summaryrefslogtreecommitdiff
path: root/drivers/infiniband/core/cq.c
blob: a4c81992267c7b588de162c06270e384842ba631 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
/*
 * Copyright (c) 2015 HGST, a Western Digital Company.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 */
#include <linux/module.h>
#include <linux/err.h>
#include <linux/slab.h>
#include <rdma/ib_verbs.h>

/* # of WCs to poll for with a single call to ib_poll_cq */
#define IB_POLL_BATCH			16
#define IB_POLL_BATCH_DIRECT		8

/* # of WCs to iterate over before yielding */
#define IB_POLL_BUDGET_IRQ		256
#define IB_POLL_BUDGET_WORKQUEUE	65536

#define IB_POLL_FLAGS \
	(IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS)

static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *wcs,
			   int batch)
{
	int i, n, completed = 0;

	/*
	 * budget might be (-1) if the caller does not
	 * want to bound this call, thus we need unsigned
	 * minimum here.
	 */
	while ((n = ib_poll_cq(cq, min_t(u32, batch,
					 budget - completed), wcs)) > 0) {
		for (i = 0; i < n; i++) {
			struct ib_wc *wc = &wcs[i];

			if (wc->wr_cqe)
				wc->wr_cqe->done(cq, wc);
			else
				WARN_ON_ONCE(wc->status == IB_WC_SUCCESS);
		}

		completed += n;

		if (n != batch || (budget != -1 && completed >= budget))
			break;
	}

	return completed;
}

/**
 * ib_process_direct_cq - process a CQ in caller context
 * @cq:		CQ to process
 * @budget:	number of CQEs to poll for
 *
 * This function is used to process all outstanding CQ entries.
 * It does not offload CQ processing to a different context and does
 * not ask for completion interrupts from the HCA.
 * Using direct processing on CQ with non IB_POLL_DIRECT type may trigger
 * concurrent processing.
 *
 * Note: do not pass -1 as %budget unless it is guaranteed that the number
 * of completions that will be processed is small.
 */
int ib_process_cq_direct(struct ib_cq *cq, int budget)
{
	struct ib_wc wcs[IB_POLL_BATCH_DIRECT];

	return __ib_process_cq(cq, budget, wcs, IB_POLL_BATCH_DIRECT);
}
EXPORT_SYMBOL(ib_process_cq_direct);

static void ib_cq_completion_direct(struct ib_cq *cq, void *private)
{
	WARN_ONCE(1, "got unsolicited completion for CQ 0x%p\n", cq);
}

static int ib_poll_handler(struct irq_poll *iop, int budget)
{
	struct ib_cq *cq = container_of(iop, struct ib_cq, iop);
	int completed;

	completed = __ib_process_cq(cq, budget, cq->wc, IB_POLL_BATCH);
	if (completed < budget) {
		irq_poll_complete(&cq->iop);
		if (ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0)
			irq_poll_sched(&cq->iop);
	}

	return completed;
}

static void ib_cq_completion_softirq(struct ib_cq *cq, void *private)
{
	irq_poll_sched(&cq->iop);
}

static void ib_cq_poll_work(struct work_struct *work)
{
	struct ib_cq *cq = container_of(work, struct ib_cq, work);
	int completed;

	completed = __ib_process_cq(cq, IB_POLL_BUDGET_WORKQUEUE, cq->wc,
				    IB_POLL_BATCH);
	if (completed >= IB_POLL_BUDGET_WORKQUEUE ||
	    ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0)
		queue_work(cq->comp_wq, &cq->work);
}

static void ib_cq_completion_workqueue(struct ib_cq *cq, void *private)
{
	queue_work(cq->comp_wq, &cq->work);
}

/**
 * __ib_alloc_cq - allocate a completion queue
 * @dev:		device to allocate the CQ for
 * @private:		driver private data, accessible from cq->cq_context
 * @nr_cqe:		number of CQEs to allocate
 * @comp_vector:	HCA completion vectors for this CQ
 * @poll_ctx:		context to poll the CQ from.
 * @caller:		module owner name.
 * @udata:		Valid user data or NULL for kernel object
 *
 * This is the proper interface to allocate a CQ for in-kernel users. A
 * CQ allocated with this interface will automatically be polled from the
 * specified context. The ULP must use wr->wr_cqe instead of wr->wr_id
 * to use this CQ abstraction.
 */
struct ib_cq *__ib_alloc_cq_user(struct ib_device *dev, void *private,
				 int nr_cqe, int comp_vector,
				 enum ib_poll_context poll_ctx,
				 const char *caller, struct ib_udata *udata)
{
	struct ib_cq_init_attr cq_attr = {
		.cqe		= nr_cqe,
		.comp_vector	= comp_vector,
	};
	struct ib_cq *cq;
	int ret = -ENOMEM;

	cq = dev->ops.create_cq(dev, &cq_attr, NULL);
	if (IS_ERR(cq))
		return cq;

	cq->device = dev;
	cq->uobject = NULL;
	cq->event_handler = NULL;
	cq->cq_context = private;
	cq->poll_ctx = poll_ctx;
	atomic_set(&cq->usecnt, 0);

	cq->wc = kmalloc_array(IB_POLL_BATCH, sizeof(*cq->wc), GFP_KERNEL);
	if (!cq->wc)
		goto out_destroy_cq;

	cq->res.type = RDMA_RESTRACK_CQ;
	rdma_restrack_set_task(&cq->res, caller);
	rdma_restrack_kadd(&cq->res);

	switch (cq->poll_ctx) {
	case IB_POLL_DIRECT:
		cq->comp_handler = ib_cq_completion_direct;
		break;
	case IB_POLL_SOFTIRQ:
		cq->comp_handler = ib_cq_completion_softirq;

		irq_poll_init(&cq->iop, IB_POLL_BUDGET_IRQ, ib_poll_handler);
		ib_req_notify_cq(cq, IB_CQ_NEXT_COMP);
		break;
	case IB_POLL_WORKQUEUE:
	case IB_POLL_UNBOUND_WORKQUEUE:
		cq->comp_handler = ib_cq_completion_workqueue;
		INIT_WORK(&cq->work, ib_cq_poll_work);
		ib_req_notify_cq(cq, IB_CQ_NEXT_COMP);
		cq->comp_wq = (cq->poll_ctx == IB_POLL_WORKQUEUE) ?
				ib_comp_wq : ib_comp_unbound_wq;
		break;
	default:
		ret = -EINVAL;
		goto out_free_wc;
	}

	return cq;

out_free_wc:
	kfree(cq->wc);
	rdma_restrack_del(&cq->res);
out_destroy_cq:
	cq->device->ops.destroy_cq(cq, udata);
	return ERR_PTR(ret);
}
EXPORT_SYMBOL(__ib_alloc_cq_user);

/**
 * ib_free_cq - free a completion queue
 * @cq:		completion queue to free.
 * @udata:	User data or NULL for kernel object
 */
void ib_free_cq_user(struct ib_cq *cq, struct ib_udata *udata)
{
	int ret;

	if (WARN_ON_ONCE(atomic_read(&cq->usecnt)))
		return;

	switch (cq->poll_ctx) {
	case IB_POLL_DIRECT:
		break;
	case IB_POLL_SOFTIRQ:
		irq_poll_disable(&cq->iop);
		break;
	case IB_POLL_WORKQUEUE:
	case IB_POLL_UNBOUND_WORKQUEUE:
		cancel_work_sync(&cq->work);
		break;
	default:
		WARN_ON_ONCE(1);
	}

	kfree(cq->wc);
	rdma_restrack_del(&cq->res);
	ret = cq->device->ops.destroy_cq(cq, udata);
	WARN_ON_ONCE(ret);
}
EXPORT_SYMBOL(ib_free_cq_user);