1/*
2 * Copyright (c) 2016 Hisilicon Limited.
3 *
4 * This software is available to you under a choice of one of two
5 * licenses.  You may choose to be licensed under the terms of the GNU
6 * General Public License (GPL) Version 2, available from the file
7 * COPYING in the main directory of this source tree, or the
8 * OpenIB.org BSD license below:
9 *
10 *     Redistribution and use in source and binary forms, with or
11 *     without modification, are permitted provided that the following
12 *     conditions are met:
13 *
14 *      - Redistributions of source code must retain the above
15 *        copyright notice, this list of conditions and the following
16 *        disclaimer.
17 *
18 *      - Redistributions in binary form must reproduce the above
19 *        copyright notice, this list of conditions and the following
20 *        disclaimer in the documentation and/or other materials
21 *        provided with the distribution.
22 *
23 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
24 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
25 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
26 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
27 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
28 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
29 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
30 * SOFTWARE.
31 */
32
33#include <linux/platform_device.h>
34#include <rdma/ib_umem.h>
35#include <rdma/uverbs_ioctl.h>
36#include "hns_roce_device.h"
37#include "hns_roce_cmd.h"
38#include "hns_roce_hem.h"
39#include <rdma/hns-abi.h>
40#include "hns_roce_common.h"
41
42static int alloc_cqc(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq)
43{
44	struct ib_device *ibdev = &hr_dev->ib_dev;
45	struct hns_roce_cmd_mailbox *mailbox;
46	struct hns_roce_cq_table *cq_table;
47	u64 mtts[MTT_MIN_COUNT] = { 0 };
48	dma_addr_t dma_handle;
49	int ret;
50
51	ret = hns_roce_mtr_find(hr_dev, &hr_cq->mtr, 0, mtts, ARRAY_SIZE(mtts),
52				&dma_handle);
53	if (!ret) {
54		ibdev_err(ibdev, "failed to find CQ mtr, ret = %d.\n", ret);
55		return -EINVAL;
56	}
57
58	cq_table = &hr_dev->cq_table;
59	ret = hns_roce_bitmap_alloc(&cq_table->bitmap, &hr_cq->cqn);
60	if (ret) {
61		ibdev_err(ibdev, "failed to alloc CQ bitmap, ret = %d.\n", ret);
62		return ret;
63	}
64
65	/* Get CQC memory HEM(Hardware Entry Memory) table */
66	ret = hns_roce_table_get(hr_dev, &cq_table->table, hr_cq->cqn);
67	if (ret) {
68		ibdev_err(ibdev, "failed to get CQ(0x%lx) context, ret = %d.\n",
69			  hr_cq->cqn, ret);
70		goto err_out;
71	}
72
73	ret = xa_err(xa_store(&cq_table->array, hr_cq->cqn, hr_cq, GFP_KERNEL));
74	if (ret) {
75		ibdev_err(ibdev, "failed to xa_store CQ, ret = %d.\n", ret);
76		goto err_put;
77	}
78
79	/* Allocate mailbox memory */
80	mailbox = hns_roce_alloc_cmd_mailbox(hr_dev);
81	if (IS_ERR(mailbox)) {
82		ret = PTR_ERR(mailbox);
83		goto err_xa;
84	}
85
86	hr_dev->hw->write_cqc(hr_dev, hr_cq, mailbox->buf, mtts, dma_handle);
87
88	/* Send mailbox to hw */
89	ret = hns_roce_cmd_mbox(hr_dev, mailbox->dma, 0, hr_cq->cqn, 0,
90			HNS_ROCE_CMD_CREATE_CQC, HNS_ROCE_CMD_TIMEOUT_MSECS);
91	hns_roce_free_cmd_mailbox(hr_dev, mailbox);
92	if (ret) {
93		ibdev_err(ibdev,
94			  "failed to send create cmd for CQ(0x%lx), ret = %d.\n",
95			  hr_cq->cqn, ret);
96		goto err_xa;
97	}
98
99	hr_cq->cons_index = 0;
100	hr_cq->arm_sn = 1;
101
102	atomic_set(&hr_cq->refcount, 1);
103	init_completion(&hr_cq->free);
104
105	return 0;
106
107err_xa:
108	xa_erase(&cq_table->array, hr_cq->cqn);
109
110err_put:
111	hns_roce_table_put(hr_dev, &cq_table->table, hr_cq->cqn);
112
113err_out:
114	hns_roce_bitmap_free(&cq_table->bitmap, hr_cq->cqn, BITMAP_NO_RR);
115	return ret;
116}
117
118static void free_cqc(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq)
119{
120	struct hns_roce_cq_table *cq_table = &hr_dev->cq_table;
121	struct device *dev = hr_dev->dev;
122	int ret;
123
124	ret = hns_roce_cmd_mbox(hr_dev, 0, 0, hr_cq->cqn, 1,
125				HNS_ROCE_CMD_DESTROY_CQC,
126				HNS_ROCE_CMD_TIMEOUT_MSECS);
127	if (ret)
128		dev_err(dev, "DESTROY_CQ failed (%d) for CQN %06lx\n", ret,
129			hr_cq->cqn);
130
131	xa_erase(&cq_table->array, hr_cq->cqn);
132
133	/* Waiting interrupt process procedure carried out */
134	synchronize_irq(hr_dev->eq_table.eq[hr_cq->vector].irq);
135
136	/* wait for all interrupt processed */
137	if (atomic_dec_and_test(&hr_cq->refcount))
138		complete(&hr_cq->free);
139	wait_for_completion(&hr_cq->free);
140
141	hns_roce_table_put(hr_dev, &cq_table->table, hr_cq->cqn);
142	hns_roce_bitmap_free(&cq_table->bitmap, hr_cq->cqn, BITMAP_NO_RR);
143}
144
145static int alloc_cq_buf(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq,
146			struct ib_udata *udata, unsigned long addr)
147{
148	struct ib_device *ibdev = &hr_dev->ib_dev;
149	struct hns_roce_buf_attr buf_attr = {};
150	int ret;
151
152	buf_attr.page_shift = hr_dev->caps.cqe_buf_pg_sz + HNS_HW_PAGE_SHIFT;
153	buf_attr.region[0].size = hr_cq->cq_depth * hr_cq->cqe_size;
154	buf_attr.region[0].hopnum = hr_dev->caps.cqe_hop_num;
155	buf_attr.region_count = 1;
156	buf_attr.fixed_page = true;
157
158	ret = hns_roce_mtr_create(hr_dev, &hr_cq->mtr, &buf_attr,
159				  hr_dev->caps.cqe_ba_pg_sz + HNS_HW_PAGE_SHIFT,
160				  udata, addr);
161	if (ret)
162		ibdev_err(ibdev, "failed to alloc CQ mtr, ret = %d.\n", ret);
163
164	return ret;
165}
166
167static void free_cq_buf(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq)
168{
169	hns_roce_mtr_destroy(hr_dev, &hr_cq->mtr);
170}
171
172static int alloc_cq_db(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq,
173		       struct ib_udata *udata, unsigned long addr,
174		       struct hns_roce_ib_create_cq_resp *resp)
175{
176	bool has_db = hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_RECORD_DB;
177	struct hns_roce_ucontext *uctx;
178	int err;
179
180	if (udata) {
181		if (has_db &&
182		    udata->outlen >= offsetofend(typeof(*resp), cap_flags)) {
183			uctx = rdma_udata_to_drv_context(udata,
184					struct hns_roce_ucontext, ibucontext);
185			err = hns_roce_db_map_user(uctx, udata, addr,
186						   &hr_cq->db);
187			if (err)
188				return err;
189			hr_cq->flags |= HNS_ROCE_CQ_FLAG_RECORD_DB;
190			resp->cap_flags |= HNS_ROCE_CQ_FLAG_RECORD_DB;
191		}
192	} else {
193		if (has_db) {
194			err = hns_roce_alloc_db(hr_dev, &hr_cq->db, 1);
195			if (err)
196				return err;
197			hr_cq->set_ci_db = hr_cq->db.db_record;
198			*hr_cq->set_ci_db = 0;
199			hr_cq->flags |= HNS_ROCE_CQ_FLAG_RECORD_DB;
200		}
201		hr_cq->cq_db_l = hr_dev->reg_base + hr_dev->odb_offset +
202				 DB_REG_OFFSET * hr_dev->priv_uar.index;
203	}
204
205	return 0;
206}
207
208static void free_cq_db(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq,
209		       struct ib_udata *udata)
210{
211	struct hns_roce_ucontext *uctx;
212
213	if (!(hr_cq->flags & HNS_ROCE_CQ_FLAG_RECORD_DB))
214		return;
215
216	hr_cq->flags &= ~HNS_ROCE_CQ_FLAG_RECORD_DB;
217	if (udata) {
218		uctx = rdma_udata_to_drv_context(udata,
219						 struct hns_roce_ucontext,
220						 ibucontext);
221		hns_roce_db_unmap_user(uctx, &hr_cq->db);
222	} else {
223		hns_roce_free_db(hr_dev, &hr_cq->db);
224	}
225}
226
227static void set_cqe_size(struct hns_roce_cq *hr_cq, struct ib_udata *udata,
228			 struct hns_roce_ib_create_cq *ucmd)
229{
230	struct hns_roce_dev *hr_dev = to_hr_dev(hr_cq->ib_cq.device);
231
232	if (udata) {
233		if (udata->inlen >= offsetofend(typeof(*ucmd), cqe_size))
234			hr_cq->cqe_size = ucmd->cqe_size;
235		else
236			hr_cq->cqe_size = HNS_ROCE_V2_CQE_SIZE;
237	} else {
238		hr_cq->cqe_size = hr_dev->caps.cqe_sz;
239	}
240}
241
242int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr,
243		       struct ib_udata *udata)
244{
245	struct hns_roce_dev *hr_dev = to_hr_dev(ib_cq->device);
246	struct hns_roce_ib_create_cq_resp resp = {};
247	struct hns_roce_cq *hr_cq = to_hr_cq(ib_cq);
248	struct ib_device *ibdev = &hr_dev->ib_dev;
249	struct hns_roce_ib_create_cq ucmd = {};
250	int vector = attr->comp_vector;
251	u32 cq_entries = attr->cqe;
252	int ret;
253
254	if (cq_entries < 1 || cq_entries > hr_dev->caps.max_cqes) {
255		ibdev_err(ibdev, "failed to check CQ count %u, max = %u.\n",
256			  cq_entries, hr_dev->caps.max_cqes);
257		return -EINVAL;
258	}
259
260	if (vector >= hr_dev->caps.num_comp_vectors) {
261		ibdev_err(ibdev, "failed to check CQ vector = %d, max = %d.\n",
262			  vector, hr_dev->caps.num_comp_vectors);
263		return -EINVAL;
264	}
265
266	cq_entries = max(cq_entries, hr_dev->caps.min_cqes);
267	cq_entries = roundup_pow_of_two(cq_entries);
268	hr_cq->ib_cq.cqe = cq_entries - 1; /* used as cqe index */
269	hr_cq->cq_depth = cq_entries;
270	hr_cq->vector = vector;
271	spin_lock_init(&hr_cq->lock);
272	INIT_LIST_HEAD(&hr_cq->sq_list);
273	INIT_LIST_HEAD(&hr_cq->rq_list);
274
275	if (udata) {
276		ret = ib_copy_from_udata(&ucmd, udata,
277					 min(udata->inlen, sizeof(ucmd)));
278		if (ret) {
279			ibdev_err(ibdev, "failed to copy CQ udata, ret = %d.\n",
280				  ret);
281			return ret;
282		}
283	}
284
285	set_cqe_size(hr_cq, udata, &ucmd);
286
287	ret = alloc_cq_buf(hr_dev, hr_cq, udata, ucmd.buf_addr);
288	if (ret) {
289		ibdev_err(ibdev, "failed to alloc CQ buf, ret = %d.\n", ret);
290		return ret;
291	}
292
293	ret = alloc_cq_db(hr_dev, hr_cq, udata, ucmd.db_addr, &resp);
294	if (ret) {
295		ibdev_err(ibdev, "failed to alloc CQ db, ret = %d.\n", ret);
296		goto err_cq_buf;
297	}
298
299	ret = alloc_cqc(hr_dev, hr_cq);
300	if (ret) {
301		ibdev_err(ibdev,
302			  "failed to alloc CQ context, ret = %d.\n", ret);
303		goto err_cq_db;
304	}
305
306	/*
307	 * For the QP created by kernel space, tptr value should be initialized
308	 * to zero; For the QP created by user space, it will cause synchronous
309	 * problems if tptr is set to zero here, so we initialize it in user
310	 * space.
311	 */
312	if (!udata && hr_cq->tptr_addr)
313		*hr_cq->tptr_addr = 0;
314
315	if (udata) {
316		resp.cqn = hr_cq->cqn;
317		ret = ib_copy_to_udata(udata, &resp,
318				       min(udata->outlen, sizeof(resp)));
319		if (ret)
320			goto err_cqc;
321	}
322
323	return 0;
324
325err_cqc:
326	free_cqc(hr_dev, hr_cq);
327err_cq_db:
328	free_cq_db(hr_dev, hr_cq, udata);
329err_cq_buf:
330	free_cq_buf(hr_dev, hr_cq);
331	return ret;
332}
333
334int hns_roce_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
335{
336	struct hns_roce_dev *hr_dev = to_hr_dev(ib_cq->device);
337	struct hns_roce_cq *hr_cq = to_hr_cq(ib_cq);
338
339	if (hr_dev->hw->destroy_cq)
340		hr_dev->hw->destroy_cq(ib_cq, udata);
341
342	free_cq_buf(hr_dev, hr_cq);
343	free_cq_db(hr_dev, hr_cq, udata);
344	free_cqc(hr_dev, hr_cq);
345	return 0;
346}
347
348void hns_roce_cq_completion(struct hns_roce_dev *hr_dev, u32 cqn)
349{
350	struct hns_roce_cq *hr_cq;
351	struct ib_cq *ibcq;
352
353	hr_cq = xa_load(&hr_dev->cq_table.array,
354			cqn & (hr_dev->caps.num_cqs - 1));
355	if (!hr_cq) {
356		dev_warn(hr_dev->dev, "Completion event for bogus CQ 0x%06x\n",
357			 cqn);
358		return;
359	}
360
361	++hr_cq->arm_sn;
362	ibcq = &hr_cq->ib_cq;
363	if (ibcq->comp_handler)
364		ibcq->comp_handler(ibcq, ibcq->cq_context);
365}
366
367void hns_roce_cq_event(struct hns_roce_dev *hr_dev, u32 cqn, int event_type)
368{
369	struct device *dev = hr_dev->dev;
370	struct hns_roce_cq *hr_cq;
371	struct ib_event event;
372	struct ib_cq *ibcq;
373
374	hr_cq = xa_load(&hr_dev->cq_table.array,
375			cqn & (hr_dev->caps.num_cqs - 1));
376	if (!hr_cq) {
377		dev_warn(dev, "Async event for bogus CQ 0x%06x\n", cqn);
378		return;
379	}
380
381	if (event_type != HNS_ROCE_EVENT_TYPE_CQ_ID_INVALID &&
382	    event_type != HNS_ROCE_EVENT_TYPE_CQ_ACCESS_ERROR &&
383	    event_type != HNS_ROCE_EVENT_TYPE_CQ_OVERFLOW) {
384		dev_err(dev, "Unexpected event type 0x%x on CQ 0x%06x\n",
385			event_type, cqn);
386		return;
387	}
388
389	atomic_inc(&hr_cq->refcount);
390
391	ibcq = &hr_cq->ib_cq;
392	if (ibcq->event_handler) {
393		event.device = ibcq->device;
394		event.element.cq = ibcq;
395		event.event = IB_EVENT_CQ_ERR;
396		ibcq->event_handler(&event, ibcq->cq_context);
397	}
398
399	if (atomic_dec_and_test(&hr_cq->refcount))
400		complete(&hr_cq->free);
401}
402
403int hns_roce_init_cq_table(struct hns_roce_dev *hr_dev)
404{
405	struct hns_roce_cq_table *cq_table = &hr_dev->cq_table;
406
407	xa_init(&cq_table->array);
408
409	return hns_roce_bitmap_init(&cq_table->bitmap, hr_dev->caps.num_cqs,
410				    hr_dev->caps.num_cqs - 1,
411				    hr_dev->caps.reserved_cqs, 0);
412}
413
414void hns_roce_cleanup_cq_table(struct hns_roce_dev *hr_dev)
415{
416	hns_roce_bitmap_cleanup(&hr_dev->cq_table.bitmap);
417}
418