Free Electrons

Embedded Linux Experts

  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
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
/*
 * Copyright(c) 2016 Intel Corporation.
 *
 * This file is provided under a dual BSD/GPLv2 license.  When using or
 * redistributing this file, you may do so under either license.
 *
 * GPL LICENSE SUMMARY
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of version 2 of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that 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.
 *
 * BSD LICENSE
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 *  - Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *  - Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *  - Neither the name of Intel Corporation nor the names of its
 *    contributors may be used to endorse or promote products derived
 *    from this software without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 */

#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/kthread.h>
#include "cq.h"
#include "vt.h"
#include "trace.h"

/**
 * rvt_cq_enter - add a new entry to the completion queue
 * @cq: completion queue
 * @entry: work completion entry to add
 * @sig: true if @entry is solicited
 *
 * This may be called with qp->s_lock held.
 */
void rvt_cq_enter(struct rvt_cq *cq, struct ib_wc *entry, bool solicited)
{
	struct rvt_cq_wc *wc;
	unsigned long flags;
	u32 head;
	u32 next;

	spin_lock_irqsave(&cq->lock, flags);

	/*
	 * Note that the head pointer might be writable by user processes.
	 * Take care to verify it is a sane value.
	 */
	wc = cq->queue;
	head = wc->head;
	if (head >= (unsigned)cq->ibcq.cqe) {
		head = cq->ibcq.cqe;
		next = 0;
	} else {
		next = head + 1;
	}

	if (unlikely(next == wc->tail)) {
		spin_unlock_irqrestore(&cq->lock, flags);
		if (cq->ibcq.event_handler) {
			struct ib_event ev;

			ev.device = cq->ibcq.device;
			ev.element.cq = &cq->ibcq;
			ev.event = IB_EVENT_CQ_ERR;
			cq->ibcq.event_handler(&ev, cq->ibcq.cq_context);
		}
		return;
	}
	trace_rvt_cq_enter(cq, entry, head);
	if (cq->ip) {
		wc->uqueue[head].wr_id = entry->wr_id;
		wc->uqueue[head].status = entry->status;
		wc->uqueue[head].opcode = entry->opcode;
		wc->uqueue[head].vendor_err = entry->vendor_err;
		wc->uqueue[head].byte_len = entry->byte_len;
		wc->uqueue[head].ex.imm_data =
			(__u32 __force)entry->ex.imm_data;
		wc->uqueue[head].qp_num = entry->qp->qp_num;
		wc->uqueue[head].src_qp = entry->src_qp;
		wc->uqueue[head].wc_flags = entry->wc_flags;
		wc->uqueue[head].pkey_index = entry->pkey_index;
		wc->uqueue[head].slid = ib_lid_cpu16(entry->slid);
		wc->uqueue[head].sl = entry->sl;
		wc->uqueue[head].dlid_path_bits = entry->dlid_path_bits;
		wc->uqueue[head].port_num = entry->port_num;
		/* Make sure entry is written before the head index. */
		smp_wmb();
	} else {
		wc->kqueue[head] = *entry;
	}
	wc->head = next;

	if (cq->notify == IB_CQ_NEXT_COMP ||
	    (cq->notify == IB_CQ_SOLICITED &&
	     (solicited || entry->status != IB_WC_SUCCESS))) {
		/*
		 * This will cause send_complete() to be called in
		 * another thread.
		 */
		spin_lock(&cq->rdi->n_cqs_lock);
		if (likely(cq->rdi->worker)) {
			cq->notify = RVT_CQ_NONE;
			cq->triggered++;
			kthread_queue_work(cq->rdi->worker, &cq->comptask);
		}
		spin_unlock(&cq->rdi->n_cqs_lock);
	}

	spin_unlock_irqrestore(&cq->lock, flags);
}
EXPORT_SYMBOL(rvt_cq_enter);

static void send_complete(struct kthread_work *work)
{
	struct rvt_cq *cq = container_of(work, struct rvt_cq, comptask);

	/*
	 * The completion handler will most likely rearm the notification
	 * and poll for all pending entries.  If a new completion entry
	 * is added while we are in this routine, queue_work()
	 * won't call us again until we return so we check triggered to
	 * see if we need to call the handler again.
	 */
	for (;;) {
		u8 triggered = cq->triggered;

		/*
		 * IPoIB connected mode assumes the callback is from a
		 * soft IRQ. We simulate this by blocking "bottom halves".
		 * See the implementation for ipoib_cm_handle_tx_wc(),
		 * netif_tx_lock_bh() and netif_tx_lock().
		 */
		local_bh_disable();
		cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context);
		local_bh_enable();

		if (cq->triggered == triggered)
			return;
	}
}

/**
 * rvt_create_cq - create a completion queue
 * @ibdev: the device this completion queue is attached to
 * @attr: creation attributes
 * @context: unused by the QLogic_IB driver
 * @udata: user data for libibverbs.so
 *
 * Called by ib_create_cq() in the generic verbs code.
 *
 * Return: pointer to the completion queue or negative errno values
 * for failure.
 */
struct ib_cq *rvt_create_cq(struct ib_device *ibdev,
			    const struct ib_cq_init_attr *attr,
			    struct ib_ucontext *context,
			    struct ib_udata *udata)
{
	struct rvt_dev_info *rdi = ib_to_rvt(ibdev);
	struct rvt_cq *cq;
	struct rvt_cq_wc *wc;
	struct ib_cq *ret;
	u32 sz;
	unsigned int entries = attr->cqe;

	if (attr->flags)
		return ERR_PTR(-EINVAL);

	if (entries < 1 || entries > rdi->dparms.props.max_cqe)
		return ERR_PTR(-EINVAL);

	/* Allocate the completion queue structure. */
	cq = kzalloc(sizeof(*cq), GFP_KERNEL);
	if (!cq)
		return ERR_PTR(-ENOMEM);

	/*
	 * Allocate the completion queue entries and head/tail pointers.
	 * This is allocated separately so that it can be resized and
	 * also mapped into user space.
	 * We need to use vmalloc() in order to support mmap and large
	 * numbers of entries.
	 */
	sz = sizeof(*wc);
	if (udata && udata->outlen >= sizeof(__u64))
		sz += sizeof(struct ib_uverbs_wc) * (entries + 1);
	else
		sz += sizeof(struct ib_wc) * (entries + 1);
	wc = vmalloc_user(sz);
	if (!wc) {
		ret = ERR_PTR(-ENOMEM);
		goto bail_cq;
	}

	/*
	 * Return the address of the WC as the offset to mmap.
	 * See rvt_mmap() for details.
	 */
	if (udata && udata->outlen >= sizeof(__u64)) {
		int err;

		cq->ip = rvt_create_mmap_info(rdi, sz, context, wc);
		if (!cq->ip) {
			ret = ERR_PTR(-ENOMEM);
			goto bail_wc;
		}

		err = ib_copy_to_udata(udata, &cq->ip->offset,
				       sizeof(cq->ip->offset));
		if (err) {
			ret = ERR_PTR(err);
			goto bail_ip;
		}
	}

	spin_lock_irq(&rdi->n_cqs_lock);
	if (rdi->n_cqs_allocated == rdi->dparms.props.max_cq) {
		spin_unlock_irq(&rdi->n_cqs_lock);
		ret = ERR_PTR(-ENOMEM);
		goto bail_ip;
	}

	rdi->n_cqs_allocated++;
	spin_unlock_irq(&rdi->n_cqs_lock);

	if (cq->ip) {
		spin_lock_irq(&rdi->pending_lock);
		list_add(&cq->ip->pending_mmaps, &rdi->pending_mmaps);
		spin_unlock_irq(&rdi->pending_lock);
	}

	/*
	 * ib_create_cq() will initialize cq->ibcq except for cq->ibcq.cqe.
	 * The number of entries should be >= the number requested or return
	 * an error.
	 */
	cq->rdi = rdi;
	cq->ibcq.cqe = entries;
	cq->notify = RVT_CQ_NONE;
	spin_lock_init(&cq->lock);
	kthread_init_work(&cq->comptask, send_complete);
	cq->queue = wc;

	ret = &cq->ibcq;

	goto done;

bail_ip:
	kfree(cq->ip);
bail_wc:
	vfree(wc);
bail_cq:
	kfree(cq);
done:
	return ret;
}

/**
 * rvt_destroy_cq - destroy a completion queue
 * @ibcq: the completion queue to destroy.
 *
 * Called by ib_destroy_cq() in the generic verbs code.
 *
 * Return: always 0
 */
int rvt_destroy_cq(struct ib_cq *ibcq)
{
	struct rvt_cq *cq = ibcq_to_rvtcq(ibcq);
	struct rvt_dev_info *rdi = cq->rdi;

	kthread_flush_work(&cq->comptask);
	spin_lock_irq(&rdi->n_cqs_lock);
	rdi->n_cqs_allocated--;
	spin_unlock_irq(&rdi->n_cqs_lock);
	if (cq->ip)
		kref_put(&cq->ip->ref, rvt_release_mmap_info);
	else
		vfree(cq->queue);
	kfree(cq);

	return 0;
}

/**
 * rvt_req_notify_cq - change the notification type for a completion queue
 * @ibcq: the completion queue
 * @notify_flags: the type of notification to request
 *
 * This may be called from interrupt context.  Also called by
 * ib_req_notify_cq() in the generic verbs code.
 *
 * Return: 0 for success.
 */
int rvt_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags notify_flags)
{
	struct rvt_cq *cq = ibcq_to_rvtcq(ibcq);
	unsigned long flags;
	int ret = 0;

	spin_lock_irqsave(&cq->lock, flags);
	/*
	 * Don't change IB_CQ_NEXT_COMP to IB_CQ_SOLICITED but allow
	 * any other transitions (see C11-31 and C11-32 in ch. 11.4.2.2).
	 */
	if (cq->notify != IB_CQ_NEXT_COMP)
		cq->notify = notify_flags & IB_CQ_SOLICITED_MASK;

	if ((notify_flags & IB_CQ_REPORT_MISSED_EVENTS) &&
	    cq->queue->head != cq->queue->tail)
		ret = 1;

	spin_unlock_irqrestore(&cq->lock, flags);

	return ret;
}

/**
 * rvt_resize_cq - change the size of the CQ
 * @ibcq: the completion queue
 *
 * Return: 0 for success.
 */
int rvt_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata)
{
	struct rvt_cq *cq = ibcq_to_rvtcq(ibcq);
	struct rvt_cq_wc *old_wc;
	struct rvt_cq_wc *wc;
	u32 head, tail, n;
	int ret;
	u32 sz;
	struct rvt_dev_info *rdi = cq->rdi;

	if (cqe < 1 || cqe > rdi->dparms.props.max_cqe)
		return -EINVAL;

	/*
	 * Need to use vmalloc() if we want to support large #s of entries.
	 */
	sz = sizeof(*wc);
	if (udata && udata->outlen >= sizeof(__u64))
		sz += sizeof(struct ib_uverbs_wc) * (cqe + 1);
	else
		sz += sizeof(struct ib_wc) * (cqe + 1);
	wc = vmalloc_user(sz);
	if (!wc)
		return -ENOMEM;

	/* Check that we can write the offset to mmap. */
	if (udata && udata->outlen >= sizeof(__u64)) {
		__u64 offset = 0;

		ret = ib_copy_to_udata(udata, &offset, sizeof(offset));
		if (ret)
			goto bail_free;
	}

	spin_lock_irq(&cq->lock);
	/*
	 * Make sure head and tail are sane since they
	 * might be user writable.
	 */
	old_wc = cq->queue;
	head = old_wc->head;
	if (head > (u32)cq->ibcq.cqe)
		head = (u32)cq->ibcq.cqe;
	tail = old_wc->tail;
	if (tail > (u32)cq->ibcq.cqe)
		tail = (u32)cq->ibcq.cqe;
	if (head < tail)
		n = cq->ibcq.cqe + 1 + head - tail;
	else
		n = head - tail;
	if (unlikely((u32)cqe < n)) {
		ret = -EINVAL;
		goto bail_unlock;
	}
	for (n = 0; tail != head; n++) {
		if (cq->ip)
			wc->uqueue[n] = old_wc->uqueue[tail];
		else
			wc->kqueue[n] = old_wc->kqueue[tail];
		if (tail == (u32)cq->ibcq.cqe)
			tail = 0;
		else
			tail++;
	}
	cq->ibcq.cqe = cqe;
	wc->head = n;
	wc->tail = 0;
	cq->queue = wc;
	spin_unlock_irq(&cq->lock);

	vfree(old_wc);

	if (cq->ip) {
		struct rvt_mmap_info *ip = cq->ip;

		rvt_update_mmap_info(rdi, ip, sz, wc);

		/*
		 * Return the offset to mmap.
		 * See rvt_mmap() for details.
		 */
		if (udata && udata->outlen >= sizeof(__u64)) {
			ret = ib_copy_to_udata(udata, &ip->offset,
					       sizeof(ip->offset));
			if (ret)
				return ret;
		}

		spin_lock_irq(&rdi->pending_lock);
		if (list_empty(&ip->pending_mmaps))
			list_add(&ip->pending_mmaps, &rdi->pending_mmaps);
		spin_unlock_irq(&rdi->pending_lock);
	}

	return 0;

bail_unlock:
	spin_unlock_irq(&cq->lock);
bail_free:
	vfree(wc);
	return ret;
}

/**
 * rvt_poll_cq - poll for work completion entries
 * @ibcq: the completion queue to poll
 * @num_entries: the maximum number of entries to return
 * @entry: pointer to array where work completions are placed
 *
 * This may be called from interrupt context.  Also called by ib_poll_cq()
 * in the generic verbs code.
 *
 * Return: the number of completion entries polled.
 */
int rvt_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *entry)
{
	struct rvt_cq *cq = ibcq_to_rvtcq(ibcq);
	struct rvt_cq_wc *wc;
	unsigned long flags;
	int npolled;
	u32 tail;

	/* The kernel can only poll a kernel completion queue */
	if (cq->ip)
		return -EINVAL;

	spin_lock_irqsave(&cq->lock, flags);

	wc = cq->queue;
	tail = wc->tail;
	if (tail > (u32)cq->ibcq.cqe)
		tail = (u32)cq->ibcq.cqe;
	for (npolled = 0; npolled < num_entries; ++npolled, ++entry) {
		if (tail == wc->head)
			break;
		/* The kernel doesn't need a RMB since it has the lock. */
		trace_rvt_cq_poll(cq, &wc->kqueue[tail], npolled);
		*entry = wc->kqueue[tail];
		if (tail >= cq->ibcq.cqe)
			tail = 0;
		else
			tail++;
	}
	wc->tail = tail;

	spin_unlock_irqrestore(&cq->lock, flags);

	return npolled;
}

/**
 * rvt_driver_cq_init - Init cq resources on behalf of driver
 * @rdi: rvt dev structure
 *
 * Return: 0 on success
 */
int rvt_driver_cq_init(struct rvt_dev_info *rdi)
{
	int cpu;
	struct kthread_worker *worker;

	if (rdi->worker)
		return 0;

	spin_lock_init(&rdi->n_cqs_lock);

	cpu = cpumask_first(cpumask_of_node(rdi->dparms.node));
	worker = kthread_create_worker_on_cpu(cpu, 0,
					      "%s", rdi->dparms.cq_name);
	if (IS_ERR(worker))
		return PTR_ERR(worker);

	set_user_nice(worker->task, MIN_NICE);
	rdi->worker = worker;
	return 0;
}

/**
 * rvt_cq_exit - tear down cq reources
 * @rdi: rvt dev structure
 */
void rvt_cq_exit(struct rvt_dev_info *rdi)
{
	struct kthread_worker *worker;

	/* block future queuing from send_complete() */
	spin_lock_irq(&rdi->n_cqs_lock);
	worker = rdi->worker;
	if (!worker) {
		spin_unlock_irq(&rdi->n_cqs_lock);
		return;
	}
	rdi->worker = NULL;
	spin_unlock_irq(&rdi->n_cqs_lock);

	kthread_destroy_worker(worker);
}