1/*
2 * Copyright (c) 2007 Cisco Systems, Inc. All rights reserved.
3 * Copyright (c) 2007, 2008 Mellanox Technologies. All rights reserved.
4 *
5 * This software is available to you under a choice of one of two
6 * licenses.  You may choose to be licensed under the terms of the GNU
7 * General Public License (GPL) Version 2, available from the file
8 * COPYING in the main directory of this source tree, or the
9 * OpenIB.org BSD license below:
10 *
11 *     Redistribution and use in source and binary forms, with or
12 *     without modification, are permitted provided that the following
13 *     conditions are met:
14 *
15 *      - Redistributions of source code must retain the above
16 *        copyright notice, this list of conditions and the following
17 *        disclaimer.
18 *
19 *      - Redistributions in binary form must reproduce the above
20 *        copyright notice, this list of conditions and the following
21 *        disclaimer in the documentation and/or other materials
22 *        provided with the distribution.
23 *
24 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
25 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
26 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
27 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
28 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
29 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
30 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
31 * SOFTWARE.
32 */
33
34#include <linux/log2.h>
35#include <linux/etherdevice.h>
36#include <net/ip.h>
37#include <linux/slab.h>
38#include <linux/netdevice.h>
39
40#include <rdma/ib_cache.h>
41#include <rdma/ib_pack.h>
42#include <rdma/ib_addr.h>
43#include <rdma/ib_mad.h>
44#include <rdma/uverbs_ioctl.h>
45
46#include <linux/mlx4/driver.h>
47#include <linux/mlx4/qp.h>
48
49#include "mlx4_ib.h"
50#include <rdma/mlx4-abi.h>
51
52static void mlx4_ib_lock_cqs(struct mlx4_ib_cq *send_cq,
53			     struct mlx4_ib_cq *recv_cq);
54static void mlx4_ib_unlock_cqs(struct mlx4_ib_cq *send_cq,
55			       struct mlx4_ib_cq *recv_cq);
56static int _mlx4_ib_modify_wq(struct ib_wq *ibwq, enum ib_wq_state new_state,
57			      struct ib_udata *udata);
58
59enum {
60	MLX4_IB_ACK_REQ_FREQ	= 8,
61};
62
63enum {
64	MLX4_IB_DEFAULT_SCHED_QUEUE	= 0x83,
65	MLX4_IB_DEFAULT_QP0_SCHED_QUEUE	= 0x3f,
66	MLX4_IB_LINK_TYPE_IB		= 0,
67	MLX4_IB_LINK_TYPE_ETH		= 1
68};
69
70enum {
71	MLX4_IB_MIN_SQ_STRIDE	= 6,
72	MLX4_IB_CACHE_LINE_SIZE	= 64,
73};
74
75enum {
76	MLX4_RAW_QP_MTU		= 7,
77	MLX4_RAW_QP_MSGMAX	= 31,
78};
79
80#ifndef ETH_ALEN
81#define ETH_ALEN        6
82#endif
83
84static const __be32 mlx4_ib_opcode[] = {
85	[IB_WR_SEND]				= cpu_to_be32(MLX4_OPCODE_SEND),
86	[IB_WR_LSO]				= cpu_to_be32(MLX4_OPCODE_LSO),
87	[IB_WR_SEND_WITH_IMM]			= cpu_to_be32(MLX4_OPCODE_SEND_IMM),
88	[IB_WR_RDMA_WRITE]			= cpu_to_be32(MLX4_OPCODE_RDMA_WRITE),
89	[IB_WR_RDMA_WRITE_WITH_IMM]		= cpu_to_be32(MLX4_OPCODE_RDMA_WRITE_IMM),
90	[IB_WR_RDMA_READ]			= cpu_to_be32(MLX4_OPCODE_RDMA_READ),
91	[IB_WR_ATOMIC_CMP_AND_SWP]		= cpu_to_be32(MLX4_OPCODE_ATOMIC_CS),
92	[IB_WR_ATOMIC_FETCH_AND_ADD]		= cpu_to_be32(MLX4_OPCODE_ATOMIC_FA),
93	[IB_WR_SEND_WITH_INV]			= cpu_to_be32(MLX4_OPCODE_SEND_INVAL),
94	[IB_WR_LOCAL_INV]			= cpu_to_be32(MLX4_OPCODE_LOCAL_INVAL),
95	[IB_WR_REG_MR]				= cpu_to_be32(MLX4_OPCODE_FMR),
96	[IB_WR_MASKED_ATOMIC_CMP_AND_SWP]	= cpu_to_be32(MLX4_OPCODE_MASKED_ATOMIC_CS),
97	[IB_WR_MASKED_ATOMIC_FETCH_AND_ADD]	= cpu_to_be32(MLX4_OPCODE_MASKED_ATOMIC_FA),
98};
99
100enum mlx4_ib_source_type {
101	MLX4_IB_QP_SRC	= 0,
102	MLX4_IB_RWQ_SRC	= 1,
103};
104
105static int is_tunnel_qp(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
106{
107	if (!mlx4_is_master(dev->dev))
108		return 0;
109
110	return qp->mqp.qpn >= dev->dev->phys_caps.base_tunnel_sqpn &&
111	       qp->mqp.qpn < dev->dev->phys_caps.base_tunnel_sqpn +
112		8 * MLX4_MFUNC_MAX;
113}
114
115static int is_sqp(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
116{
117	int proxy_sqp = 0;
118	int real_sqp = 0;
119	int i;
120	/* PPF or Native -- real SQP */
121	real_sqp = ((mlx4_is_master(dev->dev) || !mlx4_is_mfunc(dev->dev)) &&
122		    qp->mqp.qpn >= dev->dev->phys_caps.base_sqpn &&
123		    qp->mqp.qpn <= dev->dev->phys_caps.base_sqpn + 3);
124	if (real_sqp)
125		return 1;
126	/* VF or PF -- proxy SQP */
127	if (mlx4_is_mfunc(dev->dev)) {
128		for (i = 0; i < dev->dev->caps.num_ports; i++) {
129			if (qp->mqp.qpn == dev->dev->caps.spec_qps[i].qp0_proxy ||
130			    qp->mqp.qpn == dev->dev->caps.spec_qps[i].qp1_proxy) {
131				proxy_sqp = 1;
132				break;
133			}
134		}
135	}
136	if (proxy_sqp)
137		return 1;
138
139	return !!(qp->flags & MLX4_IB_ROCE_V2_GSI_QP);
140}
141
142/* used for INIT/CLOSE port logic */
143static int is_qp0(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
144{
145	int proxy_qp0 = 0;
146	int real_qp0 = 0;
147	int i;
148	/* PPF or Native -- real QP0 */
149	real_qp0 = ((mlx4_is_master(dev->dev) || !mlx4_is_mfunc(dev->dev)) &&
150		    qp->mqp.qpn >= dev->dev->phys_caps.base_sqpn &&
151		    qp->mqp.qpn <= dev->dev->phys_caps.base_sqpn + 1);
152	if (real_qp0)
153		return 1;
154	/* VF or PF -- proxy QP0 */
155	if (mlx4_is_mfunc(dev->dev)) {
156		for (i = 0; i < dev->dev->caps.num_ports; i++) {
157			if (qp->mqp.qpn == dev->dev->caps.spec_qps[i].qp0_proxy) {
158				proxy_qp0 = 1;
159				break;
160			}
161		}
162	}
163	return proxy_qp0;
164}
165
166static void *get_wqe(struct mlx4_ib_qp *qp, int offset)
167{
168	return mlx4_buf_offset(&qp->buf, offset);
169}
170
171static void *get_recv_wqe(struct mlx4_ib_qp *qp, int n)
172{
173	return get_wqe(qp, qp->rq.offset + (n << qp->rq.wqe_shift));
174}
175
176static void *get_send_wqe(struct mlx4_ib_qp *qp, int n)
177{
178	return get_wqe(qp, qp->sq.offset + (n << qp->sq.wqe_shift));
179}
180
181/*
182 * Stamp a SQ WQE so that it is invalid if prefetched by marking the
183 * first four bytes of every 64 byte chunk with 0xffffffff, except for
184 * the very first chunk of the WQE.
185 */
186static void stamp_send_wqe(struct mlx4_ib_qp *qp, int n)
187{
188	__be32 *wqe;
189	int i;
190	int s;
191	void *buf;
192	struct mlx4_wqe_ctrl_seg *ctrl;
193
194	buf = get_send_wqe(qp, n & (qp->sq.wqe_cnt - 1));
195	ctrl = (struct mlx4_wqe_ctrl_seg *)buf;
196	s = (ctrl->qpn_vlan.fence_size & 0x3f) << 4;
197	for (i = 64; i < s; i += 64) {
198		wqe = buf + i;
199		*wqe = cpu_to_be32(0xffffffff);
200	}
201}
202
203static void mlx4_ib_qp_event(struct mlx4_qp *qp, enum mlx4_event type)
204{
205	struct ib_event event;
206	struct ib_qp *ibqp = &to_mibqp(qp)->ibqp;
207
208	if (type == MLX4_EVENT_TYPE_PATH_MIG)
209		to_mibqp(qp)->port = to_mibqp(qp)->alt_port;
210
211	if (ibqp->event_handler) {
212		event.device     = ibqp->device;
213		event.element.qp = ibqp;
214		switch (type) {
215		case MLX4_EVENT_TYPE_PATH_MIG:
216			event.event = IB_EVENT_PATH_MIG;
217			break;
218		case MLX4_EVENT_TYPE_COMM_EST:
219			event.event = IB_EVENT_COMM_EST;
220			break;
221		case MLX4_EVENT_TYPE_SQ_DRAINED:
222			event.event = IB_EVENT_SQ_DRAINED;
223			break;
224		case MLX4_EVENT_TYPE_SRQ_QP_LAST_WQE:
225			event.event = IB_EVENT_QP_LAST_WQE_REACHED;
226			break;
227		case MLX4_EVENT_TYPE_WQ_CATAS_ERROR:
228			event.event = IB_EVENT_QP_FATAL;
229			break;
230		case MLX4_EVENT_TYPE_PATH_MIG_FAILED:
231			event.event = IB_EVENT_PATH_MIG_ERR;
232			break;
233		case MLX4_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
234			event.event = IB_EVENT_QP_REQ_ERR;
235			break;
236		case MLX4_EVENT_TYPE_WQ_ACCESS_ERROR:
237			event.event = IB_EVENT_QP_ACCESS_ERR;
238			break;
239		default:
240			pr_warn("Unexpected event type %d "
241			       "on QP %06x\n", type, qp->qpn);
242			return;
243		}
244
245		ibqp->event_handler(&event, ibqp->qp_context);
246	}
247}
248
249static void mlx4_ib_wq_event(struct mlx4_qp *qp, enum mlx4_event type)
250{
251	pr_warn_ratelimited("Unexpected event type %d on WQ 0x%06x. Events are not supported for WQs\n",
252			    type, qp->qpn);
253}
254
255static int send_wqe_overhead(enum mlx4_ib_qp_type type, u32 flags)
256{
257	/*
258	 * UD WQEs must have a datagram segment.
259	 * RC and UC WQEs might have a remote address segment.
260	 * MLX WQEs need two extra inline data segments (for the UD
261	 * header and space for the ICRC).
262	 */
263	switch (type) {
264	case MLX4_IB_QPT_UD:
265		return sizeof (struct mlx4_wqe_ctrl_seg) +
266			sizeof (struct mlx4_wqe_datagram_seg) +
267			((flags & MLX4_IB_QP_LSO) ? MLX4_IB_LSO_HEADER_SPARE : 0);
268	case MLX4_IB_QPT_PROXY_SMI_OWNER:
269	case MLX4_IB_QPT_PROXY_SMI:
270	case MLX4_IB_QPT_PROXY_GSI:
271		return sizeof (struct mlx4_wqe_ctrl_seg) +
272			sizeof (struct mlx4_wqe_datagram_seg) + 64;
273	case MLX4_IB_QPT_TUN_SMI_OWNER:
274	case MLX4_IB_QPT_TUN_GSI:
275		return sizeof (struct mlx4_wqe_ctrl_seg) +
276			sizeof (struct mlx4_wqe_datagram_seg);
277
278	case MLX4_IB_QPT_UC:
279		return sizeof (struct mlx4_wqe_ctrl_seg) +
280			sizeof (struct mlx4_wqe_raddr_seg);
281	case MLX4_IB_QPT_RC:
282		return sizeof (struct mlx4_wqe_ctrl_seg) +
283			sizeof (struct mlx4_wqe_masked_atomic_seg) +
284			sizeof (struct mlx4_wqe_raddr_seg);
285	case MLX4_IB_QPT_SMI:
286	case MLX4_IB_QPT_GSI:
287		return sizeof (struct mlx4_wqe_ctrl_seg) +
288			ALIGN(MLX4_IB_UD_HEADER_SIZE +
289			      DIV_ROUND_UP(MLX4_IB_UD_HEADER_SIZE,
290					   MLX4_INLINE_ALIGN) *
291			      sizeof (struct mlx4_wqe_inline_seg),
292			      sizeof (struct mlx4_wqe_data_seg)) +
293			ALIGN(4 +
294			      sizeof (struct mlx4_wqe_inline_seg),
295			      sizeof (struct mlx4_wqe_data_seg));
296	default:
297		return sizeof (struct mlx4_wqe_ctrl_seg);
298	}
299}
300
301static int set_rq_size(struct mlx4_ib_dev *dev, struct ib_qp_cap *cap,
302		       bool is_user, bool has_rq, struct mlx4_ib_qp *qp,
303		       u32 inl_recv_sz)
304{
305	/* Sanity check RQ size before proceeding */
306	if (cap->max_recv_wr > dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE ||
307	    cap->max_recv_sge > min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg))
308		return -EINVAL;
309
310	if (!has_rq) {
311		if (cap->max_recv_wr || inl_recv_sz)
312			return -EINVAL;
313
314		qp->rq.wqe_cnt = qp->rq.max_gs = 0;
315	} else {
316		u32 max_inl_recv_sz = dev->dev->caps.max_rq_sg *
317			sizeof(struct mlx4_wqe_data_seg);
318		u32 wqe_size;
319
320		/* HW requires >= 1 RQ entry with >= 1 gather entry */
321		if (is_user && (!cap->max_recv_wr || !cap->max_recv_sge ||
322				inl_recv_sz > max_inl_recv_sz))
323			return -EINVAL;
324
325		qp->rq.wqe_cnt	 = roundup_pow_of_two(max(1U, cap->max_recv_wr));
326		qp->rq.max_gs	 = roundup_pow_of_two(max(1U, cap->max_recv_sge));
327		wqe_size = qp->rq.max_gs * sizeof(struct mlx4_wqe_data_seg);
328		qp->rq.wqe_shift = ilog2(max_t(u32, wqe_size, inl_recv_sz));
329	}
330
331	/* leave userspace return values as they were, so as not to break ABI */
332	if (is_user) {
333		cap->max_recv_wr  = qp->rq.max_post = qp->rq.wqe_cnt;
334		cap->max_recv_sge = qp->rq.max_gs;
335	} else {
336		cap->max_recv_wr  = qp->rq.max_post =
337			min(dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE, qp->rq.wqe_cnt);
338		cap->max_recv_sge = min(qp->rq.max_gs,
339					min(dev->dev->caps.max_sq_sg,
340					    dev->dev->caps.max_rq_sg));
341	}
342
343	return 0;
344}
345
346static int set_kernel_sq_size(struct mlx4_ib_dev *dev, struct ib_qp_cap *cap,
347			      enum mlx4_ib_qp_type type, struct mlx4_ib_qp *qp)
348{
349	int s;
350
351	/* Sanity check SQ size before proceeding */
352	if (cap->max_send_wr  > (dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE) ||
353	    cap->max_send_sge > min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg) ||
354	    cap->max_inline_data + send_wqe_overhead(type, qp->flags) +
355	    sizeof (struct mlx4_wqe_inline_seg) > dev->dev->caps.max_sq_desc_sz)
356		return -EINVAL;
357
358	/*
359	 * For MLX transport we need 2 extra S/G entries:
360	 * one for the header and one for the checksum at the end
361	 */
362	if ((type == MLX4_IB_QPT_SMI || type == MLX4_IB_QPT_GSI ||
363	     type & (MLX4_IB_QPT_PROXY_SMI_OWNER | MLX4_IB_QPT_TUN_SMI_OWNER)) &&
364	    cap->max_send_sge + 2 > dev->dev->caps.max_sq_sg)
365		return -EINVAL;
366
367	s = max(cap->max_send_sge * sizeof (struct mlx4_wqe_data_seg),
368		cap->max_inline_data + sizeof (struct mlx4_wqe_inline_seg)) +
369		send_wqe_overhead(type, qp->flags);
370
371	if (s > dev->dev->caps.max_sq_desc_sz)
372		return -EINVAL;
373
374	qp->sq.wqe_shift = ilog2(roundup_pow_of_two(s));
375
376	/*
377	 * We need to leave 2 KB + 1 WR of headroom in the SQ to
378	 * allow HW to prefetch.
379	 */
380	qp->sq_spare_wqes = MLX4_IB_SQ_HEADROOM(qp->sq.wqe_shift);
381	qp->sq.wqe_cnt = roundup_pow_of_two(cap->max_send_wr +
382					    qp->sq_spare_wqes);
383
384	qp->sq.max_gs =
385		(min(dev->dev->caps.max_sq_desc_sz,
386		     (1 << qp->sq.wqe_shift)) -
387		 send_wqe_overhead(type, qp->flags)) /
388		sizeof (struct mlx4_wqe_data_seg);
389
390	qp->buf_size = (qp->rq.wqe_cnt << qp->rq.wqe_shift) +
391		(qp->sq.wqe_cnt << qp->sq.wqe_shift);
392	if (qp->rq.wqe_shift > qp->sq.wqe_shift) {
393		qp->rq.offset = 0;
394		qp->sq.offset = qp->rq.wqe_cnt << qp->rq.wqe_shift;
395	} else {
396		qp->rq.offset = qp->sq.wqe_cnt << qp->sq.wqe_shift;
397		qp->sq.offset = 0;
398	}
399
400	cap->max_send_wr  = qp->sq.max_post =
401		qp->sq.wqe_cnt - qp->sq_spare_wqes;
402	cap->max_send_sge = min(qp->sq.max_gs,
403				min(dev->dev->caps.max_sq_sg,
404				    dev->dev->caps.max_rq_sg));
405	/* We don't support inline sends for kernel QPs (yet) */
406	cap->max_inline_data = 0;
407
408	return 0;
409}
410
411static int set_user_sq_size(struct mlx4_ib_dev *dev,
412			    struct mlx4_ib_qp *qp,
413			    struct mlx4_ib_create_qp *ucmd)
414{
415	u32 cnt;
416
417	/* Sanity check SQ size before proceeding */
418	if (check_shl_overflow(1, ucmd->log_sq_bb_count, &cnt) ||
419	    cnt > dev->dev->caps.max_wqes)
420		return -EINVAL;
421	if (ucmd->log_sq_stride >
422		ilog2(roundup_pow_of_two(dev->dev->caps.max_sq_desc_sz)) ||
423	    ucmd->log_sq_stride < MLX4_IB_MIN_SQ_STRIDE)
424		return -EINVAL;
425
426	qp->sq.wqe_cnt   = 1 << ucmd->log_sq_bb_count;
427	qp->sq.wqe_shift = ucmd->log_sq_stride;
428
429	qp->buf_size = (qp->rq.wqe_cnt << qp->rq.wqe_shift) +
430		(qp->sq.wqe_cnt << qp->sq.wqe_shift);
431
432	return 0;
433}
434
435static int alloc_proxy_bufs(struct ib_device *dev, struct mlx4_ib_qp *qp)
436{
437	int i;
438
439	qp->sqp_proxy_rcv =
440		kmalloc_array(qp->rq.wqe_cnt, sizeof(struct mlx4_ib_buf),
441			      GFP_KERNEL);
442	if (!qp->sqp_proxy_rcv)
443		return -ENOMEM;
444	for (i = 0; i < qp->rq.wqe_cnt; i++) {
445		qp->sqp_proxy_rcv[i].addr =
446			kmalloc(sizeof (struct mlx4_ib_proxy_sqp_hdr),
447				GFP_KERNEL);
448		if (!qp->sqp_proxy_rcv[i].addr)
449			goto err;
450		qp->sqp_proxy_rcv[i].map =
451			ib_dma_map_single(dev, qp->sqp_proxy_rcv[i].addr,
452					  sizeof (struct mlx4_ib_proxy_sqp_hdr),
453					  DMA_FROM_DEVICE);
454		if (ib_dma_mapping_error(dev, qp->sqp_proxy_rcv[i].map)) {
455			kfree(qp->sqp_proxy_rcv[i].addr);
456			goto err;
457		}
458	}
459	return 0;
460
461err:
462	while (i > 0) {
463		--i;
464		ib_dma_unmap_single(dev, qp->sqp_proxy_rcv[i].map,
465				    sizeof (struct mlx4_ib_proxy_sqp_hdr),
466				    DMA_FROM_DEVICE);
467		kfree(qp->sqp_proxy_rcv[i].addr);
468	}
469	kfree(qp->sqp_proxy_rcv);
470	qp->sqp_proxy_rcv = NULL;
471	return -ENOMEM;
472}
473
474static void free_proxy_bufs(struct ib_device *dev, struct mlx4_ib_qp *qp)
475{
476	int i;
477
478	for (i = 0; i < qp->rq.wqe_cnt; i++) {
479		ib_dma_unmap_single(dev, qp->sqp_proxy_rcv[i].map,
480				    sizeof (struct mlx4_ib_proxy_sqp_hdr),
481				    DMA_FROM_DEVICE);
482		kfree(qp->sqp_proxy_rcv[i].addr);
483	}
484	kfree(qp->sqp_proxy_rcv);
485}
486
487static bool qp_has_rq(struct ib_qp_init_attr *attr)
488{
489	if (attr->qp_type == IB_QPT_XRC_INI || attr->qp_type == IB_QPT_XRC_TGT)
490		return false;
491
492	return !attr->srq;
493}
494
495static int qp0_enabled_vf(struct mlx4_dev *dev, int qpn)
496{
497	int i;
498	for (i = 0; i < dev->caps.num_ports; i++) {
499		if (qpn == dev->caps.spec_qps[i].qp0_proxy)
500			return !!dev->caps.spec_qps[i].qp0_qkey;
501	}
502	return 0;
503}
504
505static void mlx4_ib_free_qp_counter(struct mlx4_ib_dev *dev,
506				    struct mlx4_ib_qp *qp)
507{
508	mutex_lock(&dev->counters_table[qp->port - 1].mutex);
509	mlx4_counter_free(dev->dev, qp->counter_index->index);
510	list_del(&qp->counter_index->list);
511	mutex_unlock(&dev->counters_table[qp->port - 1].mutex);
512
513	kfree(qp->counter_index);
514	qp->counter_index = NULL;
515}
516
517static int set_qp_rss(struct mlx4_ib_dev *dev, struct mlx4_ib_rss *rss_ctx,
518		      struct ib_qp_init_attr *init_attr,
519		      struct mlx4_ib_create_qp_rss *ucmd)
520{
521	rss_ctx->base_qpn_tbl_sz = init_attr->rwq_ind_tbl->ind_tbl[0]->wq_num |
522		(init_attr->rwq_ind_tbl->log_ind_tbl_size << 24);
523
524	if ((ucmd->rx_hash_function == MLX4_IB_RX_HASH_FUNC_TOEPLITZ) &&
525	    (dev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_TOP)) {
526		memcpy(rss_ctx->rss_key, ucmd->rx_hash_key,
527		       MLX4_EN_RSS_KEY_SIZE);
528	} else {
529		pr_debug("RX Hash function is not supported\n");
530		return (-EOPNOTSUPP);
531	}
532
533	if (ucmd->rx_hash_fields_mask & ~(u64)(MLX4_IB_RX_HASH_SRC_IPV4	|
534					       MLX4_IB_RX_HASH_DST_IPV4	|
535					       MLX4_IB_RX_HASH_SRC_IPV6	|
536					       MLX4_IB_RX_HASH_DST_IPV6	|
537					       MLX4_IB_RX_HASH_SRC_PORT_TCP |
538					       MLX4_IB_RX_HASH_DST_PORT_TCP |
539					       MLX4_IB_RX_HASH_SRC_PORT_UDP |
540					       MLX4_IB_RX_HASH_DST_PORT_UDP |
541					       MLX4_IB_RX_HASH_INNER)) {
542		pr_debug("RX Hash fields_mask has unsupported mask (0x%llx)\n",
543			 ucmd->rx_hash_fields_mask);
544		return (-EOPNOTSUPP);
545	}
546
547	if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_IPV4) &&
548	    (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_IPV4)) {
549		rss_ctx->flags = MLX4_RSS_IPV4;
550	} else if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_IPV4) ||
551		   (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_IPV4)) {
552		pr_debug("RX Hash fields_mask is not supported - both IPv4 SRC and DST must be set\n");
553		return (-EOPNOTSUPP);
554	}
555
556	if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_IPV6) &&
557	    (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_IPV6)) {
558		rss_ctx->flags |= MLX4_RSS_IPV6;
559	} else if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_IPV6) ||
560		   (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_IPV6)) {
561		pr_debug("RX Hash fields_mask is not supported - both IPv6 SRC and DST must be set\n");
562		return (-EOPNOTSUPP);
563	}
564
565	if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_PORT_UDP) &&
566	    (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_PORT_UDP)) {
567		if (!(dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_UDP_RSS)) {
568			pr_debug("RX Hash fields_mask for UDP is not supported\n");
569			return (-EOPNOTSUPP);
570		}
571
572		if (rss_ctx->flags & MLX4_RSS_IPV4)
573			rss_ctx->flags |= MLX4_RSS_UDP_IPV4;
574		if (rss_ctx->flags & MLX4_RSS_IPV6)
575			rss_ctx->flags |= MLX4_RSS_UDP_IPV6;
576		if (!(rss_ctx->flags & (MLX4_RSS_IPV6 | MLX4_RSS_IPV4))) {
577			pr_debug("RX Hash fields_mask is not supported - UDP must be set with IPv4 or IPv6\n");
578			return (-EOPNOTSUPP);
579		}
580	} else if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_PORT_UDP) ||
581		   (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_PORT_UDP)) {
582		pr_debug("RX Hash fields_mask is not supported - both UDP SRC and DST must be set\n");
583		return (-EOPNOTSUPP);
584	}
585
586	if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_PORT_TCP) &&
587	    (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_PORT_TCP)) {
588		if (rss_ctx->flags & MLX4_RSS_IPV4)
589			rss_ctx->flags |= MLX4_RSS_TCP_IPV4;
590		if (rss_ctx->flags & MLX4_RSS_IPV6)
591			rss_ctx->flags |= MLX4_RSS_TCP_IPV6;
592		if (!(rss_ctx->flags & (MLX4_RSS_IPV6 | MLX4_RSS_IPV4))) {
593			pr_debug("RX Hash fields_mask is not supported - TCP must be set with IPv4 or IPv6\n");
594			return (-EOPNOTSUPP);
595		}
596	} else if ((ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_SRC_PORT_TCP) ||
597		   (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_DST_PORT_TCP)) {
598		pr_debug("RX Hash fields_mask is not supported - both TCP SRC and DST must be set\n");
599		return (-EOPNOTSUPP);
600	}
601
602	if (ucmd->rx_hash_fields_mask & MLX4_IB_RX_HASH_INNER) {
603		if (dev->dev->caps.tunnel_offload_mode ==
604		    MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) {
605			/*
606			 * Hash according to inner headers if exist, otherwise
607			 * according to outer headers.
608			 */
609			rss_ctx->flags |= MLX4_RSS_BY_INNER_HEADERS_IPONLY;
610		} else {
611			pr_debug("RSS Hash for inner headers isn't supported\n");
612			return (-EOPNOTSUPP);
613		}
614	}
615
616	return 0;
617}
618
619static int create_qp_rss(struct mlx4_ib_dev *dev,
620			 struct ib_qp_init_attr *init_attr,
621			 struct mlx4_ib_create_qp_rss *ucmd,
622			 struct mlx4_ib_qp *qp)
623{
624	int qpn;
625	int err;
626
627	qp->mqp.usage = MLX4_RES_USAGE_USER_VERBS;
628
629	err = mlx4_qp_reserve_range(dev->dev, 1, 1, &qpn, 0, qp->mqp.usage);
630	if (err)
631		return err;
632
633	err = mlx4_qp_alloc(dev->dev, qpn, &qp->mqp);
634	if (err)
635		goto err_qpn;
636
637	INIT_LIST_HEAD(&qp->gid_list);
638	INIT_LIST_HEAD(&qp->steering_rules);
639
640	qp->mlx4_ib_qp_type = MLX4_IB_QPT_RAW_PACKET;
641	qp->state = IB_QPS_RESET;
642
643	/* Set dummy send resources to be compatible with HV and PRM */
644	qp->sq_no_prefetch = 1;
645	qp->sq.wqe_cnt = 1;
646	qp->sq.wqe_shift = MLX4_IB_MIN_SQ_STRIDE;
647	qp->buf_size = qp->sq.wqe_cnt << MLX4_IB_MIN_SQ_STRIDE;
648	qp->mtt = (to_mqp(
649		   (struct ib_qp *)init_attr->rwq_ind_tbl->ind_tbl[0]))->mtt;
650
651	qp->rss_ctx = kzalloc(sizeof(*qp->rss_ctx), GFP_KERNEL);
652	if (!qp->rss_ctx) {
653		err = -ENOMEM;
654		goto err_qp_alloc;
655	}
656
657	err = set_qp_rss(dev, qp->rss_ctx, init_attr, ucmd);
658	if (err)
659		goto err;
660
661	return 0;
662
663err:
664	kfree(qp->rss_ctx);
665
666err_qp_alloc:
667	mlx4_qp_remove(dev->dev, &qp->mqp);
668	mlx4_qp_free(dev->dev, &qp->mqp);
669
670err_qpn:
671	mlx4_qp_release_range(dev->dev, qpn, 1);
672	return err;
673}
674
675static int _mlx4_ib_create_qp_rss(struct ib_pd *pd, struct mlx4_ib_qp *qp,
676				  struct ib_qp_init_attr *init_attr,
677				  struct ib_udata *udata)
678{
679	struct mlx4_ib_create_qp_rss ucmd = {};
680	size_t required_cmd_sz;
681	int err;
682
683	if (!udata) {
684		pr_debug("RSS QP with NULL udata\n");
685		return -EINVAL;
686	}
687
688	if (udata->outlen)
689		return -EOPNOTSUPP;
690
691	required_cmd_sz = offsetof(typeof(ucmd), reserved1) +
692					sizeof(ucmd.reserved1);
693	if (udata->inlen < required_cmd_sz) {
694		pr_debug("invalid inlen\n");
695		return -EINVAL;
696	}
697
698	if (ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata->inlen))) {
699		pr_debug("copy failed\n");
700		return -EFAULT;
701	}
702
703	if (memchr_inv(ucmd.reserved, 0, sizeof(ucmd.reserved)))
704		return -EOPNOTSUPP;
705
706	if (ucmd.comp_mask || ucmd.reserved1)
707		return -EOPNOTSUPP;
708
709	if (udata->inlen > sizeof(ucmd) &&
710	    !ib_is_udata_cleared(udata, sizeof(ucmd),
711				 udata->inlen - sizeof(ucmd))) {
712		pr_debug("inlen is not supported\n");
713		return -EOPNOTSUPP;
714	}
715
716	if (init_attr->qp_type != IB_QPT_RAW_PACKET) {
717		pr_debug("RSS QP with unsupported QP type %d\n",
718			 init_attr->qp_type);
719		return -EOPNOTSUPP;
720	}
721
722	if (init_attr->create_flags) {
723		pr_debug("RSS QP doesn't support create flags\n");
724		return -EOPNOTSUPP;
725	}
726
727	if (init_attr->send_cq || init_attr->cap.max_send_wr) {
728		pr_debug("RSS QP with unsupported send attributes\n");
729		return -EOPNOTSUPP;
730	}
731
732	qp->pri.vid = 0xFFFF;
733	qp->alt.vid = 0xFFFF;
734
735	err = create_qp_rss(to_mdev(pd->device), init_attr, &ucmd, qp);
736	if (err)
737		return err;
738
739	qp->ibqp.qp_num = qp->mqp.qpn;
740	return 0;
741}
742
743/*
744 * This function allocates a WQN from a range which is consecutive and aligned
745 * to its size. In case the range is full, then it creates a new range and
746 * allocates WQN from it. The new range will be used for following allocations.
747 */
748static int mlx4_ib_alloc_wqn(struct mlx4_ib_ucontext *context,
749			     struct mlx4_ib_qp *qp, int range_size, int *wqn)
750{
751	struct mlx4_ib_dev *dev = to_mdev(context->ibucontext.device);
752	struct mlx4_wqn_range *range;
753	int err = 0;
754
755	mutex_lock(&context->wqn_ranges_mutex);
756
757	range = list_first_entry_or_null(&context->wqn_ranges_list,
758					 struct mlx4_wqn_range, list);
759
760	if (!range || (range->refcount == range->size) || range->dirty) {
761		range = kzalloc(sizeof(*range), GFP_KERNEL);
762		if (!range) {
763			err = -ENOMEM;
764			goto out;
765		}
766
767		err = mlx4_qp_reserve_range(dev->dev, range_size,
768					    range_size, &range->base_wqn, 0,
769					    qp->mqp.usage);
770		if (err) {
771			kfree(range);
772			goto out;
773		}
774
775		range->size = range_size;
776		list_add(&range->list, &context->wqn_ranges_list);
777	} else if (range_size != 1) {
778		/*
779		 * Requesting a new range (>1) when last range is still open, is
780		 * not valid.
781		 */
782		err = -EINVAL;
783		goto out;
784	}
785
786	qp->wqn_range = range;
787
788	*wqn = range->base_wqn + range->refcount;
789
790	range->refcount++;
791
792out:
793	mutex_unlock(&context->wqn_ranges_mutex);
794
795	return err;
796}
797
798static void mlx4_ib_release_wqn(struct mlx4_ib_ucontext *context,
799				struct mlx4_ib_qp *qp, bool dirty_release)
800{
801	struct mlx4_ib_dev *dev = to_mdev(context->ibucontext.device);
802	struct mlx4_wqn_range *range;
803
804	mutex_lock(&context->wqn_ranges_mutex);
805
806	range = qp->wqn_range;
807
808	range->refcount--;
809	if (!range->refcount) {
810		mlx4_qp_release_range(dev->dev, range->base_wqn,
811				      range->size);
812		list_del(&range->list);
813		kfree(range);
814	} else if (dirty_release) {
815	/*
816	 * A range which one of its WQNs is destroyed, won't be able to be
817	 * reused for further WQN allocations.
818	 * The next created WQ will allocate a new range.
819	 */
820		range->dirty = true;
821	}
822
823	mutex_unlock(&context->wqn_ranges_mutex);
824}
825
826static int create_rq(struct ib_pd *pd, struct ib_qp_init_attr *init_attr,
827		     struct ib_udata *udata, struct mlx4_ib_qp *qp)
828{
829	struct mlx4_ib_dev *dev = to_mdev(pd->device);
830	int qpn;
831	int err;
832	struct mlx4_ib_ucontext *context = rdma_udata_to_drv_context(
833		udata, struct mlx4_ib_ucontext, ibucontext);
834	struct mlx4_ib_cq *mcq;
835	unsigned long flags;
836	int range_size;
837	struct mlx4_ib_create_wq wq;
838	size_t copy_len;
839	int shift;
840	int n;
841
842	qp->mlx4_ib_qp_type = MLX4_IB_QPT_RAW_PACKET;
843
844	spin_lock_init(&qp->sq.lock);
845	spin_lock_init(&qp->rq.lock);
846	INIT_LIST_HEAD(&qp->gid_list);
847	INIT_LIST_HEAD(&qp->steering_rules);
848
849	qp->state = IB_QPS_RESET;
850
851	copy_len = min(sizeof(struct mlx4_ib_create_wq), udata->inlen);
852
853	if (ib_copy_from_udata(&wq, udata, copy_len)) {
854		err = -EFAULT;
855		goto err;
856	}
857
858	if (wq.comp_mask || wq.reserved[0] || wq.reserved[1] ||
859	    wq.reserved[2]) {
860		pr_debug("user command isn't supported\n");
861		err = -EOPNOTSUPP;
862		goto err;
863	}
864
865	if (wq.log_range_size > ilog2(dev->dev->caps.max_rss_tbl_sz)) {
866		pr_debug("WQN range size must be equal or smaller than %d\n",
867			 dev->dev->caps.max_rss_tbl_sz);
868		err = -EOPNOTSUPP;
869		goto err;
870	}
871	range_size = 1 << wq.log_range_size;
872
873	if (init_attr->create_flags & IB_QP_CREATE_SCATTER_FCS)
874		qp->flags |= MLX4_IB_QP_SCATTER_FCS;
875
876	err = set_rq_size(dev, &init_attr->cap, true, true, qp, qp->inl_recv_sz);
877	if (err)
878		goto err;
879
880	qp->sq_no_prefetch = 1;
881	qp->sq.wqe_cnt = 1;
882	qp->sq.wqe_shift = MLX4_IB_MIN_SQ_STRIDE;
883	qp->buf_size = (qp->rq.wqe_cnt << qp->rq.wqe_shift) +
884		       (qp->sq.wqe_cnt << qp->sq.wqe_shift);
885
886	qp->umem = ib_umem_get(pd->device, wq.buf_addr, qp->buf_size, 0);
887	if (IS_ERR(qp->umem)) {
888		err = PTR_ERR(qp->umem);
889		goto err;
890	}
891
892	shift = mlx4_ib_umem_calc_optimal_mtt_size(qp->umem, 0, &n);
893	err = mlx4_mtt_init(dev->dev, n, shift, &qp->mtt);
894
895	if (err)
896		goto err_buf;
897
898	err = mlx4_ib_umem_write_mtt(dev, &qp->mtt, qp->umem);
899	if (err)
900		goto err_mtt;
901
902	err = mlx4_ib_db_map_user(udata, wq.db_addr, &qp->db);
903	if (err)
904		goto err_mtt;
905	qp->mqp.usage = MLX4_RES_USAGE_USER_VERBS;
906
907	err = mlx4_ib_alloc_wqn(context, qp, range_size, &qpn);
908	if (err)
909		goto err_wrid;
910
911	err = mlx4_qp_alloc(dev->dev, qpn, &qp->mqp);
912	if (err)
913		goto err_qpn;
914
915	/*
916	 * Hardware wants QPN written in big-endian order (after
917	 * shifting) for send doorbell.  Precompute this value to save
918	 * a little bit when posting sends.
919	 */
920	qp->doorbell_qpn = swab32(qp->mqp.qpn << 8);
921
922	qp->mqp.event = mlx4_ib_wq_event;
923
924	spin_lock_irqsave(&dev->reset_flow_resource_lock, flags);
925	mlx4_ib_lock_cqs(to_mcq(init_attr->send_cq),
926			 to_mcq(init_attr->recv_cq));
927	/* Maintain device to QPs access, needed for further handling
928	 * via reset flow
929	 */
930	list_add_tail(&qp->qps_list, &dev->qp_list);
931	/* Maintain CQ to QPs access, needed for further handling
932	 * via reset flow
933	 */
934	mcq = to_mcq(init_attr->send_cq);
935	list_add_tail(&qp->cq_send_list, &mcq->send_qp_list);
936	mcq = to_mcq(init_attr->recv_cq);
937	list_add_tail(&qp->cq_recv_list, &mcq->recv_qp_list);
938	mlx4_ib_unlock_cqs(to_mcq(init_attr->send_cq),
939			   to_mcq(init_attr->recv_cq));
940	spin_unlock_irqrestore(&dev->reset_flow_resource_lock, flags);
941	return 0;
942
943err_qpn:
944	mlx4_ib_release_wqn(context, qp, 0);
945err_wrid:
946	mlx4_ib_db_unmap_user(context, &qp->db);
947
948err_mtt:
949	mlx4_mtt_cleanup(dev->dev, &qp->mtt);
950err_buf:
951	ib_umem_release(qp->umem);
952err:
953	return err;
954}
955
956static int create_qp_common(struct ib_pd *pd, struct ib_qp_init_attr *init_attr,
957			    struct ib_udata *udata, int sqpn,
958			    struct mlx4_ib_qp *qp)
959{
960	struct mlx4_ib_dev *dev = to_mdev(pd->device);
961	int qpn;
962	int err;
963	struct mlx4_ib_ucontext *context = rdma_udata_to_drv_context(
964		udata, struct mlx4_ib_ucontext, ibucontext);
965	enum mlx4_ib_qp_type qp_type = (enum mlx4_ib_qp_type) init_attr->qp_type;
966	struct mlx4_ib_cq *mcq;
967	unsigned long flags;
968
969	/* When tunneling special qps, we use a plain UD qp */
970	if (sqpn) {
971		if (mlx4_is_mfunc(dev->dev) &&
972		    (!mlx4_is_master(dev->dev) ||
973		     !(init_attr->create_flags & MLX4_IB_SRIOV_SQP))) {
974			if (init_attr->qp_type == IB_QPT_GSI)
975				qp_type = MLX4_IB_QPT_PROXY_GSI;
976			else {
977				if (mlx4_is_master(dev->dev) ||
978				    qp0_enabled_vf(dev->dev, sqpn))
979					qp_type = MLX4_IB_QPT_PROXY_SMI_OWNER;
980				else
981					qp_type = MLX4_IB_QPT_PROXY_SMI;
982			}
983		}
984		qpn = sqpn;
985		/* add extra sg entry for tunneling */
986		init_attr->cap.max_recv_sge++;
987	} else if (init_attr->create_flags & MLX4_IB_SRIOV_TUNNEL_QP) {
988		struct mlx4_ib_qp_tunnel_init_attr *tnl_init =
989			container_of(init_attr,
990				     struct mlx4_ib_qp_tunnel_init_attr, init_attr);
991		if ((tnl_init->proxy_qp_type != IB_QPT_SMI &&
992		     tnl_init->proxy_qp_type != IB_QPT_GSI)   ||
993		    !mlx4_is_master(dev->dev))
994			return -EINVAL;
995		if (tnl_init->proxy_qp_type == IB_QPT_GSI)
996			qp_type = MLX4_IB_QPT_TUN_GSI;
997		else if (tnl_init->slave == mlx4_master_func_num(dev->dev) ||
998			 mlx4_vf_smi_enabled(dev->dev, tnl_init->slave,
999					     tnl_init->port))
1000			qp_type = MLX4_IB_QPT_TUN_SMI_OWNER;
1001		else
1002			qp_type = MLX4_IB_QPT_TUN_SMI;
1003		/* we are definitely in the PPF here, since we are creating
1004		 * tunnel QPs. base_tunnel_sqpn is therefore valid. */
1005		qpn = dev->dev->phys_caps.base_tunnel_sqpn + 8 * tnl_init->slave
1006			+ tnl_init->proxy_qp_type * 2 + tnl_init->port - 1;
1007		sqpn = qpn;
1008	}
1009
1010	if (init_attr->qp_type == IB_QPT_SMI ||
1011	    init_attr->qp_type == IB_QPT_GSI || qp_type == MLX4_IB_QPT_SMI ||
1012	    qp_type == MLX4_IB_QPT_GSI ||
1013	    (qp_type & (MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_SMI_OWNER |
1014			MLX4_IB_QPT_PROXY_GSI | MLX4_IB_QPT_TUN_SMI_OWNER))) {
1015		qp->sqp = kzalloc(sizeof(struct mlx4_ib_sqp), GFP_KERNEL);
1016		if (!qp->sqp)
1017			return -ENOMEM;
1018	}
1019
1020	qp->mlx4_ib_qp_type = qp_type;
1021
1022	spin_lock_init(&qp->sq.lock);
1023	spin_lock_init(&qp->rq.lock);
1024	INIT_LIST_HEAD(&qp->gid_list);
1025	INIT_LIST_HEAD(&qp->steering_rules);
1026
1027	qp->state = IB_QPS_RESET;
1028	if (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR)
1029		qp->sq_signal_bits = cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE);
1030
1031	if (udata) {
1032		struct mlx4_ib_create_qp ucmd;
1033		size_t copy_len;
1034		int shift;
1035		int n;
1036
1037		copy_len = sizeof(struct mlx4_ib_create_qp);
1038
1039		if (ib_copy_from_udata(&ucmd, udata, copy_len)) {
1040			err = -EFAULT;
1041			goto err;
1042		}
1043
1044		qp->inl_recv_sz = ucmd.inl_recv_sz;
1045
1046		if (init_attr->create_flags & IB_QP_CREATE_SCATTER_FCS) {
1047			if (!(dev->dev->caps.flags &
1048			      MLX4_DEV_CAP_FLAG_FCS_KEEP)) {
1049				pr_debug("scatter FCS is unsupported\n");
1050				err = -EOPNOTSUPP;
1051				goto err;
1052			}
1053
1054			qp->flags |= MLX4_IB_QP_SCATTER_FCS;
1055		}
1056
1057		err = set_rq_size(dev, &init_attr->cap, udata,
1058				  qp_has_rq(init_attr), qp, qp->inl_recv_sz);
1059		if (err)
1060			goto err;
1061
1062		qp->sq_no_prefetch = ucmd.sq_no_prefetch;
1063
1064		err = set_user_sq_size(dev, qp, &ucmd);
1065		if (err)
1066			goto err;
1067
1068		qp->umem =
1069			ib_umem_get(pd->device, ucmd.buf_addr, qp->buf_size, 0);
1070		if (IS_ERR(qp->umem)) {
1071			err = PTR_ERR(qp->umem);
1072			goto err;
1073		}
1074
1075		shift = mlx4_ib_umem_calc_optimal_mtt_size(qp->umem, 0, &n);
1076		err = mlx4_mtt_init(dev->dev, n, shift, &qp->mtt);
1077
1078		if (err)
1079			goto err_buf;
1080
1081		err = mlx4_ib_umem_write_mtt(dev, &qp->mtt, qp->umem);
1082		if (err)
1083			goto err_mtt;
1084
1085		if (qp_has_rq(init_attr)) {
1086			err = mlx4_ib_db_map_user(udata, ucmd.db_addr, &qp->db);
1087			if (err)
1088				goto err_mtt;
1089		}
1090		qp->mqp.usage = MLX4_RES_USAGE_USER_VERBS;
1091	} else {
1092		err = set_rq_size(dev, &init_attr->cap, udata,
1093				  qp_has_rq(init_attr), qp, 0);
1094		if (err)
1095			goto err;
1096
1097		qp->sq_no_prefetch = 0;
1098
1099		if (init_attr->create_flags & IB_QP_CREATE_IPOIB_UD_LSO)
1100			qp->flags |= MLX4_IB_QP_LSO;
1101
1102		if (init_attr->create_flags & IB_QP_CREATE_NETIF_QP) {
1103			if (dev->steering_support ==
1104			    MLX4_STEERING_MODE_DEVICE_MANAGED)
1105				qp->flags |= MLX4_IB_QP_NETIF;
1106			else {
1107				err = -EINVAL;
1108				goto err;
1109			}
1110		}
1111
1112		err = set_kernel_sq_size(dev, &init_attr->cap, qp_type, qp);
1113		if (err)
1114			goto err;
1115
1116		if (qp_has_rq(init_attr)) {
1117			err = mlx4_db_alloc(dev->dev, &qp->db, 0);
1118			if (err)
1119				goto err;
1120
1121			*qp->db.db = 0;
1122		}
1123
1124		if (mlx4_buf_alloc(dev->dev, qp->buf_size,  PAGE_SIZE * 2,
1125				   &qp->buf)) {
1126			err = -ENOMEM;
1127			goto err_db;
1128		}
1129
1130		err = mlx4_mtt_init(dev->dev, qp->buf.npages, qp->buf.page_shift,
1131				    &qp->mtt);
1132		if (err)
1133			goto err_buf;
1134
1135		err = mlx4_buf_write_mtt(dev->dev, &qp->mtt, &qp->buf);
1136		if (err)
1137			goto err_mtt;
1138
1139		qp->sq.wrid = kvmalloc_array(qp->sq.wqe_cnt,
1140					     sizeof(u64), GFP_KERNEL);
1141		qp->rq.wrid = kvmalloc_array(qp->rq.wqe_cnt,
1142					     sizeof(u64), GFP_KERNEL);
1143		if (!qp->sq.wrid || !qp->rq.wrid) {
1144			err = -ENOMEM;
1145			goto err_wrid;
1146		}
1147		qp->mqp.usage = MLX4_RES_USAGE_DRIVER;
1148	}
1149
1150	if (sqpn) {
1151		if (qp->mlx4_ib_qp_type & (MLX4_IB_QPT_PROXY_SMI_OWNER |
1152		    MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI)) {
1153			if (alloc_proxy_bufs(pd->device, qp)) {
1154				err = -ENOMEM;
1155				goto err_wrid;
1156			}
1157		}
1158	} else {
1159		/* Raw packet QPNs may not have bits 6,7 set in their qp_num;
1160		 * otherwise, the WQE BlueFlame setup flow wrongly causes
1161		 * VLAN insertion. */
1162		if (init_attr->qp_type == IB_QPT_RAW_PACKET)
1163			err = mlx4_qp_reserve_range(dev->dev, 1, 1, &qpn,
1164						    (init_attr->cap.max_send_wr ?
1165						     MLX4_RESERVE_ETH_BF_QP : 0) |
1166						    (init_attr->cap.max_recv_wr ?
1167						     MLX4_RESERVE_A0_QP : 0),
1168						    qp->mqp.usage);
1169		else
1170			if (qp->flags & MLX4_IB_QP_NETIF)
1171				err = mlx4_ib_steer_qp_alloc(dev, 1, &qpn);
1172			else
1173				err = mlx4_qp_reserve_range(dev->dev, 1, 1,
1174							    &qpn, 0, qp->mqp.usage);
1175		if (err)
1176			goto err_proxy;
1177	}
1178
1179	if (init_attr->create_flags & IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK)
1180		qp->flags |= MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK;
1181
1182	err = mlx4_qp_alloc(dev->dev, qpn, &qp->mqp);
1183	if (err)
1184		goto err_qpn;
1185
1186	if (init_attr->qp_type == IB_QPT_XRC_TGT)
1187		qp->mqp.qpn |= (1 << 23);
1188
1189	/*
1190	 * Hardware wants QPN written in big-endian order (after
1191	 * shifting) for send doorbell.  Precompute this value to save
1192	 * a little bit when posting sends.
1193	 */
1194	qp->doorbell_qpn = swab32(qp->mqp.qpn << 8);
1195
1196	qp->mqp.event = mlx4_ib_qp_event;
1197
1198	spin_lock_irqsave(&dev->reset_flow_resource_lock, flags);
1199	mlx4_ib_lock_cqs(to_mcq(init_attr->send_cq),
1200			 to_mcq(init_attr->recv_cq));
1201	/* Maintain device to QPs access, needed for further handling
1202	 * via reset flow
1203	 */
1204	list_add_tail(&qp->qps_list, &dev->qp_list);
1205	/* Maintain CQ to QPs access, needed for further handling
1206	 * via reset flow
1207	 */
1208	mcq = to_mcq(init_attr->send_cq);
1209	list_add_tail(&qp->cq_send_list, &mcq->send_qp_list);
1210	mcq = to_mcq(init_attr->recv_cq);
1211	list_add_tail(&qp->cq_recv_list, &mcq->recv_qp_list);
1212	mlx4_ib_unlock_cqs(to_mcq(init_attr->send_cq),
1213			   to_mcq(init_attr->recv_cq));
1214	spin_unlock_irqrestore(&dev->reset_flow_resource_lock, flags);
1215	return 0;
1216
1217err_qpn:
1218	if (!sqpn) {
1219		if (qp->flags & MLX4_IB_QP_NETIF)
1220			mlx4_ib_steer_qp_free(dev, qpn, 1);
1221		else
1222			mlx4_qp_release_range(dev->dev, qpn, 1);
1223	}
1224err_proxy:
1225	if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_GSI)
1226		free_proxy_bufs(pd->device, qp);
1227err_wrid:
1228	if (udata) {
1229		if (qp_has_rq(init_attr))
1230			mlx4_ib_db_unmap_user(context, &qp->db);
1231	} else {
1232		kvfree(qp->sq.wrid);
1233		kvfree(qp->rq.wrid);
1234	}
1235
1236err_mtt:
1237	mlx4_mtt_cleanup(dev->dev, &qp->mtt);
1238
1239err_buf:
1240	if (!qp->umem)
1241		mlx4_buf_free(dev->dev, qp->buf_size, &qp->buf);
1242	ib_umem_release(qp->umem);
1243
1244err_db:
1245	if (!udata && qp_has_rq(init_attr))
1246		mlx4_db_free(dev->dev, &qp->db);
1247
1248err:
1249	kfree(qp->sqp);
1250	return err;
1251}
1252
1253static enum mlx4_qp_state to_mlx4_state(enum ib_qp_state state)
1254{
1255	switch (state) {
1256	case IB_QPS_RESET:	return MLX4_QP_STATE_RST;
1257	case IB_QPS_INIT:	return MLX4_QP_STATE_INIT;
1258	case IB_QPS_RTR:	return MLX4_QP_STATE_RTR;
1259	case IB_QPS_RTS:	return MLX4_QP_STATE_RTS;
1260	case IB_QPS_SQD:	return MLX4_QP_STATE_SQD;
1261	case IB_QPS_SQE:	return MLX4_QP_STATE_SQER;
1262	case IB_QPS_ERR:	return MLX4_QP_STATE_ERR;
1263	default:		return -1;
1264	}
1265}
1266
1267static void mlx4_ib_lock_cqs(struct mlx4_ib_cq *send_cq, struct mlx4_ib_cq *recv_cq)
1268	__acquires(&send_cq->lock) __acquires(&recv_cq->lock)
1269{
1270	if (send_cq == recv_cq) {
1271		spin_lock(&send_cq->lock);
1272		__acquire(&recv_cq->lock);
1273	} else if (send_cq->mcq.cqn < recv_cq->mcq.cqn) {
1274		spin_lock(&send_cq->lock);
1275		spin_lock_nested(&recv_cq->lock, SINGLE_DEPTH_NESTING);
1276	} else {
1277		spin_lock(&recv_cq->lock);
1278		spin_lock_nested(&send_cq->lock, SINGLE_DEPTH_NESTING);
1279	}
1280}
1281
1282static void mlx4_ib_unlock_cqs(struct mlx4_ib_cq *send_cq, struct mlx4_ib_cq *recv_cq)
1283	__releases(&send_cq->lock) __releases(&recv_cq->lock)
1284{
1285	if (send_cq == recv_cq) {
1286		__release(&recv_cq->lock);
1287		spin_unlock(&send_cq->lock);
1288	} else if (send_cq->mcq.cqn < recv_cq->mcq.cqn) {
1289		spin_unlock(&recv_cq->lock);
1290		spin_unlock(&send_cq->lock);
1291	} else {
1292		spin_unlock(&send_cq->lock);
1293		spin_unlock(&recv_cq->lock);
1294	}
1295}
1296
1297static void del_gid_entries(struct mlx4_ib_qp *qp)
1298{
1299	struct mlx4_ib_gid_entry *ge, *tmp;
1300
1301	list_for_each_entry_safe(ge, tmp, &qp->gid_list, list) {
1302		list_del(&ge->list);
1303		kfree(ge);
1304	}
1305}
1306
1307static struct mlx4_ib_pd *get_pd(struct mlx4_ib_qp *qp)
1308{
1309	if (qp->ibqp.qp_type == IB_QPT_XRC_TGT)
1310		return to_mpd(to_mxrcd(qp->ibqp.xrcd)->pd);
1311	else
1312		return to_mpd(qp->ibqp.pd);
1313}
1314
1315static void get_cqs(struct mlx4_ib_qp *qp, enum mlx4_ib_source_type src,
1316		    struct mlx4_ib_cq **send_cq, struct mlx4_ib_cq **recv_cq)
1317{
1318	switch (qp->ibqp.qp_type) {
1319	case IB_QPT_XRC_TGT:
1320		*send_cq = to_mcq(to_mxrcd(qp->ibqp.xrcd)->cq);
1321		*recv_cq = *send_cq;
1322		break;
1323	case IB_QPT_XRC_INI:
1324		*send_cq = to_mcq(qp->ibqp.send_cq);
1325		*recv_cq = *send_cq;
1326		break;
1327	default:
1328		*recv_cq = (src == MLX4_IB_QP_SRC) ? to_mcq(qp->ibqp.recv_cq) :
1329						     to_mcq(qp->ibwq.cq);
1330		*send_cq = (src == MLX4_IB_QP_SRC) ? to_mcq(qp->ibqp.send_cq) :
1331						     *recv_cq;
1332		break;
1333	}
1334}
1335
1336static void destroy_qp_rss(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
1337{
1338	if (qp->state != IB_QPS_RESET) {
1339		int i;
1340
1341		for (i = 0; i < (1 << qp->ibqp.rwq_ind_tbl->log_ind_tbl_size);
1342		     i++) {
1343			struct ib_wq *ibwq = qp->ibqp.rwq_ind_tbl->ind_tbl[i];
1344			struct mlx4_ib_qp *wq =	to_mqp((struct ib_qp *)ibwq);
1345
1346			mutex_lock(&wq->mutex);
1347
1348			wq->rss_usecnt--;
1349
1350			mutex_unlock(&wq->mutex);
1351		}
1352
1353		if (mlx4_qp_modify(dev->dev, NULL, to_mlx4_state(qp->state),
1354				   MLX4_QP_STATE_RST, NULL, 0, 0, &qp->mqp))
1355			pr_warn("modify QP %06x to RESET failed.\n",
1356				qp->mqp.qpn);
1357	}
1358
1359	mlx4_qp_remove(dev->dev, &qp->mqp);
1360	mlx4_qp_free(dev->dev, &qp->mqp);
1361	mlx4_qp_release_range(dev->dev, qp->mqp.qpn, 1);
1362	del_gid_entries(qp);
1363}
1364
1365static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
1366			      enum mlx4_ib_source_type src,
1367			      struct ib_udata *udata)
1368{
1369	struct mlx4_ib_cq *send_cq, *recv_cq;
1370	unsigned long flags;
1371
1372	if (qp->state != IB_QPS_RESET) {
1373		if (mlx4_qp_modify(dev->dev, NULL, to_mlx4_state(qp->state),
1374				   MLX4_QP_STATE_RST, NULL, 0, 0, &qp->mqp))
1375			pr_warn("modify QP %06x to RESET failed.\n",
1376			       qp->mqp.qpn);
1377		if (qp->pri.smac || (!qp->pri.smac && qp->pri.smac_port)) {
1378			mlx4_unregister_mac(dev->dev, qp->pri.smac_port, qp->pri.smac);
1379			qp->pri.smac = 0;
1380			qp->pri.smac_port = 0;
1381		}
1382		if (qp->alt.smac) {
1383			mlx4_unregister_mac(dev->dev, qp->alt.smac_port, qp->alt.smac);
1384			qp->alt.smac = 0;
1385		}
1386		if (qp->pri.vid < 0x1000) {
1387			mlx4_unregister_vlan(dev->dev, qp->pri.vlan_port, qp->pri.vid);
1388			qp->pri.vid = 0xFFFF;
1389			qp->pri.candidate_vid = 0xFFFF;
1390			qp->pri.update_vid = 0;
1391		}
1392		if (qp->alt.vid < 0x1000) {
1393			mlx4_unregister_vlan(dev->dev, qp->alt.vlan_port, qp->alt.vid);
1394			qp->alt.vid = 0xFFFF;
1395			qp->alt.candidate_vid = 0xFFFF;
1396			qp->alt.update_vid = 0;
1397		}
1398	}
1399
1400	get_cqs(qp, src, &send_cq, &recv_cq);
1401
1402	spin_lock_irqsave(&dev->reset_flow_resource_lock, flags);
1403	mlx4_ib_lock_cqs(send_cq, recv_cq);
1404
1405	/* del from lists under both locks above to protect reset flow paths */
1406	list_del(&qp->qps_list);
1407	list_del(&qp->cq_send_list);
1408	list_del(&qp->cq_recv_list);
1409	if (!udata) {
1410		__mlx4_ib_cq_clean(recv_cq, qp->mqp.qpn,
1411				 qp->ibqp.srq ? to_msrq(qp->ibqp.srq): NULL);
1412		if (send_cq != recv_cq)
1413			__mlx4_ib_cq_clean(send_cq, qp->mqp.qpn, NULL);
1414	}
1415
1416	mlx4_qp_remove(dev->dev, &qp->mqp);
1417
1418	mlx4_ib_unlock_cqs(send_cq, recv_cq);
1419	spin_unlock_irqrestore(&dev->reset_flow_resource_lock, flags);
1420
1421	mlx4_qp_free(dev->dev, &qp->mqp);
1422
1423	if (!is_sqp(dev, qp) && !is_tunnel_qp(dev, qp)) {
1424		if (qp->flags & MLX4_IB_QP_NETIF)
1425			mlx4_ib_steer_qp_free(dev, qp->mqp.qpn, 1);
1426		else if (src == MLX4_IB_RWQ_SRC)
1427			mlx4_ib_release_wqn(
1428				rdma_udata_to_drv_context(
1429					udata,
1430					struct mlx4_ib_ucontext,
1431					ibucontext),
1432				qp, 1);
1433		else
1434			mlx4_qp_release_range(dev->dev, qp->mqp.qpn, 1);
1435	}
1436
1437	mlx4_mtt_cleanup(dev->dev, &qp->mtt);
1438
1439	if (udata) {
1440		if (qp->rq.wqe_cnt) {
1441			struct mlx4_ib_ucontext *mcontext =
1442				rdma_udata_to_drv_context(
1443					udata,
1444					struct mlx4_ib_ucontext,
1445					ibucontext);
1446
1447			mlx4_ib_db_unmap_user(mcontext, &qp->db);
1448		}
1449	} else {
1450		kvfree(qp->sq.wrid);
1451		kvfree(qp->rq.wrid);
1452		if (qp->mlx4_ib_qp_type & (MLX4_IB_QPT_PROXY_SMI_OWNER |
1453		    MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI))
1454			free_proxy_bufs(&dev->ib_dev, qp);
1455		mlx4_buf_free(dev->dev, qp->buf_size, &qp->buf);
1456		if (qp->rq.wqe_cnt)
1457			mlx4_db_free(dev->dev, &qp->db);
1458	}
1459	ib_umem_release(qp->umem);
1460
1461	del_gid_entries(qp);
1462}
1463
1464static u32 get_sqp_num(struct mlx4_ib_dev *dev, struct ib_qp_init_attr *attr)
1465{
1466	/* Native or PPF */
1467	if (!mlx4_is_mfunc(dev->dev) ||
1468	    (mlx4_is_master(dev->dev) &&
1469	     attr->create_flags & MLX4_IB_SRIOV_SQP)) {
1470		return  dev->dev->phys_caps.base_sqpn +
1471			(attr->qp_type == IB_QPT_SMI ? 0 : 2) +
1472			attr->port_num - 1;
1473	}
1474	/* PF or VF -- creating proxies */
1475	if (attr->qp_type == IB_QPT_SMI)
1476		return dev->dev->caps.spec_qps[attr->port_num - 1].qp0_proxy;
1477	else
1478		return dev->dev->caps.spec_qps[attr->port_num - 1].qp1_proxy;
1479}
1480
1481static int _mlx4_ib_create_qp(struct ib_pd *pd, struct mlx4_ib_qp *qp,
1482			      struct ib_qp_init_attr *init_attr,
1483			      struct ib_udata *udata)
1484{
1485	int err;
1486	int sup_u_create_flags = MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK;
1487	u16 xrcdn = 0;
1488
1489	if (init_attr->rwq_ind_tbl)
1490		return _mlx4_ib_create_qp_rss(pd, qp, init_attr, udata);
1491
1492	/*
1493	 * We only support LSO, vendor flag1, and multicast loopback blocking,
1494	 * and only for kernel UD QPs.
1495	 */
1496	if (init_attr->create_flags & ~(MLX4_IB_QP_LSO |
1497					MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK |
1498					MLX4_IB_SRIOV_TUNNEL_QP |
1499					MLX4_IB_SRIOV_SQP |
1500					MLX4_IB_QP_NETIF |
1501					MLX4_IB_QP_CREATE_ROCE_V2_GSI))
1502		return -EINVAL;
1503
1504	if (init_attr->create_flags & IB_QP_CREATE_NETIF_QP) {
1505		if (init_attr->qp_type != IB_QPT_UD)
1506			return -EINVAL;
1507	}
1508
1509	if (init_attr->create_flags) {
1510		if (udata && init_attr->create_flags & ~(sup_u_create_flags))
1511			return -EINVAL;
1512
1513		if ((init_attr->create_flags & ~(MLX4_IB_SRIOV_SQP |
1514						 MLX4_IB_QP_CREATE_ROCE_V2_GSI  |
1515						 MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK) &&
1516		     init_attr->qp_type != IB_QPT_UD) ||
1517		    (init_attr->create_flags & MLX4_IB_SRIOV_SQP &&
1518		     init_attr->qp_type > IB_QPT_GSI) ||
1519		    (init_attr->create_flags & MLX4_IB_QP_CREATE_ROCE_V2_GSI &&
1520		     init_attr->qp_type != IB_QPT_GSI))
1521			return -EINVAL;
1522	}
1523
1524	switch (init_attr->qp_type) {
1525	case IB_QPT_XRC_TGT:
1526		pd = to_mxrcd(init_attr->xrcd)->pd;
1527		xrcdn = to_mxrcd(init_attr->xrcd)->xrcdn;
1528		init_attr->send_cq = to_mxrcd(init_attr->xrcd)->cq;
1529		fallthrough;
1530	case IB_QPT_XRC_INI:
1531		if (!(to_mdev(pd->device)->dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC))
1532			return -ENOSYS;
1533		init_attr->recv_cq = init_attr->send_cq;
1534		fallthrough;
1535	case IB_QPT_RC:
1536	case IB_QPT_UC:
1537	case IB_QPT_RAW_PACKET:
1538	case IB_QPT_UD:
1539		qp->pri.vid = 0xFFFF;
1540		qp->alt.vid = 0xFFFF;
1541		err = create_qp_common(pd, init_attr, udata, 0, qp);
1542		if (err)
1543			return err;
1544
1545		qp->ibqp.qp_num = qp->mqp.qpn;
1546		qp->xrcdn = xrcdn;
1547		break;
1548	case IB_QPT_SMI:
1549	case IB_QPT_GSI:
1550	{
1551		int sqpn;
1552
1553		if (init_attr->create_flags & MLX4_IB_QP_CREATE_ROCE_V2_GSI) {
1554			int res = mlx4_qp_reserve_range(to_mdev(pd->device)->dev,
1555							1, 1, &sqpn, 0,
1556							MLX4_RES_USAGE_DRIVER);
1557
1558			if (res)
1559				return res;
1560		} else {
1561			sqpn = get_sqp_num(to_mdev(pd->device), init_attr);
1562		}
1563
1564		qp->pri.vid = 0xFFFF;
1565		qp->alt.vid = 0xFFFF;
1566		err = create_qp_common(pd, init_attr, udata, sqpn, qp);
1567		if (err)
1568			return err;
1569
1570		qp->port	= init_attr->port_num;
1571		qp->ibqp.qp_num = init_attr->qp_type == IB_QPT_SMI ? 0 :
1572			init_attr->create_flags & MLX4_IB_QP_CREATE_ROCE_V2_GSI ? sqpn : 1;
1573		break;
1574	}
1575	default:
1576		/* Don't support raw QPs */
1577		return -EOPNOTSUPP;
1578	}
1579	return 0;
1580}
1581
1582struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
1583				struct ib_qp_init_attr *init_attr,
1584				struct ib_udata *udata) {
1585	struct ib_device *device = pd ? pd->device : init_attr->xrcd->device;
1586	struct mlx4_ib_dev *dev = to_mdev(device);
1587	struct mlx4_ib_qp *qp;
1588	int ret;
1589
1590	qp = kzalloc(sizeof(*qp), GFP_KERNEL);
1591	if (!qp)
1592		return ERR_PTR(-ENOMEM);
1593
1594	mutex_init(&qp->mutex);
1595	ret = _mlx4_ib_create_qp(pd, qp, init_attr, udata);
1596	if (ret) {
1597		kfree(qp);
1598		return ERR_PTR(ret);
1599	}
1600
1601	if (init_attr->qp_type == IB_QPT_GSI &&
1602	    !(init_attr->create_flags & MLX4_IB_QP_CREATE_ROCE_V2_GSI)) {
1603		struct mlx4_ib_sqp *sqp = qp->sqp;
1604		int is_eth = rdma_cap_eth_ah(&dev->ib_dev, init_attr->port_num);
1605
1606		if (is_eth &&
1607		    dev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ROCE_V1_V2) {
1608			init_attr->create_flags |= MLX4_IB_QP_CREATE_ROCE_V2_GSI;
1609			sqp->roce_v2_gsi = ib_create_qp(pd, init_attr);
1610
1611			if (IS_ERR(sqp->roce_v2_gsi)) {
1612				pr_err("Failed to create GSI QP for RoCEv2 (%ld)\n", PTR_ERR(sqp->roce_v2_gsi));
1613				sqp->roce_v2_gsi = NULL;
1614			} else {
1615				to_mqp(sqp->roce_v2_gsi)->flags |=
1616					MLX4_IB_ROCE_V2_GSI_QP;
1617			}
1618
1619			init_attr->create_flags &= ~MLX4_IB_QP_CREATE_ROCE_V2_GSI;
1620		}
1621	}
1622	return &qp->ibqp;
1623}
1624
1625static int _mlx4_ib_destroy_qp(struct ib_qp *qp, struct ib_udata *udata)
1626{
1627	struct mlx4_ib_dev *dev = to_mdev(qp->device);
1628	struct mlx4_ib_qp *mqp = to_mqp(qp);
1629
1630	if (is_qp0(dev, mqp))
1631		mlx4_CLOSE_PORT(dev->dev, mqp->port);
1632
1633	if (mqp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_GSI &&
1634	    dev->qp1_proxy[mqp->port - 1] == mqp) {
1635		mutex_lock(&dev->qp1_proxy_lock[mqp->port - 1]);
1636		dev->qp1_proxy[mqp->port - 1] = NULL;
1637		mutex_unlock(&dev->qp1_proxy_lock[mqp->port - 1]);
1638	}
1639
1640	if (mqp->counter_index)
1641		mlx4_ib_free_qp_counter(dev, mqp);
1642
1643	if (qp->rwq_ind_tbl) {
1644		destroy_qp_rss(dev, mqp);
1645	} else {
1646		destroy_qp_common(dev, mqp, MLX4_IB_QP_SRC, udata);
1647	}
1648
1649	kfree(mqp->sqp);
1650	kfree(mqp);
1651
1652	return 0;
1653}
1654
1655int mlx4_ib_destroy_qp(struct ib_qp *qp, struct ib_udata *udata)
1656{
1657	struct mlx4_ib_qp *mqp = to_mqp(qp);
1658
1659	if (mqp->mlx4_ib_qp_type == MLX4_IB_QPT_GSI) {
1660		struct mlx4_ib_sqp *sqp = mqp->sqp;
1661
1662		if (sqp->roce_v2_gsi)
1663			ib_destroy_qp(sqp->roce_v2_gsi);
1664	}
1665
1666	return _mlx4_ib_destroy_qp(qp, udata);
1667}
1668
1669static int to_mlx4_st(struct mlx4_ib_dev *dev, enum mlx4_ib_qp_type type)
1670{
1671	switch (type) {
1672	case MLX4_IB_QPT_RC:		return MLX4_QP_ST_RC;
1673	case MLX4_IB_QPT_UC:		return MLX4_QP_ST_UC;
1674	case MLX4_IB_QPT_UD:		return MLX4_QP_ST_UD;
1675	case MLX4_IB_QPT_XRC_INI:
1676	case MLX4_IB_QPT_XRC_TGT:	return MLX4_QP_ST_XRC;
1677	case MLX4_IB_QPT_SMI:
1678	case MLX4_IB_QPT_GSI:
1679	case MLX4_IB_QPT_RAW_PACKET:	return MLX4_QP_ST_MLX;
1680
1681	case MLX4_IB_QPT_PROXY_SMI_OWNER:
1682	case MLX4_IB_QPT_TUN_SMI_OWNER:	return (mlx4_is_mfunc(dev->dev) ?
1683						MLX4_QP_ST_MLX : -1);
1684	case MLX4_IB_QPT_PROXY_SMI:
1685	case MLX4_IB_QPT_TUN_SMI:
1686	case MLX4_IB_QPT_PROXY_GSI:
1687	case MLX4_IB_QPT_TUN_GSI:	return (mlx4_is_mfunc(dev->dev) ?
1688						MLX4_QP_ST_UD : -1);
1689	default:			return -1;
1690	}
1691}
1692
1693static __be32 to_mlx4_access_flags(struct mlx4_ib_qp *qp, const struct ib_qp_attr *attr,
1694				   int attr_mask)
1695{
1696	u8 dest_rd_atomic;
1697	u32 access_flags;
1698	u32 hw_access_flags = 0;
1699
1700	if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC)
1701		dest_rd_atomic = attr->max_dest_rd_atomic;
1702	else
1703		dest_rd_atomic = qp->resp_depth;
1704
1705	if (attr_mask & IB_QP_ACCESS_FLAGS)
1706		access_flags = attr->qp_access_flags;
1707	else
1708		access_flags = qp->atomic_rd_en;
1709
1710	if (!dest_rd_atomic)
1711		access_flags &= IB_ACCESS_REMOTE_WRITE;
1712
1713	if (access_flags & IB_ACCESS_REMOTE_READ)
1714		hw_access_flags |= MLX4_QP_BIT_RRE;
1715	if (access_flags & IB_ACCESS_REMOTE_ATOMIC)
1716		hw_access_flags |= MLX4_QP_BIT_RAE;
1717	if (access_flags & IB_ACCESS_REMOTE_WRITE)
1718		hw_access_flags |= MLX4_QP_BIT_RWE;
1719
1720	return cpu_to_be32(hw_access_flags);
1721}
1722
1723static void store_sqp_attrs(struct mlx4_ib_sqp *sqp, const struct ib_qp_attr *attr,
1724			    int attr_mask)
1725{
1726	if (attr_mask & IB_QP_PKEY_INDEX)
1727		sqp->pkey_index = attr->pkey_index;
1728	if (attr_mask & IB_QP_QKEY)
1729		sqp->qkey = attr->qkey;
1730	if (attr_mask & IB_QP_SQ_PSN)
1731		sqp->send_psn = attr->sq_psn;
1732}
1733
1734static void mlx4_set_sched(struct mlx4_qp_path *path, u8 port)
1735{
1736	path->sched_queue = (path->sched_queue & 0xbf) | ((port - 1) << 6);
1737}
1738
1739static int _mlx4_set_path(struct mlx4_ib_dev *dev,
1740			  const struct rdma_ah_attr *ah,
1741			  u64 smac, u16 vlan_tag, struct mlx4_qp_path *path,
1742			  struct mlx4_roce_smac_vlan_info *smac_info, u8 port)
1743{
1744	int vidx;
1745	int smac_index;
1746	int err;
1747
1748	path->grh_mylmc = rdma_ah_get_path_bits(ah) & 0x7f;
1749	path->rlid = cpu_to_be16(rdma_ah_get_dlid(ah));
1750	if (rdma_ah_get_static_rate(ah)) {
1751		path->static_rate = rdma_ah_get_static_rate(ah) +
1752				    MLX4_STAT_RATE_OFFSET;
1753		while (path->static_rate > IB_RATE_2_5_GBPS + MLX4_STAT_RATE_OFFSET &&
1754		       !(1 << path->static_rate & dev->dev->caps.stat_rate_support))
1755			--path->static_rate;
1756	} else
1757		path->static_rate = 0;
1758
1759	if (rdma_ah_get_ah_flags(ah) & IB_AH_GRH) {
1760		const struct ib_global_route *grh = rdma_ah_read_grh(ah);
1761		int real_sgid_index =
1762			mlx4_ib_gid_index_to_real_index(dev, grh->sgid_attr);
1763
1764		if (real_sgid_index < 0)
1765			return real_sgid_index;
1766		if (real_sgid_index >= dev->dev->caps.gid_table_len[port]) {
1767			pr_err("sgid_index (%u) too large. max is %d\n",
1768			       real_sgid_index, dev->dev->caps.gid_table_len[port] - 1);
1769			return -1;
1770		}
1771
1772		path->grh_mylmc |= 1 << 7;
1773		path->mgid_index = real_sgid_index;
1774		path->hop_limit  = grh->hop_limit;
1775		path->tclass_flowlabel =
1776			cpu_to_be32((grh->traffic_class << 20) |
1777				    (grh->flow_label));
1778		memcpy(path->rgid, grh->dgid.raw, 16);
1779	}
1780
1781	if (ah->type == RDMA_AH_ATTR_TYPE_ROCE) {
1782		if (!(rdma_ah_get_ah_flags(ah) & IB_AH_GRH))
1783			return -1;
1784
1785		path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE |
1786			((port - 1) << 6) | ((rdma_ah_get_sl(ah) & 7) << 3);
1787
1788		path->feup |= MLX4_FEUP_FORCE_ETH_UP;
1789		if (vlan_tag < 0x1000) {
1790			if (smac_info->vid < 0x1000) {
1791				/* both valid vlan ids */
1792				if (smac_info->vid != vlan_tag) {
1793					/* different VIDs.  unreg old and reg new */
1794					err = mlx4_register_vlan(dev->dev, port, vlan_tag, &vidx);
1795					if (err)
1796						return err;
1797					smac_info->candidate_vid = vlan_tag;
1798					smac_info->candidate_vlan_index = vidx;
1799					smac_info->candidate_vlan_port = port;
1800					smac_info->update_vid = 1;
1801					path->vlan_index = vidx;
1802				} else {
1803					path->vlan_index = smac_info->vlan_index;
1804				}
1805			} else {
1806				/* no current vlan tag in qp */
1807				err = mlx4_register_vlan(dev->dev, port, vlan_tag, &vidx);
1808				if (err)
1809					return err;
1810				smac_info->candidate_vid = vlan_tag;
1811				smac_info->candidate_vlan_index = vidx;
1812				smac_info->candidate_vlan_port = port;
1813				smac_info->update_vid = 1;
1814				path->vlan_index = vidx;
1815			}
1816			path->feup |= MLX4_FVL_FORCE_ETH_VLAN;
1817			path->fl = 1 << 6;
1818		} else {
1819			/* have current vlan tag. unregister it at modify-qp success */
1820			if (smac_info->vid < 0x1000) {
1821				smac_info->candidate_vid = 0xFFFF;
1822				smac_info->update_vid = 1;
1823			}
1824		}
1825
1826		/* get smac_index for RoCE use.
1827		 * If no smac was yet assigned, register one.
1828		 * If one was already assigned, but the new mac differs,
1829		 * unregister the old one and register the new one.
1830		*/
1831		if ((!smac_info->smac && !smac_info->smac_port) ||
1832		    smac_info->smac != smac) {
1833			/* register candidate now, unreg if needed, after success */
1834			smac_index = mlx4_register_mac(dev->dev, port, smac);
1835			if (smac_index >= 0) {
1836				smac_info->candidate_smac_index = smac_index;
1837				smac_info->candidate_smac = smac;
1838				smac_info->candidate_smac_port = port;
1839			} else {
1840				return -EINVAL;
1841			}
1842		} else {
1843			smac_index = smac_info->smac_index;
1844		}
1845		memcpy(path->dmac, ah->roce.dmac, 6);
1846		path->ackto = MLX4_IB_LINK_TYPE_ETH;
1847		/* put MAC table smac index for IBoE */
1848		path->grh_mylmc = (u8) (smac_index) | 0x80;
1849	} else {
1850		path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE |
1851			((port - 1) << 6) | ((rdma_ah_get_sl(ah) & 0xf) << 2);
1852	}
1853
1854	return 0;
1855}
1856
1857static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_qp_attr *qp,
1858			 enum ib_qp_attr_mask qp_attr_mask,
1859			 struct mlx4_ib_qp *mqp,
1860			 struct mlx4_qp_path *path, u8 port,
1861			 u16 vlan_id, u8 *smac)
1862{
1863	return _mlx4_set_path(dev, &qp->ah_attr,
1864			      mlx4_mac_to_u64(smac),
1865			      vlan_id,
1866			      path, &mqp->pri, port);
1867}
1868
1869static int mlx4_set_alt_path(struct mlx4_ib_dev *dev,
1870			     const struct ib_qp_attr *qp,
1871			     enum ib_qp_attr_mask qp_attr_mask,
1872			     struct mlx4_ib_qp *mqp,
1873			     struct mlx4_qp_path *path, u8 port)
1874{
1875	return _mlx4_set_path(dev, &qp->alt_ah_attr,
1876			      0,
1877			      0xffff,
1878			      path, &mqp->alt, port);
1879}
1880
1881static void update_mcg_macs(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
1882{
1883	struct mlx4_ib_gid_entry *ge, *tmp;
1884
1885	list_for_each_entry_safe(ge, tmp, &qp->gid_list, list) {
1886		if (!ge->added && mlx4_ib_add_mc(dev, qp, &ge->gid)) {
1887			ge->added = 1;
1888			ge->port = qp->port;
1889		}
1890	}
1891}
1892
1893static int handle_eth_ud_smac_index(struct mlx4_ib_dev *dev,
1894				    struct mlx4_ib_qp *qp,
1895				    struct mlx4_qp_context *context)
1896{
1897	u64 u64_mac;
1898	int smac_index;
1899
1900	u64_mac = atomic64_read(&dev->iboe.mac[qp->port - 1]);
1901
1902	context->pri_path.sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE | ((qp->port - 1) << 6);
1903	if (!qp->pri.smac && !qp->pri.smac_port) {
1904		smac_index = mlx4_register_mac(dev->dev, qp->port, u64_mac);
1905		if (smac_index >= 0) {
1906			qp->pri.candidate_smac_index = smac_index;
1907			qp->pri.candidate_smac = u64_mac;
1908			qp->pri.candidate_smac_port = qp->port;
1909			context->pri_path.grh_mylmc = 0x80 | (u8) smac_index;
1910		} else {
1911			return -ENOENT;
1912		}
1913	}
1914	return 0;
1915}
1916
1917static int create_qp_lb_counter(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
1918{
1919	struct counter_index *new_counter_index;
1920	int err;
1921	u32 tmp_idx;
1922
1923	if (rdma_port_get_link_layer(&dev->ib_dev, qp->port) !=
1924	    IB_LINK_LAYER_ETHERNET ||
1925	    !(qp->flags & MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK) ||
1926	    !(dev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_LB_SRC_CHK))
1927		return 0;
1928
1929	err = mlx4_counter_alloc(dev->dev, &tmp_idx, MLX4_RES_USAGE_DRIVER);
1930	if (err)
1931		return err;
1932
1933	new_counter_index = kmalloc(sizeof(*new_counter_index), GFP_KERNEL);
1934	if (!new_counter_index) {
1935		mlx4_counter_free(dev->dev, tmp_idx);
1936		return -ENOMEM;
1937	}
1938
1939	new_counter_index->index = tmp_idx;
1940	new_counter_index->allocated = 1;
1941	qp->counter_index = new_counter_index;
1942
1943	mutex_lock(&dev->counters_table[qp->port - 1].mutex);
1944	list_add_tail(&new_counter_index->list,
1945		      &dev->counters_table[qp->port - 1].counters_list);
1946	mutex_unlock(&dev->counters_table[qp->port - 1].mutex);
1947
1948	return 0;
1949}
1950
1951enum {
1952	MLX4_QPC_ROCE_MODE_1 = 0,
1953	MLX4_QPC_ROCE_MODE_2 = 2,
1954	MLX4_QPC_ROCE_MODE_UNDEFINED = 0xff
1955};
1956
1957static u8 gid_type_to_qpc(enum ib_gid_type gid_type)
1958{
1959	switch (gid_type) {
1960	case IB_GID_TYPE_ROCE:
1961		return MLX4_QPC_ROCE_MODE_1;
1962	case IB_GID_TYPE_ROCE_UDP_ENCAP:
1963		return MLX4_QPC_ROCE_MODE_2;
1964	default:
1965		return MLX4_QPC_ROCE_MODE_UNDEFINED;
1966	}
1967}
1968
1969/*
1970 * Go over all RSS QP's childes (WQs) and apply their HW state according to
1971 * their logic state if the RSS QP is the first RSS QP associated for the WQ.
1972 */
1973static int bringup_rss_rwqs(struct ib_rwq_ind_table *ind_tbl, u8 port_num,
1974			    struct ib_udata *udata)
1975{
1976	int err = 0;
1977	int i;
1978
1979	for (i = 0; i < (1 << ind_tbl->log_ind_tbl_size); i++) {
1980		struct ib_wq *ibwq = ind_tbl->ind_tbl[i];
1981		struct mlx4_ib_qp *wq = to_mqp((struct ib_qp *)ibwq);
1982
1983		mutex_lock(&wq->mutex);
1984
1985		/* Mlx4_ib restrictions:
1986		 * WQ's is associated to a port according to the RSS QP it is
1987		 * associates to.
1988		 * In case the WQ is associated to a different port by another
1989		 * RSS QP, return a failure.
1990		 */
1991		if ((wq->rss_usecnt > 0) && (wq->port != port_num)) {
1992			err = -EINVAL;
1993			mutex_unlock(&wq->mutex);
1994			break;
1995		}
1996		wq->port = port_num;
1997		if ((wq->rss_usecnt == 0) && (ibwq->state == IB_WQS_RDY)) {
1998			err = _mlx4_ib_modify_wq(ibwq, IB_WQS_RDY, udata);
1999			if (err) {
2000				mutex_unlock(&wq->mutex);
2001				break;
2002			}
2003		}
2004		wq->rss_usecnt++;
2005
2006		mutex_unlock(&wq->mutex);
2007	}
2008
2009	if (i && err) {
2010		int j;
2011
2012		for (j = (i - 1); j >= 0; j--) {
2013			struct ib_wq *ibwq = ind_tbl->ind_tbl[j];
2014			struct mlx4_ib_qp *wq = to_mqp((struct ib_qp *)ibwq);
2015
2016			mutex_lock(&wq->mutex);
2017
2018			if ((wq->rss_usecnt == 1) &&
2019			    (ibwq->state == IB_WQS_RDY))
2020				if (_mlx4_ib_modify_wq(ibwq, IB_WQS_RESET,
2021						       udata))
2022					pr_warn("failed to reverse WQN=0x%06x\n",
2023						ibwq->wq_num);
2024			wq->rss_usecnt--;
2025
2026			mutex_unlock(&wq->mutex);
2027		}
2028	}
2029
2030	return err;
2031}
2032
2033static void bring_down_rss_rwqs(struct ib_rwq_ind_table *ind_tbl,
2034				struct ib_udata *udata)
2035{
2036	int i;
2037
2038	for (i = 0; i < (1 << ind_tbl->log_ind_tbl_size); i++) {
2039		struct ib_wq *ibwq = ind_tbl->ind_tbl[i];
2040		struct mlx4_ib_qp *wq = to_mqp((struct ib_qp *)ibwq);
2041
2042		mutex_lock(&wq->mutex);
2043
2044		if ((wq->rss_usecnt == 1) && (ibwq->state == IB_WQS_RDY))
2045			if (_mlx4_ib_modify_wq(ibwq, IB_WQS_RESET, udata))
2046				pr_warn("failed to reverse WQN=%x\n",
2047					ibwq->wq_num);
2048		wq->rss_usecnt--;
2049
2050		mutex_unlock(&wq->mutex);
2051	}
2052}
2053
2054static void fill_qp_rss_context(struct mlx4_qp_context *context,
2055				struct mlx4_ib_qp *qp)
2056{
2057	struct mlx4_rss_context *rss_context;
2058
2059	rss_context = (void *)context + offsetof(struct mlx4_qp_context,
2060			pri_path) + MLX4_RSS_OFFSET_IN_QPC_PRI_PATH;
2061
2062	rss_context->base_qpn = cpu_to_be32(qp->rss_ctx->base_qpn_tbl_sz);
2063	rss_context->default_qpn =
2064		cpu_to_be32(qp->rss_ctx->base_qpn_tbl_sz & 0xffffff);
2065	if (qp->rss_ctx->flags & (MLX4_RSS_UDP_IPV4 | MLX4_RSS_UDP_IPV6))
2066		rss_context->base_qpn_udp = rss_context->default_qpn;
2067	rss_context->flags = qp->rss_ctx->flags;
2068	/* Currently support just toeplitz */
2069	rss_context->hash_fn = MLX4_RSS_HASH_TOP;
2070
2071	memcpy(rss_context->rss_key, qp->rss_ctx->rss_key,
2072	       MLX4_EN_RSS_KEY_SIZE);
2073}
2074
2075static int __mlx4_ib_modify_qp(void *src, enum mlx4_ib_source_type src_type,
2076			       const struct ib_qp_attr *attr, int attr_mask,
2077			       enum ib_qp_state cur_state,
2078			       enum ib_qp_state new_state,
2079			       struct ib_udata *udata)
2080{
2081	struct ib_srq  *ibsrq;
2082	const struct ib_gid_attr *gid_attr = NULL;
2083	struct ib_rwq_ind_table *rwq_ind_tbl;
2084	enum ib_qp_type qp_type;
2085	struct mlx4_ib_dev *dev;
2086	struct mlx4_ib_qp *qp;
2087	struct mlx4_ib_pd *pd;
2088	struct mlx4_ib_cq *send_cq, *recv_cq;
2089	struct mlx4_ib_ucontext *ucontext = rdma_udata_to_drv_context(
2090		udata, struct mlx4_ib_ucontext, ibucontext);
2091	struct mlx4_qp_context *context;
2092	enum mlx4_qp_optpar optpar = 0;
2093	int sqd_event;
2094	int steer_qp = 0;
2095	int err = -EINVAL;
2096	int counter_index;
2097
2098	if (src_type == MLX4_IB_RWQ_SRC) {
2099		struct ib_wq *ibwq;
2100
2101		ibwq	    = (struct ib_wq *)src;
2102		ibsrq	    = NULL;
2103		rwq_ind_tbl = NULL;
2104		qp_type     = IB_QPT_RAW_PACKET;
2105		qp	    = to_mqp((struct ib_qp *)ibwq);
2106		dev	    = to_mdev(ibwq->device);
2107		pd	    = to_mpd(ibwq->pd);
2108	} else {
2109		struct ib_qp *ibqp;
2110
2111		ibqp	    = (struct ib_qp *)src;
2112		ibsrq	    = ibqp->srq;
2113		rwq_ind_tbl = ibqp->rwq_ind_tbl;
2114		qp_type     = ibqp->qp_type;
2115		qp	    = to_mqp(ibqp);
2116		dev	    = to_mdev(ibqp->device);
2117		pd	    = get_pd(qp);
2118	}
2119
2120	/* APM is not supported under RoCE */
2121	if (attr_mask & IB_QP_ALT_PATH &&
2122	    rdma_port_get_link_layer(&dev->ib_dev, qp->port) ==
2123	    IB_LINK_LAYER_ETHERNET)
2124		return -ENOTSUPP;
2125
2126	context = kzalloc(sizeof *context, GFP_KERNEL);
2127	if (!context)
2128		return -ENOMEM;
2129
2130	context->flags = cpu_to_be32((to_mlx4_state(new_state) << 28) |
2131				     (to_mlx4_st(dev, qp->mlx4_ib_qp_type) << 16));
2132
2133	if (!(attr_mask & IB_QP_PATH_MIG_STATE))
2134		context->flags |= cpu_to_be32(MLX4_QP_PM_MIGRATED << 11);
2135	else {
2136		optpar |= MLX4_QP_OPTPAR_PM_STATE;
2137		switch (attr->path_mig_state) {
2138		case IB_MIG_MIGRATED:
2139			context->flags |= cpu_to_be32(MLX4_QP_PM_MIGRATED << 11);
2140			break;
2141		case IB_MIG_REARM:
2142			context->flags |= cpu_to_be32(MLX4_QP_PM_REARM << 11);
2143			break;
2144		case IB_MIG_ARMED:
2145			context->flags |= cpu_to_be32(MLX4_QP_PM_ARMED << 11);
2146			break;
2147		}
2148	}
2149
2150	if (qp->inl_recv_sz)
2151		context->param3 |= cpu_to_be32(1 << 25);
2152
2153	if (qp->flags & MLX4_IB_QP_SCATTER_FCS)
2154		context->param3 |= cpu_to_be32(1 << 29);
2155
2156	if (qp_type == IB_QPT_GSI || qp_type == IB_QPT_SMI)
2157		context->mtu_msgmax = (IB_MTU_4096 << 5) | 11;
2158	else if (qp_type == IB_QPT_RAW_PACKET)
2159		context->mtu_msgmax = (MLX4_RAW_QP_MTU << 5) | MLX4_RAW_QP_MSGMAX;
2160	else if (qp_type == IB_QPT_UD) {
2161		if (qp->flags & MLX4_IB_QP_LSO)
2162			context->mtu_msgmax = (IB_MTU_4096 << 5) |
2163					      ilog2(dev->dev->caps.max_gso_sz);
2164		else
2165			context->mtu_msgmax = (IB_MTU_4096 << 5) | 13;
2166	} else if (attr_mask & IB_QP_PATH_MTU) {
2167		if (attr->path_mtu < IB_MTU_256 || attr->path_mtu > IB_MTU_4096) {
2168			pr_err("path MTU (%u) is invalid\n",
2169			       attr->path_mtu);
2170			goto out;
2171		}
2172		context->mtu_msgmax = (attr->path_mtu << 5) |
2173			ilog2(dev->dev->caps.max_msg_sz);
2174	}
2175
2176	if (!rwq_ind_tbl) { /* PRM RSS receive side should be left zeros */
2177		if (qp->rq.wqe_cnt)
2178			context->rq_size_stride = ilog2(qp->rq.wqe_cnt) << 3;
2179		context->rq_size_stride |= qp->rq.wqe_shift - 4;
2180	}
2181
2182	if (qp->sq.wqe_cnt)
2183		context->sq_size_stride = ilog2(qp->sq.wqe_cnt) << 3;
2184	context->sq_size_stride |= qp->sq.wqe_shift - 4;
2185
2186	if (new_state == IB_QPS_RESET && qp->counter_index)
2187		mlx4_ib_free_qp_counter(dev, qp);
2188
2189	if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) {
2190		context->sq_size_stride |= !!qp->sq_no_prefetch << 7;
2191		context->xrcd = cpu_to_be32((u32) qp->xrcdn);
2192		if (qp_type == IB_QPT_RAW_PACKET)
2193			context->param3 |= cpu_to_be32(1 << 30);
2194	}
2195
2196	if (ucontext)
2197		context->usr_page = cpu_to_be32(
2198			mlx4_to_hw_uar_index(dev->dev, ucontext->uar.index));
2199	else
2200		context->usr_page = cpu_to_be32(
2201			mlx4_to_hw_uar_index(dev->dev, dev->priv_uar.index));
2202
2203	if (attr_mask & IB_QP_DEST_QPN)
2204		context->remote_qpn = cpu_to_be32(attr->dest_qp_num);
2205
2206	if (attr_mask & IB_QP_PORT) {
2207		if (cur_state == IB_QPS_SQD && new_state == IB_QPS_SQD &&
2208		    !(attr_mask & IB_QP_AV)) {
2209			mlx4_set_sched(&context->pri_path, attr->port_num);
2210			optpar |= MLX4_QP_OPTPAR_SCHED_QUEUE;
2211		}
2212	}
2213
2214	if (cur_state == IB_QPS_INIT && new_state == IB_QPS_RTR) {
2215		err = create_qp_lb_counter(dev, qp);
2216		if (err)
2217			goto out;
2218
2219		counter_index =
2220			dev->counters_table[qp->port - 1].default_counter;
2221		if (qp->counter_index)
2222			counter_index = qp->counter_index->index;
2223
2224		if (counter_index != -1) {
2225			context->pri_path.counter_index = counter_index;
2226			optpar |= MLX4_QP_OPTPAR_COUNTER_INDEX;
2227			if (qp->counter_index) {
2228				context->pri_path.fl |=
2229					MLX4_FL_ETH_SRC_CHECK_MC_LB;
2230				context->pri_path.vlan_control |=
2231					MLX4_CTRL_ETH_SRC_CHECK_IF_COUNTER;
2232			}
2233		} else
2234			context->pri_path.counter_index =
2235				MLX4_SINK_COUNTER_INDEX(dev->dev);
2236
2237		if (qp->flags & MLX4_IB_QP_NETIF) {
2238			mlx4_ib_steer_qp_reg(dev, qp, 1);
2239			steer_qp = 1;
2240		}
2241
2242		if (qp_type == IB_QPT_GSI) {
2243			enum ib_gid_type gid_type = qp->flags & MLX4_IB_ROCE_V2_GSI_QP ?
2244				IB_GID_TYPE_ROCE_UDP_ENCAP : IB_GID_TYPE_ROCE;
2245			u8 qpc_roce_mode = gid_type_to_qpc(gid_type);
2246
2247			context->rlkey_roce_mode |= (qpc_roce_mode << 6);
2248		}
2249	}
2250
2251	if (attr_mask & IB_QP_PKEY_INDEX) {
2252		if (qp->mlx4_ib_qp_type & MLX4_IB_QPT_ANY_SRIOV)
2253			context->pri_path.disable_pkey_check = 0x40;
2254		context->pri_path.pkey_index = attr->pkey_index;
2255		optpar |= MLX4_QP_OPTPAR_PKEY_INDEX;
2256	}
2257
2258	if (attr_mask & IB_QP_AV) {
2259		u8 port_num = mlx4_is_bonded(dev->dev) ? 1 :
2260			attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
2261		u16 vlan = 0xffff;
2262		u8 smac[ETH_ALEN];
2263		int is_eth =
2264			rdma_cap_eth_ah(&dev->ib_dev, port_num) &&
2265			rdma_ah_get_ah_flags(&attr->ah_attr) & IB_AH_GRH;
2266
2267		if (is_eth) {
2268			gid_attr = attr->ah_attr.grh.sgid_attr;
2269			err = rdma_read_gid_l2_fields(gid_attr, &vlan,
2270						      &smac[0]);
2271			if (err)
2272				goto out;
2273		}
2274
2275		if (mlx4_set_path(dev, attr, attr_mask, qp, &context->pri_path,
2276				  port_num, vlan, smac))
2277			goto out;
2278
2279		optpar |= (MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH |
2280			   MLX4_QP_OPTPAR_SCHED_QUEUE);
2281
2282		if (is_eth &&
2283		    (cur_state == IB_QPS_INIT && new_state == IB_QPS_RTR)) {
2284			u8 qpc_roce_mode = gid_type_to_qpc(gid_attr->gid_type);
2285
2286			if (qpc_roce_mode == MLX4_QPC_ROCE_MODE_UNDEFINED) {
2287				err = -EINVAL;
2288				goto out;
2289			}
2290			context->rlkey_roce_mode |= (qpc_roce_mode << 6);
2291		}
2292
2293	}
2294
2295	if (attr_mask & IB_QP_TIMEOUT) {
2296		context->pri_path.ackto |= attr->timeout << 3;
2297		optpar |= MLX4_QP_OPTPAR_ACK_TIMEOUT;
2298	}
2299
2300	if (attr_mask & IB_QP_ALT_PATH) {
2301		if (attr->alt_port_num == 0 ||
2302		    attr->alt_port_num > dev->dev->caps.num_ports)
2303			goto out;
2304
2305		if (attr->alt_pkey_index >=
2306		    dev->dev->caps.pkey_table_len[attr->alt_port_num])
2307			goto out;
2308
2309		if (mlx4_set_alt_path(dev, attr, attr_mask, qp,
2310				      &context->alt_path,
2311				      attr->alt_port_num))
2312			goto out;
2313
2314		context->alt_path.pkey_index = attr->alt_pkey_index;
2315		context->alt_path.ackto = attr->alt_timeout << 3;
2316		optpar |= MLX4_QP_OPTPAR_ALT_ADDR_PATH;
2317	}
2318
2319	context->pd = cpu_to_be32(pd->pdn);
2320
2321	if (!rwq_ind_tbl) {
2322		context->params1 = cpu_to_be32(MLX4_IB_ACK_REQ_FREQ << 28);
2323		get_cqs(qp, src_type, &send_cq, &recv_cq);
2324	} else { /* Set dummy CQs to be compatible with HV and PRM */
2325		send_cq = to_mcq(rwq_ind_tbl->ind_tbl[0]->cq);
2326		recv_cq = send_cq;
2327	}
2328	context->cqn_send = cpu_to_be32(send_cq->mcq.cqn);
2329	context->cqn_recv = cpu_to_be32(recv_cq->mcq.cqn);
2330
2331	/* Set "fast registration enabled" for all kernel QPs */
2332	if (!ucontext)
2333		context->params1 |= cpu_to_be32(1 << 11);
2334
2335	if (attr_mask & IB_QP_RNR_RETRY) {
2336		context->params1 |= cpu_to_be32(attr->rnr_retry << 13);
2337		optpar |= MLX4_QP_OPTPAR_RNR_RETRY;
2338	}
2339
2340	if (attr_mask & IB_QP_RETRY_CNT) {
2341		context->params1 |= cpu_to_be32(attr->retry_cnt << 16);
2342		optpar |= MLX4_QP_OPTPAR_RETRY_COUNT;
2343	}
2344
2345	if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC) {
2346		if (attr->max_rd_atomic)
2347			context->params1 |=
2348				cpu_to_be32(fls(attr->max_rd_atomic - 1) << 21);
2349		optpar |= MLX4_QP_OPTPAR_SRA_MAX;
2350	}
2351
2352	if (attr_mask & IB_QP_SQ_PSN)
2353		context->next_send_psn = cpu_to_be32(attr->sq_psn);
2354
2355	if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC) {
2356		if (attr->max_dest_rd_atomic)
2357			context->params2 |=
2358				cpu_to_be32(fls(attr->max_dest_rd_atomic - 1) << 21);
2359		optpar |= MLX4_QP_OPTPAR_RRA_MAX;
2360	}
2361
2362	if (attr_mask & (IB_QP_ACCESS_FLAGS | IB_QP_MAX_DEST_RD_ATOMIC)) {
2363		context->params2 |= to_mlx4_access_flags(qp, attr, attr_mask);
2364		optpar |= MLX4_QP_OPTPAR_RWE | MLX4_QP_OPTPAR_RRE | MLX4_QP_OPTPAR_RAE;
2365	}
2366
2367	if (ibsrq)
2368		context->params2 |= cpu_to_be32(MLX4_QP_BIT_RIC);
2369
2370	if (attr_mask & IB_QP_MIN_RNR_TIMER) {
2371		context->rnr_nextrecvpsn |= cpu_to_be32(attr->min_rnr_timer << 24);
2372		optpar |= MLX4_QP_OPTPAR_RNR_TIMEOUT;
2373	}
2374	if (attr_mask & IB_QP_RQ_PSN)
2375		context->rnr_nextrecvpsn |= cpu_to_be32(attr->rq_psn);
2376
2377	/* proxy and tunnel qp qkeys will be changed in modify-qp wrappers */
2378	if (attr_mask & IB_QP_QKEY) {
2379		if (qp->mlx4_ib_qp_type &
2380		    (MLX4_IB_QPT_PROXY_SMI_OWNER | MLX4_IB_QPT_TUN_SMI_OWNER))
2381			context->qkey = cpu_to_be32(IB_QP_SET_QKEY);
2382		else {
2383			if (mlx4_is_mfunc(dev->dev) &&
2384			    !(qp->mlx4_ib_qp_type & MLX4_IB_QPT_ANY_SRIOV) &&
2385			    (attr->qkey & MLX4_RESERVED_QKEY_MASK) ==
2386			    MLX4_RESERVED_QKEY_BASE) {
2387				pr_err("Cannot use reserved QKEY"
2388				       " 0x%x (range 0xffff0000..0xffffffff"
2389				       " is reserved)\n", attr->qkey);
2390				err = -EINVAL;
2391				goto out;
2392			}
2393			context->qkey = cpu_to_be32(attr->qkey);
2394		}
2395		optpar |= MLX4_QP_OPTPAR_Q_KEY;
2396	}
2397
2398	if (ibsrq)
2399		context->srqn = cpu_to_be32(1 << 24 |
2400					    to_msrq(ibsrq)->msrq.srqn);
2401
2402	if (qp->rq.wqe_cnt &&
2403	    cur_state == IB_QPS_RESET &&
2404	    new_state == IB_QPS_INIT)
2405		context->db_rec_addr = cpu_to_be64(qp->db.dma);
2406
2407	if (cur_state == IB_QPS_INIT &&
2408	    new_state == IB_QPS_RTR  &&
2409	    (qp_type == IB_QPT_GSI || qp_type == IB_QPT_SMI ||
2410	     qp_type == IB_QPT_UD || qp_type == IB_QPT_RAW_PACKET)) {
2411		context->pri_path.sched_queue = (qp->port - 1) << 6;
2412		if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_SMI ||
2413		    qp->mlx4_ib_qp_type &
2414		    (MLX4_IB_QPT_PROXY_SMI_OWNER | MLX4_IB_QPT_TUN_SMI_OWNER)) {
2415			context->pri_path.sched_queue |= MLX4_IB_DEFAULT_QP0_SCHED_QUEUE;
2416			if (qp->mlx4_ib_qp_type != MLX4_IB_QPT_SMI)
2417				context->pri_path.fl = 0x80;
2418		} else {
2419			if (qp->mlx4_ib_qp_type & MLX4_IB_QPT_ANY_SRIOV)
2420				context->pri_path.fl = 0x80;
2421			context->pri_path.sched_queue |= MLX4_IB_DEFAULT_SCHED_QUEUE;
2422		}
2423		if (rdma_port_get_link_layer(&dev->ib_dev, qp->port) ==
2424		    IB_LINK_LAYER_ETHERNET) {
2425			if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_TUN_GSI ||
2426			    qp->mlx4_ib_qp_type == MLX4_IB_QPT_GSI)
2427				context->pri_path.feup = 1 << 7; /* don't fsm */
2428			/* handle smac_index */
2429			if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_UD ||
2430			    qp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_GSI ||
2431			    qp->mlx4_ib_qp_type == MLX4_IB_QPT_TUN_GSI) {
2432				err = handle_eth_ud_smac_index(dev, qp, context);
2433				if (err) {
2434					err = -EINVAL;
2435					goto out;
2436				}
2437				if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_GSI)
2438					dev->qp1_proxy[qp->port - 1] = qp;
2439			}
2440		}
2441	}
2442
2443	if (qp_type == IB_QPT_RAW_PACKET) {
2444		context->pri_path.ackto = (context->pri_path.ackto & 0xf8) |
2445					MLX4_IB_LINK_TYPE_ETH;
2446		if (dev->dev->caps.tunnel_offload_mode ==  MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) {
2447			/* set QP to receive both tunneled & non-tunneled packets */
2448			if (!rwq_ind_tbl)
2449				context->srqn = cpu_to_be32(7 << 28);
2450		}
2451	}
2452
2453	if (qp_type == IB_QPT_UD && (new_state == IB_QPS_RTR)) {
2454		int is_eth = rdma_port_get_link_layer(
2455				&dev->ib_dev, qp->port) ==
2456				IB_LINK_LAYER_ETHERNET;
2457		if (is_eth) {
2458			context->pri_path.ackto = MLX4_IB_LINK_TYPE_ETH;
2459			optpar |= MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH;
2460		}
2461	}
2462
2463	if (cur_state == IB_QPS_RTS && new_state == IB_QPS_SQD	&&
2464	    attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY && attr->en_sqd_async_notify)
2465		sqd_event = 1;
2466	else
2467		sqd_event = 0;
2468
2469	if (!ucontext &&
2470	    cur_state == IB_QPS_RESET &&
2471	    new_state == IB_QPS_INIT)
2472		context->rlkey_roce_mode |= (1 << 4);
2473
2474	/*
2475	 * Before passing a kernel QP to the HW, make sure that the
2476	 * ownership bits of the send queue are set and the SQ
2477	 * headroom is stamped so that the hardware doesn't start
2478	 * processing stale work requests.
2479	 */
2480	if (!ucontext &&
2481	    cur_state == IB_QPS_RESET &&
2482	    new_state == IB_QPS_INIT) {
2483		struct mlx4_wqe_ctrl_seg *ctrl;
2484		int i;
2485
2486		for (i = 0; i < qp->sq.wqe_cnt; ++i) {
2487			ctrl = get_send_wqe(qp, i);
2488			ctrl->owner_opcode = cpu_to_be32(1 << 31);
2489			ctrl->qpn_vlan.fence_size =
2490				1 << (qp->sq.wqe_shift - 4);
2491			stamp_send_wqe(qp, i);
2492		}
2493	}
2494
2495	if (rwq_ind_tbl	&&
2496	    cur_state == IB_QPS_RESET &&
2497	    new_state == IB_QPS_INIT) {
2498		fill_qp_rss_context(context, qp);
2499		context->flags |= cpu_to_be32(1 << MLX4_RSS_QPC_FLAG_OFFSET);
2500	}
2501
2502	err = mlx4_qp_modify(dev->dev, &qp->mtt, to_mlx4_state(cur_state),
2503			     to_mlx4_state(new_state), context, optpar,
2504			     sqd_event, &qp->mqp);
2505	if (err)
2506		goto out;
2507
2508	qp->state = new_state;
2509
2510	if (attr_mask & IB_QP_ACCESS_FLAGS)
2511		qp->atomic_rd_en = attr->qp_access_flags;
2512	if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC)
2513		qp->resp_depth = attr->max_dest_rd_atomic;
2514	if (attr_mask & IB_QP_PORT) {
2515		qp->port = attr->port_num;
2516		update_mcg_macs(dev, qp);
2517	}
2518	if (attr_mask & IB_QP_ALT_PATH)
2519		qp->alt_port = attr->alt_port_num;
2520
2521	if (is_sqp(dev, qp))
2522		store_sqp_attrs(qp->sqp, attr, attr_mask);
2523
2524	/*
2525	 * If we moved QP0 to RTR, bring the IB link up; if we moved
2526	 * QP0 to RESET or ERROR, bring the link back down.
2527	 */
2528	if (is_qp0(dev, qp)) {
2529		if (cur_state != IB_QPS_RTR && new_state == IB_QPS_RTR)
2530			if (mlx4_INIT_PORT(dev->dev, qp->port))
2531				pr_warn("INIT_PORT failed for port %d\n",
2532				       qp->port);
2533
2534		if (cur_state != IB_QPS_RESET && cur_state != IB_QPS_ERR &&
2535		    (new_state == IB_QPS_RESET || new_state == IB_QPS_ERR))
2536			mlx4_CLOSE_PORT(dev->dev, qp->port);
2537	}
2538
2539	/*
2540	 * If we moved a kernel QP to RESET, clean up all old CQ
2541	 * entries and reinitialize the QP.
2542	 */
2543	if (new_state == IB_QPS_RESET) {
2544		if (!ucontext) {
2545			mlx4_ib_cq_clean(recv_cq, qp->mqp.qpn,
2546					 ibsrq ? to_msrq(ibsrq) : NULL);
2547			if (send_cq != recv_cq)
2548				mlx4_ib_cq_clean(send_cq, qp->mqp.qpn, NULL);
2549
2550			qp->rq.head = 0;
2551			qp->rq.tail = 0;
2552			qp->sq.head = 0;
2553			qp->sq.tail = 0;
2554			qp->sq_next_wqe = 0;
2555			if (qp->rq.wqe_cnt)
2556				*qp->db.db  = 0;
2557
2558			if (qp->flags & MLX4_IB_QP_NETIF)
2559				mlx4_ib_steer_qp_reg(dev, qp, 0);
2560		}
2561		if (qp->pri.smac || (!qp->pri.smac && qp->pri.smac_port)) {
2562			mlx4_unregister_mac(dev->dev, qp->pri.smac_port, qp->pri.smac);
2563			qp->pri.smac = 0;
2564			qp->pri.smac_port = 0;
2565		}
2566		if (qp->alt.smac) {
2567			mlx4_unregister_mac(dev->dev, qp->alt.smac_port, qp->alt.smac);
2568			qp->alt.smac = 0;
2569		}
2570		if (qp->pri.vid < 0x1000) {
2571			mlx4_unregister_vlan(dev->dev, qp->pri.vlan_port, qp->pri.vid);
2572			qp->pri.vid = 0xFFFF;
2573			qp->pri.candidate_vid = 0xFFFF;
2574			qp->pri.update_vid = 0;
2575		}
2576
2577		if (qp->alt.vid < 0x1000) {
2578			mlx4_unregister_vlan(dev->dev, qp->alt.vlan_port, qp->alt.vid);
2579			qp->alt.vid = 0xFFFF;
2580			qp->alt.candidate_vid = 0xFFFF;
2581			qp->alt.update_vid = 0;
2582		}
2583	}
2584out:
2585	if (err && qp->counter_index)
2586		mlx4_ib_free_qp_counter(dev, qp);
2587	if (err && steer_qp)
2588		mlx4_ib_steer_qp_reg(dev, qp, 0);
2589	kfree(context);
2590	if (qp->pri.candidate_smac ||
2591	    (!qp->pri.candidate_smac && qp->pri.candidate_smac_port)) {
2592		if (err) {
2593			mlx4_unregister_mac(dev->dev, qp->pri.candidate_smac_port, qp->pri.candidate_smac);
2594		} else {
2595			if (qp->pri.smac || (!qp->pri.smac && qp->pri.smac_port))
2596				mlx4_unregister_mac(dev->dev, qp->pri.smac_port, qp->pri.smac);
2597			qp->pri.smac = qp->pri.candidate_smac;
2598			qp->pri.smac_index = qp->pri.candidate_smac_index;
2599			qp->pri.smac_port = qp->pri.candidate_smac_port;
2600		}
2601		qp->pri.candidate_smac = 0;
2602		qp->pri.candidate_smac_index = 0;
2603		qp->pri.candidate_smac_port = 0;
2604	}
2605	if (qp->alt.candidate_smac) {
2606		if (err) {
2607			mlx4_unregister_mac(dev->dev, qp->alt.candidate_smac_port, qp->alt.candidate_smac);
2608		} else {
2609			if (qp->alt.smac)
2610				mlx4_unregister_mac(dev->dev, qp->alt.smac_port, qp->alt.smac);
2611			qp->alt.smac = qp->alt.candidate_smac;
2612			qp->alt.smac_index = qp->alt.candidate_smac_index;
2613			qp->alt.smac_port = qp->alt.candidate_smac_port;
2614		}
2615		qp->alt.candidate_smac = 0;
2616		qp->alt.candidate_smac_index = 0;
2617		qp->alt.candidate_smac_port = 0;
2618	}
2619
2620	if (qp->pri.update_vid) {
2621		if (err) {
2622			if (qp->pri.candidate_vid < 0x1000)
2623				mlx4_unregister_vlan(dev->dev, qp->pri.candidate_vlan_port,
2624						     qp->pri.candidate_vid);
2625		} else {
2626			if (qp->pri.vid < 0x1000)
2627				mlx4_unregister_vlan(dev->dev, qp->pri.vlan_port,
2628						     qp->pri.vid);
2629			qp->pri.vid = qp->pri.candidate_vid;
2630			qp->pri.vlan_port = qp->pri.candidate_vlan_port;
2631			qp->pri.vlan_index =  qp->pri.candidate_vlan_index;
2632		}
2633		qp->pri.candidate_vid = 0xFFFF;
2634		qp->pri.update_vid = 0;
2635	}
2636
2637	if (qp->alt.update_vid) {
2638		if (err) {
2639			if (qp->alt.candidate_vid < 0x1000)
2640				mlx4_unregister_vlan(dev->dev, qp->alt.candidate_vlan_port,
2641						     qp->alt.candidate_vid);
2642		} else {
2643			if (qp->alt.vid < 0x1000)
2644				mlx4_unregister_vlan(dev->dev, qp->alt.vlan_port,
2645						     qp->alt.vid);
2646			qp->alt.vid = qp->alt.candidate_vid;
2647			qp->alt.vlan_port = qp->alt.candidate_vlan_port;
2648			qp->alt.vlan_index =  qp->alt.candidate_vlan_index;
2649		}
2650		qp->alt.candidate_vid = 0xFFFF;
2651		qp->alt.update_vid = 0;
2652	}
2653
2654	return err;
2655}
2656
2657enum {
2658	MLX4_IB_MODIFY_QP_RSS_SUP_ATTR_MSK = (IB_QP_STATE	|
2659					      IB_QP_PORT),
2660};
2661
2662static int _mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
2663			      int attr_mask, struct ib_udata *udata)
2664{
2665	struct mlx4_ib_dev *dev = to_mdev(ibqp->device);
2666	struct mlx4_ib_qp *qp = to_mqp(ibqp);
2667	enum ib_qp_state cur_state, new_state;
2668	int err = -EINVAL;
2669	mutex_lock(&qp->mutex);
2670
2671	cur_state = attr_mask & IB_QP_CUR_STATE ? attr->cur_qp_state : qp->state;
2672	new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
2673
2674	if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type,
2675				attr_mask)) {
2676		pr_debug("qpn 0x%x: invalid attribute mask specified "
2677			 "for transition %d to %d. qp_type %d,"
2678			 " attr_mask 0x%x\n",
2679			 ibqp->qp_num, cur_state, new_state,
2680			 ibqp->qp_type, attr_mask);
2681		goto out;
2682	}
2683
2684	if (ibqp->rwq_ind_tbl) {
2685		if (!(((cur_state == IB_QPS_RESET) &&
2686		       (new_state == IB_QPS_INIT)) ||
2687		      ((cur_state == IB_QPS_INIT)  &&
2688		       (new_state == IB_QPS_RTR)))) {
2689			pr_debug("qpn 0x%x: RSS QP unsupported transition %d to %d\n",
2690				 ibqp->qp_num, cur_state, new_state);
2691
2692			err = -EOPNOTSUPP;
2693			goto out;
2694		}
2695
2696		if (attr_mask & ~MLX4_IB_MODIFY_QP_RSS_SUP_ATTR_MSK) {
2697			pr_debug("qpn 0x%x: RSS QP unsupported attribute mask 0x%x for transition %d to %d\n",
2698				 ibqp->qp_num, attr_mask, cur_state, new_state);
2699
2700			err = -EOPNOTSUPP;
2701			goto out;
2702		}
2703	}
2704
2705	if (mlx4_is_bonded(dev->dev) && (attr_mask & IB_QP_PORT)) {
2706		if ((cur_state == IB_QPS_RESET) && (new_state == IB_QPS_INIT)) {
2707			if ((ibqp->qp_type == IB_QPT_RC) ||
2708			    (ibqp->qp_type == IB_QPT_UD) ||
2709			    (ibqp->qp_type == IB_QPT_UC) ||
2710			    (ibqp->qp_type == IB_QPT_RAW_PACKET) ||
2711			    (ibqp->qp_type == IB_QPT_XRC_INI)) {
2712				attr->port_num = mlx4_ib_bond_next_port(dev);
2713			}
2714		} else {
2715			/* no sense in changing port_num
2716			 * when ports are bonded */
2717			attr_mask &= ~IB_QP_PORT;
2718		}
2719	}
2720
2721	if ((attr_mask & IB_QP_PORT) &&
2722	    (attr->port_num == 0 || attr->port_num > dev->num_ports)) {
2723		pr_debug("qpn 0x%x: invalid port number (%d) specified "
2724			 "for transition %d to %d. qp_type %d\n",
2725			 ibqp->qp_num, attr->port_num, cur_state,
2726			 new_state, ibqp->qp_type);
2727		goto out;
2728	}
2729
2730	if ((attr_mask & IB_QP_PORT) && (ibqp->qp_type == IB_QPT_RAW_PACKET) &&
2731	    (rdma_port_get_link_layer(&dev->ib_dev, attr->port_num) !=
2732	     IB_LINK_LAYER_ETHERNET))
2733		goto out;
2734
2735	if (attr_mask & IB_QP_PKEY_INDEX) {
2736		int p = attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
2737		if (attr->pkey_index >= dev->dev->caps.pkey_table_len[p]) {
2738			pr_debug("qpn 0x%x: invalid pkey index (%d) specified "
2739				 "for transition %d to %d. qp_type %d\n",
2740				 ibqp->qp_num, attr->pkey_index, cur_state,
2741				 new_state, ibqp->qp_type);
2742			goto out;
2743		}
2744	}
2745
2746	if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC &&
2747	    attr->max_rd_atomic > dev->dev->caps.max_qp_init_rdma) {
2748		pr_debug("qpn 0x%x: max_rd_atomic (%d) too large. "
2749			 "Transition %d to %d. qp_type %d\n",
2750			 ibqp->qp_num, attr->max_rd_atomic, cur_state,
2751			 new_state, ibqp->qp_type);
2752		goto out;
2753	}
2754
2755	if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC &&
2756	    attr->max_dest_rd_atomic > dev->dev->caps.max_qp_dest_rdma) {
2757		pr_debug("qpn 0x%x: max_dest_rd_atomic (%d) too large. "
2758			 "Transition %d to %d. qp_type %d\n",
2759			 ibqp->qp_num, attr->max_dest_rd_atomic, cur_state,
2760			 new_state, ibqp->qp_type);
2761		goto out;
2762	}
2763
2764	if (cur_state == new_state && cur_state == IB_QPS_RESET) {
2765		err = 0;
2766		goto out;
2767	}
2768
2769	if (ibqp->rwq_ind_tbl && (new_state == IB_QPS_INIT)) {
2770		err = bringup_rss_rwqs(ibqp->rwq_ind_tbl, attr->port_num,
2771				       udata);
2772		if (err)
2773			goto out;
2774	}
2775
2776	err = __mlx4_ib_modify_qp(ibqp, MLX4_IB_QP_SRC, attr, attr_mask,
2777				  cur_state, new_state, udata);
2778
2779	if (ibqp->rwq_ind_tbl && err)
2780		bring_down_rss_rwqs(ibqp->rwq_ind_tbl, udata);
2781
2782	if (mlx4_is_bonded(dev->dev) && (attr_mask & IB_QP_PORT))
2783		attr->port_num = 1;
2784
2785out:
2786	mutex_unlock(&qp->mutex);
2787	return err;
2788}
2789
2790int mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
2791		      int attr_mask, struct ib_udata *udata)
2792{
2793	struct mlx4_ib_qp *mqp = to_mqp(ibqp);
2794	int ret;
2795
2796	ret = _mlx4_ib_modify_qp(ibqp, attr, attr_mask, udata);
2797
2798	if (mqp->mlx4_ib_qp_type == MLX4_IB_QPT_GSI) {
2799		struct mlx4_ib_sqp *sqp = mqp->sqp;
2800		int err = 0;
2801
2802		if (sqp->roce_v2_gsi)
2803			err = ib_modify_qp(sqp->roce_v2_gsi, attr, attr_mask);
2804		if (err)
2805			pr_err("Failed to modify GSI QP for RoCEv2 (%d)\n",
2806			       err);
2807	}
2808	return ret;
2809}
2810
2811static int vf_get_qp0_qkey(struct mlx4_dev *dev, int qpn, u32 *qkey)
2812{
2813	int i;
2814	for (i = 0; i < dev->caps.num_ports; i++) {
2815		if (qpn == dev->caps.spec_qps[i].qp0_proxy ||
2816		    qpn == dev->caps.spec_qps[i].qp0_tunnel) {
2817			*qkey = dev->caps.spec_qps[i].qp0_qkey;
2818			return 0;
2819		}
2820	}
2821	return -EINVAL;
2822}
2823
2824static int build_sriov_qp0_header(struct mlx4_ib_qp *qp,
2825				  const struct ib_ud_wr *wr,
2826				  void *wqe, unsigned *mlx_seg_len)
2827{
2828	struct mlx4_ib_dev *mdev = to_mdev(qp->ibqp.device);
2829	struct mlx4_ib_sqp *sqp = qp->sqp;
2830	struct ib_device *ib_dev = qp->ibqp.device;
2831	struct mlx4_wqe_mlx_seg *mlx = wqe;
2832	struct mlx4_wqe_inline_seg *inl = wqe + sizeof *mlx;
2833	struct mlx4_ib_ah *ah = to_mah(wr->ah);
2834	u16 pkey;
2835	u32 qkey;
2836	int send_size;
2837	int header_size;
2838	int spc;
2839	int err;
2840	int i;
2841
2842	if (wr->wr.opcode != IB_WR_SEND)
2843		return -EINVAL;
2844
2845	send_size = 0;
2846
2847	for (i = 0; i < wr->wr.num_sge; ++i)
2848		send_size += wr->wr.sg_list[i].length;
2849
2850	/* for proxy-qp0 sends, need to add in size of tunnel header */
2851	/* for tunnel-qp0 sends, tunnel header is already in s/g list */
2852	if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_SMI_OWNER)
2853		send_size += sizeof (struct mlx4_ib_tunnel_header);
2854
2855	ib_ud_header_init(send_size, 1, 0, 0, 0, 0, 0, 0, &sqp->ud_header);
2856
2857	if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_SMI_OWNER) {
2858		sqp->ud_header.lrh.service_level =
2859			be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 28;
2860		sqp->ud_header.lrh.destination_lid =
2861			cpu_to_be16(ah->av.ib.g_slid & 0x7f);
2862		sqp->ud_header.lrh.source_lid =
2863			cpu_to_be16(ah->av.ib.g_slid & 0x7f);
2864	}
2865
2866	mlx->flags &= cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE);
2867
2868	/* force loopback */
2869	mlx->flags |= cpu_to_be32(MLX4_WQE_MLX_VL15 | 0x1 | MLX4_WQE_MLX_SLR);
2870	mlx->rlid = sqp->ud_header.lrh.destination_lid;
2871
2872	sqp->ud_header.lrh.virtual_lane    = 0;
2873	sqp->ud_header.bth.solicited_event = !!(wr->wr.send_flags & IB_SEND_SOLICITED);
2874	err = ib_get_cached_pkey(ib_dev, qp->port, 0, &pkey);
2875	if (err)
2876		return err;
2877	sqp->ud_header.bth.pkey = cpu_to_be16(pkey);
2878	if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_TUN_SMI_OWNER)
2879		sqp->ud_header.bth.destination_qpn = cpu_to_be32(wr->remote_qpn);
2880	else
2881		sqp->ud_header.bth.destination_qpn =
2882			cpu_to_be32(mdev->dev->caps.spec_qps[qp->port - 1].qp0_tunnel);
2883
2884	sqp->ud_header.bth.psn = cpu_to_be32((sqp->send_psn++) & ((1 << 24) - 1));
2885	if (mlx4_is_master(mdev->dev)) {
2886		if (mlx4_get_parav_qkey(mdev->dev, qp->mqp.qpn, &qkey))
2887			return -EINVAL;
2888	} else {
2889		if (vf_get_qp0_qkey(mdev->dev, qp->mqp.qpn, &qkey))
2890			return -EINVAL;
2891	}
2892	sqp->ud_header.deth.qkey = cpu_to_be32(qkey);
2893	sqp->ud_header.deth.source_qpn = cpu_to_be32(qp->mqp.qpn);
2894
2895	sqp->ud_header.bth.opcode        = IB_OPCODE_UD_SEND_ONLY;
2896	sqp->ud_header.immediate_present = 0;
2897
2898	header_size = ib_ud_header_pack(&sqp->ud_header, sqp->header_buf);
2899
2900	/*
2901	 * Inline data segments may not cross a 64 byte boundary.  If
2902	 * our UD header is bigger than the space available up to the
2903	 * next 64 byte boundary in the WQE, use two inline data
2904	 * segments to hold the UD header.
2905	 */
2906	spc = MLX4_INLINE_ALIGN -
2907	      ((unsigned long) (inl + 1) & (MLX4_INLINE_ALIGN - 1));
2908	if (header_size <= spc) {
2909		inl->byte_count = cpu_to_be32(1 << 31 | header_size);
2910		memcpy(inl + 1, sqp->header_buf, header_size);
2911		i = 1;
2912	} else {
2913		inl->byte_count = cpu_to_be32(1 << 31 | spc);
2914		memcpy(inl + 1, sqp->header_buf, spc);
2915
2916		inl = (void *) (inl + 1) + spc;
2917		memcpy(inl + 1, sqp->header_buf + spc, header_size - spc);
2918		/*
2919		 * Need a barrier here to make sure all the data is
2920		 * visible before the byte_count field is set.
2921		 * Otherwise the HCA prefetcher could grab the 64-byte
2922		 * chunk with this inline segment and get a valid (!=
2923		 * 0xffffffff) byte count but stale data, and end up
2924		 * generating a packet with bad headers.
2925		 *
2926		 * The first inline segment's byte_count field doesn't
2927		 * need a barrier, because it comes after a
2928		 * control/MLX segment and therefore is at an offset
2929		 * of 16 mod 64.
2930		 */
2931		wmb();
2932		inl->byte_count = cpu_to_be32(1 << 31 | (header_size - spc));
2933		i = 2;
2934	}
2935
2936	*mlx_seg_len =
2937	ALIGN(i * sizeof (struct mlx4_wqe_inline_seg) + header_size, 16);
2938	return 0;
2939}
2940
2941static u8 sl_to_vl(struct mlx4_ib_dev *dev, u8 sl, int port_num)
2942{
2943	union sl2vl_tbl_to_u64 tmp_vltab;
2944	u8 vl;
2945
2946	if (sl > 15)
2947		return 0xf;
2948	tmp_vltab.sl64 = atomic64_read(&dev->sl2vl[port_num - 1]);
2949	vl = tmp_vltab.sl8[sl >> 1];
2950	if (sl & 1)
2951		vl &= 0x0f;
2952	else
2953		vl >>= 4;
2954	return vl;
2955}
2956
2957static int fill_gid_by_hw_index(struct mlx4_ib_dev *ibdev, u8 port_num,
2958				int index, union ib_gid *gid,
2959				enum ib_gid_type *gid_type)
2960{
2961	struct mlx4_ib_iboe *iboe = &ibdev->iboe;
2962	struct mlx4_port_gid_table *port_gid_table;
2963	unsigned long flags;
2964
2965	port_gid_table = &iboe->gids[port_num - 1];
2966	spin_lock_irqsave(&iboe->lock, flags);
2967	memcpy(gid, &port_gid_table->gids[index].gid, sizeof(*gid));
2968	*gid_type = port_gid_table->gids[index].gid_type;
2969	spin_unlock_irqrestore(&iboe->lock, flags);
2970	if (rdma_is_zero_gid(gid))
2971		return -ENOENT;
2972
2973	return 0;
2974}
2975
2976#define MLX4_ROCEV2_QP1_SPORT 0xC000
2977static int build_mlx_header(struct mlx4_ib_qp *qp, const struct ib_ud_wr *wr,
2978			    void *wqe, unsigned *mlx_seg_len)
2979{
2980	struct mlx4_ib_sqp *sqp = qp->sqp;
2981	struct ib_device *ib_dev = qp->ibqp.device;
2982	struct mlx4_ib_dev *ibdev = to_mdev(ib_dev);
2983	struct mlx4_wqe_mlx_seg *mlx = wqe;
2984	struct mlx4_wqe_ctrl_seg *ctrl = wqe;
2985	struct mlx4_wqe_inline_seg *inl = wqe + sizeof *mlx;
2986	struct mlx4_ib_ah *ah = to_mah(wr->ah);
2987	union ib_gid sgid;
2988	u16 pkey;
2989	int send_size;
2990	int header_size;
2991	int spc;
2992	int i;
2993	int err = 0;
2994	u16 vlan = 0xffff;
2995	bool is_eth;
2996	bool is_vlan = false;
2997	bool is_grh;
2998	bool is_udp = false;
2999	int ip_version = 0;
3000
3001	send_size = 0;
3002	for (i = 0; i < wr->wr.num_sge; ++i)
3003		send_size += wr->wr.sg_list[i].length;
3004
3005	is_eth = rdma_port_get_link_layer(qp->ibqp.device, qp->port) == IB_LINK_LAYER_ETHERNET;
3006	is_grh = mlx4_ib_ah_grh_present(ah);
3007	if (is_eth) {
3008		enum ib_gid_type gid_type;
3009		if (mlx4_is_mfunc(to_mdev(ib_dev)->dev)) {
3010			/* When multi-function is enabled, the ib_core gid
3011			 * indexes don't necessarily match the hw ones, so
3012			 * we must use our own cache */
3013			err = mlx4_get_roce_gid_from_slave(to_mdev(ib_dev)->dev,
3014							   be32_to_cpu(ah->av.ib.port_pd) >> 24,
3015							   ah->av.ib.gid_index, &sgid.raw[0]);
3016			if (err)
3017				return err;
3018		} else  {
3019			err = fill_gid_by_hw_index(ibdev, qp->port,
3020						   ah->av.ib.gid_index, &sgid,
3021						   &gid_type);
3022			if (!err) {
3023				is_udp = gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP;
3024				if (is_udp) {
3025					if (ipv6_addr_v4mapped((struct in6_addr *)&sgid))
3026						ip_version = 4;
3027					else
3028						ip_version = 6;
3029					is_grh = false;
3030				}
3031			} else {
3032				return err;
3033			}
3034		}
3035		if (ah->av.eth.vlan != cpu_to_be16(0xffff)) {
3036			vlan = be16_to_cpu(ah->av.eth.vlan) & 0x0fff;
3037			is_vlan = true;
3038		}
3039	}
3040	err = ib_ud_header_init(send_size, !is_eth, is_eth, is_vlan, is_grh,
3041			  ip_version, is_udp, 0, &sqp->ud_header);
3042	if (err)
3043		return err;
3044
3045	if (!is_eth) {
3046		sqp->ud_header.lrh.service_level =
3047			be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 28;
3048		sqp->ud_header.lrh.destination_lid = ah->av.ib.dlid;
3049		sqp->ud_header.lrh.source_lid = cpu_to_be16(ah->av.ib.g_slid & 0x7f);
3050	}
3051
3052	if (is_grh || (ip_version == 6)) {
3053		sqp->ud_header.grh.traffic_class =
3054			(be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 20) & 0xff;
3055		sqp->ud_header.grh.flow_label    =
3056			ah->av.ib.sl_tclass_flowlabel & cpu_to_be32(0xfffff);
3057		sqp->ud_header.grh.hop_limit     = ah->av.ib.hop_limit;
3058		if (is_eth) {
3059			memcpy(sqp->ud_header.grh.source_gid.raw, sgid.raw, 16);
3060		} else {
3061			if (mlx4_is_mfunc(to_mdev(ib_dev)->dev)) {
3062				/* When multi-function is enabled, the ib_core gid
3063				 * indexes don't necessarily match the hw ones, so
3064				 * we must use our own cache
3065				 */
3066				sqp->ud_header.grh.source_gid.global
3067					.subnet_prefix =
3068					cpu_to_be64(atomic64_read(
3069						&(to_mdev(ib_dev)
3070							  ->sriov
3071							  .demux[qp->port - 1]
3072							  .subnet_prefix)));
3073				sqp->ud_header.grh.source_gid.global
3074					.interface_id =
3075					to_mdev(ib_dev)
3076						->sriov.demux[qp->port - 1]
3077						.guid_cache[ah->av.ib.gid_index];
3078			} else {
3079				sqp->ud_header.grh.source_gid =
3080					ah->ibah.sgid_attr->gid;
3081			}
3082		}
3083		memcpy(sqp->ud_header.grh.destination_gid.raw,
3084		       ah->av.ib.dgid, 16);
3085	}
3086
3087	if (ip_version == 4) {
3088		sqp->ud_header.ip4.tos =
3089			(be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 20) & 0xff;
3090		sqp->ud_header.ip4.id = 0;
3091		sqp->ud_header.ip4.frag_off = htons(IP_DF);
3092		sqp->ud_header.ip4.ttl = ah->av.eth.hop_limit;
3093
3094		memcpy(&sqp->ud_header.ip4.saddr,
3095		       sgid.raw + 12, 4);
3096		memcpy(&sqp->ud_header.ip4.daddr, ah->av.ib.dgid + 12, 4);
3097		sqp->ud_header.ip4.check = ib_ud_ip4_csum(&sqp->ud_header);
3098	}
3099
3100	if (is_udp) {
3101		sqp->ud_header.udp.dport = htons(ROCE_V2_UDP_DPORT);
3102		sqp->ud_header.udp.sport = htons(MLX4_ROCEV2_QP1_SPORT);
3103		sqp->ud_header.udp.csum = 0;
3104	}
3105
3106	mlx->flags &= cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE);
3107
3108	if (!is_eth) {
3109		mlx->flags |=
3110			cpu_to_be32((!qp->ibqp.qp_num ? MLX4_WQE_MLX_VL15 : 0) |
3111				    (sqp->ud_header.lrh.destination_lid ==
3112						     IB_LID_PERMISSIVE ?
3113					     MLX4_WQE_MLX_SLR :
3114					     0) |
3115				    (sqp->ud_header.lrh.service_level << 8));
3116		if (ah->av.ib.port_pd & cpu_to_be32(0x80000000))
3117			mlx->flags |= cpu_to_be32(0x1); /* force loopback */
3118		mlx->rlid = sqp->ud_header.lrh.destination_lid;
3119	}
3120
3121	switch (wr->wr.opcode) {
3122	case IB_WR_SEND:
3123		sqp->ud_header.bth.opcode	 = IB_OPCODE_UD_SEND_ONLY;
3124		sqp->ud_header.immediate_present = 0;
3125		break;
3126	case IB_WR_SEND_WITH_IMM:
3127		sqp->ud_header.bth.opcode	 = IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE;
3128		sqp->ud_header.immediate_present = 1;
3129		sqp->ud_header.immediate_data    = wr->wr.ex.imm_data;
3130		break;
3131	default:
3132		return -EINVAL;
3133	}
3134
3135	if (is_eth) {
3136		struct in6_addr in6;
3137		u16 ether_type;
3138		u16 pcp = (be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 29) << 13;
3139
3140		ether_type = (!is_udp) ? ETH_P_IBOE:
3141			(ip_version == 4 ? ETH_P_IP : ETH_P_IPV6);
3142
3143		mlx->sched_prio = cpu_to_be16(pcp);
3144
3145		ether_addr_copy(sqp->ud_header.eth.smac_h, ah->av.eth.s_mac);
3146		memcpy(sqp->ud_header.eth.dmac_h, ah->av.eth.mac, 6);
3147		memcpy(&ctrl->srcrb_flags16[0], ah->av.eth.mac, 2);
3148		memcpy(&ctrl->imm, ah->av.eth.mac + 2, 4);
3149		memcpy(&in6, sgid.raw, sizeof(in6));
3150
3151
3152		if (!memcmp(sqp->ud_header.eth.smac_h, sqp->ud_header.eth.dmac_h, 6))
3153			mlx->flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK);
3154		if (!is_vlan) {
3155			sqp->ud_header.eth.type = cpu_to_be16(ether_type);
3156		} else {
3157			sqp->ud_header.vlan.type = cpu_to_be16(ether_type);
3158			sqp->ud_header.vlan.tag = cpu_to_be16(vlan | pcp);
3159		}
3160	} else {
3161		sqp->ud_header.lrh.virtual_lane =
3162			!qp->ibqp.qp_num ?
3163				15 :
3164				sl_to_vl(to_mdev(ib_dev),
3165					 sqp->ud_header.lrh.service_level,
3166					 qp->port);
3167		if (qp->ibqp.qp_num && sqp->ud_header.lrh.virtual_lane == 15)
3168			return -EINVAL;
3169		if (sqp->ud_header.lrh.destination_lid == IB_LID_PERMISSIVE)
3170			sqp->ud_header.lrh.source_lid = IB_LID_PERMISSIVE;
3171	}
3172	sqp->ud_header.bth.solicited_event = !!(wr->wr.send_flags & IB_SEND_SOLICITED);
3173	if (!qp->ibqp.qp_num)
3174		err = ib_get_cached_pkey(ib_dev, qp->port, sqp->pkey_index,
3175					 &pkey);
3176	else
3177		err = ib_get_cached_pkey(ib_dev, qp->port, wr->pkey_index,
3178					 &pkey);
3179	if (err)
3180		return err;
3181
3182	sqp->ud_header.bth.pkey = cpu_to_be16(pkey);
3183	sqp->ud_header.bth.destination_qpn = cpu_to_be32(wr->remote_qpn);
3184	sqp->ud_header.bth.psn = cpu_to_be32((sqp->send_psn++) & ((1 << 24) - 1));
3185	sqp->ud_header.deth.qkey = cpu_to_be32(wr->remote_qkey & 0x80000000 ?
3186					       sqp->qkey : wr->remote_qkey);
3187	sqp->ud_header.deth.source_qpn = cpu_to_be32(qp->ibqp.qp_num);
3188
3189	header_size = ib_ud_header_pack(&sqp->ud_header, sqp->header_buf);
3190
3191	if (0) {
3192		pr_err("built UD header of size %d:\n", header_size);
3193		for (i = 0; i < header_size / 4; ++i) {
3194			if (i % 8 == 0)
3195				pr_err("  [%02x] ", i * 4);
3196			pr_cont(" %08x",
3197				be32_to_cpu(((__be32 *) sqp->header_buf)[i]));
3198			if ((i + 1) % 8 == 0)
3199				pr_cont("\n");
3200		}
3201		pr_err("\n");
3202	}
3203
3204	/*
3205	 * Inline data segments may not cross a 64 byte boundary.  If
3206	 * our UD header is bigger than the space available up to the
3207	 * next 64 byte boundary in the WQE, use two inline data
3208	 * segments to hold the UD header.
3209	 */
3210	spc = MLX4_INLINE_ALIGN -
3211		((unsigned long) (inl + 1) & (MLX4_INLINE_ALIGN - 1));
3212	if (header_size <= spc) {
3213		inl->byte_count = cpu_to_be32(1 << 31 | header_size);
3214		memcpy(inl + 1, sqp->header_buf, header_size);
3215		i = 1;
3216	} else {
3217		inl->byte_count = cpu_to_be32(1 << 31 | spc);
3218		memcpy(inl + 1, sqp->header_buf, spc);
3219
3220		inl = (void *) (inl + 1) + spc;
3221		memcpy(inl + 1, sqp->header_buf + spc, header_size - spc);
3222		/*
3223		 * Need a barrier here to make sure all the data is
3224		 * visible before the byte_count field is set.
3225		 * Otherwise the HCA prefetcher could grab the 64-byte
3226		 * chunk with this inline segment and get a valid (!=
3227		 * 0xffffffff) byte count but stale data, and end up
3228		 * generating a packet with bad headers.
3229		 *
3230		 * The first inline segment's byte_count field doesn't
3231		 * need a barrier, because it comes after a
3232		 * control/MLX segment and therefore is at an offset
3233		 * of 16 mod 64.
3234		 */
3235		wmb();
3236		inl->byte_count = cpu_to_be32(1 << 31 | (header_size - spc));
3237		i = 2;
3238	}
3239
3240	*mlx_seg_len =
3241		ALIGN(i * sizeof (struct mlx4_wqe_inline_seg) + header_size, 16);
3242	return 0;
3243}
3244
3245static int mlx4_wq_overflow(struct mlx4_ib_wq *wq, int nreq, struct ib_cq *ib_cq)
3246{
3247	unsigned cur;
3248	struct mlx4_ib_cq *cq;
3249
3250	cur = wq->head - wq->tail;
3251	if (likely(cur + nreq < wq->max_post))
3252		return 0;
3253
3254	cq = to_mcq(ib_cq);
3255	spin_lock(&cq->lock);
3256	cur = wq->head - wq->tail;
3257	spin_unlock(&cq->lock);
3258
3259	return cur + nreq >= wq->max_post;
3260}
3261
3262static __be32 convert_access(int acc)
3263{
3264	return (acc & IB_ACCESS_REMOTE_ATOMIC ?
3265		cpu_to_be32(MLX4_WQE_FMR_AND_BIND_PERM_ATOMIC)       : 0) |
3266	       (acc & IB_ACCESS_REMOTE_WRITE  ?
3267		cpu_to_be32(MLX4_WQE_FMR_AND_BIND_PERM_REMOTE_WRITE) : 0) |
3268	       (acc & IB_ACCESS_REMOTE_READ   ?
3269		cpu_to_be32(MLX4_WQE_FMR_AND_BIND_PERM_REMOTE_READ)  : 0) |
3270	       (acc & IB_ACCESS_LOCAL_WRITE   ? cpu_to_be32(MLX4_WQE_FMR_PERM_LOCAL_WRITE)  : 0) |
3271		cpu_to_be32(MLX4_WQE_FMR_PERM_LOCAL_READ);
3272}
3273
3274static void set_reg_seg(struct mlx4_wqe_fmr_seg *fseg,
3275			const struct ib_reg_wr *wr)
3276{
3277	struct mlx4_ib_mr *mr = to_mmr(wr->mr);
3278
3279	fseg->flags		= convert_access(wr->access);
3280	fseg->mem_key		= cpu_to_be32(wr->key);
3281	fseg->buf_list		= cpu_to_be64(mr->page_map);
3282	fseg->start_addr	= cpu_to_be64(mr->ibmr.iova);
3283	fseg->reg_len		= cpu_to_be64(mr->ibmr.length);
3284	fseg->offset		= 0; /* XXX -- is this just for ZBVA? */
3285	fseg->page_size		= cpu_to_be32(ilog2(mr->ibmr.page_size));
3286	fseg->reserved[0]	= 0;
3287	fseg->reserved[1]	= 0;
3288}
3289
3290static void set_local_inv_seg(struct mlx4_wqe_local_inval_seg *iseg, u32 rkey)
3291{
3292	memset(iseg, 0, sizeof(*iseg));
3293	iseg->mem_key = cpu_to_be32(rkey);
3294}
3295
3296static __always_inline void set_raddr_seg(struct mlx4_wqe_raddr_seg *rseg,
3297					  u64 remote_addr, u32 rkey)
3298{
3299	rseg->raddr    = cpu_to_be64(remote_addr);
3300	rseg->rkey     = cpu_to_be32(rkey);
3301	rseg->reserved = 0;
3302}
3303
3304static void set_atomic_seg(struct mlx4_wqe_atomic_seg *aseg,
3305			   const struct ib_atomic_wr *wr)
3306{
3307	if (wr->wr.opcode == IB_WR_ATOMIC_CMP_AND_SWP) {
3308		aseg->swap_add = cpu_to_be64(wr->swap);
3309		aseg->compare  = cpu_to_be64(wr->compare_add);
3310	} else if (wr->wr.opcode == IB_WR_MASKED_ATOMIC_FETCH_AND_ADD) {
3311		aseg->swap_add = cpu_to_be64(wr->compare_add);
3312		aseg->compare  = cpu_to_be64(wr->compare_add_mask);
3313	} else {
3314		aseg->swap_add = cpu_to_be64(wr->compare_add);
3315		aseg->compare  = 0;
3316	}
3317
3318}
3319
3320static void set_masked_atomic_seg(struct mlx4_wqe_masked_atomic_seg *aseg,
3321				  const struct ib_atomic_wr *wr)
3322{
3323	aseg->swap_add		= cpu_to_be64(wr->swap);
3324	aseg->swap_add_mask	= cpu_to_be64(wr->swap_mask);
3325	aseg->compare		= cpu_to_be64(wr->compare_add);
3326	aseg->compare_mask	= cpu_to_be64(wr->compare_add_mask);
3327}
3328
3329static void set_datagram_seg(struct mlx4_wqe_datagram_seg *dseg,
3330			     const struct ib_ud_wr *wr)
3331{
3332	memcpy(dseg->av, &to_mah(wr->ah)->av, sizeof (struct mlx4_av));
3333	dseg->dqpn = cpu_to_be32(wr->remote_qpn);
3334	dseg->qkey = cpu_to_be32(wr->remote_qkey);
3335	dseg->vlan = to_mah(wr->ah)->av.eth.vlan;
3336	memcpy(dseg->mac, to_mah(wr->ah)->av.eth.mac, 6);
3337}
3338
3339static void set_tunnel_datagram_seg(struct mlx4_ib_dev *dev,
3340				    struct mlx4_wqe_datagram_seg *dseg,
3341				    const struct ib_ud_wr *wr,
3342				    enum mlx4_ib_qp_type qpt)
3343{
3344	union mlx4_ext_av *av = &to_mah(wr->ah)->av;
3345	struct mlx4_av sqp_av = {0};
3346	int port = *((u8 *) &av->ib.port_pd) & 0x3;
3347
3348	/* force loopback */
3349	sqp_av.port_pd = av->ib.port_pd | cpu_to_be32(0x80000000);
3350	sqp_av.g_slid = av->ib.g_slid & 0x7f; /* no GRH */
3351	sqp_av.sl_tclass_flowlabel = av->ib.sl_tclass_flowlabel &
3352			cpu_to_be32(0xf0000000);
3353
3354	memcpy(dseg->av, &sqp_av, sizeof (struct mlx4_av));
3355	if (qpt == MLX4_IB_QPT_PROXY_GSI)
3356		dseg->dqpn = cpu_to_be32(dev->dev->caps.spec_qps[port - 1].qp1_tunnel);
3357	else
3358		dseg->dqpn = cpu_to_be32(dev->dev->caps.spec_qps[port - 1].qp0_tunnel);
3359	/* Use QKEY from the QP context, which is set by master */
3360	dseg->qkey = cpu_to_be32(IB_QP_SET_QKEY);
3361}
3362
3363static void build_tunnel_header(const struct ib_ud_wr *wr, void *wqe,
3364				unsigned *mlx_seg_len)
3365{
3366	struct mlx4_wqe_inline_seg *inl = wqe;
3367	struct mlx4_ib_tunnel_header hdr;
3368	struct mlx4_ib_ah *ah = to_mah(wr->ah);
3369	int spc;
3370	int i;
3371
3372	memcpy(&hdr.av, &ah->av, sizeof hdr.av);
3373	hdr.remote_qpn = cpu_to_be32(wr->remote_qpn);
3374	hdr.pkey_index = cpu_to_be16(wr->pkey_index);
3375	hdr.qkey = cpu_to_be32(wr->remote_qkey);
3376	memcpy(hdr.mac, ah->av.eth.mac, 6);
3377	hdr.vlan = ah->av.eth.vlan;
3378
3379	spc = MLX4_INLINE_ALIGN -
3380		((unsigned long) (inl + 1) & (MLX4_INLINE_ALIGN - 1));
3381	if (sizeof (hdr) <= spc) {
3382		memcpy(inl + 1, &hdr, sizeof (hdr));
3383		wmb();
3384		inl->byte_count = cpu_to_be32(1 << 31 | sizeof (hdr));
3385		i = 1;
3386	} else {
3387		memcpy(inl + 1, &hdr, spc);
3388		wmb();
3389		inl->byte_count = cpu_to_be32(1 << 31 | spc);
3390
3391		inl = (void *) (inl + 1) + spc;
3392		memcpy(inl + 1, (void *) &hdr + spc, sizeof (hdr) - spc);
3393		wmb();
3394		inl->byte_count = cpu_to_be32(1 << 31 | (sizeof (hdr) - spc));
3395		i = 2;
3396	}
3397
3398	*mlx_seg_len =
3399		ALIGN(i * sizeof (struct mlx4_wqe_inline_seg) + sizeof (hdr), 16);
3400}
3401
3402static void set_mlx_icrc_seg(void *dseg)
3403{
3404	u32 *t = dseg;
3405	struct mlx4_wqe_inline_seg *iseg = dseg;
3406
3407	t[1] = 0;
3408
3409	/*
3410	 * Need a barrier here before writing the byte_count field to
3411	 * make sure that all the data is visible before the
3412	 * byte_count field is set.  Otherwise, if the segment begins
3413	 * a new cacheline, the HCA prefetcher could grab the 64-byte
3414	 * chunk and get a valid (!= * 0xffffffff) byte count but
3415	 * stale data, and end up sending the wrong data.
3416	 */
3417	wmb();
3418
3419	iseg->byte_count = cpu_to_be32((1 << 31) | 4);
3420}
3421
3422static void set_data_seg(struct mlx4_wqe_data_seg *dseg, struct ib_sge *sg)
3423{
3424	dseg->lkey       = cpu_to_be32(sg->lkey);
3425	dseg->addr       = cpu_to_be64(sg->addr);
3426
3427	/*
3428	 * Need a barrier here before writing the byte_count field to
3429	 * make sure that all the data is visible before the
3430	 * byte_count field is set.  Otherwise, if the segment begins
3431	 * a new cacheline, the HCA prefetcher could grab the 64-byte
3432	 * chunk and get a valid (!= * 0xffffffff) byte count but
3433	 * stale data, and end up sending the wrong data.
3434	 */
3435	wmb();
3436
3437	dseg->byte_count = cpu_to_be32(sg->length);
3438}
3439
3440static void __set_data_seg(struct mlx4_wqe_data_seg *dseg, struct ib_sge *sg)
3441{
3442	dseg->byte_count = cpu_to_be32(sg->length);
3443	dseg->lkey       = cpu_to_be32(sg->lkey);
3444	dseg->addr       = cpu_to_be64(sg->addr);
3445}
3446
3447static int build_lso_seg(struct mlx4_wqe_lso_seg *wqe,
3448			 const struct ib_ud_wr *wr, struct mlx4_ib_qp *qp,
3449			 unsigned *lso_seg_len, __be32 *lso_hdr_sz, __be32 *blh)
3450{
3451	unsigned halign = ALIGN(sizeof *wqe + wr->hlen, 16);
3452
3453	if (unlikely(halign > MLX4_IB_CACHE_LINE_SIZE))
3454		*blh = cpu_to_be32(1 << 6);
3455
3456	if (unlikely(!(qp->flags & MLX4_IB_QP_LSO) &&
3457		     wr->wr.num_sge > qp->sq.max_gs - (halign >> 4)))
3458		return -EINVAL;
3459
3460	memcpy(wqe->header, wr->header, wr->hlen);
3461
3462	*lso_hdr_sz  = cpu_to_be32(wr->mss << 16 | wr->hlen);
3463	*lso_seg_len = halign;
3464	return 0;
3465}
3466
3467static __be32 send_ieth(const struct ib_send_wr *wr)
3468{
3469	switch (wr->opcode) {
3470	case IB_WR_SEND_WITH_IMM:
3471	case IB_WR_RDMA_WRITE_WITH_IMM:
3472		return wr->ex.imm_data;
3473
3474	case IB_WR_SEND_WITH_INV:
3475		return cpu_to_be32(wr->ex.invalidate_rkey);
3476
3477	default:
3478		return 0;
3479	}
3480}
3481
3482static void add_zero_len_inline(void *wqe)
3483{
3484	struct mlx4_wqe_inline_seg *inl = wqe;
3485	memset(wqe, 0, 16);
3486	inl->byte_count = cpu_to_be32(1 << 31);
3487}
3488
3489static int _mlx4_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
3490			      const struct ib_send_wr **bad_wr, bool drain)
3491{
3492	struct mlx4_ib_qp *qp = to_mqp(ibqp);
3493	void *wqe;
3494	struct mlx4_wqe_ctrl_seg *ctrl;
3495	struct mlx4_wqe_data_seg *dseg;
3496	unsigned long flags;
3497	int nreq;
3498	int err = 0;
3499	unsigned ind;
3500	int size;
3501	unsigned seglen;
3502	__be32 dummy;
3503	__be32 *lso_wqe;
3504	__be32 lso_hdr_sz;
3505	__be32 blh;
3506	int i;
3507	struct mlx4_ib_dev *mdev = to_mdev(ibqp->device);
3508
3509	if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_GSI) {
3510		struct mlx4_ib_sqp *sqp = qp->sqp;
3511
3512		if (sqp->roce_v2_gsi) {
3513			struct mlx4_ib_ah *ah = to_mah(ud_wr(wr)->ah);
3514			enum ib_gid_type gid_type;
3515			union ib_gid gid;
3516
3517			if (!fill_gid_by_hw_index(mdev, qp->port,
3518					   ah->av.ib.gid_index,
3519					   &gid, &gid_type))
3520				qp = (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) ?
3521						to_mqp(sqp->roce_v2_gsi) : qp;
3522			else
3523				pr_err("Failed to get gid at index %d. RoCEv2 will not work properly\n",
3524				       ah->av.ib.gid_index);
3525		}
3526	}
3527
3528	spin_lock_irqsave(&qp->sq.lock, flags);
3529	if (mdev->dev->persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR &&
3530	    !drain) {
3531		err = -EIO;
3532		*bad_wr = wr;
3533		nreq = 0;
3534		goto out;
3535	}
3536
3537	ind = qp->sq_next_wqe;
3538
3539	for (nreq = 0; wr; ++nreq, wr = wr->next) {
3540		lso_wqe = &dummy;
3541		blh = 0;
3542
3543		if (mlx4_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq)) {
3544			err = -ENOMEM;
3545			*bad_wr = wr;
3546			goto out;
3547		}
3548
3549		if (unlikely(wr->num_sge > qp->sq.max_gs)) {
3550			err = -EINVAL;
3551			*bad_wr = wr;
3552			goto out;
3553		}
3554
3555		ctrl = wqe = get_send_wqe(qp, ind & (qp->sq.wqe_cnt - 1));
3556		qp->sq.wrid[(qp->sq.head + nreq) & (qp->sq.wqe_cnt - 1)] = wr->wr_id;
3557
3558		ctrl->srcrb_flags =
3559			(wr->send_flags & IB_SEND_SIGNALED ?
3560			 cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE) : 0) |
3561			(wr->send_flags & IB_SEND_SOLICITED ?
3562			 cpu_to_be32(MLX4_WQE_CTRL_SOLICITED) : 0) |
3563			((wr->send_flags & IB_SEND_IP_CSUM) ?
3564			 cpu_to_be32(MLX4_WQE_CTRL_IP_CSUM |
3565				     MLX4_WQE_CTRL_TCP_UDP_CSUM) : 0) |
3566			qp->sq_signal_bits;
3567
3568		ctrl->imm = send_ieth(wr);
3569
3570		wqe += sizeof *ctrl;
3571		size = sizeof *ctrl / 16;
3572
3573		switch (qp->mlx4_ib_qp_type) {
3574		case MLX4_IB_QPT_RC:
3575		case MLX4_IB_QPT_UC:
3576			switch (wr->opcode) {
3577			case IB_WR_ATOMIC_CMP_AND_SWP:
3578			case IB_WR_ATOMIC_FETCH_AND_ADD:
3579			case IB_WR_MASKED_ATOMIC_FETCH_AND_ADD:
3580				set_raddr_seg(wqe, atomic_wr(wr)->remote_addr,
3581					      atomic_wr(wr)->rkey);
3582				wqe  += sizeof (struct mlx4_wqe_raddr_seg);
3583
3584				set_atomic_seg(wqe, atomic_wr(wr));
3585				wqe  += sizeof (struct mlx4_wqe_atomic_seg);
3586
3587				size += (sizeof (struct mlx4_wqe_raddr_seg) +
3588					 sizeof (struct mlx4_wqe_atomic_seg)) / 16;
3589
3590				break;
3591
3592			case IB_WR_MASKED_ATOMIC_CMP_AND_SWP:
3593				set_raddr_seg(wqe, atomic_wr(wr)->remote_addr,
3594					      atomic_wr(wr)->rkey);
3595				wqe  += sizeof (struct mlx4_wqe_raddr_seg);
3596
3597				set_masked_atomic_seg(wqe, atomic_wr(wr));
3598				wqe  += sizeof (struct mlx4_wqe_masked_atomic_seg);
3599
3600				size += (sizeof (struct mlx4_wqe_raddr_seg) +
3601					 sizeof (struct mlx4_wqe_masked_atomic_seg)) / 16;
3602
3603				break;
3604
3605			case IB_WR_RDMA_READ:
3606			case IB_WR_RDMA_WRITE:
3607			case IB_WR_RDMA_WRITE_WITH_IMM:
3608				set_raddr_seg(wqe, rdma_wr(wr)->remote_addr,
3609					      rdma_wr(wr)->rkey);
3610				wqe  += sizeof (struct mlx4_wqe_raddr_seg);
3611				size += sizeof (struct mlx4_wqe_raddr_seg) / 16;
3612				break;
3613
3614			case IB_WR_LOCAL_INV:
3615				ctrl->srcrb_flags |=
3616					cpu_to_be32(MLX4_WQE_CTRL_STRONG_ORDER);
3617				set_local_inv_seg(wqe, wr->ex.invalidate_rkey);
3618				wqe  += sizeof (struct mlx4_wqe_local_inval_seg);
3619				size += sizeof (struct mlx4_wqe_local_inval_seg) / 16;
3620				break;
3621
3622			case IB_WR_REG_MR:
3623				ctrl->srcrb_flags |=
3624					cpu_to_be32(MLX4_WQE_CTRL_STRONG_ORDER);
3625				set_reg_seg(wqe, reg_wr(wr));
3626				wqe  += sizeof(struct mlx4_wqe_fmr_seg);
3627				size += sizeof(struct mlx4_wqe_fmr_seg) / 16;
3628				break;
3629
3630			default:
3631				/* No extra segments required for sends */
3632				break;
3633			}
3634			break;
3635
3636		case MLX4_IB_QPT_TUN_SMI_OWNER:
3637			err = build_sriov_qp0_header(qp, ud_wr(wr), ctrl,
3638						     &seglen);
3639			if (unlikely(err)) {
3640				*bad_wr = wr;
3641				goto out;
3642			}
3643			wqe  += seglen;
3644			size += seglen / 16;
3645			break;
3646		case MLX4_IB_QPT_TUN_SMI:
3647		case MLX4_IB_QPT_TUN_GSI:
3648			/* this is a UD qp used in MAD responses to slaves. */
3649			set_datagram_seg(wqe, ud_wr(wr));
3650			/* set the forced-loopback bit in the data seg av */
3651			*(__be32 *) wqe |= cpu_to_be32(0x80000000);
3652			wqe  += sizeof (struct mlx4_wqe_datagram_seg);
3653			size += sizeof (struct mlx4_wqe_datagram_seg) / 16;
3654			break;
3655		case MLX4_IB_QPT_UD:
3656			set_datagram_seg(wqe, ud_wr(wr));
3657			wqe  += sizeof (struct mlx4_wqe_datagram_seg);
3658			size += sizeof (struct mlx4_wqe_datagram_seg) / 16;
3659
3660			if (wr->opcode == IB_WR_LSO) {
3661				err = build_lso_seg(wqe, ud_wr(wr), qp, &seglen,
3662						&lso_hdr_sz, &blh);
3663				if (unlikely(err)) {
3664					*bad_wr = wr;
3665					goto out;
3666				}
3667				lso_wqe = (__be32 *) wqe;
3668				wqe  += seglen;
3669				size += seglen / 16;
3670			}
3671			break;
3672
3673		case MLX4_IB_QPT_PROXY_SMI_OWNER:
3674			err = build_sriov_qp0_header(qp, ud_wr(wr), ctrl,
3675						     &seglen);
3676			if (unlikely(err)) {
3677				*bad_wr = wr;
3678				goto out;
3679			}
3680			wqe  += seglen;
3681			size += seglen / 16;
3682			/* to start tunnel header on a cache-line boundary */
3683			add_zero_len_inline(wqe);
3684			wqe += 16;
3685			size++;
3686			build_tunnel_header(ud_wr(wr), wqe, &seglen);
3687			wqe  += seglen;
3688			size += seglen / 16;
3689			break;
3690		case MLX4_IB_QPT_PROXY_SMI:
3691		case MLX4_IB_QPT_PROXY_GSI:
3692			/* If we are tunneling special qps, this is a UD qp.
3693			 * In this case we first add a UD segment targeting
3694			 * the tunnel qp, and then add a header with address
3695			 * information */
3696			set_tunnel_datagram_seg(to_mdev(ibqp->device), wqe,
3697						ud_wr(wr),
3698						qp->mlx4_ib_qp_type);
3699			wqe  += sizeof (struct mlx4_wqe_datagram_seg);
3700			size += sizeof (struct mlx4_wqe_datagram_seg) / 16;
3701			build_tunnel_header(ud_wr(wr), wqe, &seglen);
3702			wqe  += seglen;
3703			size += seglen / 16;
3704			break;
3705
3706		case MLX4_IB_QPT_SMI:
3707		case MLX4_IB_QPT_GSI:
3708			err = build_mlx_header(qp, ud_wr(wr), ctrl, &seglen);
3709			if (unlikely(err)) {
3710				*bad_wr = wr;
3711				goto out;
3712			}
3713			wqe  += seglen;
3714			size += seglen / 16;
3715			break;
3716
3717		default:
3718			break;
3719		}
3720
3721		/*
3722		 * Write data segments in reverse order, so as to
3723		 * overwrite cacheline stamp last within each
3724		 * cacheline.  This avoids issues with WQE
3725		 * prefetching.
3726		 */
3727
3728		dseg = wqe;
3729		dseg += wr->num_sge - 1;
3730		size += wr->num_sge * (sizeof (struct mlx4_wqe_data_seg) / 16);
3731
3732		/* Add one more inline data segment for ICRC for MLX sends */
3733		if (unlikely(qp->mlx4_ib_qp_type == MLX4_IB_QPT_SMI ||
3734			     qp->mlx4_ib_qp_type == MLX4_IB_QPT_GSI ||
3735			     qp->mlx4_ib_qp_type &
3736			     (MLX4_IB_QPT_PROXY_SMI_OWNER | MLX4_IB_QPT_TUN_SMI_OWNER))) {
3737			set_mlx_icrc_seg(dseg + 1);
3738			size += sizeof (struct mlx4_wqe_data_seg) / 16;
3739		}
3740
3741		for (i = wr->num_sge - 1; i >= 0; --i, --dseg)
3742			set_data_seg(dseg, wr->sg_list + i);
3743
3744		/*
3745		 * Possibly overwrite stamping in cacheline with LSO
3746		 * segment only after making sure all data segments
3747		 * are written.
3748		 */
3749		wmb();
3750		*lso_wqe = lso_hdr_sz;
3751
3752		ctrl->qpn_vlan.fence_size = (wr->send_flags & IB_SEND_FENCE ?
3753					     MLX4_WQE_CTRL_FENCE : 0) | size;
3754
3755		/*
3756		 * Make sure descriptor is fully written before
3757		 * setting ownership bit (because HW can start
3758		 * executing as soon as we do).
3759		 */
3760		wmb();
3761
3762		if (wr->opcode < 0 || wr->opcode >= ARRAY_SIZE(mlx4_ib_opcode)) {
3763			*bad_wr = wr;
3764			err = -EINVAL;
3765			goto out;
3766		}
3767
3768		ctrl->owner_opcode = mlx4_ib_opcode[wr->opcode] |
3769			(ind & qp->sq.wqe_cnt ? cpu_to_be32(1 << 31) : 0) | blh;
3770
3771		/*
3772		 * We can improve latency by not stamping the last
3773		 * send queue WQE until after ringing the doorbell, so
3774		 * only stamp here if there are still more WQEs to post.
3775		 */
3776		if (wr->next)
3777			stamp_send_wqe(qp, ind + qp->sq_spare_wqes);
3778		ind++;
3779	}
3780
3781out:
3782	if (likely(nreq)) {
3783		qp->sq.head += nreq;
3784
3785		/*
3786		 * Make sure that descriptors are written before
3787		 * doorbell record.
3788		 */
3789		wmb();
3790
3791		writel_relaxed(qp->doorbell_qpn,
3792			to_mdev(ibqp->device)->uar_map + MLX4_SEND_DOORBELL);
3793
3794		stamp_send_wqe(qp, ind + qp->sq_spare_wqes - 1);
3795
3796		qp->sq_next_wqe = ind;
3797	}
3798
3799	spin_unlock_irqrestore(&qp->sq.lock, flags);
3800
3801	return err;
3802}
3803
3804int mlx4_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
3805		      const struct ib_send_wr **bad_wr)
3806{
3807	return _mlx4_ib_post_send(ibqp, wr, bad_wr, false);
3808}
3809
3810static int _mlx4_ib_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr,
3811			      const struct ib_recv_wr **bad_wr, bool drain)
3812{
3813	struct mlx4_ib_qp *qp = to_mqp(ibqp);
3814	struct mlx4_wqe_data_seg *scat;
3815	unsigned long flags;
3816	int err = 0;
3817	int nreq;
3818	int ind;
3819	int max_gs;
3820	int i;
3821	struct mlx4_ib_dev *mdev = to_mdev(ibqp->device);
3822
3823	max_gs = qp->rq.max_gs;
3824	spin_lock_irqsave(&qp->rq.lock, flags);
3825
3826	if (mdev->dev->persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR &&
3827	    !drain) {
3828		err = -EIO;
3829		*bad_wr = wr;
3830		nreq = 0;
3831		goto out;
3832	}
3833
3834	ind = qp->rq.head & (qp->rq.wqe_cnt - 1);
3835
3836	for (nreq = 0; wr; ++nreq, wr = wr->next) {
3837		if (mlx4_wq_overflow(&qp->rq, nreq, qp->ibqp.recv_cq)) {
3838			err = -ENOMEM;
3839			*bad_wr = wr;
3840			goto out;
3841		}
3842
3843		if (unlikely(wr->num_sge > qp->rq.max_gs)) {
3844			err = -EINVAL;
3845			*bad_wr = wr;
3846			goto out;
3847		}
3848
3849		scat = get_recv_wqe(qp, ind);
3850
3851		if (qp->mlx4_ib_qp_type & (MLX4_IB_QPT_PROXY_SMI_OWNER |
3852		    MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI)) {
3853			ib_dma_sync_single_for_device(ibqp->device,
3854						      qp->sqp_proxy_rcv[ind].map,
3855						      sizeof (struct mlx4_ib_proxy_sqp_hdr),
3856						      DMA_FROM_DEVICE);
3857			scat->byte_count =
3858				cpu_to_be32(sizeof (struct mlx4_ib_proxy_sqp_hdr));
3859			/* use dma lkey from upper layer entry */
3860			scat->lkey = cpu_to_be32(wr->sg_list->lkey);
3861			scat->addr = cpu_to_be64(qp->sqp_proxy_rcv[ind].map);
3862			scat++;
3863			max_gs--;
3864		}
3865
3866		for (i = 0; i < wr->num_sge; ++i)
3867			__set_data_seg(scat + i, wr->sg_list + i);
3868
3869		if (i < max_gs) {
3870			scat[i].byte_count = 0;
3871			scat[i].lkey       = cpu_to_be32(MLX4_INVALID_LKEY);
3872			scat[i].addr       = 0;
3873		}
3874
3875		qp->rq.wrid[ind] = wr->wr_id;
3876
3877		ind = (ind + 1) & (qp->rq.wqe_cnt - 1);
3878	}
3879
3880out:
3881	if (likely(nreq)) {
3882		qp->rq.head += nreq;
3883
3884		/*
3885		 * Make sure that descriptors are written before
3886		 * doorbell record.
3887		 */
3888		wmb();
3889
3890		*qp->db.db = cpu_to_be32(qp->rq.head & 0xffff);
3891	}
3892
3893	spin_unlock_irqrestore(&qp->rq.lock, flags);
3894
3895	return err;
3896}
3897
3898int mlx4_ib_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr,
3899		      const struct ib_recv_wr **bad_wr)
3900{
3901	return _mlx4_ib_post_recv(ibqp, wr, bad_wr, false);
3902}
3903
3904static inline enum ib_qp_state to_ib_qp_state(enum mlx4_qp_state mlx4_state)
3905{
3906	switch (mlx4_state) {
3907	case MLX4_QP_STATE_RST:      return IB_QPS_RESET;
3908	case MLX4_QP_STATE_INIT:     return IB_QPS_INIT;
3909	case MLX4_QP_STATE_RTR:      return IB_QPS_RTR;
3910	case MLX4_QP_STATE_RTS:      return IB_QPS_RTS;
3911	case MLX4_QP_STATE_SQ_DRAINING:
3912	case MLX4_QP_STATE_SQD:      return IB_QPS_SQD;
3913	case MLX4_QP_STATE_SQER:     return IB_QPS_SQE;
3914	case MLX4_QP_STATE_ERR:      return IB_QPS_ERR;
3915	default:		     return -1;
3916	}
3917}
3918
3919static inline enum ib_mig_state to_ib_mig_state(int mlx4_mig_state)
3920{
3921	switch (mlx4_mig_state) {
3922	case MLX4_QP_PM_ARMED:		return IB_MIG_ARMED;
3923	case MLX4_QP_PM_REARM:		return IB_MIG_REARM;
3924	case MLX4_QP_PM_MIGRATED:	return IB_MIG_MIGRATED;
3925	default: return -1;
3926	}
3927}
3928
3929static int to_ib_qp_access_flags(int mlx4_flags)
3930{
3931	int ib_flags = 0;
3932
3933	if (mlx4_flags & MLX4_QP_BIT_RRE)
3934		ib_flags |= IB_ACCESS_REMOTE_READ;
3935	if (mlx4_flags & MLX4_QP_BIT_RWE)
3936		ib_flags |= IB_ACCESS_REMOTE_WRITE;
3937	if (mlx4_flags & MLX4_QP_BIT_RAE)
3938		ib_flags |= IB_ACCESS_REMOTE_ATOMIC;
3939
3940	return ib_flags;
3941}
3942
3943static void to_rdma_ah_attr(struct mlx4_ib_dev *ibdev,
3944			    struct rdma_ah_attr *ah_attr,
3945			    struct mlx4_qp_path *path)
3946{
3947	struct mlx4_dev *dev = ibdev->dev;
3948	u8 port_num = path->sched_queue & 0x40 ? 2 : 1;
3949
3950	memset(ah_attr, 0, sizeof(*ah_attr));
3951	if (port_num == 0 || port_num > dev->caps.num_ports)
3952		return;
3953	ah_attr->type = rdma_ah_find_type(&ibdev->ib_dev, port_num);
3954
3955	if (ah_attr->type == RDMA_AH_ATTR_TYPE_ROCE)
3956		rdma_ah_set_sl(ah_attr, ((path->sched_queue >> 3) & 0x7) |
3957			       ((path->sched_queue & 4) << 1));
3958	else
3959		rdma_ah_set_sl(ah_attr, (path->sched_queue >> 2) & 0xf);
3960	rdma_ah_set_port_num(ah_attr, port_num);
3961
3962	rdma_ah_set_dlid(ah_attr, be16_to_cpu(path->rlid));
3963	rdma_ah_set_path_bits(ah_attr, path->grh_mylmc & 0x7f);
3964	rdma_ah_set_static_rate(ah_attr,
3965				path->static_rate ? path->static_rate - 5 : 0);
3966	if (path->grh_mylmc & (1 << 7)) {
3967		rdma_ah_set_grh(ah_attr, NULL,
3968				be32_to_cpu(path->tclass_flowlabel) & 0xfffff,
3969				path->mgid_index,
3970				path->hop_limit,
3971				(be32_to_cpu(path->tclass_flowlabel)
3972				 >> 20) & 0xff);
3973		rdma_ah_set_dgid_raw(ah_attr, path->rgid);
3974	}
3975}
3976
3977int mlx4_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr_mask,
3978		     struct ib_qp_init_attr *qp_init_attr)
3979{
3980	struct mlx4_ib_dev *dev = to_mdev(ibqp->device);
3981	struct mlx4_ib_qp *qp = to_mqp(ibqp);
3982	struct mlx4_qp_context context;
3983	int mlx4_state;
3984	int err = 0;
3985
3986	if (ibqp->rwq_ind_tbl)
3987		return -EOPNOTSUPP;
3988
3989	mutex_lock(&qp->mutex);
3990
3991	if (qp->state == IB_QPS_RESET) {
3992		qp_attr->qp_state = IB_QPS_RESET;
3993		goto done;
3994	}
3995
3996	err = mlx4_qp_query(dev->dev, &qp->mqp, &context);
3997	if (err) {
3998		err = -EINVAL;
3999		goto out;
4000	}
4001
4002	mlx4_state = be32_to_cpu(context.flags) >> 28;
4003
4004	qp->state		     = to_ib_qp_state(mlx4_state);
4005	qp_attr->qp_state	     = qp->state;
4006	qp_attr->path_mtu	     = context.mtu_msgmax >> 5;
4007	qp_attr->path_mig_state	     =
4008		to_ib_mig_state((be32_to_cpu(context.flags) >> 11) & 0x3);
4009	qp_attr->qkey		     = be32_to_cpu(context.qkey);
4010	qp_attr->rq_psn		     = be32_to_cpu(context.rnr_nextrecvpsn) & 0xffffff;
4011	qp_attr->sq_psn		     = be32_to_cpu(context.next_send_psn) & 0xffffff;
4012	qp_attr->dest_qp_num	     = be32_to_cpu(context.remote_qpn) & 0xffffff;
4013	qp_attr->qp_access_flags     =
4014		to_ib_qp_access_flags(be32_to_cpu(context.params2));
4015
4016	if (qp->ibqp.qp_type == IB_QPT_RC || qp->ibqp.qp_type == IB_QPT_UC) {
4017		to_rdma_ah_attr(dev, &qp_attr->ah_attr, &context.pri_path);
4018		to_rdma_ah_attr(dev, &qp_attr->alt_ah_attr, &context.alt_path);
4019		qp_attr->alt_pkey_index = context.alt_path.pkey_index & 0x7f;
4020		qp_attr->alt_port_num	=
4021			rdma_ah_get_port_num(&qp_attr->alt_ah_attr);
4022	}
4023
4024	qp_attr->pkey_index = context.pri_path.pkey_index & 0x7f;
4025	if (qp_attr->qp_state == IB_QPS_INIT)
4026		qp_attr->port_num = qp->port;
4027	else
4028		qp_attr->port_num = context.pri_path.sched_queue & 0x40 ? 2 : 1;
4029
4030	/* qp_attr->en_sqd_async_notify is only applicable in modify qp */
4031	qp_attr->sq_draining = mlx4_state == MLX4_QP_STATE_SQ_DRAINING;
4032
4033	qp_attr->max_rd_atomic = 1 << ((be32_to_cpu(context.params1) >> 21) & 0x7);
4034
4035	qp_attr->max_dest_rd_atomic =
4036		1 << ((be32_to_cpu(context.params2) >> 21) & 0x7);
4037	qp_attr->min_rnr_timer	    =
4038		(be32_to_cpu(context.rnr_nextrecvpsn) >> 24) & 0x1f;
4039	qp_attr->timeout	    = context.pri_path.ackto >> 3;
4040	qp_attr->retry_cnt	    = (be32_to_cpu(context.params1) >> 16) & 0x7;
4041	qp_attr->rnr_retry	    = (be32_to_cpu(context.params1) >> 13) & 0x7;
4042	qp_attr->alt_timeout	    = context.alt_path.ackto >> 3;
4043
4044done:
4045	qp_attr->cur_qp_state	     = qp_attr->qp_state;
4046	qp_attr->cap.max_recv_wr     = qp->rq.wqe_cnt;
4047	qp_attr->cap.max_recv_sge    = qp->rq.max_gs;
4048
4049	if (!ibqp->uobject) {
4050		qp_attr->cap.max_send_wr  = qp->sq.wqe_cnt;
4051		qp_attr->cap.max_send_sge = qp->sq.max_gs;
4052	} else {
4053		qp_attr->cap.max_send_wr  = 0;
4054		qp_attr->cap.max_send_sge = 0;
4055	}
4056
4057	/*
4058	 * We don't support inline sends for kernel QPs (yet), and we
4059	 * don't know what userspace's value should be.
4060	 */
4061	qp_attr->cap.max_inline_data = 0;
4062
4063	qp_init_attr->cap	     = qp_attr->cap;
4064
4065	qp_init_attr->create_flags = 0;
4066	if (qp->flags & MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK)
4067		qp_init_attr->create_flags |= IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK;
4068
4069	if (qp->flags & MLX4_IB_QP_LSO)
4070		qp_init_attr->create_flags |= IB_QP_CREATE_IPOIB_UD_LSO;
4071
4072	if (qp->flags & MLX4_IB_QP_NETIF)
4073		qp_init_attr->create_flags |= IB_QP_CREATE_NETIF_QP;
4074
4075	qp_init_attr->sq_sig_type =
4076		qp->sq_signal_bits == cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE) ?
4077		IB_SIGNAL_ALL_WR : IB_SIGNAL_REQ_WR;
4078
4079out:
4080	mutex_unlock(&qp->mutex);
4081	return err;
4082}
4083
4084struct ib_wq *mlx4_ib_create_wq(struct ib_pd *pd,
4085				struct ib_wq_init_attr *init_attr,
4086				struct ib_udata *udata)
4087{
4088	struct mlx4_dev *dev = to_mdev(pd->device)->dev;
4089	struct ib_qp_init_attr ib_qp_init_attr = {};
4090	struct mlx4_ib_qp *qp;
4091	struct mlx4_ib_create_wq ucmd;
4092	int err, required_cmd_sz;
4093
4094	if (!udata)
4095		return ERR_PTR(-EINVAL);
4096
4097	required_cmd_sz = offsetof(typeof(ucmd), comp_mask) +
4098			  sizeof(ucmd.comp_mask);
4099	if (udata->inlen < required_cmd_sz) {
4100		pr_debug("invalid inlen\n");
4101		return ERR_PTR(-EINVAL);
4102	}
4103
4104	if (udata->inlen > sizeof(ucmd) &&
4105	    !ib_is_udata_cleared(udata, sizeof(ucmd),
4106				 udata->inlen - sizeof(ucmd))) {
4107		pr_debug("inlen is not supported\n");
4108		return ERR_PTR(-EOPNOTSUPP);
4109	}
4110
4111	if (udata->outlen)
4112		return ERR_PTR(-EOPNOTSUPP);
4113
4114	if (init_attr->wq_type != IB_WQT_RQ) {
4115		pr_debug("unsupported wq type %d\n", init_attr->wq_type);
4116		return ERR_PTR(-EOPNOTSUPP);
4117	}
4118
4119	if (init_attr->create_flags & ~IB_WQ_FLAGS_SCATTER_FCS ||
4120	    !(dev->caps.flags & MLX4_DEV_CAP_FLAG_FCS_KEEP)) {
4121		pr_debug("unsupported create_flags %u\n",
4122			 init_attr->create_flags);
4123		return ERR_PTR(-EOPNOTSUPP);
4124	}
4125
4126	qp = kzalloc(sizeof(*qp), GFP_KERNEL);
4127	if (!qp)
4128		return ERR_PTR(-ENOMEM);
4129
4130	mutex_init(&qp->mutex);
4131	qp->pri.vid = 0xFFFF;
4132	qp->alt.vid = 0xFFFF;
4133
4134	ib_qp_init_attr.qp_context = init_attr->wq_context;
4135	ib_qp_init_attr.qp_type = IB_QPT_RAW_PACKET;
4136	ib_qp_init_attr.cap.max_recv_wr = init_attr->max_wr;
4137	ib_qp_init_attr.cap.max_recv_sge = init_attr->max_sge;
4138	ib_qp_init_attr.recv_cq = init_attr->cq;
4139	ib_qp_init_attr.send_cq = ib_qp_init_attr.recv_cq; /* Dummy CQ */
4140
4141	if (init_attr->create_flags & IB_WQ_FLAGS_SCATTER_FCS)
4142		ib_qp_init_attr.create_flags |= IB_QP_CREATE_SCATTER_FCS;
4143
4144	err = create_rq(pd, &ib_qp_init_attr, udata, qp);
4145	if (err) {
4146		kfree(qp);
4147		return ERR_PTR(err);
4148	}
4149
4150	qp->ibwq.event_handler = init_attr->event_handler;
4151	qp->ibwq.wq_num = qp->mqp.qpn;
4152	qp->ibwq.state = IB_WQS_RESET;
4153
4154	return &qp->ibwq;
4155}
4156
4157static int ib_wq2qp_state(enum ib_wq_state state)
4158{
4159	switch (state) {
4160	case IB_WQS_RESET:
4161		return IB_QPS_RESET;
4162	case IB_WQS_RDY:
4163		return IB_QPS_RTR;
4164	default:
4165		return IB_QPS_ERR;
4166	}
4167}
4168
4169static int _mlx4_ib_modify_wq(struct ib_wq *ibwq, enum ib_wq_state new_state,
4170			      struct ib_udata *udata)
4171{
4172	struct mlx4_ib_qp *qp = to_mqp((struct ib_qp *)ibwq);
4173	enum ib_qp_state qp_cur_state;
4174	enum ib_qp_state qp_new_state;
4175	int attr_mask;
4176	int err;
4177
4178	/* ib_qp.state represents the WQ HW state while ib_wq.state represents
4179	 * the WQ logic state.
4180	 */
4181	qp_cur_state = qp->state;
4182	qp_new_state = ib_wq2qp_state(new_state);
4183
4184	if (ib_wq2qp_state(new_state) == qp_cur_state)
4185		return 0;
4186
4187	if (new_state == IB_WQS_RDY) {
4188		struct ib_qp_attr attr = {};
4189
4190		attr.port_num = qp->port;
4191		attr_mask = IB_QP_PORT;
4192
4193		err = __mlx4_ib_modify_qp(ibwq, MLX4_IB_RWQ_SRC, &attr,
4194					  attr_mask, IB_QPS_RESET, IB_QPS_INIT,
4195					  udata);
4196		if (err) {
4197			pr_debug("WQN=0x%06x failed to apply RST->INIT on the HW QP\n",
4198				 ibwq->wq_num);
4199			return err;
4200		}
4201
4202		qp_cur_state = IB_QPS_INIT;
4203	}
4204
4205	attr_mask = 0;
4206	err = __mlx4_ib_modify_qp(ibwq, MLX4_IB_RWQ_SRC, NULL, attr_mask,
4207				  qp_cur_state,  qp_new_state, udata);
4208
4209	if (err && (qp_cur_state == IB_QPS_INIT)) {
4210		qp_new_state = IB_QPS_RESET;
4211		if (__mlx4_ib_modify_qp(ibwq, MLX4_IB_RWQ_SRC, NULL,
4212					attr_mask, IB_QPS_INIT, IB_QPS_RESET,
4213					udata)) {
4214			pr_warn("WQN=0x%06x failed with reverting HW's resources failure\n",
4215				ibwq->wq_num);
4216			qp_new_state = IB_QPS_INIT;
4217		}
4218	}
4219
4220	qp->state = qp_new_state;
4221
4222	return err;
4223}
4224
4225int mlx4_ib_modify_wq(struct ib_wq *ibwq, struct ib_wq_attr *wq_attr,
4226		      u32 wq_attr_mask, struct ib_udata *udata)
4227{
4228	struct mlx4_ib_qp *qp = to_mqp((struct ib_qp *)ibwq);
4229	struct mlx4_ib_modify_wq ucmd = {};
4230	size_t required_cmd_sz;
4231	enum ib_wq_state cur_state, new_state;
4232	int err = 0;
4233
4234	required_cmd_sz = offsetof(typeof(ucmd), reserved) +
4235				   sizeof(ucmd.reserved);
4236	if (udata->inlen < required_cmd_sz)
4237		return -EINVAL;
4238
4239	if (udata->inlen > sizeof(ucmd) &&
4240	    !ib_is_udata_cleared(udata, sizeof(ucmd),
4241				 udata->inlen - sizeof(ucmd)))
4242		return -EOPNOTSUPP;
4243
4244	if (ib_copy_from_udata(&ucmd, udata, min(sizeof(ucmd), udata->inlen)))
4245		return -EFAULT;
4246
4247	if (ucmd.comp_mask || ucmd.reserved)
4248		return -EOPNOTSUPP;
4249
4250	if (wq_attr_mask & IB_WQ_FLAGS)
4251		return -EOPNOTSUPP;
4252
4253	cur_state = wq_attr->curr_wq_state;
4254	new_state = wq_attr->wq_state;
4255
4256	if ((new_state == IB_WQS_RDY) && (cur_state == IB_WQS_ERR))
4257		return -EINVAL;
4258
4259	if ((new_state == IB_WQS_ERR) && (cur_state == IB_WQS_RESET))
4260		return -EINVAL;
4261
4262	/* Need to protect against the parent RSS which also may modify WQ
4263	 * state.
4264	 */
4265	mutex_lock(&qp->mutex);
4266
4267	/* Can update HW state only if a RSS QP has already associated to this
4268	 * WQ, so we can apply its port on the WQ.
4269	 */
4270	if (qp->rss_usecnt)
4271		err = _mlx4_ib_modify_wq(ibwq, new_state, udata);
4272
4273	if (!err)
4274		ibwq->state = new_state;
4275
4276	mutex_unlock(&qp->mutex);
4277
4278	return err;
4279}
4280
4281int mlx4_ib_destroy_wq(struct ib_wq *ibwq, struct ib_udata *udata)
4282{
4283	struct mlx4_ib_dev *dev = to_mdev(ibwq->device);
4284	struct mlx4_ib_qp *qp = to_mqp((struct ib_qp *)ibwq);
4285
4286	if (qp->counter_index)
4287		mlx4_ib_free_qp_counter(dev, qp);
4288
4289	destroy_qp_common(dev, qp, MLX4_IB_RWQ_SRC, udata);
4290
4291	kfree(qp);
4292	return 0;
4293}
4294
4295int mlx4_ib_create_rwq_ind_table(struct ib_rwq_ind_table *rwq_ind_table,
4296				 struct ib_rwq_ind_table_init_attr *init_attr,
4297				 struct ib_udata *udata)
4298{
4299	struct mlx4_ib_create_rwq_ind_tbl_resp resp = {};
4300	unsigned int ind_tbl_size = 1 << init_attr->log_ind_tbl_size;
4301	struct ib_device *device = rwq_ind_table->device;
4302	unsigned int base_wqn;
4303	size_t min_resp_len;
4304	int i, err = 0;
4305
4306	if (udata->inlen > 0 &&
4307	    !ib_is_udata_cleared(udata, 0,
4308				 udata->inlen))
4309		return -EOPNOTSUPP;
4310
4311	min_resp_len = offsetof(typeof(resp), reserved) + sizeof(resp.reserved);
4312	if (udata->outlen && udata->outlen < min_resp_len)
4313		return -EINVAL;
4314
4315	if (ind_tbl_size >
4316	    device->attrs.rss_caps.max_rwq_indirection_table_size) {
4317		pr_debug("log_ind_tbl_size = %d is bigger than supported = %d\n",
4318			 ind_tbl_size,
4319			 device->attrs.rss_caps.max_rwq_indirection_table_size);
4320		return -EINVAL;
4321	}
4322
4323	base_wqn = init_attr->ind_tbl[0]->wq_num;
4324
4325	if (base_wqn % ind_tbl_size) {
4326		pr_debug("WQN=0x%x isn't aligned with indirection table size\n",
4327			 base_wqn);
4328		return -EINVAL;
4329	}
4330
4331	for (i = 1; i < ind_tbl_size; i++) {
4332		if (++base_wqn != init_attr->ind_tbl[i]->wq_num) {
4333			pr_debug("indirection table's WQNs aren't consecutive\n");
4334			return -EINVAL;
4335		}
4336	}
4337
4338	if (udata->outlen) {
4339		resp.response_length = offsetof(typeof(resp), response_length) +
4340					sizeof(resp.response_length);
4341		err = ib_copy_to_udata(udata, &resp, resp.response_length);
4342	}
4343
4344	return err;
4345}
4346
4347struct mlx4_ib_drain_cqe {
4348	struct ib_cqe cqe;
4349	struct completion done;
4350};
4351
4352static void mlx4_ib_drain_qp_done(struct ib_cq *cq, struct ib_wc *wc)
4353{
4354	struct mlx4_ib_drain_cqe *cqe = container_of(wc->wr_cqe,
4355						     struct mlx4_ib_drain_cqe,
4356						     cqe);
4357
4358	complete(&cqe->done);
4359}
4360
4361/* This function returns only once the drained WR was completed */
4362static void handle_drain_completion(struct ib_cq *cq,
4363				    struct mlx4_ib_drain_cqe *sdrain,
4364				    struct mlx4_ib_dev *dev)
4365{
4366	struct mlx4_dev *mdev = dev->dev;
4367
4368	if (cq->poll_ctx == IB_POLL_DIRECT) {
4369		while (wait_for_completion_timeout(&sdrain->done, HZ / 10) <= 0)
4370			ib_process_cq_direct(cq, -1);
4371		return;
4372	}
4373
4374	if (mdev->persist->state == MLX4_DEVICE_STATE_INTERNAL_ERROR) {
4375		struct mlx4_ib_cq *mcq = to_mcq(cq);
4376		bool triggered = false;
4377		unsigned long flags;
4378
4379		spin_lock_irqsave(&dev->reset_flow_resource_lock, flags);
4380		/* Make sure that the CQ handler won't run if wasn't run yet */
4381		if (!mcq->mcq.reset_notify_added)
4382			mcq->mcq.reset_notify_added = 1;
4383		else
4384			triggered = true;
4385		spin_unlock_irqrestore(&dev->reset_flow_resource_lock, flags);
4386
4387		if (triggered) {
4388			/* Wait for any scheduled/running task to be ended */
4389			switch (cq->poll_ctx) {
4390			case IB_POLL_SOFTIRQ:
4391				irq_poll_disable(&cq->iop);
4392				irq_poll_enable(&cq->iop);
4393				break;
4394			case IB_POLL_WORKQUEUE:
4395				cancel_work_sync(&cq->work);
4396				break;
4397			default:
4398				WARN_ON_ONCE(1);
4399			}
4400		}
4401
4402		/* Run the CQ handler - this makes sure that the drain WR will
4403		 * be processed if wasn't processed yet.
4404		 */
4405		mcq->mcq.comp(&mcq->mcq);
4406	}
4407
4408	wait_for_completion(&sdrain->done);
4409}
4410
4411void mlx4_ib_drain_sq(struct ib_qp *qp)
4412{
4413	struct ib_cq *cq = qp->send_cq;
4414	struct ib_qp_attr attr = { .qp_state = IB_QPS_ERR };
4415	struct mlx4_ib_drain_cqe sdrain;
4416	const struct ib_send_wr *bad_swr;
4417	struct ib_rdma_wr swr = {
4418		.wr = {
4419			.next = NULL,
4420			{ .wr_cqe	= &sdrain.cqe, },
4421			.opcode	= IB_WR_RDMA_WRITE,
4422		},
4423	};
4424	int ret;
4425	struct mlx4_ib_dev *dev = to_mdev(qp->device);
4426	struct mlx4_dev *mdev = dev->dev;
4427
4428	ret = ib_modify_qp(qp, &attr, IB_QP_STATE);
4429	if (ret && mdev->persist->state != MLX4_DEVICE_STATE_INTERNAL_ERROR) {
4430		WARN_ONCE(ret, "failed to drain send queue: %d\n", ret);
4431		return;
4432	}
4433
4434	sdrain.cqe.done = mlx4_ib_drain_qp_done;
4435	init_completion(&sdrain.done);
4436
4437	ret = _mlx4_ib_post_send(qp, &swr.wr, &bad_swr, true);
4438	if (ret) {
4439		WARN_ONCE(ret, "failed to drain send queue: %d\n", ret);
4440		return;
4441	}
4442
4443	handle_drain_completion(cq, &sdrain, dev);
4444}
4445
4446void mlx4_ib_drain_rq(struct ib_qp *qp)
4447{
4448	struct ib_cq *cq = qp->recv_cq;
4449	struct ib_qp_attr attr = { .qp_state = IB_QPS_ERR };
4450	struct mlx4_ib_drain_cqe rdrain;
4451	struct ib_recv_wr rwr = {};
4452	const struct ib_recv_wr *bad_rwr;
4453	int ret;
4454	struct mlx4_ib_dev *dev = to_mdev(qp->device);
4455	struct mlx4_dev *mdev = dev->dev;
4456
4457	ret = ib_modify_qp(qp, &attr, IB_QP_STATE);
4458	if (ret && mdev->persist->state != MLX4_DEVICE_STATE_INTERNAL_ERROR) {
4459		WARN_ONCE(ret, "failed to drain recv queue: %d\n", ret);
4460		return;
4461	}
4462
4463	rwr.wr_cqe = &rdrain.cqe;
4464	rdrain.cqe.done = mlx4_ib_drain_qp_done;
4465	init_completion(&rdrain.done);
4466
4467	ret = _mlx4_ib_post_recv(qp, &rwr, &bad_rwr, true);
4468	if (ret) {
4469		WARN_ONCE(ret, "failed to drain recv queue: %d\n", ret);
4470		return;
4471	}
4472
4473	handle_drain_completion(cq, &rdrain, dev);
4474}
4475