1/*
2 * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved.
3 *
4 * This software is available to you under a choice of one of two
5 * licenses.  You may choose to be licensed under the terms of the GNU
6 * General Public License (GPL) Version 2, available from the file
7 * COPYING in the main directory of this source tree, or the
8 * OpenIB.org BSD license below:
9 *
10 *     Redistribution and use in source and binary forms, with or
11 *     without modification, are permitted provided that the following
12 *     conditions are met:
13 *
14 *      - Redistributions of source code must retain the above
15 *        copyright notice, this list of conditions and the following
16 *        disclaimer.
17 *
18 *      - Redistributions in binary form must reproduce the above
19 *        copyright notice, this list of conditions and the following
20 *        disclaimer in the documentation and/or other materials
21 *        provided with the distribution.
22 *
23 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
24 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
25 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
26 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
27 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
28 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
29 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
30 * SOFTWARE.
31 */
32
33#include <linux/kref.h>
34#include <rdma/ib_umem.h>
35#include <rdma/ib_user_verbs.h>
36#include <rdma/ib_cache.h>
37#include "mlx5_ib.h"
38#include "srq.h"
39#include "qp.h"
40
41static void mlx5_ib_cq_comp(struct mlx5_core_cq *cq, struct mlx5_eqe *eqe)
42{
43	struct ib_cq *ibcq = &to_mibcq(cq)->ibcq;
44
45	ibcq->comp_handler(ibcq, ibcq->cq_context);
46}
47
48static void mlx5_ib_cq_event(struct mlx5_core_cq *mcq, enum mlx5_event type)
49{
50	struct mlx5_ib_cq *cq = container_of(mcq, struct mlx5_ib_cq, mcq);
51	struct mlx5_ib_dev *dev = to_mdev(cq->ibcq.device);
52	struct ib_cq *ibcq = &cq->ibcq;
53	struct ib_event event;
54
55	if (type != MLX5_EVENT_TYPE_CQ_ERROR) {
56		mlx5_ib_warn(dev, "Unexpected event type %d on CQ %06x\n",
57			     type, mcq->cqn);
58		return;
59	}
60
61	if (ibcq->event_handler) {
62		event.device     = &dev->ib_dev;
63		event.event      = IB_EVENT_CQ_ERR;
64		event.element.cq = ibcq;
65		ibcq->event_handler(&event, ibcq->cq_context);
66	}
67}
68
69static void *get_cqe(struct mlx5_ib_cq *cq, int n)
70{
71	return mlx5_frag_buf_get_wqe(&cq->buf.fbc, n);
72}
73
74static u8 sw_ownership_bit(int n, int nent)
75{
76	return (n & nent) ? 1 : 0;
77}
78
79static void *get_sw_cqe(struct mlx5_ib_cq *cq, int n)
80{
81	void *cqe = get_cqe(cq, n & cq->ibcq.cqe);
82	struct mlx5_cqe64 *cqe64;
83
84	cqe64 = (cq->mcq.cqe_sz == 64) ? cqe : cqe + 64;
85
86	if (likely(get_cqe_opcode(cqe64) != MLX5_CQE_INVALID) &&
87	    !((cqe64->op_own & MLX5_CQE_OWNER_MASK) ^ !!(n & (cq->ibcq.cqe + 1)))) {
88		return cqe;
89	} else {
90		return NULL;
91	}
92}
93
94static void *next_cqe_sw(struct mlx5_ib_cq *cq)
95{
96	return get_sw_cqe(cq, cq->mcq.cons_index);
97}
98
99static enum ib_wc_opcode get_umr_comp(struct mlx5_ib_wq *wq, int idx)
100{
101	switch (wq->wr_data[idx]) {
102	case MLX5_IB_WR_UMR:
103		return 0;
104
105	case IB_WR_LOCAL_INV:
106		return IB_WC_LOCAL_INV;
107
108	case IB_WR_REG_MR:
109		return IB_WC_REG_MR;
110
111	default:
112		pr_warn("unknown completion status\n");
113		return 0;
114	}
115}
116
117static void handle_good_req(struct ib_wc *wc, struct mlx5_cqe64 *cqe,
118			    struct mlx5_ib_wq *wq, int idx)
119{
120	wc->wc_flags = 0;
121	switch (be32_to_cpu(cqe->sop_drop_qpn) >> 24) {
122	case MLX5_OPCODE_RDMA_WRITE_IMM:
123		wc->wc_flags |= IB_WC_WITH_IMM;
124		fallthrough;
125	case MLX5_OPCODE_RDMA_WRITE:
126		wc->opcode    = IB_WC_RDMA_WRITE;
127		break;
128	case MLX5_OPCODE_SEND_IMM:
129		wc->wc_flags |= IB_WC_WITH_IMM;
130		fallthrough;
131	case MLX5_OPCODE_SEND:
132	case MLX5_OPCODE_SEND_INVAL:
133		wc->opcode    = IB_WC_SEND;
134		break;
135	case MLX5_OPCODE_RDMA_READ:
136		wc->opcode    = IB_WC_RDMA_READ;
137		wc->byte_len  = be32_to_cpu(cqe->byte_cnt);
138		break;
139	case MLX5_OPCODE_ATOMIC_CS:
140		wc->opcode    = IB_WC_COMP_SWAP;
141		wc->byte_len  = 8;
142		break;
143	case MLX5_OPCODE_ATOMIC_FA:
144		wc->opcode    = IB_WC_FETCH_ADD;
145		wc->byte_len  = 8;
146		break;
147	case MLX5_OPCODE_ATOMIC_MASKED_CS:
148		wc->opcode    = IB_WC_MASKED_COMP_SWAP;
149		wc->byte_len  = 8;
150		break;
151	case MLX5_OPCODE_ATOMIC_MASKED_FA:
152		wc->opcode    = IB_WC_MASKED_FETCH_ADD;
153		wc->byte_len  = 8;
154		break;
155	case MLX5_OPCODE_UMR:
156		wc->opcode = get_umr_comp(wq, idx);
157		break;
158	}
159}
160
161enum {
162	MLX5_GRH_IN_BUFFER = 1,
163	MLX5_GRH_IN_CQE	   = 2,
164};
165
166static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe,
167			     struct mlx5_ib_qp *qp)
168{
169	enum rdma_link_layer ll = rdma_port_get_link_layer(qp->ibqp.device, 1);
170	struct mlx5_ib_dev *dev = to_mdev(qp->ibqp.device);
171	struct mlx5_ib_srq *srq = NULL;
172	struct mlx5_ib_wq *wq;
173	u16 wqe_ctr;
174	u8  roce_packet_type;
175	bool vlan_present;
176	u8 g;
177
178	if (qp->ibqp.srq || qp->ibqp.xrcd) {
179		struct mlx5_core_srq *msrq = NULL;
180
181		if (qp->ibqp.xrcd) {
182			msrq = mlx5_cmd_get_srq(dev, be32_to_cpu(cqe->srqn));
183			if (msrq)
184				srq = to_mibsrq(msrq);
185		} else {
186			srq = to_msrq(qp->ibqp.srq);
187		}
188		if (srq) {
189			wqe_ctr = be16_to_cpu(cqe->wqe_counter);
190			wc->wr_id = srq->wrid[wqe_ctr];
191			mlx5_ib_free_srq_wqe(srq, wqe_ctr);
192			if (msrq)
193				mlx5_core_res_put(&msrq->common);
194		}
195	} else {
196		wq	  = &qp->rq;
197		wc->wr_id = wq->wrid[wq->tail & (wq->wqe_cnt - 1)];
198		++wq->tail;
199	}
200	wc->byte_len = be32_to_cpu(cqe->byte_cnt);
201
202	switch (get_cqe_opcode(cqe)) {
203	case MLX5_CQE_RESP_WR_IMM:
204		wc->opcode	= IB_WC_RECV_RDMA_WITH_IMM;
205		wc->wc_flags	= IB_WC_WITH_IMM;
206		wc->ex.imm_data = cqe->immediate;
207		break;
208	case MLX5_CQE_RESP_SEND:
209		wc->opcode   = IB_WC_RECV;
210		wc->wc_flags = IB_WC_IP_CSUM_OK;
211		if (unlikely(!((cqe->hds_ip_ext & CQE_L3_OK) &&
212			       (cqe->hds_ip_ext & CQE_L4_OK))))
213			wc->wc_flags = 0;
214		break;
215	case MLX5_CQE_RESP_SEND_IMM:
216		wc->opcode	= IB_WC_RECV;
217		wc->wc_flags	= IB_WC_WITH_IMM;
218		wc->ex.imm_data = cqe->immediate;
219		break;
220	case MLX5_CQE_RESP_SEND_INV:
221		wc->opcode	= IB_WC_RECV;
222		wc->wc_flags	= IB_WC_WITH_INVALIDATE;
223		wc->ex.invalidate_rkey = be32_to_cpu(cqe->inval_rkey);
224		break;
225	}
226	wc->src_qp	   = be32_to_cpu(cqe->flags_rqpn) & 0xffffff;
227	wc->dlid_path_bits = cqe->ml_path;
228	g = (be32_to_cpu(cqe->flags_rqpn) >> 28) & 3;
229	wc->wc_flags |= g ? IB_WC_GRH : 0;
230	if (unlikely(is_qp1(qp->ibqp.qp_type))) {
231		u16 pkey = be32_to_cpu(cqe->pkey) & 0xffff;
232
233		ib_find_cached_pkey(&dev->ib_dev, qp->port, pkey,
234				    &wc->pkey_index);
235	} else {
236		wc->pkey_index = 0;
237	}
238
239	if (ll != IB_LINK_LAYER_ETHERNET) {
240		wc->slid = be16_to_cpu(cqe->slid);
241		wc->sl = (be32_to_cpu(cqe->flags_rqpn) >> 24) & 0xf;
242		return;
243	}
244
245	wc->slid = 0;
246	vlan_present = cqe->l4_l3_hdr_type & 0x1;
247	roce_packet_type   = (be32_to_cpu(cqe->flags_rqpn) >> 24) & 0x3;
248	if (vlan_present) {
249		wc->vlan_id = (be16_to_cpu(cqe->vlan_info)) & 0xfff;
250		wc->sl = (be16_to_cpu(cqe->vlan_info) >> 13) & 0x7;
251		wc->wc_flags |= IB_WC_WITH_VLAN;
252	} else {
253		wc->sl = 0;
254	}
255
256	switch (roce_packet_type) {
257	case MLX5_CQE_ROCE_L3_HEADER_TYPE_GRH:
258		wc->network_hdr_type = RDMA_NETWORK_ROCE_V1;
259		break;
260	case MLX5_CQE_ROCE_L3_HEADER_TYPE_IPV6:
261		wc->network_hdr_type = RDMA_NETWORK_IPV6;
262		break;
263	case MLX5_CQE_ROCE_L3_HEADER_TYPE_IPV4:
264		wc->network_hdr_type = RDMA_NETWORK_IPV4;
265		break;
266	}
267	wc->wc_flags |= IB_WC_WITH_NETWORK_HDR_TYPE;
268}
269
270static void dump_cqe(struct mlx5_ib_dev *dev, struct mlx5_err_cqe *cqe)
271{
272	mlx5_ib_warn(dev, "dump error cqe\n");
273	mlx5_dump_err_cqe(dev->mdev, cqe);
274}
275
276static void mlx5_handle_error_cqe(struct mlx5_ib_dev *dev,
277				  struct mlx5_err_cqe *cqe,
278				  struct ib_wc *wc)
279{
280	int dump = 1;
281
282	switch (cqe->syndrome) {
283	case MLX5_CQE_SYNDROME_LOCAL_LENGTH_ERR:
284		wc->status = IB_WC_LOC_LEN_ERR;
285		break;
286	case MLX5_CQE_SYNDROME_LOCAL_QP_OP_ERR:
287		wc->status = IB_WC_LOC_QP_OP_ERR;
288		break;
289	case MLX5_CQE_SYNDROME_LOCAL_PROT_ERR:
290		wc->status = IB_WC_LOC_PROT_ERR;
291		break;
292	case MLX5_CQE_SYNDROME_WR_FLUSH_ERR:
293		dump = 0;
294		wc->status = IB_WC_WR_FLUSH_ERR;
295		break;
296	case MLX5_CQE_SYNDROME_MW_BIND_ERR:
297		wc->status = IB_WC_MW_BIND_ERR;
298		break;
299	case MLX5_CQE_SYNDROME_BAD_RESP_ERR:
300		wc->status = IB_WC_BAD_RESP_ERR;
301		break;
302	case MLX5_CQE_SYNDROME_LOCAL_ACCESS_ERR:
303		wc->status = IB_WC_LOC_ACCESS_ERR;
304		break;
305	case MLX5_CQE_SYNDROME_REMOTE_INVAL_REQ_ERR:
306		wc->status = IB_WC_REM_INV_REQ_ERR;
307		break;
308	case MLX5_CQE_SYNDROME_REMOTE_ACCESS_ERR:
309		wc->status = IB_WC_REM_ACCESS_ERR;
310		break;
311	case MLX5_CQE_SYNDROME_REMOTE_OP_ERR:
312		wc->status = IB_WC_REM_OP_ERR;
313		break;
314	case MLX5_CQE_SYNDROME_TRANSPORT_RETRY_EXC_ERR:
315		wc->status = IB_WC_RETRY_EXC_ERR;
316		dump = 0;
317		break;
318	case MLX5_CQE_SYNDROME_RNR_RETRY_EXC_ERR:
319		wc->status = IB_WC_RNR_RETRY_EXC_ERR;
320		dump = 0;
321		break;
322	case MLX5_CQE_SYNDROME_REMOTE_ABORTED_ERR:
323		wc->status = IB_WC_REM_ABORT_ERR;
324		break;
325	default:
326		wc->status = IB_WC_GENERAL_ERR;
327		break;
328	}
329
330	wc->vendor_err = cqe->vendor_err_synd;
331	if (dump)
332		dump_cqe(dev, cqe);
333}
334
335static void handle_atomics(struct mlx5_ib_qp *qp, struct mlx5_cqe64 *cqe64,
336			   u16 tail, u16 head)
337{
338	u16 idx;
339
340	do {
341		idx = tail & (qp->sq.wqe_cnt - 1);
342		if (idx == head)
343			break;
344
345		tail = qp->sq.w_list[idx].next;
346	} while (1);
347	tail = qp->sq.w_list[idx].next;
348	qp->sq.last_poll = tail;
349}
350
351static void free_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf)
352{
353	mlx5_frag_buf_free(dev->mdev, &buf->frag_buf);
354}
355
356static void get_sig_err_item(struct mlx5_sig_err_cqe *cqe,
357			     struct ib_sig_err *item)
358{
359	u16 syndrome = be16_to_cpu(cqe->syndrome);
360
361#define GUARD_ERR   (1 << 13)
362#define APPTAG_ERR  (1 << 12)
363#define REFTAG_ERR  (1 << 11)
364
365	if (syndrome & GUARD_ERR) {
366		item->err_type = IB_SIG_BAD_GUARD;
367		item->expected = be32_to_cpu(cqe->expected_trans_sig) >> 16;
368		item->actual = be32_to_cpu(cqe->actual_trans_sig) >> 16;
369	} else
370	if (syndrome & REFTAG_ERR) {
371		item->err_type = IB_SIG_BAD_REFTAG;
372		item->expected = be32_to_cpu(cqe->expected_reftag);
373		item->actual = be32_to_cpu(cqe->actual_reftag);
374	} else
375	if (syndrome & APPTAG_ERR) {
376		item->err_type = IB_SIG_BAD_APPTAG;
377		item->expected = be32_to_cpu(cqe->expected_trans_sig) & 0xffff;
378		item->actual = be32_to_cpu(cqe->actual_trans_sig) & 0xffff;
379	} else {
380		pr_err("Got signature completion error with bad syndrome %04x\n",
381		       syndrome);
382	}
383
384	item->sig_err_offset = be64_to_cpu(cqe->err_offset);
385	item->key = be32_to_cpu(cqe->mkey);
386}
387
388static void sw_comp(struct mlx5_ib_qp *qp, int num_entries, struct ib_wc *wc,
389		    int *npolled, bool is_send)
390{
391	struct mlx5_ib_wq *wq;
392	unsigned int cur;
393	int np;
394	int i;
395
396	wq = (is_send) ? &qp->sq : &qp->rq;
397	cur = wq->head - wq->tail;
398	np = *npolled;
399
400	if (cur == 0)
401		return;
402
403	for (i = 0;  i < cur && np < num_entries; i++) {
404		unsigned int idx;
405
406		idx = (is_send) ? wq->last_poll : wq->tail;
407		idx &= (wq->wqe_cnt - 1);
408		wc->wr_id = wq->wrid[idx];
409		wc->status = IB_WC_WR_FLUSH_ERR;
410		wc->vendor_err = MLX5_CQE_SYNDROME_WR_FLUSH_ERR;
411		wq->tail++;
412		if (is_send)
413			wq->last_poll = wq->w_list[idx].next;
414		np++;
415		wc->qp = &qp->ibqp;
416		wc++;
417	}
418	*npolled = np;
419}
420
421static void mlx5_ib_poll_sw_comp(struct mlx5_ib_cq *cq, int num_entries,
422				 struct ib_wc *wc, int *npolled)
423{
424	struct mlx5_ib_qp *qp;
425
426	*npolled = 0;
427	/* Find uncompleted WQEs belonging to that cq and return mmics ones */
428	list_for_each_entry(qp, &cq->list_send_qp, cq_send_list) {
429		sw_comp(qp, num_entries, wc + *npolled, npolled, true);
430		if (*npolled >= num_entries)
431			return;
432	}
433
434	list_for_each_entry(qp, &cq->list_recv_qp, cq_recv_list) {
435		sw_comp(qp, num_entries, wc + *npolled, npolled, false);
436		if (*npolled >= num_entries)
437			return;
438	}
439}
440
441static int mlx5_poll_one(struct mlx5_ib_cq *cq,
442			 struct mlx5_ib_qp **cur_qp,
443			 struct ib_wc *wc)
444{
445	struct mlx5_ib_dev *dev = to_mdev(cq->ibcq.device);
446	struct mlx5_err_cqe *err_cqe;
447	struct mlx5_cqe64 *cqe64;
448	struct mlx5_core_qp *mqp;
449	struct mlx5_ib_wq *wq;
450	uint8_t opcode;
451	uint32_t qpn;
452	u16 wqe_ctr;
453	void *cqe;
454	int idx;
455
456repoll:
457	cqe = next_cqe_sw(cq);
458	if (!cqe)
459		return -EAGAIN;
460
461	cqe64 = (cq->mcq.cqe_sz == 64) ? cqe : cqe + 64;
462
463	++cq->mcq.cons_index;
464
465	/* Make sure we read CQ entry contents after we've checked the
466	 * ownership bit.
467	 */
468	rmb();
469
470	opcode = get_cqe_opcode(cqe64);
471	if (unlikely(opcode == MLX5_CQE_RESIZE_CQ)) {
472		if (likely(cq->resize_buf)) {
473			free_cq_buf(dev, &cq->buf);
474			cq->buf = *cq->resize_buf;
475			kfree(cq->resize_buf);
476			cq->resize_buf = NULL;
477			goto repoll;
478		} else {
479			mlx5_ib_warn(dev, "unexpected resize cqe\n");
480		}
481	}
482
483	qpn = ntohl(cqe64->sop_drop_qpn) & 0xffffff;
484	if (!*cur_qp || (qpn != (*cur_qp)->ibqp.qp_num)) {
485		/* We do not have to take the QP table lock here,
486		 * because CQs will be locked while QPs are removed
487		 * from the table.
488		 */
489		mqp = radix_tree_lookup(&dev->qp_table.tree, qpn);
490		*cur_qp = to_mibqp(mqp);
491	}
492
493	wc->qp  = &(*cur_qp)->ibqp;
494	switch (opcode) {
495	case MLX5_CQE_REQ:
496		wq = &(*cur_qp)->sq;
497		wqe_ctr = be16_to_cpu(cqe64->wqe_counter);
498		idx = wqe_ctr & (wq->wqe_cnt - 1);
499		handle_good_req(wc, cqe64, wq, idx);
500		handle_atomics(*cur_qp, cqe64, wq->last_poll, idx);
501		wc->wr_id = wq->wrid[idx];
502		wq->tail = wq->wqe_head[idx] + 1;
503		wc->status = IB_WC_SUCCESS;
504		break;
505	case MLX5_CQE_RESP_WR_IMM:
506	case MLX5_CQE_RESP_SEND:
507	case MLX5_CQE_RESP_SEND_IMM:
508	case MLX5_CQE_RESP_SEND_INV:
509		handle_responder(wc, cqe64, *cur_qp);
510		wc->status = IB_WC_SUCCESS;
511		break;
512	case MLX5_CQE_RESIZE_CQ:
513		break;
514	case MLX5_CQE_REQ_ERR:
515	case MLX5_CQE_RESP_ERR:
516		err_cqe = (struct mlx5_err_cqe *)cqe64;
517		mlx5_handle_error_cqe(dev, err_cqe, wc);
518		mlx5_ib_dbg(dev, "%s error cqe on cqn 0x%x:\n",
519			    opcode == MLX5_CQE_REQ_ERR ?
520			    "Requestor" : "Responder", cq->mcq.cqn);
521		mlx5_ib_dbg(dev, "syndrome 0x%x, vendor syndrome 0x%x\n",
522			    err_cqe->syndrome, err_cqe->vendor_err_synd);
523		if (opcode == MLX5_CQE_REQ_ERR) {
524			wq = &(*cur_qp)->sq;
525			wqe_ctr = be16_to_cpu(cqe64->wqe_counter);
526			idx = wqe_ctr & (wq->wqe_cnt - 1);
527			wc->wr_id = wq->wrid[idx];
528			wq->tail = wq->wqe_head[idx] + 1;
529		} else {
530			struct mlx5_ib_srq *srq;
531
532			if ((*cur_qp)->ibqp.srq) {
533				srq = to_msrq((*cur_qp)->ibqp.srq);
534				wqe_ctr = be16_to_cpu(cqe64->wqe_counter);
535				wc->wr_id = srq->wrid[wqe_ctr];
536				mlx5_ib_free_srq_wqe(srq, wqe_ctr);
537			} else {
538				wq = &(*cur_qp)->rq;
539				wc->wr_id = wq->wrid[wq->tail & (wq->wqe_cnt - 1)];
540				++wq->tail;
541			}
542		}
543		break;
544	case MLX5_CQE_SIG_ERR: {
545		struct mlx5_sig_err_cqe *sig_err_cqe =
546			(struct mlx5_sig_err_cqe *)cqe64;
547		struct mlx5_core_sig_ctx *sig;
548
549		xa_lock(&dev->sig_mrs);
550		sig = xa_load(&dev->sig_mrs,
551				mlx5_base_mkey(be32_to_cpu(sig_err_cqe->mkey)));
552		get_sig_err_item(sig_err_cqe, &sig->err_item);
553		sig->sig_err_exists = true;
554		sig->sigerr_count++;
555
556		mlx5_ib_warn(dev, "CQN: 0x%x Got SIGERR on key: 0x%x err_type %x err_offset %llx expected %x actual %x\n",
557			     cq->mcq.cqn, sig->err_item.key,
558			     sig->err_item.err_type,
559			     sig->err_item.sig_err_offset,
560			     sig->err_item.expected,
561			     sig->err_item.actual);
562
563		xa_unlock(&dev->sig_mrs);
564		goto repoll;
565	}
566	}
567
568	return 0;
569}
570
571static int poll_soft_wc(struct mlx5_ib_cq *cq, int num_entries,
572			struct ib_wc *wc, bool is_fatal_err)
573{
574	struct mlx5_ib_dev *dev = to_mdev(cq->ibcq.device);
575	struct mlx5_ib_wc *soft_wc, *next;
576	int npolled = 0;
577
578	list_for_each_entry_safe(soft_wc, next, &cq->wc_list, list) {
579		if (npolled >= num_entries)
580			break;
581
582		mlx5_ib_dbg(dev, "polled software generated completion on CQ 0x%x\n",
583			    cq->mcq.cqn);
584
585		if (unlikely(is_fatal_err)) {
586			soft_wc->wc.status = IB_WC_WR_FLUSH_ERR;
587			soft_wc->wc.vendor_err = MLX5_CQE_SYNDROME_WR_FLUSH_ERR;
588		}
589		wc[npolled++] = soft_wc->wc;
590		list_del(&soft_wc->list);
591		kfree(soft_wc);
592	}
593
594	return npolled;
595}
596
597int mlx5_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
598{
599	struct mlx5_ib_cq *cq = to_mcq(ibcq);
600	struct mlx5_ib_qp *cur_qp = NULL;
601	struct mlx5_ib_dev *dev = to_mdev(cq->ibcq.device);
602	struct mlx5_core_dev *mdev = dev->mdev;
603	unsigned long flags;
604	int soft_polled = 0;
605	int npolled;
606
607	spin_lock_irqsave(&cq->lock, flags);
608	if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
609		/* make sure no soft wqe's are waiting */
610		if (unlikely(!list_empty(&cq->wc_list)))
611			soft_polled = poll_soft_wc(cq, num_entries, wc, true);
612
613		mlx5_ib_poll_sw_comp(cq, num_entries - soft_polled,
614				     wc + soft_polled, &npolled);
615		goto out;
616	}
617
618	if (unlikely(!list_empty(&cq->wc_list)))
619		soft_polled = poll_soft_wc(cq, num_entries, wc, false);
620
621	for (npolled = 0; npolled < num_entries - soft_polled; npolled++) {
622		if (mlx5_poll_one(cq, &cur_qp, wc + soft_polled + npolled))
623			break;
624	}
625
626	if (npolled)
627		mlx5_cq_set_ci(&cq->mcq);
628out:
629	spin_unlock_irqrestore(&cq->lock, flags);
630
631	return soft_polled + npolled;
632}
633
634int mlx5_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
635{
636	struct mlx5_core_dev *mdev = to_mdev(ibcq->device)->mdev;
637	struct mlx5_ib_cq *cq = to_mcq(ibcq);
638	void __iomem *uar_page = mdev->priv.uar->map;
639	unsigned long irq_flags;
640	int ret = 0;
641
642	spin_lock_irqsave(&cq->lock, irq_flags);
643	if (cq->notify_flags != IB_CQ_NEXT_COMP)
644		cq->notify_flags = flags & IB_CQ_SOLICITED_MASK;
645
646	if ((flags & IB_CQ_REPORT_MISSED_EVENTS) && !list_empty(&cq->wc_list))
647		ret = 1;
648	spin_unlock_irqrestore(&cq->lock, irq_flags);
649
650	mlx5_cq_arm(&cq->mcq,
651		    (flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED ?
652		    MLX5_CQ_DB_REQ_NOT_SOL : MLX5_CQ_DB_REQ_NOT,
653		    uar_page, to_mcq(ibcq)->mcq.cons_index);
654
655	return ret;
656}
657
658static int alloc_cq_frag_buf(struct mlx5_ib_dev *dev,
659			     struct mlx5_ib_cq_buf *buf,
660			     int nent,
661			     int cqe_size)
662{
663	struct mlx5_frag_buf *frag_buf = &buf->frag_buf;
664	u8 log_wq_stride = 6 + (cqe_size == 128 ? 1 : 0);
665	u8 log_wq_sz     = ilog2(cqe_size);
666	int err;
667
668	err = mlx5_frag_buf_alloc_node(dev->mdev,
669				       nent * cqe_size,
670				       frag_buf,
671				       dev->mdev->priv.numa_node);
672	if (err)
673		return err;
674
675	mlx5_init_fbc(frag_buf->frags, log_wq_stride, log_wq_sz, &buf->fbc);
676
677	buf->cqe_size = cqe_size;
678	buf->nent = nent;
679
680	return 0;
681}
682
683enum {
684	MLX5_CQE_RES_FORMAT_HASH = 0,
685	MLX5_CQE_RES_FORMAT_CSUM = 1,
686	MLX5_CQE_RES_FORMAT_CSUM_STRIDX = 3,
687};
688
689static int mini_cqe_res_format_to_hw(struct mlx5_ib_dev *dev, u8 format)
690{
691	switch (format) {
692	case MLX5_IB_CQE_RES_FORMAT_HASH:
693		return MLX5_CQE_RES_FORMAT_HASH;
694	case MLX5_IB_CQE_RES_FORMAT_CSUM:
695		return MLX5_CQE_RES_FORMAT_CSUM;
696	case MLX5_IB_CQE_RES_FORMAT_CSUM_STRIDX:
697		if (MLX5_CAP_GEN(dev->mdev, mini_cqe_resp_stride_index))
698			return MLX5_CQE_RES_FORMAT_CSUM_STRIDX;
699		return -EOPNOTSUPP;
700	default:
701		return -EINVAL;
702	}
703}
704
705static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
706			  struct mlx5_ib_cq *cq, int entries, u32 **cqb,
707			  int *cqe_size, int *index, int *inlen)
708{
709	struct mlx5_ib_create_cq ucmd = {};
710	size_t ucmdlen;
711	int page_shift;
712	__be64 *pas;
713	int npages;
714	int ncont;
715	void *cqc;
716	int err;
717	struct mlx5_ib_ucontext *context = rdma_udata_to_drv_context(
718		udata, struct mlx5_ib_ucontext, ibucontext);
719
720	ucmdlen = min(udata->inlen, sizeof(ucmd));
721	if (ucmdlen < offsetof(struct mlx5_ib_create_cq, flags))
722		return -EINVAL;
723
724	if (ib_copy_from_udata(&ucmd, udata, ucmdlen))
725		return -EFAULT;
726
727	if ((ucmd.flags & ~(MLX5_IB_CREATE_CQ_FLAGS_CQE_128B_PAD |
728			    MLX5_IB_CREATE_CQ_FLAGS_UAR_PAGE_INDEX)))
729		return -EINVAL;
730
731	if ((ucmd.cqe_size != 64 && ucmd.cqe_size != 128) ||
732	    ucmd.reserved0 || ucmd.reserved1)
733		return -EINVAL;
734
735	*cqe_size = ucmd.cqe_size;
736
737	cq->buf.umem =
738		ib_umem_get(&dev->ib_dev, ucmd.buf_addr,
739			    entries * ucmd.cqe_size, IB_ACCESS_LOCAL_WRITE);
740	if (IS_ERR(cq->buf.umem)) {
741		err = PTR_ERR(cq->buf.umem);
742		return err;
743	}
744
745	err = mlx5_ib_db_map_user(context, udata, ucmd.db_addr, &cq->db);
746	if (err)
747		goto err_umem;
748
749	mlx5_ib_cont_pages(cq->buf.umem, ucmd.buf_addr, 0, &npages, &page_shift,
750			   &ncont, NULL);
751	mlx5_ib_dbg(dev, "addr 0x%llx, size %u, npages %d, page_shift %d, ncont %d\n",
752		    ucmd.buf_addr, entries * ucmd.cqe_size, npages, page_shift, ncont);
753
754	*inlen = MLX5_ST_SZ_BYTES(create_cq_in) +
755		 MLX5_FLD_SZ_BYTES(create_cq_in, pas[0]) * ncont;
756	*cqb = kvzalloc(*inlen, GFP_KERNEL);
757	if (!*cqb) {
758		err = -ENOMEM;
759		goto err_db;
760	}
761
762	pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, *cqb, pas);
763	mlx5_ib_populate_pas(dev, cq->buf.umem, page_shift, pas, 0);
764
765	cqc = MLX5_ADDR_OF(create_cq_in, *cqb, cq_context);
766	MLX5_SET(cqc, cqc, log_page_size,
767		 page_shift - MLX5_ADAPTER_PAGE_SHIFT);
768
769	if (ucmd.flags & MLX5_IB_CREATE_CQ_FLAGS_UAR_PAGE_INDEX) {
770		*index = ucmd.uar_page_index;
771	} else if (context->bfregi.lib_uar_dyn) {
772		err = -EINVAL;
773		goto err_cqb;
774	} else {
775		*index = context->bfregi.sys_pages[0];
776	}
777
778	if (ucmd.cqe_comp_en == 1) {
779		int mini_cqe_format;
780
781		if (!((*cqe_size == 128 &&
782		       MLX5_CAP_GEN(dev->mdev, cqe_compression_128)) ||
783		      (*cqe_size == 64  &&
784		       MLX5_CAP_GEN(dev->mdev, cqe_compression)))) {
785			err = -EOPNOTSUPP;
786			mlx5_ib_warn(dev, "CQE compression is not supported for size %d!\n",
787				     *cqe_size);
788			goto err_cqb;
789		}
790
791		mini_cqe_format =
792			mini_cqe_res_format_to_hw(dev,
793						  ucmd.cqe_comp_res_format);
794		if (mini_cqe_format < 0) {
795			err = mini_cqe_format;
796			mlx5_ib_dbg(dev, "CQE compression res format %d error: %d\n",
797				    ucmd.cqe_comp_res_format, err);
798			goto err_cqb;
799		}
800
801		MLX5_SET(cqc, cqc, cqe_comp_en, 1);
802		MLX5_SET(cqc, cqc, mini_cqe_res_format, mini_cqe_format);
803	}
804
805	if (ucmd.flags & MLX5_IB_CREATE_CQ_FLAGS_CQE_128B_PAD) {
806		if (*cqe_size != 128 ||
807		    !MLX5_CAP_GEN(dev->mdev, cqe_128_always)) {
808			err = -EOPNOTSUPP;
809			mlx5_ib_warn(dev,
810				     "CQE padding is not supported for CQE size of %dB!\n",
811				     *cqe_size);
812			goto err_cqb;
813		}
814
815		cq->private_flags |= MLX5_IB_CQ_PR_FLAGS_CQE_128_PAD;
816	}
817
818	MLX5_SET(create_cq_in, *cqb, uid, context->devx_uid);
819	return 0;
820
821err_cqb:
822	kvfree(*cqb);
823
824err_db:
825	mlx5_ib_db_unmap_user(context, &cq->db);
826
827err_umem:
828	ib_umem_release(cq->buf.umem);
829	return err;
830}
831
832static void destroy_cq_user(struct mlx5_ib_cq *cq, struct ib_udata *udata)
833{
834	struct mlx5_ib_ucontext *context = rdma_udata_to_drv_context(
835		udata, struct mlx5_ib_ucontext, ibucontext);
836
837	mlx5_ib_db_unmap_user(context, &cq->db);
838	ib_umem_release(cq->buf.umem);
839}
840
841static void init_cq_frag_buf(struct mlx5_ib_cq_buf *buf)
842{
843	int i;
844	void *cqe;
845	struct mlx5_cqe64 *cqe64;
846
847	for (i = 0; i < buf->nent; i++) {
848		cqe = mlx5_frag_buf_get_wqe(&buf->fbc, i);
849		cqe64 = buf->cqe_size == 64 ? cqe : cqe + 64;
850		cqe64->op_own = MLX5_CQE_INVALID << 4;
851	}
852}
853
854static int create_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
855			    int entries, int cqe_size,
856			    u32 **cqb, int *index, int *inlen)
857{
858	__be64 *pas;
859	void *cqc;
860	int err;
861
862	err = mlx5_db_alloc(dev->mdev, &cq->db);
863	if (err)
864		return err;
865
866	cq->mcq.set_ci_db  = cq->db.db;
867	cq->mcq.arm_db     = cq->db.db + 1;
868	cq->mcq.cqe_sz = cqe_size;
869
870	err = alloc_cq_frag_buf(dev, &cq->buf, entries, cqe_size);
871	if (err)
872		goto err_db;
873
874	init_cq_frag_buf(&cq->buf);
875
876	*inlen = MLX5_ST_SZ_BYTES(create_cq_in) +
877		 MLX5_FLD_SZ_BYTES(create_cq_in, pas[0]) *
878		 cq->buf.frag_buf.npages;
879	*cqb = kvzalloc(*inlen, GFP_KERNEL);
880	if (!*cqb) {
881		err = -ENOMEM;
882		goto err_buf;
883	}
884
885	pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, *cqb, pas);
886	mlx5_fill_page_frag_array(&cq->buf.frag_buf, pas);
887
888	cqc = MLX5_ADDR_OF(create_cq_in, *cqb, cq_context);
889	MLX5_SET(cqc, cqc, log_page_size,
890		 cq->buf.frag_buf.page_shift -
891		 MLX5_ADAPTER_PAGE_SHIFT);
892
893	*index = dev->mdev->priv.uar->index;
894
895	return 0;
896
897err_buf:
898	free_cq_buf(dev, &cq->buf);
899
900err_db:
901	mlx5_db_free(dev->mdev, &cq->db);
902	return err;
903}
904
905static void destroy_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq)
906{
907	free_cq_buf(dev, &cq->buf);
908	mlx5_db_free(dev->mdev, &cq->db);
909}
910
911static void notify_soft_wc_handler(struct work_struct *work)
912{
913	struct mlx5_ib_cq *cq = container_of(work, struct mlx5_ib_cq,
914					     notify_work);
915
916	cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context);
917}
918
919int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
920		      struct ib_udata *udata)
921{
922	struct ib_device *ibdev = ibcq->device;
923	int entries = attr->cqe;
924	int vector = attr->comp_vector;
925	struct mlx5_ib_dev *dev = to_mdev(ibdev);
926	struct mlx5_ib_cq *cq = to_mcq(ibcq);
927	u32 out[MLX5_ST_SZ_DW(create_cq_out)];
928	int index;
929	int inlen;
930	u32 *cqb = NULL;
931	void *cqc;
932	int cqe_size;
933	int eqn;
934	int err;
935
936	if (entries < 0 ||
937	    (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz))))
938		return -EINVAL;
939
940	if (check_cq_create_flags(attr->flags))
941		return -EOPNOTSUPP;
942
943	entries = roundup_pow_of_two(entries + 1);
944	if (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)))
945		return -EINVAL;
946
947	cq->ibcq.cqe = entries - 1;
948	mutex_init(&cq->resize_mutex);
949	spin_lock_init(&cq->lock);
950	cq->resize_buf = NULL;
951	cq->resize_umem = NULL;
952	cq->create_flags = attr->flags;
953	INIT_LIST_HEAD(&cq->list_send_qp);
954	INIT_LIST_HEAD(&cq->list_recv_qp);
955
956	if (udata) {
957		err = create_cq_user(dev, udata, cq, entries, &cqb, &cqe_size,
958				     &index, &inlen);
959		if (err)
960			return err;
961	} else {
962		cqe_size = cache_line_size() == 128 ? 128 : 64;
963		err = create_cq_kernel(dev, cq, entries, cqe_size, &cqb,
964				       &index, &inlen);
965		if (err)
966			return err;
967
968		INIT_WORK(&cq->notify_work, notify_soft_wc_handler);
969	}
970
971	err = mlx5_vector2eqn(dev->mdev, vector, &eqn);
972	if (err)
973		goto err_cqb;
974
975	cq->cqe_size = cqe_size;
976
977	cqc = MLX5_ADDR_OF(create_cq_in, cqb, cq_context);
978	MLX5_SET(cqc, cqc, cqe_sz,
979		 cqe_sz_to_mlx_sz(cqe_size,
980				  cq->private_flags &
981				  MLX5_IB_CQ_PR_FLAGS_CQE_128_PAD));
982	MLX5_SET(cqc, cqc, log_cq_size, ilog2(entries));
983	MLX5_SET(cqc, cqc, uar_page, index);
984	MLX5_SET(cqc, cqc, c_eqn, eqn);
985	MLX5_SET64(cqc, cqc, dbr_addr, cq->db.dma);
986	if (cq->create_flags & IB_UVERBS_CQ_FLAGS_IGNORE_OVERRUN)
987		MLX5_SET(cqc, cqc, oi, 1);
988
989	err = mlx5_core_create_cq(dev->mdev, &cq->mcq, cqb, inlen, out, sizeof(out));
990	if (err)
991		goto err_cqb;
992
993	mlx5_ib_dbg(dev, "cqn 0x%x\n", cq->mcq.cqn);
994	if (udata)
995		cq->mcq.tasklet_ctx.comp = mlx5_ib_cq_comp;
996	else
997		cq->mcq.comp  = mlx5_ib_cq_comp;
998	cq->mcq.event = mlx5_ib_cq_event;
999
1000	INIT_LIST_HEAD(&cq->wc_list);
1001
1002	if (udata)
1003		if (ib_copy_to_udata(udata, &cq->mcq.cqn, sizeof(__u32))) {
1004			err = -EFAULT;
1005			goto err_cmd;
1006		}
1007
1008
1009	kvfree(cqb);
1010	return 0;
1011
1012err_cmd:
1013	mlx5_core_destroy_cq(dev->mdev, &cq->mcq);
1014
1015err_cqb:
1016	kvfree(cqb);
1017	if (udata)
1018		destroy_cq_user(cq, udata);
1019	else
1020		destroy_cq_kernel(dev, cq);
1021	return err;
1022}
1023
1024int mlx5_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
1025{
1026	struct mlx5_ib_dev *dev = to_mdev(cq->device);
1027	struct mlx5_ib_cq *mcq = to_mcq(cq);
1028	int ret;
1029
1030	ret = mlx5_core_destroy_cq(dev->mdev, &mcq->mcq);
1031	if (ret)
1032		return ret;
1033
1034	if (udata)
1035		destroy_cq_user(mcq, udata);
1036	else
1037		destroy_cq_kernel(dev, mcq);
1038	return 0;
1039}
1040
1041static int is_equal_rsn(struct mlx5_cqe64 *cqe64, u32 rsn)
1042{
1043	return rsn == (ntohl(cqe64->sop_drop_qpn) & 0xffffff);
1044}
1045
1046void __mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 rsn, struct mlx5_ib_srq *srq)
1047{
1048	struct mlx5_cqe64 *cqe64, *dest64;
1049	void *cqe, *dest;
1050	u32 prod_index;
1051	int nfreed = 0;
1052	u8 owner_bit;
1053
1054	if (!cq)
1055		return;
1056
1057	/* First we need to find the current producer index, so we
1058	 * know where to start cleaning from.  It doesn't matter if HW
1059	 * adds new entries after this loop -- the QP we're worried
1060	 * about is already in RESET, so the new entries won't come
1061	 * from our QP and therefore don't need to be checked.
1062	 */
1063	for (prod_index = cq->mcq.cons_index; get_sw_cqe(cq, prod_index); prod_index++)
1064		if (prod_index == cq->mcq.cons_index + cq->ibcq.cqe)
1065			break;
1066
1067	/* Now sweep backwards through the CQ, removing CQ entries
1068	 * that match our QP by copying older entries on top of them.
1069	 */
1070	while ((int) --prod_index - (int) cq->mcq.cons_index >= 0) {
1071		cqe = get_cqe(cq, prod_index & cq->ibcq.cqe);
1072		cqe64 = (cq->mcq.cqe_sz == 64) ? cqe : cqe + 64;
1073		if (is_equal_rsn(cqe64, rsn)) {
1074			if (srq && (ntohl(cqe64->srqn) & 0xffffff))
1075				mlx5_ib_free_srq_wqe(srq, be16_to_cpu(cqe64->wqe_counter));
1076			++nfreed;
1077		} else if (nfreed) {
1078			dest = get_cqe(cq, (prod_index + nfreed) & cq->ibcq.cqe);
1079			dest64 = (cq->mcq.cqe_sz == 64) ? dest : dest + 64;
1080			owner_bit = dest64->op_own & MLX5_CQE_OWNER_MASK;
1081			memcpy(dest, cqe, cq->mcq.cqe_sz);
1082			dest64->op_own = owner_bit |
1083				(dest64->op_own & ~MLX5_CQE_OWNER_MASK);
1084		}
1085	}
1086
1087	if (nfreed) {
1088		cq->mcq.cons_index += nfreed;
1089		/* Make sure update of buffer contents is done before
1090		 * updating consumer index.
1091		 */
1092		wmb();
1093		mlx5_cq_set_ci(&cq->mcq);
1094	}
1095}
1096
1097void mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 qpn, struct mlx5_ib_srq *srq)
1098{
1099	if (!cq)
1100		return;
1101
1102	spin_lock_irq(&cq->lock);
1103	__mlx5_ib_cq_clean(cq, qpn, srq);
1104	spin_unlock_irq(&cq->lock);
1105}
1106
1107int mlx5_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period)
1108{
1109	struct mlx5_ib_dev *dev = to_mdev(cq->device);
1110	struct mlx5_ib_cq *mcq = to_mcq(cq);
1111	int err;
1112
1113	if (!MLX5_CAP_GEN(dev->mdev, cq_moderation))
1114		return -EOPNOTSUPP;
1115
1116	if (cq_period > MLX5_MAX_CQ_PERIOD)
1117		return -EINVAL;
1118
1119	err = mlx5_core_modify_cq_moderation(dev->mdev, &mcq->mcq,
1120					     cq_period, cq_count);
1121	if (err)
1122		mlx5_ib_warn(dev, "modify cq 0x%x failed\n", mcq->mcq.cqn);
1123
1124	return err;
1125}
1126
1127static int resize_user(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
1128		       int entries, struct ib_udata *udata, int *npas,
1129		       int *page_shift, int *cqe_size)
1130{
1131	struct mlx5_ib_resize_cq ucmd;
1132	struct ib_umem *umem;
1133	int err;
1134	int npages;
1135
1136	err = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd));
1137	if (err)
1138		return err;
1139
1140	if (ucmd.reserved0 || ucmd.reserved1)
1141		return -EINVAL;
1142
1143	/* check multiplication overflow */
1144	if (ucmd.cqe_size && SIZE_MAX / ucmd.cqe_size <= entries - 1)
1145		return -EINVAL;
1146
1147	umem = ib_umem_get(&dev->ib_dev, ucmd.buf_addr,
1148			   (size_t)ucmd.cqe_size * entries,
1149			   IB_ACCESS_LOCAL_WRITE);
1150	if (IS_ERR(umem)) {
1151		err = PTR_ERR(umem);
1152		return err;
1153	}
1154
1155	mlx5_ib_cont_pages(umem, ucmd.buf_addr, 0, &npages, page_shift,
1156			   npas, NULL);
1157
1158	cq->resize_umem = umem;
1159	*cqe_size = ucmd.cqe_size;
1160
1161	return 0;
1162}
1163
1164static int resize_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
1165			 int entries, int cqe_size)
1166{
1167	int err;
1168
1169	cq->resize_buf = kzalloc(sizeof(*cq->resize_buf), GFP_KERNEL);
1170	if (!cq->resize_buf)
1171		return -ENOMEM;
1172
1173	err = alloc_cq_frag_buf(dev, cq->resize_buf, entries, cqe_size);
1174	if (err)
1175		goto ex;
1176
1177	init_cq_frag_buf(cq->resize_buf);
1178
1179	return 0;
1180
1181ex:
1182	kfree(cq->resize_buf);
1183	return err;
1184}
1185
1186static int copy_resize_cqes(struct mlx5_ib_cq *cq)
1187{
1188	struct mlx5_ib_dev *dev = to_mdev(cq->ibcq.device);
1189	struct mlx5_cqe64 *scqe64;
1190	struct mlx5_cqe64 *dcqe64;
1191	void *start_cqe;
1192	void *scqe;
1193	void *dcqe;
1194	int ssize;
1195	int dsize;
1196	int i;
1197	u8 sw_own;
1198
1199	ssize = cq->buf.cqe_size;
1200	dsize = cq->resize_buf->cqe_size;
1201	if (ssize != dsize) {
1202		mlx5_ib_warn(dev, "resize from different cqe size is not supported\n");
1203		return -EINVAL;
1204	}
1205
1206	i = cq->mcq.cons_index;
1207	scqe = get_sw_cqe(cq, i);
1208	scqe64 = ssize == 64 ? scqe : scqe + 64;
1209	start_cqe = scqe;
1210	if (!scqe) {
1211		mlx5_ib_warn(dev, "expected cqe in sw ownership\n");
1212		return -EINVAL;
1213	}
1214
1215	while (get_cqe_opcode(scqe64) != MLX5_CQE_RESIZE_CQ) {
1216		dcqe = mlx5_frag_buf_get_wqe(&cq->resize_buf->fbc,
1217					     (i + 1) & cq->resize_buf->nent);
1218		dcqe64 = dsize == 64 ? dcqe : dcqe + 64;
1219		sw_own = sw_ownership_bit(i + 1, cq->resize_buf->nent);
1220		memcpy(dcqe, scqe, dsize);
1221		dcqe64->op_own = (dcqe64->op_own & ~MLX5_CQE_OWNER_MASK) | sw_own;
1222
1223		++i;
1224		scqe = get_sw_cqe(cq, i);
1225		scqe64 = ssize == 64 ? scqe : scqe + 64;
1226		if (!scqe) {
1227			mlx5_ib_warn(dev, "expected cqe in sw ownership\n");
1228			return -EINVAL;
1229		}
1230
1231		if (scqe == start_cqe) {
1232			pr_warn("resize CQ failed to get resize CQE, CQN 0x%x\n",
1233				cq->mcq.cqn);
1234			return -ENOMEM;
1235		}
1236	}
1237	++cq->mcq.cons_index;
1238	return 0;
1239}
1240
1241int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
1242{
1243	struct mlx5_ib_dev *dev = to_mdev(ibcq->device);
1244	struct mlx5_ib_cq *cq = to_mcq(ibcq);
1245	void *cqc;
1246	u32 *in;
1247	int err;
1248	int npas;
1249	__be64 *pas;
1250	int page_shift;
1251	int inlen;
1252	int cqe_size;
1253	unsigned long flags;
1254
1255	if (!MLX5_CAP_GEN(dev->mdev, cq_resize)) {
1256		pr_info("Firmware does not support resize CQ\n");
1257		return -ENOSYS;
1258	}
1259
1260	if (entries < 1 ||
1261	    entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz))) {
1262		mlx5_ib_warn(dev, "wrong entries number %d, max %d\n",
1263			     entries,
1264			     1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz));
1265		return -EINVAL;
1266	}
1267
1268	entries = roundup_pow_of_two(entries + 1);
1269	if (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)) + 1)
1270		return -EINVAL;
1271
1272	if (entries == ibcq->cqe + 1)
1273		return 0;
1274
1275	mutex_lock(&cq->resize_mutex);
1276	if (udata) {
1277		err = resize_user(dev, cq, entries, udata, &npas, &page_shift,
1278				  &cqe_size);
1279	} else {
1280		cqe_size = 64;
1281		err = resize_kernel(dev, cq, entries, cqe_size);
1282		if (!err) {
1283			struct mlx5_frag_buf *frag_buf = &cq->resize_buf->frag_buf;
1284
1285			npas = frag_buf->npages;
1286			page_shift = frag_buf->page_shift;
1287		}
1288	}
1289
1290	if (err)
1291		goto ex;
1292
1293	inlen = MLX5_ST_SZ_BYTES(modify_cq_in) +
1294		MLX5_FLD_SZ_BYTES(modify_cq_in, pas[0]) * npas;
1295
1296	in = kvzalloc(inlen, GFP_KERNEL);
1297	if (!in) {
1298		err = -ENOMEM;
1299		goto ex_resize;
1300	}
1301
1302	pas = (__be64 *)MLX5_ADDR_OF(modify_cq_in, in, pas);
1303	if (udata)
1304		mlx5_ib_populate_pas(dev, cq->resize_umem, page_shift,
1305				     pas, 0);
1306	else
1307		mlx5_fill_page_frag_array(&cq->resize_buf->frag_buf, pas);
1308
1309	MLX5_SET(modify_cq_in, in,
1310		 modify_field_select_resize_field_select.resize_field_select.resize_field_select,
1311		 MLX5_MODIFY_CQ_MASK_LOG_SIZE  |
1312		 MLX5_MODIFY_CQ_MASK_PG_OFFSET |
1313		 MLX5_MODIFY_CQ_MASK_PG_SIZE);
1314
1315	cqc = MLX5_ADDR_OF(modify_cq_in, in, cq_context);
1316
1317	MLX5_SET(cqc, cqc, log_page_size,
1318		 page_shift - MLX5_ADAPTER_PAGE_SHIFT);
1319	MLX5_SET(cqc, cqc, cqe_sz,
1320		 cqe_sz_to_mlx_sz(cqe_size,
1321				  cq->private_flags &
1322				  MLX5_IB_CQ_PR_FLAGS_CQE_128_PAD));
1323	MLX5_SET(cqc, cqc, log_cq_size, ilog2(entries));
1324
1325	MLX5_SET(modify_cq_in, in, op_mod, MLX5_CQ_OPMOD_RESIZE);
1326	MLX5_SET(modify_cq_in, in, cqn, cq->mcq.cqn);
1327
1328	err = mlx5_core_modify_cq(dev->mdev, &cq->mcq, in, inlen);
1329	if (err)
1330		goto ex_alloc;
1331
1332	if (udata) {
1333		cq->ibcq.cqe = entries - 1;
1334		ib_umem_release(cq->buf.umem);
1335		cq->buf.umem = cq->resize_umem;
1336		cq->resize_umem = NULL;
1337	} else {
1338		struct mlx5_ib_cq_buf tbuf;
1339		int resized = 0;
1340
1341		spin_lock_irqsave(&cq->lock, flags);
1342		if (cq->resize_buf) {
1343			err = copy_resize_cqes(cq);
1344			if (!err) {
1345				tbuf = cq->buf;
1346				cq->buf = *cq->resize_buf;
1347				kfree(cq->resize_buf);
1348				cq->resize_buf = NULL;
1349				resized = 1;
1350			}
1351		}
1352		cq->ibcq.cqe = entries - 1;
1353		spin_unlock_irqrestore(&cq->lock, flags);
1354		if (resized)
1355			free_cq_buf(dev, &tbuf);
1356	}
1357	mutex_unlock(&cq->resize_mutex);
1358
1359	kvfree(in);
1360	return 0;
1361
1362ex_alloc:
1363	kvfree(in);
1364
1365ex_resize:
1366	ib_umem_release(cq->resize_umem);
1367	if (!udata) {
1368		free_cq_buf(dev, cq->resize_buf);
1369		cq->resize_buf = NULL;
1370	}
1371ex:
1372	mutex_unlock(&cq->resize_mutex);
1373	return err;
1374}
1375
1376int mlx5_ib_get_cqe_size(struct ib_cq *ibcq)
1377{
1378	struct mlx5_ib_cq *cq;
1379
1380	if (!ibcq)
1381		return 128;
1382
1383	cq = to_mcq(ibcq);
1384	return cq->cqe_size;
1385}
1386
1387/* Called from atomic context */
1388int mlx5_ib_generate_wc(struct ib_cq *ibcq, struct ib_wc *wc)
1389{
1390	struct mlx5_ib_wc *soft_wc;
1391	struct mlx5_ib_cq *cq = to_mcq(ibcq);
1392	unsigned long flags;
1393
1394	soft_wc = kmalloc(sizeof(*soft_wc), GFP_ATOMIC);
1395	if (!soft_wc)
1396		return -ENOMEM;
1397
1398	soft_wc->wc = *wc;
1399	spin_lock_irqsave(&cq->lock, flags);
1400	list_add_tail(&soft_wc->list, &cq->wc_list);
1401	if (cq->notify_flags == IB_CQ_NEXT_COMP ||
1402	    wc->status != IB_WC_SUCCESS) {
1403		cq->notify_flags = 0;
1404		schedule_work(&cq->notify_work);
1405	}
1406	spin_unlock_irqrestore(&cq->lock, flags);
1407
1408	return 0;
1409}
1410