1/*
2 * Copyright (c) 2012-2016 VMware, Inc.  All rights reserved.
3 *
4 * This program is free software; you can redistribute it and/or
5 * modify it under the terms of EITHER the GNU General Public License
6 * version 2 as published by the Free Software Foundation or the BSD
7 * 2-Clause License. This program is distributed in the hope that it
8 * will be useful, but WITHOUT ANY WARRANTY; WITHOUT EVEN THE IMPLIED
9 * WARRANTY OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE.
10 * See the GNU General Public License version 2 for more details at
11 * http://www.gnu.org/licenses/old-licenses/gpl-2.0.en.html.
12 *
13 * You should have received a copy of the GNU General Public License
14 * along with this program available in the file COPYING in the main
15 * directory of this source tree.
16 *
17 * The BSD 2-Clause License
18 *
19 *     Redistribution and use in source and binary forms, with or
20 *     without modification, are permitted provided that the following
21 *     conditions are met:
22 *
23 *      - Redistributions of source code must retain the above
24 *        copyright notice, this list of conditions and the following
25 *        disclaimer.
26 *
27 *      - Redistributions in binary form must reproduce the above
28 *        copyright notice, this list of conditions and the following
29 *        disclaimer in the documentation and/or other materials
30 *        provided with the distribution.
31 *
32 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
33 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
34 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
35 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
36 * COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT,
37 * INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
38 * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
39 * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
40 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
41 * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
42 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
43 * OF THE POSSIBILITY OF SUCH DAMAGE.
44 */
45
46#include <asm/page.h>
47#include <linux/io.h>
48#include <linux/wait.h>
49#include <rdma/ib_addr.h>
50#include <rdma/ib_smi.h>
51#include <rdma/ib_user_verbs.h>
52#include <rdma/uverbs_ioctl.h>
53
54#include "pvrdma.h"
55
56/**
57 * pvrdma_req_notify_cq - request notification for a completion queue
58 * @ibcq: the completion queue
59 * @notify_flags: notification flags
60 *
61 * @return: 0 for success.
62 */
63int pvrdma_req_notify_cq(struct ib_cq *ibcq,
64			 enum ib_cq_notify_flags notify_flags)
65{
66	struct pvrdma_dev *dev = to_vdev(ibcq->device);
67	struct pvrdma_cq *cq = to_vcq(ibcq);
68	u32 val = cq->cq_handle;
69	unsigned long flags;
70	int has_data = 0;
71
72	val |= (notify_flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED ?
73		PVRDMA_UAR_CQ_ARM_SOL : PVRDMA_UAR_CQ_ARM;
74
75	spin_lock_irqsave(&cq->cq_lock, flags);
76
77	pvrdma_write_uar_cq(dev, val);
78
79	if (notify_flags & IB_CQ_REPORT_MISSED_EVENTS) {
80		unsigned int head;
81
82		has_data = pvrdma_idx_ring_has_data(&cq->ring_state->rx,
83						    cq->ibcq.cqe, &head);
84		if (unlikely(has_data == PVRDMA_INVALID_IDX))
85			dev_err(&dev->pdev->dev, "CQ ring state invalid\n");
86	}
87
88	spin_unlock_irqrestore(&cq->cq_lock, flags);
89
90	return has_data;
91}
92
93/**
94 * pvrdma_create_cq - create completion queue
95 * @ibcq: Allocated CQ
96 * @attr: completion queue attributes
97 * @udata: user data
98 *
99 * @return: 0 on success
100 */
101int pvrdma_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
102		     struct ib_udata *udata)
103{
104	struct ib_device *ibdev = ibcq->device;
105	int entries = attr->cqe;
106	struct pvrdma_dev *dev = to_vdev(ibdev);
107	struct pvrdma_cq *cq = to_vcq(ibcq);
108	int ret;
109	int npages;
110	unsigned long flags;
111	union pvrdma_cmd_req req;
112	union pvrdma_cmd_resp rsp;
113	struct pvrdma_cmd_create_cq *cmd = &req.create_cq;
114	struct pvrdma_cmd_create_cq_resp *resp = &rsp.create_cq_resp;
115	struct pvrdma_create_cq_resp cq_resp = {};
116	struct pvrdma_create_cq ucmd;
117	struct pvrdma_ucontext *context = rdma_udata_to_drv_context(
118		udata, struct pvrdma_ucontext, ibucontext);
119
120	BUILD_BUG_ON(sizeof(struct pvrdma_cqe) != 64);
121
122	entries = roundup_pow_of_two(entries);
123	if (entries < 1 || entries > dev->dsr->caps.max_cqe)
124		return -EINVAL;
125
126	if (!atomic_add_unless(&dev->num_cqs, 1, dev->dsr->caps.max_cq))
127		return -ENOMEM;
128
129	cq->ibcq.cqe = entries;
130	cq->is_kernel = !udata;
131
132	if (!cq->is_kernel) {
133		if (ib_copy_from_udata(&ucmd, udata, sizeof(ucmd))) {
134			ret = -EFAULT;
135			goto err_cq;
136		}
137
138		cq->umem = ib_umem_get(ibdev, ucmd.buf_addr, ucmd.buf_size,
139				       IB_ACCESS_LOCAL_WRITE);
140		if (IS_ERR(cq->umem)) {
141			ret = PTR_ERR(cq->umem);
142			goto err_cq;
143		}
144
145		npages = ib_umem_num_dma_blocks(cq->umem, PAGE_SIZE);
146	} else {
147		/* One extra page for shared ring state */
148		npages = 1 + (entries * sizeof(struct pvrdma_cqe) +
149			      PAGE_SIZE - 1) / PAGE_SIZE;
150
151		/* Skip header page. */
152		cq->offset = PAGE_SIZE;
153	}
154
155	if (npages < 0 || npages > PVRDMA_PAGE_DIR_MAX_PAGES) {
156		dev_warn(&dev->pdev->dev,
157			 "overflow pages in completion queue\n");
158		ret = -EINVAL;
159		goto err_umem;
160	}
161
162	ret = pvrdma_page_dir_init(dev, &cq->pdir, npages, cq->is_kernel);
163	if (ret) {
164		dev_warn(&dev->pdev->dev,
165			 "could not allocate page directory\n");
166		goto err_umem;
167	}
168
169	/* Ring state is always the first page. Set in library for user cq. */
170	if (cq->is_kernel)
171		cq->ring_state = cq->pdir.pages[0];
172	else
173		pvrdma_page_dir_insert_umem(&cq->pdir, cq->umem, 0);
174
175	refcount_set(&cq->refcnt, 1);
176	init_completion(&cq->free);
177	spin_lock_init(&cq->cq_lock);
178
179	memset(cmd, 0, sizeof(*cmd));
180	cmd->hdr.cmd = PVRDMA_CMD_CREATE_CQ;
181	cmd->nchunks = npages;
182	cmd->ctx_handle = context ? context->ctx_handle : 0;
183	cmd->cqe = entries;
184	cmd->pdir_dma = cq->pdir.dir_dma;
185	ret = pvrdma_cmd_post(dev, &req, &rsp, PVRDMA_CMD_CREATE_CQ_RESP);
186	if (ret < 0) {
187		dev_warn(&dev->pdev->dev,
188			 "could not create completion queue, error: %d\n", ret);
189		goto err_page_dir;
190	}
191
192	cq->ibcq.cqe = resp->cqe;
193	cq->cq_handle = resp->cq_handle;
194	cq_resp.cqn = resp->cq_handle;
195	spin_lock_irqsave(&dev->cq_tbl_lock, flags);
196	dev->cq_tbl[cq->cq_handle % dev->dsr->caps.max_cq] = cq;
197	spin_unlock_irqrestore(&dev->cq_tbl_lock, flags);
198
199	if (!cq->is_kernel) {
200		cq->uar = &context->uar;
201
202		/* Copy udata back. */
203		if (ib_copy_to_udata(udata, &cq_resp, sizeof(cq_resp))) {
204			dev_warn(&dev->pdev->dev,
205				 "failed to copy back udata\n");
206			pvrdma_destroy_cq(&cq->ibcq, udata);
207			return -EINVAL;
208		}
209	}
210
211	return 0;
212
213err_page_dir:
214	pvrdma_page_dir_cleanup(dev, &cq->pdir);
215err_umem:
216	ib_umem_release(cq->umem);
217err_cq:
218	atomic_dec(&dev->num_cqs);
219	return ret;
220}
221
222static void pvrdma_free_cq(struct pvrdma_dev *dev, struct pvrdma_cq *cq)
223{
224	if (refcount_dec_and_test(&cq->refcnt))
225		complete(&cq->free);
226	wait_for_completion(&cq->free);
227
228	ib_umem_release(cq->umem);
229
230	pvrdma_page_dir_cleanup(dev, &cq->pdir);
231}
232
233/**
234 * pvrdma_destroy_cq - destroy completion queue
235 * @cq: the completion queue to destroy.
236 * @udata: user data or null for kernel object
237 */
238int pvrdma_destroy_cq(struct ib_cq *cq, struct ib_udata *udata)
239{
240	struct pvrdma_cq *vcq = to_vcq(cq);
241	union pvrdma_cmd_req req;
242	struct pvrdma_cmd_destroy_cq *cmd = &req.destroy_cq;
243	struct pvrdma_dev *dev = to_vdev(cq->device);
244	unsigned long flags;
245	int ret;
246
247	memset(cmd, 0, sizeof(*cmd));
248	cmd->hdr.cmd = PVRDMA_CMD_DESTROY_CQ;
249	cmd->cq_handle = vcq->cq_handle;
250
251	ret = pvrdma_cmd_post(dev, &req, NULL, 0);
252	if (ret < 0)
253		dev_warn(&dev->pdev->dev,
254			 "could not destroy completion queue, error: %d\n",
255			 ret);
256
257	/* free cq's resources */
258	spin_lock_irqsave(&dev->cq_tbl_lock, flags);
259	dev->cq_tbl[vcq->cq_handle] = NULL;
260	spin_unlock_irqrestore(&dev->cq_tbl_lock, flags);
261
262	pvrdma_free_cq(dev, vcq);
263	atomic_dec(&dev->num_cqs);
264	return 0;
265}
266
267static inline struct pvrdma_cqe *get_cqe(struct pvrdma_cq *cq, int i)
268{
269	return (struct pvrdma_cqe *)pvrdma_page_dir_get_ptr(
270					&cq->pdir,
271					cq->offset +
272					sizeof(struct pvrdma_cqe) * i);
273}
274
275void _pvrdma_flush_cqe(struct pvrdma_qp *qp, struct pvrdma_cq *cq)
276{
277	unsigned int head;
278	int has_data;
279
280	if (!cq->is_kernel)
281		return;
282
283	/* Lock held */
284	has_data = pvrdma_idx_ring_has_data(&cq->ring_state->rx,
285					    cq->ibcq.cqe, &head);
286	if (unlikely(has_data > 0)) {
287		int items;
288		int curr;
289		int tail = pvrdma_idx(&cq->ring_state->rx.prod_tail,
290				      cq->ibcq.cqe);
291		struct pvrdma_cqe *cqe;
292		struct pvrdma_cqe *curr_cqe;
293
294		items = (tail > head) ? (tail - head) :
295			(cq->ibcq.cqe - head + tail);
296		curr = --tail;
297		while (items-- > 0) {
298			if (curr < 0)
299				curr = cq->ibcq.cqe - 1;
300			if (tail < 0)
301				tail = cq->ibcq.cqe - 1;
302			curr_cqe = get_cqe(cq, curr);
303			if ((curr_cqe->qp & 0xFFFF) != qp->qp_handle) {
304				if (curr != tail) {
305					cqe = get_cqe(cq, tail);
306					*cqe = *curr_cqe;
307				}
308				tail--;
309			} else {
310				pvrdma_idx_ring_inc(
311					&cq->ring_state->rx.cons_head,
312					cq->ibcq.cqe);
313			}
314			curr--;
315		}
316	}
317}
318
319static int pvrdma_poll_one(struct pvrdma_cq *cq, struct pvrdma_qp **cur_qp,
320			   struct ib_wc *wc)
321{
322	struct pvrdma_dev *dev = to_vdev(cq->ibcq.device);
323	int has_data;
324	unsigned int head;
325	bool tried = false;
326	struct pvrdma_cqe *cqe;
327
328retry:
329	has_data = pvrdma_idx_ring_has_data(&cq->ring_state->rx,
330					    cq->ibcq.cqe, &head);
331	if (has_data == 0) {
332		if (tried)
333			return -EAGAIN;
334
335		pvrdma_write_uar_cq(dev, cq->cq_handle | PVRDMA_UAR_CQ_POLL);
336
337		tried = true;
338		goto retry;
339	} else if (has_data == PVRDMA_INVALID_IDX) {
340		dev_err(&dev->pdev->dev, "CQ ring state invalid\n");
341		return -EAGAIN;
342	}
343
344	cqe = get_cqe(cq, head);
345
346	/* Ensure cqe is valid. */
347	rmb();
348	if (dev->qp_tbl[cqe->qp & 0xffff])
349		*cur_qp = (struct pvrdma_qp *)dev->qp_tbl[cqe->qp & 0xffff];
350	else
351		return -EAGAIN;
352
353	wc->opcode = pvrdma_wc_opcode_to_ib(cqe->opcode);
354	wc->status = pvrdma_wc_status_to_ib(cqe->status);
355	wc->wr_id = cqe->wr_id;
356	wc->qp = &(*cur_qp)->ibqp;
357	wc->byte_len = cqe->byte_len;
358	wc->ex.imm_data = cqe->imm_data;
359	wc->src_qp = cqe->src_qp;
360	wc->wc_flags = pvrdma_wc_flags_to_ib(cqe->wc_flags);
361	wc->pkey_index = cqe->pkey_index;
362	wc->slid = cqe->slid;
363	wc->sl = cqe->sl;
364	wc->dlid_path_bits = cqe->dlid_path_bits;
365	wc->port_num = cqe->port_num;
366	wc->vendor_err = cqe->vendor_err;
367	wc->network_hdr_type = pvrdma_network_type_to_ib(cqe->network_hdr_type);
368
369	/* Update shared ring state */
370	pvrdma_idx_ring_inc(&cq->ring_state->rx.cons_head, cq->ibcq.cqe);
371
372	return 0;
373}
374
375/**
376 * pvrdma_poll_cq - poll for work completion queue entries
377 * @ibcq: completion queue
378 * @num_entries: the maximum number of entries
379 * @wc: pointer to work completion array
380 *
381 * @return: number of polled completion entries
382 */
383int pvrdma_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
384{
385	struct pvrdma_cq *cq = to_vcq(ibcq);
386	struct pvrdma_qp *cur_qp = NULL;
387	unsigned long flags;
388	int npolled;
389
390	if (num_entries < 1 || wc == NULL)
391		return 0;
392
393	spin_lock_irqsave(&cq->cq_lock, flags);
394	for (npolled = 0; npolled < num_entries; ++npolled) {
395		if (pvrdma_poll_one(cq, &cur_qp, wc + npolled))
396			break;
397	}
398
399	spin_unlock_irqrestore(&cq->cq_lock, flags);
400
401	/* Ensure we do not return errors from poll_cq */
402	return npolled;
403}
404