg->conn_cfg[i].tid_seg[seg].count)
267			return &p_cfg->conn_cfg[i].tid_seg[seg];
268	return NULL;
269}
270
271static void qed_cxt_set_srq_count(struct qed_hwfn *p_hwfn,
272				  u32 num_srqs, u32 num_xrc_srqs)
273{
274	struct qed_cxt_mngr *p_mgr = p_hwfn->p_cxt_mngr;
275
276	p_mgr->srq_count = num_srqs;
277	p_mgr->xrc_srq_count = num_xrc_srqs;
278}
279
280u32 qed_cxt_get_ilt_page_size(struct qed_hwfn *p_hwfn,
281			      enum ilt_clients ilt_client)
282{
283	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
284	struct qed_ilt_client_cfg *p_cli = &p_mngr->clients[ilt_client];
285
286	return ILT_PAGE_IN_BYTES(p_cli->p_size.val);
287}
288
289static u32 qed_cxt_xrc_srqs_per_page(struct qed_hwfn *p_hwfn)
290{
291	u32 page_size;
292
293	page_size = qed_cxt_get_ilt_page_size(p_hwfn, ILT_CLI_TSDM);
294	return page_size / XRC_SRQ_CXT_SIZE;
295}
296
297u32 qed_cxt_get_total_srq_count(struct qed_hwfn *p_hwfn)
298{
299	struct qed_cxt_mngr *p_mgr = p_hwfn->p_cxt_mngr;
300	u32 total_srqs;
301
302	total_srqs = p_mgr->srq_count + p_mgr->xrc_srq_count;
303
304	return total_srqs;
305}
306
307/* set the iids count per protocol */
308static void qed_cxt_set_proto_cid_count(struct qed_hwfn *p_hwfn,
309					enum protocol_type type,
310					u32 cid_count, u32 vf_cid_cnt)
311{
312	struct qed_cxt_mngr *p_mgr = p_hwfn->p_cxt_mngr;
313	struct qed_conn_type_cfg *p_conn = &p_mgr->conn_cfg[type];
314
315	p_conn->cid_count = roundup(cid_count, DQ_RANGE_ALIGN);
316	p_conn->cids_per_vf = roundup(vf_cid_cnt, DQ_RANGE_ALIGN);
317
318	if (type == PROTOCOLID_ROCE) {
319		u32 page_sz = p_mgr->clients[ILT_CLI_CDUC].p_size.val;
320		u32 cxt_size = CONN_CXT_SIZE(p_hwfn);
321		u32 elems_per_page = ILT_PAGE_IN_BYTES(page_sz) / cxt_size;
322		u32 align = elems_per_page * DQ_RANGE_ALIGN;
323
324		p_conn->cid_count = roundup(p_conn->cid_count, align);
325	}
326}
327
328u32 qed_cxt_get_proto_cid_count(struct qed_hwfn *p_hwfn,
329				enum protocol_type type, u32 *vf_cid)
330{
331	if (vf_cid)
332		*vf_cid = p_hwfn->p_cxt_mngr->conn_cfg[type].cids_per_vf;
333
334	return p_hwfn->p_cxt_mngr->conn_cfg[type].cid_count;
335}
336
337u32 qed_cxt_get_proto_cid_start(struct qed_hwfn *p_hwfn,
338				enum protocol_type type)
339{
340	return p_hwfn->p_cxt_mngr->acquired[type].start_cid;
341}
342
343u32 qed_cxt_get_proto_tid_count(struct qed_hwfn *p_hwfn,
344				enum protocol_type type)
345{
346	u32 cnt = 0;
347	int i;
348
349	for (i = 0; i < TASK_SEGMENTS; i++)
350		cnt += p_hwfn->p_cxt_mngr->conn_cfg[type].tid_seg[i].count;
351
352	return cnt;
353}
354
355static void qed_cxt_set_proto_tid_count(struct qed_hwfn *p_hwfn,
356					enum protocol_type proto,
357					u8 seg,
358					u8 seg_type, u32 count, bool has_fl)
359{
360	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
361	struct qed_tid_seg *p_seg = &p_mngr->conn_cfg[proto].tid_seg[seg];
362
363	p_seg->count = count;
364	p_seg->has_fl_mem = has_fl;
365	p_seg->type = seg_type;
366}
367
368static void qed_ilt_cli_blk_fill(struct qed_ilt_client_cfg *p_cli,
369				 struct qed_ilt_cli_blk *p_blk,
370				 u32 start_line, u32 total_size, u32 elem_size)
371{
372	u32 ilt_size = ILT_PAGE_IN_BYTES(p_cli->p_size.val);
373
374	/* verify thatits called only once for each block */
375	if (p_blk->total_size)
376		return;
377
378	p_blk->total_size = total_size;
379	p_blk->real_size_in_page = 0;
380	if (elem_size)
381		p_blk->real_size_in_page = (ilt_size / elem_size) * elem_size;
382	p_blk->start_line = start_line;
383}
384
385static void qed_ilt_cli_adv_line(struct qed_hwfn *p_hwfn,
386				 struct qed_ilt_client_cfg *p_cli,
387				 struct qed_ilt_cli_blk *p_blk,
388				 u32 *p_line, enum ilt_clients client_id)
389{
390	if (!p_blk->total_size)
391		return;
392
393	if (!p_cli->active)
394		p_cli->first.val = *p_line;
395
396	p_cli->active = true;
397	*p_line += DIV_ROUND_UP(p_blk->total_size, p_blk->real_size_in_page);
398	p_cli->last.val = *p_line - 1;
399
400	DP_VERBOSE(p_hwfn, QED_MSG_ILT,
401		   "ILT[Client %d] - Lines: [%08x - %08x]. Block - Size %08x [Real %08x] Start line %d\n",
402		   client_id, p_cli->first.val,
403		   p_cli->last.val, p_blk->total_size,
404		   p_blk->real_size_in_page, p_blk->start_line);
405}
406
407static u32 qed_ilt_get_dynamic_line_cnt(struct qed_hwfn *p_hwfn,
408					enum ilt_clients ilt_client)
409{
410	u32 cid_count = p_hwfn->p_cxt_mngr->conn_cfg[PROTOCOLID_ROCE].cid_count;
411	struct qed_ilt_client_cfg *p_cli;
412	u32 lines_to_skip = 0;
413	u32 cxts_per_p;
414
415	if (ilt_client == ILT_CLI_CDUC) {
416		p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_CDUC];
417
418		cxts_per_p = ILT_PAGE_IN_BYTES(p_cli->p_size.val) /
419		    (u32) CONN_CXT_SIZE(p_hwfn);
420
421		lines_to_skip = cid_count / cxts_per_p;
422	}
423
424	return lines_to_skip;
425}
426
427static struct qed_ilt_client_cfg *qed_cxt_set_cli(struct qed_ilt_client_cfg
428						  *p_cli)
429{
430	p_cli->active = false;
431	p_cli->first.val = 0;
432	p_cli->last.val = 0;
433	return p_cli;
434}
435
436static struct qed_ilt_cli_blk *qed_cxt_set_blk(struct qed_ilt_cli_blk *p_blk)
437{
438	p_blk->total_size = 0;
439	return p_blk;
440}
441
442static void qed_cxt_ilt_blk_reset(struct qed_hwfn *p_hwfn)
443{
444	struct qed_ilt_client_cfg *clients = p_hwfn->p_cxt_mngr->clients;
445	u32 cli_idx, blk_idx;
446
447	for (cli_idx = 0; cli_idx < MAX_ILT_CLIENTS; cli_idx++) {
448		for (blk_idx = 0; blk_idx < ILT_CLI_PF_BLOCKS; blk_idx++)
449			clients[cli_idx].pf_blks[blk_idx].total_size = 0;
450
451		for (blk_idx = 0; blk_idx < ILT_CLI_VF_BLOCKS; blk_idx++)
452			clients[cli_idx].vf_blks[blk_idx].total_size = 0;
453	}
454}
455
456int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn, u32 *line_count)
457{
458	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
459	u32 curr_line, total, i, task_size, line;
460	struct qed_ilt_client_cfg *p_cli;
461	struct qed_ilt_cli_blk *p_blk;
462	struct qed_cdu_iids cdu_iids;
463	struct qed_src_iids src_iids;
464	struct qed_qm_iids qm_iids;
465	struct qed_tm_iids tm_iids;
466	struct qed_tid_seg *p_seg;
467
468	memset(&qm_iids, 0, sizeof(qm_iids));
469	memset(&cdu_iids, 0, sizeof(cdu_iids));
470	memset(&src_iids, 0, sizeof(src_iids));
471	memset(&tm_iids, 0, sizeof(tm_iids));
472
473	p_mngr->pf_start_line = RESC_START(p_hwfn, QED_ILT);
474
475	/* Reset all ILT blocks at the beginning of ILT computing in order
476	 * to prevent memory allocation for irrelevant blocks afterwards.
477	 */
478	qed_cxt_ilt_blk_reset(p_hwfn);
479
480	DP_VERBOSE(p_hwfn, QED_MSG_ILT,
481		   "hwfn [%d] - Set context manager starting line to be 0x%08x\n",
482		   p_hwfn->my_id, p_hwfn->p_cxt_mngr->pf_start_line);
483
484	/* CDUC */
485	p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_CDUC]);
486
487	curr_line = p_mngr->pf_start_line;
488
489	/* CDUC PF */
490	p_cli->pf_total_lines = 0;
491
492	/* get the counters for the CDUC and QM clients  */
493	qed_cxt_cdu_iids(p_mngr, &cdu_iids);
494
495	p_blk = qed_cxt_set_blk(&p_cli->pf_blks[CDUC_BLK]);
496
497	total = cdu_iids.pf_cids * CONN_CXT_SIZE(p_hwfn);
498
499	qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
500			     total, CONN_CXT_SIZE(p_hwfn));
501
502	qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line, ILT_CLI_CDUC);
503	p_cli->pf_total_lines = curr_line - p_blk->start_line;
504
505	p_blk->dynamic_line_cnt = qed_ilt_get_dynamic_line_cnt(p_hwfn,
506							       ILT_CLI_CDUC);
507
508	/* CDUC VF */
509	p_blk = qed_cxt_set_blk(&p_cli->vf_blks[CDUC_BLK]);
510	total = cdu_iids.per_vf_cids * CONN_CXT_SIZE(p_hwfn);
511
512	qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
513			     total, CONN_CXT_SIZE(p_hwfn));
514
515	qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line, ILT_CLI_CDUC);
516	p_cli->vf_total_lines = curr_line - p_blk->start_line;
517
518	for (i = 1; i < p_mngr->vf_count; i++)
519		qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line,
520				     ILT_CLI_CDUC);
521
522	/* CDUT PF */
523	p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_CDUT]);
524	p_cli->first.val = curr_line;
525
526	/* first the 'working' task memory */
527	for (i = 0; i < NUM_TASK_PF_SEGMENTS; i++) {
528		p_seg = qed_cxt_tid_seg_info(p_hwfn, i);
529		if (!p_seg || p_seg->count == 0)
530			continue;
531
532		p_blk = qed_cxt_set_blk(&p_cli->pf_blks[CDUT_SEG_BLK(i)]);
533		total = p_seg->count * p_mngr->task_type_size[p_seg->type];
534		qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line, total,
535				     p_mngr->task_type_size[p_seg->type]);
536
537		qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line,
538				     ILT_CLI_CDUT);
539	}
540
541	/* next the 'init' task memory (forced load memory) */
542	for (i = 0; i < NUM_TASK_PF_SEGMENTS; i++) {
543		p_seg = qed_cxt_tid_seg_info(p_hwfn, i);
544		if (!p_seg || p_seg->count == 0)
545			continue;
546
547		p_blk =
548		    qed_cxt_set_blk(&p_cli->pf_blks[CDUT_FL_SEG_BLK(i, PF)]);
549
550		if (!p_seg->has_fl_mem) {
551			/* The segment is active (total size pf 'working'
552			 * memory is > 0) but has no FL (forced-load, Init)
553			 * memory. Thus:
554			 *
555			 * 1.   The total-size in the corrsponding FL block of
556			 *      the ILT client is set to 0 - No ILT line are
557			 *      provisioned and no ILT memory allocated.
558			 *
559			 * 2.   The start-line of said block is set to the
560			 *      start line of the matching working memory
561			 *      block in the ILT client. This is later used to
562			 *      configure the CDU segment offset registers and
563			 *      results in an FL command for TIDs of this
564			 *      segement behaves as regular load commands
565			 *      (loading TIDs from the working memory).
566			 */
567			line = p_cli->pf_blks[CDUT_SEG_BLK(i)].start_line;
568
569			qed_ilt_cli_blk_fill(p_cli, p_blk, line, 0, 0);
570			continue;
571		}
572		total = p_seg->count * p_mngr->task_type_size[p_seg->type];
573
574		qed_ilt_cli_blk_fill(p_cli, p_blk,
575				     curr_line, total,
576				     p_mngr->task_type_size[p_seg->type]);
577
578		qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line,
579				     ILT_CLI_CDUT);
580	}
581	p_cli->pf_total_lines = curr_line - p_cli->pf_blks[0].start_line;
582
583	/* CDUT VF */
584	p_seg = qed_cxt_tid_seg_info(p_hwfn, TASK_SEGMENT_VF);
585	if (p_seg && p_seg->count) {
586		/* Stricly speaking we need to iterate over all VF
587		 * task segment types, but a VF has only 1 segment
588		 */
589
590		/* 'working' memory */
591		total = p_seg->count * p_mngr->task_type_size[p_seg->type];
592
593		p_blk = qed_cxt_set_blk(&p_cli->vf_blks[CDUT_SEG_BLK(0)]);
594		qed_ilt_cli_blk_fill(p_cli, p_blk,
595				     curr_line, total,
596				     p_mngr->task_type_size[p_seg->type]);
597
598		qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line,
599				     ILT_CLI_CDUT);
600
601		/* 'init' memory */
602		p_blk =
603		    qed_cxt_set_blk(&p_cli->vf_blks[CDUT_FL_SEG_BLK(0, VF)]);
604		if (!p_seg->has_fl_mem) {
605			/* see comment above */
606			line = p_cli->vf_blks[CDUT_SEG_BLK(0)].start_line;
607			qed_ilt_cli_blk_fill(p_cli, p_blk, line, 0, 0);
608		} else {
609			task_size = p_mngr->task_type_size[p_seg->type];
610			qed_ilt_cli_blk_fill(p_cli, p_blk,
611					     curr_line, total, task_size);
612			qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line,
613					     ILT_CLI_CDUT);
614		}
615		p_cli->vf_total_lines = curr_line -
616		    p_cli->vf_blks[0].start_line;
617
618		/* Now for the rest of the VFs */
619		for (i = 1; i < p_mngr->vf_count; i++) {
620			p_blk = &p_cli->vf_blks[CDUT_SEG_BLK(0)];
621			qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line,
622					     ILT_CLI_CDUT);
623
624			p_blk = &p_cli->vf_blks[CDUT_FL_SEG_BLK(0, VF)];
625			qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line,
626					     ILT_CLI_CDUT);
627		}
628	}
629
630	/* QM */
631	p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_QM]);
632	p_blk = qed_cxt_set_blk(&p_cli->pf_blks[0]);
633
634	qed_cxt_qm_iids(p_hwfn, &qm_iids);
635	total = qed_qm_pf_mem_size(qm_iids.cids,
636				   qm_iids.vf_cids, qm_iids.tids,
637				   p_hwfn->qm_info.num_pqs,
638				   p_hwfn->qm_info.num_vf_pqs);
639
640	DP_VERBOSE(p_hwfn,
641		   QED_MSG_ILT,
642		   "QM ILT Info, (cids=%d, vf_cids=%d, tids=%d, num_pqs=%d, num_vf_pqs=%d, memory_size=%d)\n",
643		   qm_iids.cids,
644		   qm_iids.vf_cids,
645		   qm_iids.tids,
646		   p_hwfn->qm_info.num_pqs, p_hwfn->qm_info.num_vf_pqs, total);
647
648	qed_ilt_cli_blk_fill(p_cli, p_blk,
649			     curr_line, total * 0x1000,
650			     QM_PQ_ELEMENT_SIZE);
651
652	qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line, ILT_CLI_QM);
653	p_cli->pf_total_lines = curr_line - p_blk->start_line;
654
655	/* SRC */
656	p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_SRC]);
657	qed_cxt_src_iids(p_mngr, &src_iids);
658
659	/* Both the PF and VFs searcher connections are stored in the per PF
660	 * database. Thus sum the PF searcher cids and all the VFs searcher
661	 * cids.
662	 */
663	total = src_iids.pf_cids + src_iids.per_vf_cids * p_mngr->vf_count;
664	if (total) {
665		u32 local_max = max_t(u32, total,
666				      SRC_MIN_NUM_ELEMS);
667
668		total = roundup_pow_of_two(local_max);
669
670		p_blk = qed_cxt_set_blk(&p_cli->pf_blks[0]);
671		qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
672				     total * sizeof(struct src_ent),
673				     sizeof(struct src_ent));
674
675		qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line,
676				     ILT_CLI_SRC);
677		p_cli->pf_total_lines = curr_line - p_blk->start_line;
678	}
679
680	/* TM PF */
681	p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_TM]);
682	qed_cxt_tm_iids(p_hwfn, p_mngr, &tm_iids);
683	total = tm_iids.pf_cids + tm_iids.pf_tids_total;
684	if (total) {
685		p_blk = qed_cxt_set_blk(&p_cli->pf_blks[0]);
686		qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
687				     total * TM_ELEM_SIZE, TM_ELEM_SIZE);
688
689		qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line,
690				     ILT_CLI_TM);
691		p_cli->pf_total_lines = curr_line - p_blk->start_line;
692	}
693
694	/* TM VF */
695	total = tm_iids.per_vf_cids + tm_iids.per_vf_tids;
696	if (total) {
697		p_blk = qed_cxt_set_blk(&p_cli->vf_blks[0]);
698		qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
699				     total * TM_ELEM_SIZE, TM_ELEM_SIZE);
700
701		qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line,
702				     ILT_CLI_TM);
703
704		p_cli->vf_total_lines = curr_line - p_blk->start_line;
705		for (i = 1; i < p_mngr->vf_count; i++)
706			qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line,
707					     ILT_CLI_TM);
708	}
709
710	/* TSDM (SRQ CONTEXT) */
711	total = qed_cxt_get_total_srq_count(p_hwfn);
712
713	if (total) {
714		p_cli = qed_cxt_set_cli(&p_mngr->clients[ILT_CLI_TSDM]);
715		p_blk = qed_cxt_set_blk(&p_cli->pf_blks[SRQ_BLK]);
716		qed_ilt_cli_blk_fill(p_cli, p_blk, curr_line,
717				     total * SRQ_CXT_SIZE, SRQ_CXT_SIZE);
718
719		qed_ilt_cli_adv_line(p_hwfn, p_cli, p_blk, &curr_line,
720				     ILT_CLI_TSDM);
721		p_cli->pf_total_lines = curr_line - p_blk->start_line;
722	}
723
724	*line_count = curr_line - p_hwfn->p_cxt_mngr->pf_start_line;
725
726	if (curr_line - p_hwfn->p_cxt_mngr->pf_start_line >
727	    RESC_NUM(p_hwfn, QED_ILT))
728		return -EINVAL;
729
730	return 0;
731}
732
733u32 qed_cxt_cfg_ilt_compute_excess(struct qed_hwfn *p_hwfn, u32 used_lines)
734{
735	struct qed_ilt_client_cfg *p_cli;
736	u32 excess_lines, available_lines;
737	struct qed_cxt_mngr *p_mngr;
738	u32 ilt_page_size, elem_size;
739	struct qed_tid_seg *p_seg;
740	int i;
741
742	available_lines = RESC_NUM(p_hwfn, QED_ILT);
743	excess_lines = used_lines - available_lines;
744
745	if (!excess_lines)
746		return 0;
747
748	if (!QED_IS_RDMA_PERSONALITY(p_hwfn))
749		return 0;
750
751	p_mngr = p_hwfn->p_cxt_mngr;
752	p_cli = &p_mngr->clients[ILT_CLI_CDUT];
753	ilt_page_size = ILT_PAGE_IN_BYTES(p_cli->p_size.val);
754
755	for (i = 0; i < NUM_TASK_PF_SEGMENTS; i++) {
756		p_seg = qed_cxt_tid_seg_info(p_hwfn, i);
757		if (!p_seg || p_seg->count == 0)
758			continue;
759
760		elem_size = p_mngr->task_type_size[p_seg->type];
761		if (!elem_size)
762			continue;
763
764		return (ilt_page_size / elem_size) * excess_lines;
765	}
766
767	DP_NOTICE(p_hwfn, "failed computing excess ILT lines\n");
768	return 0;
769}
770
771static void qed_cxt_src_t2_free(struct qed_hwfn *p_hwfn)
772{
773	struct qed_src_t2 *p_t2 = &p_hwfn->p_cxt_mngr->src_t2;
774	u32 i;
775
776	if (!p_t2 || !p_t2->dma_mem)
777		return;
778
779	for (i = 0; i < p_t2->num_pages; i++)
780		if (p_t2->dma_mem[i].virt_addr)
781			dma_free_coherent(&p_hwfn->cdev->pdev->dev,
782					  p_t2->dma_mem[i].size,
783					  p_t2->dma_mem[i].virt_addr,
784					  p_t2->dma_mem[i].phys_addr);
785
786	kfree(p_t2->dma_mem);
787	p_t2->dma_mem = NULL;
788}
789
790static int
791qed_cxt_t2_alloc_pages(struct qed_hwfn *p_hwfn,
792		       struct qed_src_t2 *p_t2, u32 total_size, u32 page_size)
793{
794	void **p_virt;
795	u32 size, i;
796
797	if (!p_t2 || !p_t2->dma_mem)
798		return -EINVAL;
799
800	for (i = 0; i < p_t2->num_pages; i++) {
801		size = min_t(u32, total_size, page_size);
802		p_virt = &p_t2->dma_mem[i].virt_addr;
803
804		*p_virt = dma_alloc_coherent(&p_hwfn->cdev->pdev->dev,
805					     size,
806					     &p_t2->dma_mem[i].phys_addr,
807					     GFP_KERNEL);
808		if (!p_t2->dma_mem[i].virt_addr)
809			return -ENOMEM;
810
811		memset(*p_virt, 0, size);
812		p_t2->dma_mem[i].size = size;
813		total_size -= size;
814	}
815
816	return 0;
817}
818
819static int qed_cxt_src_t2_alloc(struct qed_hwfn *p_hwfn)
820{
821	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
822	u32 conn_num, total_size, ent_per_page, psz, i;
823	struct phys_mem_desc *p_t2_last_page;
824	struct qed_ilt_client_cfg *p_src;
825	struct qed_src_iids src_iids;
826	struct qed_src_t2 *p_t2;
827	int rc;
828
829	memset(&src_iids, 0, sizeof(src_iids));
830
831	/* if the SRC ILT client is inactive - there are no connection
832	 * requiring the searcer, leave.
833	 */
834	p_src = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_SRC];
835	if (!p_src->active)
836		return 0;
837
838	qed_cxt_src_iids(p_mngr, &src_iids);
839	conn_num = src_iids.pf_cids + src_iids.per_vf_cids * p_mngr->vf_count;
840	total_size = conn_num * sizeof(struct src_ent);
841
842	/* use the same page size as the SRC ILT client */
843	psz = ILT_PAGE_IN_BYTES(p_src->p_size.val);
844	p_t2 = &p_mngr->src_t2;
845	p_t2->num_pages = DIV_ROUND_UP(total_size, psz);
846
847	/* allocate t2 */
848	p_t2->dma_mem = kcalloc(p_t2->num_pages, sizeof(struct phys_mem_desc),
849				GFP_KERNEL);
850	if (!p_t2->dma_mem) {
851		DP_NOTICE(p_hwfn, "Failed to allocate t2 table\n");
852		rc = -ENOMEM;
853		goto t2_fail;
854	}
855
856	rc = qed_cxt_t2_alloc_pages(p_hwfn, p_t2, total_size, psz);
857	if (rc)
858		goto t2_fail;
859
860	/* Set the t2 pointers */
861
862	/* entries per page - must be a power of two */
863	ent_per_page = psz / sizeof(struct src_ent);
864
865	p_t2->first_free = (u64)p_t2->dma_mem[0].phys_addr;
866
867	p_t2_last_page = &p_t2->dma_mem[(conn_num - 1) / ent_per_page];
868	p_t2->last_free = (u64)p_t2_last_page->phys_addr +
869	    ((conn_num - 1) & (ent_per_page - 1)) * sizeof(struct src_ent);
870
871	for (i = 0; i < p_t2->num_pages; i++) {
872		u32 ent_num = min_t(u32,
873				    ent_per_page,
874				    conn_num);
875		struct src_ent *entries = p_t2->dma_mem[i].virt_addr;
876		u64 p_ent_phys = (u64)p_t2->dma_mem[i].phys_addr, val;
877		u32 j;
878
879		for (j = 0; j < ent_num - 1; j++) {
880			val = p_ent_phys + (j + 1) * sizeof(struct src_ent);
881			entries[j].next = cpu_to_be64(val);
882		}
883
884		if (i < p_t2->num_pages - 1)
885			val = (u64)p_t2->dma_mem[i + 1].phys_addr;
886		else
887			val = 0;
888		entries[j].next = cpu_to_be64(val);
889
890		conn_num -= ent_num;
891	}
892
893	return 0;
894
895t2_fail:
896	qed_cxt_src_t2_free(p_hwfn);
897	return rc;
898}
899
900#define for_each_ilt_valid_client(pos, clients)	\
901	for (pos = 0; pos < MAX_ILT_CLIENTS; pos++)	\
902		if (!clients[pos].active) {	\
903			continue;		\
904		} else				\
905
906/* Total number of ILT lines used by this PF */
907static u32 qed_cxt_ilt_shadow_size(struct qed_ilt_client_cfg *ilt_clients)
908{
909	u32 size = 0;
910	u32 i;
911
912	for_each_ilt_valid_client(i, ilt_clients)
913	    size += (ilt_clients[i].last.val - ilt_clients[i].first.val + 1);
914
915	return size;
916}
917
918static void qed_ilt_shadow_free(struct qed_hwfn *p_hwfn)
919{
920	struct qed_ilt_client_cfg *p_cli = p_hwfn->p_cxt_mngr->clients;
921	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
922	u32 ilt_size, i;
923
924	ilt_size = qed_cxt_ilt_shadow_size(p_cli);
925
926	for (i = 0; p_mngr->ilt_shadow && i < ilt_size; i++) {
927		struct phys_mem_desc *p_dma = &p_mngr->ilt_shadow[i];
928
929		if (p_dma->virt_addr)
930			dma_free_coherent(&p_hwfn->cdev->pdev->dev,
931					  p_dma->size, p_dma->virt_addr,
932					  p_dma->phys_addr);
933		p_dma->virt_addr = NULL;
934	}
935	kfree(p_mngr->ilt_shadow);
936	p_mngr->ilt_shadow = NULL;
937}
938
939static int qed_ilt_blk_alloc(struct qed_hwfn *p_hwfn,
940			     struct qed_ilt_cli_blk *p_blk,
941			     enum ilt_clients ilt_client,
942			     u32 start_line_offset)
943{
944	struct phys_mem_desc *ilt_shadow = p_hwfn->p_cxt_mngr->ilt_shadow;
945	u32 lines, line, sz_left, lines_to_skip = 0;
946
947	/* Special handling for RoCE that supports dynamic allocation */
948	if (QED_IS_RDMA_PERSONALITY(p_hwfn) &&
949	    ((ilt_client == ILT_CLI_CDUT) || ilt_client == ILT_CLI_TSDM))
950		return 0;
951
952	lines_to_skip = p_blk->dynamic_line_cnt;
953
954	if (!p_blk->total_size)
955		return 0;
956
957	sz_left = p_blk->total_size;
958	lines = DIV_ROUND_UP(sz_left, p_blk->real_size_in_page) - lines_to_skip;
959	line = p_blk->start_line + start_line_offset -
960	    p_hwfn->p_cxt_mngr->pf_start_line + lines_to_skip;
961
962	for (; lines; lines--) {
963		dma_addr_t p_phys;
964		void *p_virt;
965		u32 size;
966
967		size = min_t(u32, sz_left, p_blk->real_size_in_page);
968		p_virt = dma_alloc_coherent(&p_hwfn->cdev->pdev->dev, size,
969					    &p_phys, GFP_KERNEL);
970		if (!p_virt)
971			return -ENOMEM;
972
973		ilt_shadow[line].phys_addr = p_phys;
974		ilt_shadow[line].virt_addr = p_virt;
975		ilt_shadow[line].size = size;
976
977		DP_VERBOSE(p_hwfn, QED_MSG_ILT,
978			   "ILT shadow: Line [%d] Physical 0x%llx Virtual %p Size %d\n",
979			    line, (u64)p_phys, p_virt, size);
980
981		sz_left -= size;
982		line++;
983	}
984
985	return 0;
986}
987
988static int qed_ilt_shadow_alloc(struct qed_hwfn *p_hwfn)
989{
990	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
991	struct qed_ilt_client_cfg *clients = p_mngr->clients;
992	struct qed_ilt_cli_blk *p_blk;
993	u32 size, i, j, k;
994	int rc;
995
996	size = qed_cxt_ilt_shadow_size(clients);
997	p_mngr->ilt_shadow = kcalloc(size, sizeof(struct phys_mem_desc),
998				     GFP_KERNEL);
999	if (!p_mngr->ilt_shadow) {
1000		rc = -ENOMEM;
1001		goto ilt_shadow_fail;
1002	}
1003
1004	DP_VERBOSE(p_hwfn, QED_MSG_ILT,
1005		   "Allocated 0x%x bytes for ilt shadow\n",
1006		   (u32)(size * sizeof(struct phys_mem_desc)));
1007
1008	for_each_ilt_valid_client(i, clients) {
1009		for (j = 0; j < ILT_CLI_PF_BLOCKS; j++) {
1010			p_blk = &clients[i].pf_blks[j];
1011			rc = qed_ilt_blk_alloc(p_hwfn, p_blk, i, 0);
1012			if (rc)
1013				goto ilt_shadow_fail;
1014		}
1015		for (k = 0; k < p_mngr->vf_count; k++) {
1016			for (j = 0; j < ILT_CLI_VF_BLOCKS; j++) {
1017				u32 lines = clients[i].vf_total_lines * k;
1018
1019				p_blk = &clients[i].vf_blks[j];
1020				rc = qed_ilt_blk_alloc(p_hwfn, p_blk, i, lines);
1021				if (rc)
1022					goto ilt_shadow_fail;
1023			}
1024		}
1025	}
1026
1027	return 0;
1028
1029ilt_shadow_fail:
1030	qed_ilt_shadow_free(p_hwfn);
1031	return rc;
1032}
1033
1034static void qed_cid_map_free(struct qed_hwfn *p_hwfn)
1035{
1036	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
1037	u32 type, vf;
1038
1039	for (type = 0; type < MAX_CONN_TYPES; type++) {
1040		kfree(p_mngr->acquired[type].cid_map);
1041		p_mngr->acquired[type].max_count = 0;
1042		p_mngr->acquired[type].start_cid = 0;
1043
1044		for (vf = 0; vf < MAX_NUM_VFS; vf++) {
1045			kfree(p_mngr->acquired_vf[type][vf].cid_map);
1046			p_mngr->acquired_vf[type][vf].max_count = 0;
1047			p_mngr->acquired_vf[type][vf].start_cid = 0;
1048		}
1049	}
1050}
1051
1052static int
1053qed_cid_map_alloc_single(struct qed_hwfn *p_hwfn,
1054			 u32 type,
1055			 u32 cid_start,
1056			 u32 cid_count, struct qed_cid_acquired_map *p_map)
1057{
1058	u32 size;
1059
1060	if (!cid_count)
1061		return 0;
1062
1063	size = DIV_ROUND_UP(cid_count,
1064			    sizeof(unsigned long) * BITS_PER_BYTE) *
1065	       sizeof(unsigned long);
1066	p_map->cid_map = kzalloc(size, GFP_KERNEL);
1067	if (!p_map->cid_map)
1068		return -ENOMEM;
1069
1070	p_map->max_count = cid_count;
1071	p_map->start_cid = cid_start;
1072
1073	DP_VERBOSE(p_hwfn, QED_MSG_CXT,
1074		   "Type %08x start: %08x count %08x\n",
1075		   type, p_map->start_cid, p_map->max_count);
1076
1077	return 0;
1078}
1079
1080static int qed_cid_map_alloc(struct qed_hwfn *p_hwfn)
1081{
1082	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
1083	u32 start_cid = 0, vf_start_cid = 0;
1084	u32 type, vf;
1085
1086	for (type = 0; type < MAX_CONN_TYPES; type++) {
1087		struct qed_conn_type_cfg *p_cfg = &p_mngr->conn_cfg[type];
1088		struct qed_cid_acquired_map *p_map;
1089
1090		/* Handle PF maps */
1091		p_map = &p_mngr->acquired[type];
1092		if (qed_cid_map_alloc_single(p_hwfn, type, start_cid,
1093					     p_cfg->cid_count, p_map))
1094			goto cid_map_fail;
1095
1096		/* Handle VF maps */
1097		for (vf = 0; vf < MAX_NUM_VFS; vf++) {
1098			p_map = &p_mngr->acquired_vf[type][vf];
1099			if (qed_cid_map_alloc_single(p_hwfn, type,
1100						     vf_start_cid,
1101						     p_cfg->cids_per_vf, p_map))
1102				goto cid_map_fail;
1103		}
1104
1105		start_cid += p_cfg->cid_count;
1106		vf_start_cid += p_cfg->cids_per_vf;
1107	}
1108
1109	return 0;
1110
1111cid_map_fail:
1112	qed_cid_map_free(p_hwfn);
1113	return -ENOMEM;
1114}
1115
1116int qed_cxt_mngr_alloc(struct qed_hwfn *p_hwfn)
1117{
1118	struct qed_ilt_client_cfg *clients;
1119	struct qed_cxt_mngr *p_mngr;
1120	u32 i;
1121
1122	p_mngr = kzalloc(sizeof(*p_mngr), GFP_KERNEL);
1123	if (!p_mngr)
1124		return -ENOMEM;
1125
1126	/* Initialize ILT client registers */
1127	clients = p_mngr->clients;
1128	clients[ILT_CLI_CDUC].first.reg = ILT_CFG_REG(CDUC, FIRST_ILT);
1129	clients[ILT_CLI_CDUC].last.reg = ILT_CFG_REG(CDUC, LAST_ILT);
1130	clients[ILT_CLI_CDUC].p_size.reg = ILT_CFG_REG(CDUC, P_SIZE);
1131
1132	clients[ILT_CLI_QM].first.reg = ILT_CFG_REG(QM, FIRST_ILT);
1133	clients[ILT_CLI_QM].last.reg = ILT_CFG_REG(QM, LAST_ILT);
1134	clients[ILT_CLI_QM].p_size.reg = ILT_CFG_REG(QM, P_SIZE);
1135
1136	clients[ILT_CLI_TM].first.reg = ILT_CFG_REG(TM, FIRST_ILT);
1137	clients[ILT_CLI_TM].last.reg = ILT_CFG_REG(TM, LAST_ILT);
1138	clients[ILT_CLI_TM].p_size.reg = ILT_CFG_REG(TM, P_SIZE);
1139
1140	clients[ILT_CLI_SRC].first.reg = ILT_CFG_REG(SRC, FIRST_ILT);
1141	clients[ILT_CLI_SRC].last.reg = ILT_CFG_REG(SRC, LAST_ILT);
1142	clients[ILT_CLI_SRC].p_size.reg = ILT_CFG_REG(SRC, P_SIZE);
1143
1144	clients[ILT_CLI_CDUT].first.reg = ILT_CFG_REG(CDUT, FIRST_ILT);
1145	clients[ILT_CLI_CDUT].last.reg = ILT_CFG_REG(CDUT, LAST_ILT);
1146	clients[ILT_CLI_CDUT].p_size.reg = ILT_CFG_REG(CDUT, P_SIZE);
1147
1148	clients[ILT_CLI_TSDM].first.reg = ILT_CFG_REG(TSDM, FIRST_ILT);
1149	clients[ILT_CLI_TSDM].last.reg = ILT_CFG_REG(TSDM, LAST_ILT);
1150	clients[ILT_CLI_TSDM].p_size.reg = ILT_CFG_REG(TSDM, P_SIZE);
1151	/* default ILT page size for all clients is 64K */
1152	for (i = 0; i < MAX_ILT_CLIENTS; i++)
1153		p_mngr->clients[i].p_size.val = ILT_DEFAULT_HW_P_SIZE;
1154
1155	p_mngr->conn_ctx_size = CONN_CXT_SIZE(p_hwfn);
1156
1157	/* Initialize task sizes */
1158	p_mngr->task_type_size[0] = TYPE0_TASK_CXT_SIZE(p_hwfn);
1159	p_mngr->task_type_size[1] = TYPE1_TASK_CXT_SIZE(p_hwfn);
1160
1161	if (p_hwfn->cdev->p_iov_info) {
1162		p_mngr->vf_count = p_hwfn->cdev->p_iov_info->total_vfs;
1163		p_mngr->first_vf_in_pf =
1164			p_hwfn->cdev->p_iov_info->first_vf_in_pf;
1165	}
1166	/* Initialize the dynamic ILT allocation mutex */
1167	mutex_init(&p_mngr->mutex);
1168
1169	/* Set the cxt mangr pointer priori to further allocations */
1170	p_hwfn->p_cxt_mngr = p_mngr;
1171
1172	return 0;
1173}
1174
1175int qed_cxt_tables_alloc(struct qed_hwfn *p_hwfn)
1176{
1177	int rc;
1178
1179	/* Allocate the ILT shadow table */
1180	rc = qed_ilt_shadow_alloc(p_hwfn);
1181	if (rc)
1182		goto tables_alloc_fail;
1183
1184	/* Allocate the T2  table */
1185	rc = qed_cxt_src_t2_alloc(p_hwfn);
1186	if (rc)
1187		goto tables_alloc_fail;
1188
1189	/* Allocate and initialize the acquired cids bitmaps */
1190	rc = qed_cid_map_alloc(p_hwfn);
1191	if (rc)
1192		goto tables_alloc_fail;
1193
1194	return 0;
1195
1196tables_alloc_fail:
1197	qed_cxt_mngr_free(p_hwfn);
1198	return rc;
1199}
1200
1201void qed_cxt_mngr_free(struct qed_hwfn *p_hwfn)
1202{
1203	if (!p_hwfn->p_cxt_mngr)
1204		return;
1205
1206	qed_cid_map_free(p_hwfn);
1207	qed_cxt_src_t2_free(p_hwfn);
1208	qed_ilt_shadow_free(p_hwfn);
1209	kfree(p_hwfn->p_cxt_mngr);
1210
1211	p_hwfn->p_cxt_mngr = NULL;
1212}
1213
1214void qed_cxt_mngr_setup(struct qed_hwfn *p_hwfn)
1215{
1216	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
1217	struct qed_cid_acquired_map *p_map;
1218	struct qed_conn_type_cfg *p_cfg;
1219	int type;
1220	u32 len;
1221
1222	/* Reset acquired cids */
1223	for (type = 0; type < MAX_CONN_TYPES; type++) {
1224		u32 vf;
1225
1226		p_cfg = &p_mngr->conn_cfg[type];
1227		if (p_cfg->cid_count) {
1228			p_map = &p_mngr->acquired[type];
1229			len = DIV_ROUND_UP(p_map->max_count,
1230					   sizeof(unsigned long) *
1231					   BITS_PER_BYTE) *
1232			      sizeof(unsigned long);
1233			memset(p_map->cid_map, 0, len);
1234		}
1235
1236		if (!p_cfg->cids_per_vf)
1237			continue;
1238
1239		for (vf = 0; vf < MAX_NUM_VFS; vf++) {
1240			p_map = &p_mngr->acquired_vf[type][vf];
1241			len = DIV_ROUND_UP(p_map->max_count,
1242					   sizeof(unsigned long) *
1243					   BITS_PER_BYTE) *
1244			      sizeof(unsigned long);
1245			memset(p_map->cid_map, 0, len);
1246		}
1247	}
1248}
1249
1250/* CDU Common */
1251#define CDUC_CXT_SIZE_SHIFT \
1252	CDU_REG_CID_ADDR_PARAMS_CONTEXT_SIZE_SHIFT
1253
1254#define CDUC_CXT_SIZE_MASK \
1255	(CDU_REG_CID_ADDR_PARAMS_CONTEXT_SIZE >> CDUC_CXT_SIZE_SHIFT)
1256
1257#define CDUC_BLOCK_WASTE_SHIFT \
1258	CDU_REG_CID_ADDR_PARAMS_BLOCK_WASTE_SHIFT
1259
1260#define CDUC_BLOCK_WASTE_MASK \
1261	(CDU_REG_CID_ADDR_PARAMS_BLOCK_WASTE >> CDUC_BLOCK_WASTE_SHIFT)
1262
1263#define CDUC_NCIB_SHIFT	\
1264	CDU_REG_CID_ADDR_PARAMS_NCIB_SHIFT
1265
1266#define CDUC_NCIB_MASK \
1267	(CDU_REG_CID_ADDR_PARAMS_NCIB >> CDUC_NCIB_SHIFT)
1268
1269#define CDUT_TYPE0_CXT_SIZE_SHIFT \
1270	CDU_REG_SEGMENT0_PARAMS_T0_TID_SIZE_SHIFT
1271
1272#define CDUT_TYPE0_CXT_SIZE_MASK		\
1273	(CDU_REG_SEGMENT0_PARAMS_T0_TID_SIZE >>	\
1274	 CDUT_TYPE0_CXT_SIZE_SHIFT)
1275
1276#define CDUT_TYPE0_BLOCK_WASTE_SHIFT \
1277	CDU_REG_SEGMENT0_PARAMS_T0_TID_BLOCK_WASTE_SHIFT
1278
1279#define CDUT_TYPE0_BLOCK_WASTE_MASK		       \
1280	(CDU_REG_SEGMENT0_PARAMS_T0_TID_BLOCK_WASTE >> \
1281	 CDUT_TYPE0_BLOCK_WASTE_SHIFT)
1282
1283#define CDUT_TYPE0_NCIB_SHIFT \
1284	CDU_REG_SEGMENT0_PARAMS_T0_NUM_TIDS_IN_BLOCK_SHIFT
1285
1286#define CDUT_TYPE0_NCIB_MASK				 \
1287	(CDU_REG_SEGMENT0_PARAMS_T0_NUM_TIDS_IN_BLOCK >> \
1288	 CDUT_TYPE0_NCIB_SHIFT)
1289
1290#define CDUT_TYPE1_CXT_SIZE_SHIFT \
1291	CDU_REG_SEGMENT1_PARAMS_T1_TID_SIZE_SHIFT
1292
1293#define CDUT_TYPE1_CXT_SIZE_MASK		\
1294	(CDU_REG_SEGMENT1_PARAMS_T1_TID_SIZE >>	\
1295	 CDUT_TYPE1_CXT_SIZE_SHIFT)
1296
1297#define CDUT_TYPE1_BLOCK_WASTE_SHIFT \
1298	CDU_REG_SEGMENT1_PARAMS_T1_TID_BLOCK_WASTE_SHIFT
1299
1300#define CDUT_TYPE1_BLOCK_WASTE_MASK		       \
1301	(CDU_REG_SEGMENT1_PARAMS_T1_TID_BLOCK_WASTE >> \
1302	 CDUT_TYPE1_BLOCK_WASTE_SHIFT)
1303
1304#define CDUT_TYPE1_NCIB_SHIFT \
1305	CDU_REG_SEGMENT1_PARAMS_T1_NUM_TIDS_IN_BLOCK_SHIFT
1306
1307#define CDUT_TYPE1_NCIB_MASK				 \
1308	(CDU_REG_SEGMENT1_PARAMS_T1_NUM_TIDS_IN_BLOCK >> \
1309	 CDUT_TYPE1_NCIB_SHIFT)
1310
1311static void qed_cdu_init_common(struct qed_hwfn *p_hwfn)
1312{
1313	u32 page_sz, elems_per_page, block_waste, cxt_size, cdu_params = 0;
1314
1315	/* CDUC - connection configuration */
1316	page_sz = p_hwfn->p_cxt_mngr->clients[ILT_CLI_CDUC].p_size.val;
1317	cxt_size = CONN_CXT_SIZE(p_hwfn);
1318	elems_per_page = ILT_PAGE_IN_BYTES(page_sz) / cxt_size;
1319	block_waste = ILT_PAGE_IN_BYTES(page_sz) - elems_per_page * cxt_size;
1320
1321	SET_FIELD(cdu_params, CDUC_CXT_SIZE, cxt_size);
1322	SET_FIELD(cdu_params, CDUC_BLOCK_WASTE, block_waste);
1323	SET_FIELD(cdu_params, CDUC_NCIB, elems_per_page);
1324	STORE_RT_REG(p_hwfn, CDU_REG_CID_ADDR_PARAMS_RT_OFFSET, cdu_params);
1325
1326	/* CDUT - type-0 tasks configuration */
1327	page_sz = p_hwfn->p_cxt_mngr->clients[ILT_CLI_CDUT].p_size.val;
1328	cxt_size = p_hwfn->p_cxt_mngr->task_type_size[0];
1329	elems_per_page = ILT_PAGE_IN_BYTES(page_sz) / cxt_size;
1330	block_waste = ILT_PAGE_IN_BYTES(page_sz) - elems_per_page * cxt_size;
1331
1332	/* cxt size and block-waste are multipes of 8 */
1333	cdu_params = 0;
1334	SET_FIELD(cdu_params, CDUT_TYPE0_CXT_SIZE, (cxt_size >> 3));
1335	SET_FIELD(cdu_params, CDUT_TYPE0_BLOCK_WASTE, (block_waste >> 3));
1336	SET_FIELD(cdu_params, CDUT_TYPE0_NCIB, elems_per_page);
1337	STORE_RT_REG(p_hwfn, CDU_REG_SEGMENT0_PARAMS_RT_OFFSET, cdu_params);
1338
1339	/* CDUT - type-1 tasks configuration */
1340	cxt_size = p_hwfn->p_cxt_mngr->task_type_size[1];
1341	elems_per_page = ILT_PAGE_IN_BYTES(page_sz) / cxt_size;
1342	block_waste = ILT_PAGE_IN_BYTES(page_sz) - elems_per_page * cxt_size;
1343
1344	/* cxt size and block-waste are multipes of 8 */
1345	cdu_params = 0;
1346	SET_FIELD(cdu_params, CDUT_TYPE1_CXT_SIZE, (cxt_size >> 3));
1347	SET_FIELD(cdu_params, CDUT_TYPE1_BLOCK_WASTE, (block_waste >> 3));
1348	SET_FIELD(cdu_params, CDUT_TYPE1_NCIB, elems_per_page);
1349	STORE_RT_REG(p_hwfn, CDU_REG_SEGMENT1_PARAMS_RT_OFFSET, cdu_params);
1350}
1351
1352/* CDU PF */
1353#define CDU_SEG_REG_TYPE_SHIFT          CDU_SEG_TYPE_OFFSET_REG_TYPE_SHIFT
1354#define CDU_SEG_REG_TYPE_MASK           0x1
1355#define CDU_SEG_REG_OFFSET_SHIFT        0
1356#define CDU_SEG_REG_OFFSET_MASK         CDU_SEG_TYPE_OFFSET_REG_OFFSET_MASK
1357
1358static void qed_cdu_init_pf(struct qed_hwfn *p_hwfn)
1359{
1360	struct qed_ilt_client_cfg *p_cli;
1361	struct qed_tid_seg *p_seg;
1362	u32 cdu_seg_params, offset;
1363	int i;
1364
1365	static const u32 rt_type_offset_arr[] = {
1366		CDU_REG_PF_SEG0_TYPE_OFFSET_RT_OFFSET,
1367		CDU_REG_PF_SEG1_TYPE_OFFSET_RT_OFFSET,
1368		CDU_REG_PF_SEG2_TYPE_OFFSET_RT_OFFSET,
1369		CDU_REG_PF_SEG3_TYPE_OFFSET_RT_OFFSET
1370	};
1371
1372	static const u32 rt_type_offset_fl_arr[] = {
1373		CDU_REG_PF_FL_SEG0_TYPE_OFFSET_RT_OFFSET,
1374		CDU_REG_PF_FL_SEG1_TYPE_OFFSET_RT_OFFSET,
1375		CDU_REG_PF_FL_SEG2_TYPE_OFFSET_RT_OFFSET,
1376		CDU_REG_PF_FL_SEG3_TYPE_OFFSET_RT_OFFSET
1377	};
1378
1379	p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_CDUT];
1380
1381	/* There are initializations only for CDUT during pf Phase */
1382	for (i = 0; i < NUM_TASK_PF_SEGMENTS; i++) {
1383		/* Segment 0 */
1384		p_seg = qed_cxt_tid_seg_info(p_hwfn, i);
1385		if (!p_seg)
1386			continue;
1387
1388		/* Note: start_line is already adjusted for the CDU
1389		 * segment register granularity, so we just need to
1390		 * divide. Adjustment is implicit as we assume ILT
1391		 * Page size is larger than 32K!
1392		 */
1393		offset = (ILT_PAGE_IN_BYTES(p_cli->p_size.val) *
1394			  (p_cli->pf_blks[CDUT_SEG_BLK(i)].start_line -
1395			   p_cli->first.val)) / CDUT_SEG_ALIGNMET_IN_BYTES;
1396
1397		cdu_seg_params = 0;
1398		SET_FIELD(cdu_seg_params, CDU_SEG_REG_TYPE, p_seg->type);
1399		SET_FIELD(cdu_seg_params, CDU_SEG_REG_OFFSET, offset);
1400		STORE_RT_REG(p_hwfn, rt_type_offset_arr[i], cdu_seg_params);
1401
1402		offset = (ILT_PAGE_IN_BYTES(p_cli->p_size.val) *
1403			  (p_cli->pf_blks[CDUT_FL_SEG_BLK(i, PF)].start_line -
1404			   p_cli->first.val)) / CDUT_SEG_ALIGNMET_IN_BYTES;
1405
1406		cdu_seg_params = 0;
1407		SET_FIELD(cdu_seg_params, CDU_SEG_REG_TYPE, p_seg->type);
1408		SET_FIELD(cdu_seg_params, CDU_SEG_REG_OFFSET, offset);
1409		STORE_RT_REG(p_hwfn, rt_type_offset_fl_arr[i], cdu_seg_params);
1410	}
1411}
1412
1413void qed_qm_init_pf(struct qed_hwfn *p_hwfn,
1414		    struct qed_ptt *p_ptt, bool is_pf_loading)
1415{
1416	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
1417	struct qed_qm_pf_rt_init_params params;
1418	struct qed_qm_iids iids;
1419
1420	memset(&iids, 0, sizeof(iids));
1421	qed_cxt_qm_iids(p_hwfn, &iids);
1422
1423	memset(&params, 0, sizeof(params));
1424	params.port_id = p_hwfn->port_id;
1425	params.pf_id = p_hwfn->rel_pf_id;
1426	params.max_phys_tcs_per_port = qm_info->max_phys_tcs_per_port;
1427	params.is_pf_loading = is_pf_loading;
1428	params.num_pf_cids = iids.cids;
1429	params.num_vf_cids = iids.vf_cids;
1430	params.num_tids = iids.tids;
1431	params.start_pq = qm_info->start_pq;
1432	params.num_pf_pqs = qm_info->num_pqs - qm_info->num_vf_pqs;
1433	params.num_vf_pqs = qm_info->num_vf_pqs;
1434	params.start_vport = qm_info->start_vport;
1435	params.num_vports = qm_info->num_vports;
1436	params.pf_wfq = qm_info->pf_wfq;
1437	params.pf_rl = qm_info->pf_rl;
1438	params.pq_params = qm_info->qm_pq_params;
1439	params.vport_params = qm_info->qm_vport_params;
1440
1441	qed_qm_pf_rt_init(p_hwfn, p_ptt, &params);
1442}
1443
1444/* CM PF */
1445static void qed_cm_init_pf(struct qed_hwfn *p_hwfn)
1446{
1447	/* XCM pure-LB queue */
1448	STORE_RT_REG(p_hwfn, XCM_REG_CON_PHY_Q3_RT_OFFSET,
1449		     qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_LB));
1450}
1451
1452/* DQ PF */
1453static void qed_dq_init_pf(struct qed_hwfn *p_hwfn)
1454{
1455	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
1456	u32 dq_pf_max_cid = 0, dq_vf_max_cid = 0;
1457
1458	dq_pf_max_cid += (p_mngr->conn_cfg[0].cid_count >> DQ_RANGE_SHIFT);
1459	STORE_RT_REG(p_hwfn, DORQ_REG_PF_MAX_ICID_0_RT_OFFSET, dq_pf_max_cid);
1460
1461	dq_vf_max_cid += (p_mngr->conn_cfg[0].cids_per_vf >> DQ_RANGE_SHIFT);
1462	STORE_RT_REG(p_hwfn, DORQ_REG_VF_MAX_ICID_0_RT_OFFSET, dq_vf_max_cid);
1463
1464	dq_pf_max_cid += (p_mngr->conn_cfg[1].cid_count >> DQ_RANGE_SHIFT);
1465	STORE_RT_REG(p_hwfn, DORQ_REG_PF_MAX_ICID_1_RT_OFFSET, dq_pf_max_cid);
1466
1467	dq_vf_max_cid += (p_mngr->conn_cfg[1].cids_per_vf >> DQ_RANGE_SHIFT);
1468	STORE_RT_REG(p_hwfn, DORQ_REG_VF_MAX_ICID_1_RT_OFFSET, dq_vf_max_cid);
1469
1470	dq_pf_max_cid += (p_mngr->conn_cfg[2].cid_count >> DQ_RANGE_SHIFT);
1471	STORE_RT_REG(p_hwfn, DORQ_REG_PF_MAX_ICID_2_RT_OFFSET, dq_pf_max_cid);
1472
1473	dq_vf_max_cid += (p_mngr->conn_cfg[2].cids_per_vf >> DQ_RANGE_SHIFT);
1474	STORE_RT_REG(p_hwfn, DORQ_REG_VF_MAX_ICID_2_RT_OFFSET, dq_vf_max_cid);
1475
1476	dq_pf_max_cid += (p_mngr->conn_cfg[3].cid_count >> DQ_RANGE_SHIFT);
1477	STORE_RT_REG(p_hwfn, DORQ_REG_PF_MAX_ICID_3_RT_OFFSET, dq_pf_max_cid);
1478
1479	dq_vf_max_cid += (p_mngr->conn_cfg[3].cids_per_vf >> DQ_RANGE_SHIFT);
1480	STORE_RT_REG(p_hwfn, DORQ_REG_VF_MAX_ICID_3_RT_OFFSET, dq_vf_max_cid);
1481
1482	dq_pf_max_cid += (p_mngr->conn_cfg[4].cid_count >> DQ_RANGE_SHIFT);
1483	STORE_RT_REG(p_hwfn, DORQ_REG_PF_MAX_ICID_4_RT_OFFSET, dq_pf_max_cid);
1484
1485	dq_vf_max_cid += (p_mngr->conn_cfg[4].cids_per_vf >> DQ_RANGE_SHIFT);
1486	STORE_RT_REG(p_hwfn, DORQ_REG_VF_MAX_ICID_4_RT_OFFSET, dq_vf_max_cid);
1487
1488	dq_pf_max_cid += (p_mngr->conn_cfg[5].cid_count >> DQ_RANGE_SHIFT);
1489	STORE_RT_REG(p_hwfn, DORQ_REG_PF_MAX_ICID_5_RT_OFFSET, dq_pf_max_cid);
1490
1491	dq_vf_max_cid += (p_mngr->conn_cfg[5].cids_per_vf >> DQ_RANGE_SHIFT);
1492	STORE_RT_REG(p_hwfn, DORQ_REG_VF_MAX_ICID_5_RT_OFFSET, dq_vf_max_cid);
1493
1494	/* Connection types 6 & 7 are not in use, yet they must be configured
1495	 * as the highest possible connection. Not configuring them means the
1496	 * defaults will be  used, and with a large number of cids a bug may
1497	 * occur, if the defaults will be smaller than dq_pf_max_cid /
1498	 * dq_vf_max_cid.
1499	 */
1500	STORE_RT_REG(p_hwfn, DORQ_REG_PF_MAX_ICID_6_RT_OFFSET, dq_pf_max_cid);
1501	STORE_RT_REG(p_hwfn, DORQ_REG_VF_MAX_ICID_6_RT_OFFSET, dq_vf_max_cid);
1502
1503	STORE_RT_REG(p_hwfn, DORQ_REG_PF_MAX_ICID_7_RT_OFFSET, dq_pf_max_cid);
1504	STORE_RT_REG(p_hwfn, DORQ_REG_VF_MAX_ICID_7_RT_OFFSET, dq_vf_max_cid);
1505}
1506
1507static void qed_ilt_bounds_init(struct qed_hwfn *p_hwfn)
1508{
1509	struct qed_ilt_client_cfg *ilt_clients;
1510	int i;
1511
1512	ilt_clients = p_hwfn->p_cxt_mngr->clients;
1513	for_each_ilt_valid_client(i, ilt_clients) {
1514		STORE_RT_REG(p_hwfn,
1515			     ilt_clients[i].first.reg,
1516			     ilt_clients[i].first.val);
1517		STORE_RT_REG(p_hwfn,
1518			     ilt_clients[i].last.reg, ilt_clients[i].last.val);
1519		STORE_RT_REG(p_hwfn,
1520			     ilt_clients[i].p_size.reg,
1521			     ilt_clients[i].p_size.val);
1522	}
1523}
1524
1525static void qed_ilt_vf_bounds_init(struct qed_hwfn *p_hwfn)
1526{
1527	struct qed_ilt_client_cfg *p_cli;
1528	u32 blk_factor;
1529
1530	/* For simplicty  we set the 'block' to be an ILT page */
1531	if (p_hwfn->cdev->p_iov_info) {
1532		struct qed_hw_sriov_info *p_iov = p_hwfn->cdev->p_iov_info;
1533
1534		STORE_RT_REG(p_hwfn,
1535			     PSWRQ2_REG_VF_BASE_RT_OFFSET,
1536			     p_iov->first_vf_in_pf);
1537		STORE_RT_REG(p_hwfn,
1538			     PSWRQ2_REG_VF_LAST_ILT_RT_OFFSET,
1539			     p_iov->first_vf_in_pf + p_iov->total_vfs);
1540	}
1541
1542	p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_CDUC];
1543	blk_factor = ilog2(ILT_PAGE_IN_BYTES(p_cli->p_size.val) >> 10);
1544	if (p_cli->active) {
1545		STORE_RT_REG(p_hwfn,
1546			     PSWRQ2_REG_CDUC_BLOCKS_FACTOR_RT_OFFSET,
1547			     blk_factor);
1548		STORE_RT_REG(p_hwfn,
1549			     PSWRQ2_REG_CDUC_NUMBER_OF_PF_BLOCKS_RT_OFFSET,
1550			     p_cli->pf_total_lines);
1551		STORE_RT_REG(p_hwfn,
1552			     PSWRQ2_REG_CDUC_VF_BLOCKS_RT_OFFSET,
1553			     p_cli->vf_total_lines);
1554	}
1555
1556	p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_CDUT];
1557	blk_factor = ilog2(ILT_PAGE_IN_BYTES(p_cli->p_size.val) >> 10);
1558	if (p_cli->active) {
1559		STORE_RT_REG(p_hwfn,
1560			     PSWRQ2_REG_CDUT_BLOCKS_FACTOR_RT_OFFSET,
1561			     blk_factor);
1562		STORE_RT_REG(p_hwfn,
1563			     PSWRQ2_REG_CDUT_NUMBER_OF_PF_BLOCKS_RT_OFFSET,
1564			     p_cli->pf_total_lines);
1565		STORE_RT_REG(p_hwfn,
1566			     PSWRQ2_REG_CDUT_VF_BLOCKS_RT_OFFSET,
1567			     p_cli->vf_total_lines);
1568	}
1569
1570	p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_TM];
1571	blk_factor = ilog2(ILT_PAGE_IN_BYTES(p_cli->p_size.val) >> 10);
1572	if (p_cli->active) {
1573		STORE_RT_REG(p_hwfn,
1574			     PSWRQ2_REG_TM_BLOCKS_FACTOR_RT_OFFSET, blk_factor);
1575		STORE_RT_REG(p_hwfn,
1576			     PSWRQ2_REG_TM_NUMBER_OF_PF_BLOCKS_RT_OFFSET,
1577			     p_cli->pf_total_lines);
1578		STORE_RT_REG(p_hwfn,
1579			     PSWRQ2_REG_TM_VF_BLOCKS_RT_OFFSET,
1580			     p_cli->vf_total_lines);
1581	}
1582}
1583
1584/* ILT (PSWRQ2) PF */
1585static void qed_ilt_init_pf(struct qed_hwfn *p_hwfn)
1586{
1587	struct qed_ilt_client_cfg *clients;
1588	struct qed_cxt_mngr *p_mngr;
1589	struct phys_mem_desc *p_shdw;
1590	u32 line, rt_offst, i;
1591
1592	qed_ilt_bounds_init(p_hwfn);
1593	qed_ilt_vf_bounds_init(p_hwfn);
1594
1595	p_mngr = p_hwfn->p_cxt_mngr;
1596	p_shdw = p_mngr->ilt_shadow;
1597	clients = p_hwfn->p_cxt_mngr->clients;
1598
1599	for_each_ilt_valid_client(i, clients) {
1600		/** Client's 1st val and RT array are absolute, ILT shadows'
1601		 *  lines are relative.
1602		 */
1603		line = clients[i].first.val - p_mngr->pf_start_line;
1604		rt_offst = PSWRQ2_REG_ILT_MEMORY_RT_OFFSET +
1605			   clients[i].first.val * ILT_ENTRY_IN_REGS;
1606
1607		for (; line <= clients[i].last.val - p_mngr->pf_start_line;
1608		     line++, rt_offst += ILT_ENTRY_IN_REGS) {
1609			u64 ilt_hw_entry = 0;
1610
1611			/** p_virt could be NULL incase of dynamic
1612			 *  allocation
1613			 */
1614			if (p_shdw[line].virt_addr) {
1615				SET_FIELD(ilt_hw_entry, ILT_ENTRY_VALID, 1ULL);
1616				SET_FIELD(ilt_hw_entry, ILT_ENTRY_PHY_ADDR,
1617					  (p_shdw[line].phys_addr >> 12));
1618
1619				DP_VERBOSE(p_hwfn, QED_MSG_ILT,
1620					   "Setting RT[0x%08x] from ILT[0x%08x] [Client is %d] to Physical addr: 0x%llx\n",
1621					   rt_offst, line, i,
1622					   (u64)(p_shdw[line].phys_addr >> 12));
1623			}
1624
1625			STORE_RT_REG_AGG(p_hwfn, rt_offst, ilt_hw_entry);
1626		}
1627	}
1628}
1629
1630/* SRC (Searcher) PF */
1631static void qed_src_init_pf(struct qed_hwfn *p_hwfn)
1632{
1633	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
1634	u32 rounded_conn_num, conn_num, conn_max;
1635	struct qed_src_iids src_iids;
1636
1637	memset(&src_iids, 0, sizeof(src_iids));
1638	qed_cxt_src_iids(p_mngr, &src_iids);
1639	conn_num = src_iids.pf_cids + src_iids.per_vf_cids * p_mngr->vf_count;
1640	if (!conn_num)
1641		return;
1642
1643	conn_max = max_t(u32, conn_num, SRC_MIN_NUM_ELEMS);
1644	rounded_conn_num = roundup_pow_of_two(conn_max);
1645
1646	STORE_RT_REG(p_hwfn, SRC_REG_COUNTFREE_RT_OFFSET, conn_num);
1647	STORE_RT_REG(p_hwfn, SRC_REG_NUMBER_HASH_BITS_RT_OFFSET,
1648		     ilog2(rounded_conn_num));
1649
1650	STORE_RT_REG_AGG(p_hwfn, SRC_REG_FIRSTFREE_RT_OFFSET,
1651			 p_hwfn->p_cxt_mngr->src_t2.first_free);
1652	STORE_RT_REG_AGG(p_hwfn, SRC_REG_LASTFREE_RT_OFFSET,
1653			 p_hwfn->p_cxt_mngr->src_t2.last_free);
1654}
1655
1656/* Timers PF */
1657#define TM_CFG_NUM_IDS_SHIFT            0
1658#define TM_CFG_NUM_IDS_MASK             0xFFFFULL
1659#define TM_CFG_PRE_SCAN_OFFSET_SHIFT    16
1660#define TM_CFG_PRE_SCAN_OFFSET_MASK     0x1FFULL
1661#define TM_CFG_PARENT_PF_SHIFT          25
1662#define TM_CFG_PARENT_PF_MASK           0x7ULL
1663
1664#define TM_CFG_CID_PRE_SCAN_ROWS_SHIFT  30
1665#define TM_CFG_CID_PRE_SCAN_ROWS_MASK   0x1FFULL
1666
1667#define TM_CFG_TID_OFFSET_SHIFT         30
1668#define TM_CFG_TID_OFFSET_MASK          0x7FFFFULL
1669#define TM_CFG_TID_PRE_SCAN_ROWS_SHIFT  49
1670#define TM_CFG_TID_PRE_SCAN_ROWS_MASK   0x1FFULL
1671
1672static void qed_tm_init_pf(struct qed_hwfn *p_hwfn)
1673{
1674	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
1675	u32 active_seg_mask = 0, tm_offset, rt_reg;
1676	struct qed_tm_iids tm_iids;
1677	u64 cfg_word;
1678	u8 i;
1679
1680	memset(&tm_iids, 0, sizeof(tm_iids));
1681	qed_cxt_tm_iids(p_hwfn, p_mngr, &tm_iids);
1682
1683	/* @@@TBD No pre-scan for now */
1684
1685	/* Note: We assume consecutive VFs for a PF */
1686	for (i = 0; i < p_mngr->vf_count; i++) {
1687		cfg_word = 0;
1688		SET_FIELD(cfg_word, TM_CFG_NUM_IDS, tm_iids.per_vf_cids);
1689		SET_FIELD(cfg_word, TM_CFG_PRE_SCAN_OFFSET, 0);
1690		SET_FIELD(cfg_word, TM_CFG_PARENT_PF, p_hwfn->rel_pf_id);
1691		SET_FIELD(cfg_word, TM_CFG_CID_PRE_SCAN_ROWS, 0);
1692		rt_reg = TM_REG_CONFIG_CONN_MEM_RT_OFFSET +
1693		    (sizeof(cfg_word) / sizeof(u32)) *
1694		    (p_hwfn->cdev->p_iov_info->first_vf_in_pf + i);
1695		STORE_RT_REG_AGG(p_hwfn, rt_reg, cfg_word);
1696	}
1697
1698	cfg_word = 0;
1699	SET_FIELD(cfg_word, TM_CFG_NUM_IDS, tm_iids.pf_cids);
1700	SET_FIELD(cfg_word, TM_CFG_PRE_SCAN_OFFSET, 0);
1701	SET_FIELD(cfg_word, TM_CFG_PARENT_PF, 0);	/* n/a for PF */
1702	SET_FIELD(cfg_word, TM_CFG_CID_PRE_SCAN_ROWS, 0);	/* scan all   */
1703
1704	rt_reg = TM_REG_CONFIG_CONN_MEM_RT_OFFSET +
1705	    (sizeof(cfg_word) / sizeof(u32)) *
1706	    (NUM_OF_VFS(p_hwfn->cdev) + p_hwfn->rel_pf_id);
1707	STORE_RT_REG_AGG(p_hwfn, rt_reg, cfg_word);
1708
1709	/* enale scan */
1710	STORE_RT_REG(p_hwfn, TM_REG_PF_ENABLE_CONN_RT_OFFSET,
1711		     tm_iids.pf_cids ? 0x1 : 0x0);
1712
1713	/* @@@TBD how to enable the scan for the VFs */
1714
1715	tm_offset = tm_iids.per_vf_cids;
1716
1717	/* Note: We assume consecutive VFs for a PF */
1718	for (i = 0; i < p_mngr->vf_count; i++) {
1719		cfg_word = 0;
1720		SET_FIELD(cfg_word, TM_CFG_NUM_IDS, tm_iids.per_vf_tids);
1721		SET_FIELD(cfg_word, TM_CFG_PRE_SCAN_OFFSET, 0);
1722		SET_FIELD(cfg_word, TM_CFG_PARENT_PF, p_hwfn->rel_pf_id);
1723		SET_FIELD(cfg_word, TM_CFG_TID_OFFSET, tm_offset);
1724		SET_FIELD(cfg_word, TM_CFG_TID_PRE_SCAN_ROWS, (u64) 0);
1725
1726		rt_reg = TM_REG_CONFIG_TASK_MEM_RT_OFFSET +
1727		    (sizeof(cfg_word) / sizeof(u32)) *
1728		    (p_hwfn->cdev->p_iov_info->first_vf_in_pf + i);
1729
1730		STORE_RT_REG_AGG(p_hwfn, rt_reg, cfg_word);
1731	}
1732
1733	tm_offset = tm_iids.pf_cids;
1734	for (i = 0; i < NUM_TASK_PF_SEGMENTS; i++) {
1735		cfg_word = 0;
1736		SET_FIELD(cfg_word, TM_CFG_NUM_IDS, tm_iids.pf_tids[i]);
1737		SET_FIELD(cfg_word, TM_CFG_PRE_SCAN_OFFSET, 0);
1738		SET_FIELD(cfg_word, TM_CFG_PARENT_PF, 0);
1739		SET_FIELD(cfg_word, TM_CFG_TID_OFFSET, tm_offset);
1740		SET_FIELD(cfg_word, TM_CFG_TID_PRE_SCAN_ROWS, (u64) 0);
1741
1742		rt_reg = TM_REG_CONFIG_TASK_MEM_RT_OFFSET +
1743		    (sizeof(cfg_word) / sizeof(u32)) *
1744		    (NUM_OF_VFS(p_hwfn->cdev) +
1745		     p_hwfn->rel_pf_id * NUM_TASK_PF_SEGMENTS + i);
1746
1747		STORE_RT_REG_AGG(p_hwfn, rt_reg, cfg_word);
1748		active_seg_mask |= (tm_iids.pf_tids[i] ? BIT(i) : 0);
1749
1750		tm_offset += tm_iids.pf_tids[i];
1751	}
1752
1753	if (QED_IS_RDMA_PERSONALITY(p_hwfn))
1754		active_seg_mask = 0;
1755
1756	STORE_RT_REG(p_hwfn, TM_REG_PF_ENABLE_TASK_RT_OFFSET, active_seg_mask);
1757
1758	/* @@@TBD how to enable the scan for the VFs */
1759}
1760
1761static void qed_prs_init_common(struct qed_hwfn *p_hwfn)
1762{
1763	if ((p_hwfn->hw_info.personality == QED_PCI_FCOE) &&
1764	    p_hwfn->pf_params.fcoe_pf_params.is_target)
1765		STORE_RT_REG(p_hwfn,
1766			     PRS_REG_SEARCH_RESP_INITIATOR_TYPE_RT_OFFSET, 0);
1767}
1768
1769static void qed_prs_init_pf(struct qed_hwfn *p_hwfn)
1770{
1771	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
1772	struct qed_conn_type_cfg *p_fcoe;
1773	struct qed_tid_seg *p_tid;
1774
1775	p_fcoe = &p_mngr->conn_cfg[PROTOCOLID_FCOE];
1776
1777	/* If FCoE is active set the MAX OX_ID (tid) in the Parser */
1778	if (!p_fcoe->cid_count)
1779		return;
1780
1781	p_tid = &p_fcoe->tid_seg[QED_CXT_FCOE_TID_SEG];
1782	if (p_hwfn->pf_params.fcoe_pf_params.is_target) {
1783		STORE_RT_REG_AGG(p_hwfn,
1784				 PRS_REG_TASK_ID_MAX_TARGET_PF_RT_OFFSET,
1785				 p_tid->count);
1786	} else {
1787		STORE_RT_REG_AGG(p_hwfn,
1788				 PRS_REG_TASK_ID_MAX_INITIATOR_PF_RT_OFFSET,
1789				 p_tid->count);
1790	}
1791}
1792
1793void qed_cxt_hw_init_common(struct qed_hwfn *p_hwfn)
1794{
1795	qed_cdu_init_common(p_hwfn);
1796	qed_prs_init_common(p_hwfn);
1797}
1798
1799void qed_cxt_hw_init_pf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
1800{
1801	qed_qm_init_pf(p_hwfn, p_ptt, true);
1802	qed_cm_init_pf(p_hwfn);
1803	qed_dq_init_pf(p_hwfn);
1804	qed_cdu_init_pf(p_hwfn);
1805	qed_ilt_init_pf(p_hwfn);
1806	qed_src_init_pf(p_hwfn);
1807	qed_tm_init_pf(p_hwfn);
1808	qed_prs_init_pf(p_hwfn);
1809}
1810
1811int _qed_cxt_acquire_cid(struct qed_hwfn *p_hwfn,
1812			 enum protocol_type type, u32 *p_cid, u8 vfid)
1813{
1814	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
1815	struct qed_cid_acquired_map *p_map;
1816	u32 rel_cid;
1817
1818	if (type >= MAX_CONN_TYPES) {
1819		DP_NOTICE(p_hwfn, "Invalid protocol type %d", type);
1820		return -EINVAL;
1821	}
1822
1823	if (vfid >= MAX_NUM_VFS && vfid != QED_CXT_PF_CID) {
1824		DP_NOTICE(p_hwfn, "VF [%02x] is out of range\n", vfid);
1825		return -EINVAL;
1826	}
1827
1828	/* Determine the right map to take this CID from */
1829	if (vfid == QED_CXT_PF_CID)
1830		p_map = &p_mngr->acquired[type];
1831	else
1832		p_map = &p_mngr->acquired_vf[type][vfid];
1833
1834	if (!p_map->cid_map) {
1835		DP_NOTICE(p_hwfn, "Invalid protocol type %d", type);
1836		return -EINVAL;
1837	}
1838
1839	rel_cid = find_first_zero_bit(p_map->cid_map, p_map->max_count);
1840
1841	if (rel_cid >= p_map->max_count) {
1842		DP_NOTICE(p_hwfn, "no CID available for protocol %d\n", type);
1843		return -EINVAL;
1844	}
1845
1846	__set_bit(rel_cid, p_map->cid_map);
1847
1848	*p_cid = rel_cid + p_map->start_cid;
1849
1850	DP_VERBOSE(p_hwfn, QED_MSG_CXT,
1851		   "Acquired cid 0x%08x [rel. %08x] vfid %02x type %d\n",
1852		   *p_cid, rel_cid, vfid, type);
1853
1854	return 0;
1855}
1856
1857int qed_cxt_acquire_cid(struct qed_hwfn *p_hwfn,
1858			enum protocol_type type, u32 *p_cid)
1859{
1860	return _qed_cxt_acquire_cid(p_hwfn, type, p_cid, QED_CXT_PF_CID);
1861}
1862
1863static bool qed_cxt_test_cid_acquired(struct qed_hwfn *p_hwfn,
1864				      u32 cid,
1865				      u8 vfid,
1866				      enum protocol_type *p_type,
1867				      struct qed_cid_acquired_map **pp_map)
1868{
1869	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
1870	u32 rel_cid;
1871
1872	/* Iterate over protocols and find matching cid range */
1873	for (*p_type = 0; *p_type < MAX_CONN_TYPES; (*p_type)++) {
1874		if (vfid == QED_CXT_PF_CID)
1875			*pp_map = &p_mngr->acquired[*p_type];
1876		else
1877			*pp_map = &p_mngr->acquired_vf[*p_type][vfid];
1878
1879		if (!((*pp_map)->cid_map))
1880			continue;
1881		if (cid >= (*pp_map)->start_cid &&
1882		    cid < (*pp_map)->start_cid + (*pp_map)->max_count)
1883			break;
1884	}
1885
1886	if (*p_type == MAX_CONN_TYPES) {
1887		DP_NOTICE(p_hwfn, "Invalid CID %d vfid %02x", cid, vfid);
1888		goto fail;
1889	}
1890
1891	rel_cid = cid - (*pp_map)->start_cid;
1892	if (!test_bit(rel_cid, (*pp_map)->cid_map)) {
1893		DP_NOTICE(p_hwfn, "CID %d [vifd %02x] not acquired",
1894			  cid, vfid);
1895		goto fail;
1896	}
1897
1898	return true;
1899fail:
1900	*p_type = MAX_CONN_TYPES;
1901	*pp_map = NULL;
1902	return false;
1903}
1904
1905void _qed_cxt_release_cid(struct qed_hwfn *p_hwfn, u32 cid, u8 vfid)
1906{
1907	struct qed_cid_acquired_map *p_map = NULL;
1908	enum protocol_type type;
1909	bool b_acquired;
1910	u32 rel_cid;
1911
1912	if (vfid != QED_CXT_PF_CID && vfid > MAX_NUM_VFS) {
1913		DP_NOTICE(p_hwfn,
1914			  "Trying to return incorrect CID belonging to VF %02x\n",
1915			  vfid);
1916		return;
1917	}
1918
1919	/* Test acquired and find matching per-protocol map */
1920	b_acquired = qed_cxt_test_cid_acquired(p_hwfn, cid, vfid,
1921					       &type, &p_map);
1922
1923	if (!b_acquired)
1924		return;
1925
1926	rel_cid = cid - p_map->start_cid;
1927	clear_bit(rel_cid, p_map->cid_map);
1928
1929	DP_VERBOSE(p_hwfn, QED_MSG_CXT,
1930		   "Released CID 0x%08x [rel. %08x] vfid %02x type %d\n",
1931		   cid, rel_cid, vfid, type);
1932}
1933
1934void qed_cxt_release_cid(struct qed_hwfn *p_hwfn, u32 cid)
1935{
1936	_qed_cxt_release_cid(p_hwfn, cid, QED_CXT_PF_CID);
1937}
1938
1939int qed_cxt_get_cid_info(struct qed_hwfn *p_hwfn, struct qed_cxt_info *p_info)
1940{
1941	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
1942	struct qed_cid_acquired_map *p_map = NULL;
1943	u32 conn_cxt_size, hw_p_size, cxts_per_p, line;
1944	enum protocol_type type;
1945	bool b_acquired;
1946
1947	/* Test acquired and find matching per-protocol map */
1948	b_acquired = qed_cxt_test_cid_acquired(p_hwfn, p_info->iid,
1949					       QED_CXT_PF_CID, &type, &p_map);
1950
1951	if (!b_acquired)
1952		return -EINVAL;
1953
1954	/* set the protocl type */
1955	p_info->type = type;
1956
1957	/* compute context virtual pointer */
1958	hw_p_size = p_hwfn->p_cxt_mngr->clients[ILT_CLI_CDUC].p_size.val;
1959
1960	conn_cxt_size = CONN_CXT_SIZE(p_hwfn);
1961	cxts_per_p = ILT_PAGE_IN_BYTES(hw_p_size) / conn_cxt_size;
1962	line = p_info->iid / cxts_per_p;
1963
1964	/* Make sure context is allocated (dynamic allocation) */
1965	if (!p_mngr->ilt_shadow[line].virt_addr)
1966		return -EINVAL;
1967
1968	p_info->p_cxt = p_mngr->ilt_shadow[line].virt_addr +
1969			p_info->iid % cxts_per_p * conn_cxt_size;
1970
1971	DP_VERBOSE(p_hwfn, (QED_MSG_ILT | QED_MSG_CXT),
1972		   "Accessing ILT shadow[%d]: CXT pointer is at %p (for iid %d)\n",
1973		   p_info->iid / cxts_per_p, p_info->p_cxt, p_info->iid);
1974
1975	return 0;
1976}
1977
1978static void qed_rdma_set_pf_params(struct qed_hwfn *p_hwfn,
1979				   struct qed_rdma_pf_params *p_params,
1980				   u32 num_tasks)
1981{
1982	u32 num_cons, num_qps;
1983	enum protocol_type proto;
1984
1985	if (p_hwfn->mcp_info->func_info.protocol == QED_PCI_ETH_RDMA) {
1986		DP_VERBOSE(p_hwfn, QED_MSG_SP,
1987			   "Current day drivers don't support RoCE & iWARP simultaneously on the same PF. Default to RoCE-only\n");
1988		p_hwfn->hw_info.personality = QED_PCI_ETH_ROCE;
1989	}
1990
1991	switch (p_hwfn->hw_info.personality) {
1992	case QED_PCI_ETH_IWARP:
1993		/* Each QP requires one connection */
1994		num_cons = min_t(u32, IWARP_MAX_QPS, p_params->num_qps);
1995		proto = PROTOCOLID_IWARP;
1996		break;
1997	case QED_PCI_ETH_ROCE:
1998		num_qps = min_t(u32, ROCE_MAX_QPS, p_params->num_qps);
1999		num_cons = num_qps * 2;	/* each QP requires two connections */
2000		proto = PROTOCOLID_ROCE;
2001		break;
2002	default:
2003		return;
2004	}
2005
2006	if (num_cons && num_tasks) {
2007		u32 num_srqs, num_xrc_srqs;
2008
2009		qed_cxt_set_proto_cid_count(p_hwfn, proto, num_cons, 0);
2010
2011		/* Deliberatly passing ROCE for tasks id. This is because
2012		 * iWARP / RoCE share the task id.
2013		 */
2014		qed_cxt_set_proto_tid_count(p_hwfn, PROTOCOLID_ROCE,
2015					    QED_CXT_ROCE_TID_SEG, 1,
2016					    num_tasks, false);
2017
2018		num_srqs = min_t(u32, QED_RDMA_MAX_SRQS, p_params->num_srqs);
2019
2020		/* XRC SRQs populate a single ILT page */
2021		num_xrc_srqs = qed_cxt_xrc_srqs_per_page(p_hwfn);
2022
2023		qed_cxt_set_srq_count(p_hwfn, num_srqs, num_xrc_srqs);
2024	} else {
2025		DP_INFO(p_hwfn->cdev,
2026			"RDMA personality used without setting params!\n");
2027	}
2028}
2029
2030int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks)
2031{
2032	/* Set the number of required CORE connections */
2033	u32 core_cids = 1; /* SPQ */
2034
2035	if (p_hwfn->using_ll2)
2036		core_cids += 4;
2037	qed_cxt_set_proto_cid_count(p_hwfn, PROTOCOLID_CORE, core_cids, 0);
2038
2039	switch (p_hwfn->hw_info.personality) {
2040	case QED_PCI_ETH_RDMA:
2041	case QED_PCI_ETH_IWARP:
2042	case QED_PCI_ETH_ROCE:
2043	{
2044			qed_rdma_set_pf_params(p_hwfn,
2045					       &p_hwfn->
2046					       pf_params.rdma_pf_params,
2047					       rdma_tasks);
2048		/* no need for break since RoCE coexist with Ethernet */
2049	}
2050		fallthrough;
2051	case QED_PCI_ETH:
2052	{
2053		struct qed_eth_pf_params *p_params =
2054		    &p_hwfn->pf_params.eth_pf_params;
2055
2056		if (!p_params->num_vf_cons)
2057			p_params->num_vf_cons =
2058			    ETH_PF_PARAMS_VF_CONS_DEFAULT;
2059		qed_cxt_set_proto_cid_count(p_hwfn, PROTOCOLID_ETH,
2060					    p_params->num_cons,
2061					    p_params->num_vf_cons);
2062		p_hwfn->p_cxt_mngr->arfs_count = p_params->num_arfs_filters;
2063		break;
2064	}
2065	case QED_PCI_FCOE:
2066	{
2067		struct qed_fcoe_pf_params *p_params;
2068
2069		p_params = &p_hwfn->pf_params.fcoe_pf_params;
2070
2071		if (p_params->num_cons && p_params->num_tasks) {
2072			qed_cxt_set_proto_cid_count(p_hwfn,
2073						    PROTOCOLID_FCOE,
2074						    p_params->num_cons,
2075						    0);
2076
2077			qed_cxt_set_proto_tid_count(p_hwfn, PROTOCOLID_FCOE,
2078						    QED_CXT_FCOE_TID_SEG, 0,
2079						    p_params->num_tasks, true);
2080		} else {
2081			DP_INFO(p_hwfn->cdev,
2082				"Fcoe personality used without setting params!\n");
2083		}
2084		break;
2085	}
2086	case QED_PCI_ISCSI:
2087	{
2088		struct qed_iscsi_pf_params *p_params;
2089
2090		p_params = &p_hwfn->pf_params.iscsi_pf_params;
2091
2092		if (p_params->num_cons && p_params->num_tasks) {
2093			qed_cxt_set_proto_cid_count(p_hwfn,
2094						    PROTOCOLID_ISCSI,
2095						    p_params->num_cons,
2096						    0);
2097
2098			qed_cxt_set_proto_tid_count(p_hwfn,
2099						    PROTOCOLID_ISCSI,
2100						    QED_CXT_ISCSI_TID_SEG,
2101						    0,
2102						    p_params->num_tasks,
2103						    true);
2104		} else {
2105			DP_INFO(p_hwfn->cdev,
2106				"Iscsi personality used without setting params!\n");
2107		}
2108		break;
2109	}
2110	default:
2111		return -EINVAL;
2112	}
2113
2114	return 0;
2115}
2116
2117int qed_cxt_get_tid_mem_info(struct qed_hwfn *p_hwfn,
2118			     struct qed_tid_mem *p_info)
2119{
2120	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
2121	u32 proto, seg, total_lines, i, shadow_line;
2122	struct qed_ilt_client_cfg *p_cli;
2123	struct qed_ilt_cli_blk *p_fl_seg;
2124	struct qed_tid_seg *p_seg_info;
2125
2126	/* Verify the personality */
2127	switch (p_hwfn->hw_info.personality) {
2128	case QED_PCI_FCOE:
2129		proto = PROTOCOLID_FCOE;
2130		seg = QED_CXT_FCOE_TID_SEG;
2131		break;
2132	case QED_PCI_ISCSI:
2133		proto = PROTOCOLID_ISCSI;
2134		seg = QED_CXT_ISCSI_TID_SEG;
2135		break;
2136	default:
2137		return -EINVAL;
2138	}
2139
2140	p_cli = &p_mngr->clients[ILT_CLI_CDUT];
2141	if (!p_cli->active)
2142		return -EINVAL;
2143
2144	p_seg_info = &p_mngr->conn_cfg[proto].tid_seg[seg];
2145	if (!p_seg_info->has_fl_mem)
2146		return -EINVAL;
2147
2148	p_fl_seg = &p_cli->pf_blks[CDUT_FL_SEG_BLK(seg, PF)];
2149	total_lines = DIV_ROUND_UP(p_fl_seg->total_size,
2150				   p_fl_seg->real_size_in_page);
2151
2152	for (i = 0; i < total_lines; i++) {
2153		shadow_line = i + p_fl_seg->start_line -
2154		    p_hwfn->p_cxt_mngr->pf_start_line;
2155		p_info->blocks[i] = p_mngr->ilt_shadow[shadow_line].virt_addr;
2156	}
2157	p_info->waste = ILT_PAGE_IN_BYTES(p_cli->p_size.val) -
2158	    p_fl_seg->real_size_in_page;
2159	p_info->tid_size = p_mngr->task_type_size[p_seg_info->type];
2160	p_info->num_tids_per_block = p_fl_seg->real_size_in_page /
2161	    p_info->tid_size;
2162
2163	return 0;
2164}
2165
2166/* This function is very RoCE oriented, if another protocol in the future
2167 * will want this feature we'll need to modify the function to be more generic
2168 */
2169int
2170qed_cxt_dynamic_ilt_alloc(struct qed_hwfn *p_hwfn,
2171			  enum qed_cxt_elem_type elem_type, u32 iid)
2172{
2173	u32 reg_offset, shadow_line, elem_size, hw_p_size, elems_per_p, line;
2174	struct tdif_task_context *tdif_context;
2175	struct qed_ilt_client_cfg *p_cli;
2176	struct qed_ilt_cli_blk *p_blk;
2177	struct qed_ptt *p_ptt;
2178	dma_addr_t p_phys;
2179	u64 ilt_hw_entry;
2180	void *p_virt;
2181	u32 flags1;
2182	int rc = 0;
2183
2184	switch (elem_type) {
2185	case QED_ELEM_CXT:
2186		p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_CDUC];
2187		elem_size = CONN_CXT_SIZE(p_hwfn);
2188		p_blk = &p_cli->pf_blks[CDUC_BLK];
2189		break;
2190	case QED_ELEM_SRQ:
2191		/* The first ILT page is not used for regular SRQs. Skip it. */
2192		iid += p_hwfn->p_cxt_mngr->xrc_srq_count;
2193		p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_TSDM];
2194		elem_size = SRQ_CXT_SIZE;
2195		p_blk = &p_cli->pf_blks[SRQ_BLK];
2196		break;
2197	case QED_ELEM_XRC_SRQ:
2198		p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_TSDM];
2199		elem_size = XRC_SRQ_CXT_SIZE;
2200		p_blk = &p_cli->pf_blks[SRQ_BLK];
2201		break;
2202	case QED_ELEM_TASK:
2203		p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_CDUT];
2204		elem_size = TYPE1_TASK_CXT_SIZE(p_hwfn);
2205		p_blk = &p_cli->pf_blks[CDUT_SEG_BLK(QED_CXT_ROCE_TID_SEG)];
2206		break;
2207	default:
2208		DP_NOTICE(p_hwfn, "-EINVALID elem type = %d", elem_type);
2209		return -EINVAL;
2210	}
2211
2212	/* Calculate line in ilt */
2213	hw_p_size = p_cli->p_size.val;
2214	elems_per_p = ILT_PAGE_IN_BYTES(hw_p_size) / elem_size;
2215	line = p_blk->start_line + (iid / elems_per_p);
2216	shadow_line = line - p_hwfn->p_cxt_mngr->pf_start_line;
2217
2218	/* If line is already allocated, do nothing, otherwise allocate it and
2219	 * write it to the PSWRQ2 registers.
2220	 * This section can be run in parallel from different contexts and thus
2221	 * a mutex protection is needed.
2222	 */
2223
2224	mutex_lock(&p_hwfn->p_cxt_mngr->mutex);
2225
2226	if (p_hwfn->p_cxt_mngr->ilt_shadow[shadow_line].virt_addr)
2227		goto out0;
2228
2229	p_ptt = qed_ptt_acquire(p_hwfn);
2230	if (!p_ptt) {
2231		DP_NOTICE(p_hwfn,
2232			  "QED_TIME_OUT on ptt acquire - dynamic allocation");
2233		rc = -EBUSY;
2234		goto out0;
2235	}
2236
2237	p_virt = dma_alloc_coherent(&p_hwfn->cdev->pdev->dev,
2238				    p_blk->real_size_in_page, &p_phys,
2239				    GFP_KERNEL);
2240	if (!p_virt) {
2241		rc = -ENOMEM;
2242		goto out1;
2243	}
2244
2245	/* configuration of refTagMask to 0xF is required for RoCE DIF MR only,
2246	 * to compensate for a HW bug, but it is configured even if DIF is not
2247	 * enabled. This is harmless and allows us to avoid a dedicated API. We
2248	 * configure the field for all of the contexts on the newly allocated
2249	 * page.
2250	 */
2251	if (elem_type == QED_ELEM_TASK) {
2252		u32 elem_i;
2253		u8 *elem_start = (u8 *)p_virt;
2254		union type1_task_context *elem;
2255
2256		for (elem_i = 0; elem_i < elems_per_p; elem_i++) {
2257			elem = (union type1_task_context *)elem_start;
2258			tdif_context = &elem->roce_ctx.tdif_context;
2259
2260			flags1 = le32_to_cpu(tdif_context->flags1);
2261			SET_FIELD(flags1, TDIF_TASK_CONTEXT_REF_TAG_MASK, 0xf);
2262			tdif_context->flags1 = cpu_to_le32(flags1);
2263
2264			elem_start += TYPE1_TASK_CXT_SIZE(p_hwfn);
2265		}
2266	}
2267
2268	p_hwfn->p_cxt_mngr->ilt_shadow[shadow_line].virt_addr = p_virt;
2269	p_hwfn->p_cxt_mngr->ilt_shadow[shadow_line].phys_addr = p_phys;
2270	p_hwfn->p_cxt_mngr->ilt_shadow[shadow_line].size =
2271	    p_blk->real_size_in_page;
2272
2273	/* compute absolute offset */
2274	reg_offset = PSWRQ2_REG_ILT_MEMORY +
2275	    (line * ILT_REG_SIZE_IN_BYTES * ILT_ENTRY_IN_REGS);
2276
2277	ilt_hw_entry = 0;
2278	SET_FIELD(ilt_hw_entry, ILT_ENTRY_VALID, 1ULL);
2279	SET_FIELD(ilt_hw_entry, ILT_ENTRY_PHY_ADDR,
2280		  (p_hwfn->p_cxt_mngr->ilt_shadow[shadow_line].phys_addr
2281		   >> 12));
2282
2283	/* Write via DMAE since the PSWRQ2_REG_ILT_MEMORY line is a wide-bus */
2284	qed_dmae_host2grc(p_hwfn, p_ptt, (u64) (uintptr_t)&ilt_hw_entry,
2285			  reg_offset, sizeof(ilt_hw_entry) / sizeof(u32),
2286			  NULL);
2287
2288	if (elem_type == QED_ELEM_CXT) {
2289		u32 last_cid_allocated = (1 + (iid / elems_per_p)) *
2290		    elems_per_p;
2291
2292		/* Update the relevant register in the parser */
2293		qed_wr(p_hwfn, p_ptt, PRS_REG_ROCE_DEST_QP_MAX_PF,
2294		       last_cid_allocated - 1);
2295
2296		if (!p_hwfn->b_rdma_enabled_in_prs) {
2297			/* Enable RDMA search */
2298			qed_wr(p_hwfn, p_ptt, p_hwfn->rdma_prs_search_reg, 1);
2299			p_hwfn->b_rdma_enabled_in_prs = true;
2300		}
2301	}
2302
2303out1:
2304	qed_ptt_release(p_hwfn, p_ptt);
2305out0:
2306	mutex_unlock(&p_hwfn->p_cxt_mngr->mutex);
2307
2308	return rc;
2309}
2310
2311/* This function is very RoCE oriented, if another protocol in the future
2312 * will want this feature we'll need to modify the function to be more generic
2313 */
2314static int
2315qed_cxt_free_ilt_range(struct qed_hwfn *p_hwfn,
2316		       enum qed_cxt_elem_type elem_type,
2317		       u32 start_iid, u32 count)
2318{
2319	u32 start_line, end_line, shadow_start_line, shadow_end_line;
2320	u32 reg_offset, elem_size, hw_p_size, elems_per_p;
2321	struct qed_ilt_client_cfg *p_cli;
2322	struct qed_ilt_cli_blk *p_blk;
2323	u32 end_iid = start_iid + count;
2324	struct qed_ptt *p_ptt;
2325	u64 ilt_hw_entry = 0;
2326	u32 i;
2327
2328	switch (elem_type) {
2329	case QED_ELEM_CXT:
2330		p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_CDUC];
2331		elem_size = CONN_CXT_SIZE(p_hwfn);
2332		p_blk = &p_cli->pf_blks[CDUC_BLK];
2333		break;
2334	case QED_ELEM_SRQ:
2335		p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_TSDM];
2336		elem_size = SRQ_CXT_SIZE;
2337		p_blk = &p_cli->pf_blks[SRQ_BLK];
2338		break;
2339	case QED_ELEM_XRC_SRQ:
2340		p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_TSDM];
2341		elem_size = XRC_SRQ_CXT_SIZE;
2342		p_blk = &p_cli->pf_blks[SRQ_BLK];
2343		break;
2344	case QED_ELEM_TASK:
2345		p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_CDUT];
2346		elem_size = TYPE1_TASK_CXT_SIZE(p_hwfn);
2347		p_blk = &p_cli->pf_blks[CDUT_SEG_BLK(QED_CXT_ROCE_TID_SEG)];
2348		break;
2349	default:
2350		DP_NOTICE(p_hwfn, "-EINVALID elem type = %d", elem_type);
2351		return -EINVAL;
2352	}
2353
2354	/* Calculate line in ilt */
2355	hw_p_size = p_cli->p_size.val;
2356	elems_per_p = ILT_PAGE_IN_BYTES(hw_p_size) / elem_size;
2357	start_line = p_blk->start_line + (start_iid / elems_per_p);
2358	end_line = p_blk->start_line + (end_iid / elems_per_p);
2359	if (((end_iid + 1) / elems_per_p) != (end_iid / elems_per_p))
2360		end_line--;
2361
2362	shadow_start_line = start_line - p_hwfn->p_cxt_mngr->pf_start_line;
2363	shadow_end_line = end_line - p_hwfn->p_cxt_mngr->pf_start_line;
2364
2365	p_ptt = qed_ptt_acquire(p_hwfn);
2366	if (!p_ptt) {
2367		DP_NOTICE(p_hwfn,
2368			  "QED_TIME_OUT on ptt acquire - dynamic allocation");
2369		return -EBUSY;
2370	}
2371
2372	for (i = shadow_start_line; i < shadow_end_line; i++) {
2373		if (!p_hwfn->p_cxt_mngr->ilt_shadow[i].virt_addr)
2374			continue;
2375
2376		dma_free_coherent(&p_hwfn->cdev->pdev->dev,
2377				  p_hwfn->p_cxt_mngr->ilt_shadow[i].size,
2378				  p_hwfn->p_cxt_mngr->ilt_shadow[i].virt_addr,
2379				  p_hwfn->p_cxt_mngr->ilt_shadow[i].phys_addr);
2380
2381		p_hwfn->p_cxt_mngr->ilt_shadow[i].virt_addr = NULL;
2382		p_hwfn->p_cxt_mngr->ilt_shadow[i].phys_addr = 0;
2383		p_hwfn->p_cxt_mngr->ilt_shadow[i].size = 0;
2384
2385		/* compute absolute offset */
2386		reg_offset = PSWRQ2_REG_ILT_MEMORY +
2387		    ((start_line++) * ILT_REG_SIZE_IN_BYTES *
2388		     ILT_ENTRY_IN_REGS);
2389
2390		/* Write via DMAE since the PSWRQ2_REG_ILT_MEMORY line is a
2391		 * wide-bus.
2392		 */
2393		qed_dmae_host2grc(p_hwfn, p_ptt,
2394				  (u64) (uintptr_t) &ilt_hw_entry,
2395				  reg_offset,
2396				  sizeof(ilt_hw_entry) / sizeof(u32),
2397				  NULL);
2398	}
2399
2400	qed_ptt_release(p_hwfn, p_ptt);
2401
2402	return 0;
2403}
2404
2405int qed_cxt_free_proto_ilt(struct qed_hwfn *p_hwfn, enum protocol_type proto)
2406{
2407	int rc;
2408	u32 cid;
2409
2410	/* Free Connection CXT */
2411	rc = qed_cxt_free_ilt_range(p_hwfn, QED_ELEM_CXT,
2412				    qed_cxt_get_proto_cid_start(p_hwfn,
2413								proto),
2414				    qed_cxt_get_proto_cid_count(p_hwfn,
2415								proto, &cid));
2416
2417	if (rc)
2418		return rc;
2419
2420	/* Free Task CXT ( Intentionally RoCE as task-id is shared between
2421	 * RoCE and iWARP )
2422	 */
2423	proto = PROTOCOLID_ROCE;
2424	rc = qed_cxt_free_ilt_range(p_hwfn, QED_ELEM_TASK, 0,
2425				    qed_cxt_get_proto_tid_count(p_hwfn, proto));
2426	if (rc)
2427		return rc;
2428
2429	/* Free TSDM CXT */
2430	rc = qed_cxt_free_ilt_range(p_hwfn, QED_ELEM_XRC_SRQ, 0,
2431				    p_hwfn->p_cxt_mngr->xrc_srq_count);
2432
2433	rc = qed_cxt_free_ilt_range(p_hwfn, QED_ELEM_SRQ,
2434				    p_hwfn->p_cxt_mngr->xrc_srq_count,
2435				    p_hwfn->p_cxt_mngr->srq_count);
2436
2437	return rc;
2438}
2439
2440int qed_cxt_get_task_ctx(struct qed_hwfn *p_hwfn,
2441			 u32 tid, u8 ctx_type, void **pp_task_ctx)
2442{
2443	struct qed_cxt_mngr *p_mngr = p_hwfn->p_cxt_mngr;
2444	struct qed_ilt_client_cfg *p_cli;
2445	struct qed_tid_seg *p_seg_info;
2446	struct qed_ilt_cli_blk *p_seg;
2447	u32 num_tids_per_block;
2448	u32 tid_size, ilt_idx;
2449	u32 total_lines;
2450	u32 proto, seg;
2451
2452	/* Verify the personality */
2453	switch (p_hwfn->hw_info.personality) {
2454	case QED_PCI_FCOE:
2455		proto = PROTOCOLID_FCOE;
2456		seg = QED_CXT_FCOE_TID_SEG;
2457		break;
2458	case QED_PCI_ISCSI:
2459		proto = PROTOCOLID_ISCSI;
2460		seg = QED_CXT_ISCSI_TID_SEG;
2461		break;
2462	default:
2463		return -EINVAL;
2464	}
2465
2466	p_cli = &p_mngr->clients[ILT_CLI_CDUT];
2467	if (!p_cli->active)
2468		return -EINVAL;
2469
2470	p_seg_info = &p_mngr->conn_cfg[proto].tid_seg[seg];
2471
2472	if (ctx_type == QED_CTX_WORKING_MEM) {
2473		p_seg = &p_cli->pf_blks[CDUT_SEG_BLK(seg)];
2474	} else if (ctx_type == QED_CTX_FL_MEM) {
2475		if (!p_seg_info->has_fl_mem)
2476			return -EINVAL;
2477		p_seg = &p_cli->pf_blks[CDUT_FL_SEG_BLK(seg, PF)];
2478	} else {
2479		return -EINVAL;
2480	}
2481	total_lines = DIV_ROUND_UP(p_seg->total_size, p_seg->real_size_in_page);
2482	tid_size = p_mngr->task_type_size[p_seg_info->type];
2483	num_tids_per_block = p_seg->real_size_in_page / tid_size;
2484
2485	if (total_lines < tid / num_tids_per_block)
2486		return -EINVAL;
2487
2488	ilt_idx = tid / num_tids_per_block + p_seg->start_line -
2489		  p_mngr->pf_start_line;
2490	*pp_task_ctx = (u8 *)p_mngr->ilt_shadow[ilt_idx].virt_addr +
2491		       (tid % num_tids_per_block) * tid_size;
2492
2493	return 0;
2494}
2495
2496static u16 qed_blk_calculate_pages(struct qed_ilt_cli_blk *p_blk)
2497{
2498	if (p_blk->real_size_in_page == 0)
2499		return 0;
2500
2501	return DIV_ROUND_UP(p_blk->total_size, p_blk->real_size_in_page);
2502}
2503
2504u16 qed_get_cdut_num_pf_init_pages(struct qed_hwfn *p_hwfn)
2505{
2506	struct qed_ilt_client_cfg *p_cli;
2507	struct qed_ilt_cli_blk *p_blk;
2508	u16 i, pages = 0;
2509
2510	p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_CDUT];
2511	for (i = 0; i < NUM_TASK_PF_SEGMENTS; i++) {
2512		p_blk = &p_cli->pf_blks[CDUT_FL_SEG_BLK(i, PF)];
2513		pages += qed_blk_calculate_pages(p_blk);
2514	}
2515
2516	return pages;
2517}
2518
2519u16 qed_get_cdut_num_vf_init_pages(struct qed_hwfn *p_hwfn)
2520{
2521	struct qed_ilt_client_cfg *p_cli;
2522	struct qed_ilt_cli_blk *p_blk;
2523	u16 i, pages = 0;
2524
2525	p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_CDUT];
2526	for (i = 0; i < NUM_TASK_VF_SEGMENTS; i++) {
2527		p_blk = &p_cli->vf_blks[CDUT_FL_SEG_BLK(i, VF)];
2528		pages += qed_blk_calculate_pages(p_blk);
2529	}
2530
2531	return pages;
2532}
2533
2534u16 qed_get_cdut_num_pf_work_pages(struct qed_hwfn *p_hwfn)
2535{
2536	struct qed_ilt_client_cfg *p_cli;
2537	struct qed_ilt_cli_blk *p_blk;
2538	u16 i, pages = 0;
2539
2540	p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_CDUT];
2541	for (i = 0; i < NUM_TASK_PF_SEGMENTS; i++) {
2542		p_blk = &p_cli->pf_blks[CDUT_SEG_BLK(i)];
2543		pages += qed_blk_calculate_pages(p_blk);
2544	}
2545
2546	return pages;
2547}
2548
2549u16 qed_get_cdut_num_vf_work_pages(struct qed_hwfn *p_hwfn)
2550{
2551	struct qed_ilt_client_cfg *p_cli;
2552	struct qed_ilt_cli_blk *p_blk;
2553	u16 pages = 0, i;
2554
2555	p_cli = &p_hwfn->p_cxt_mngr->clients[ILT_CLI_CDUT];
2556	for (i = 0; i < NUM_TASK_VF_SEGMENTS; i++) {
2557		p_blk = &p_cli->vf_blks[CDUT_SEG_BLK(i)];
2558		pages += qed_blk_calculate_pages(p_blk);
2559	}
2560
2561	return pages;
2562}
2563