summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/mellanox/mlx4/cq.c
blob: 3b8576b9c2f92e0b52da8355759eb82e33125902 (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
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
/*
 * Copyright (c) 2004, 2005 Topspin Communications.  All rights reserved.
 * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
 * Copyright (c) 2005, 2006, 2007 Cisco Systems, Inc. All rights reserved.
 * Copyright (c) 2005, 2006, 2007, 2008 Mellanox Technologies. All rights reserved.
 * Copyright (c) 2004 Voltaire, Inc. All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     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.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#include <linux/hardirq.h>
#include <linux/export.h>

#include <linux/mlx4/cmd.h>
#include <linux/mlx4/cq.h>

#include "mlx4.h"
#include "icm.h"

#define MLX4_CQ_STATUS_OK		( 0 << 28)
#define MLX4_CQ_STATUS_OVERFLOW		( 9 << 28)
#define MLX4_CQ_STATUS_WRITE_FAIL	(10 << 28)
#define MLX4_CQ_FLAG_CC			( 1 << 18)
#define MLX4_CQ_FLAG_OI			( 1 << 17)
#define MLX4_CQ_STATE_ARMED		( 9 <<  8)
#define MLX4_CQ_STATE_ARMED_SOL		( 6 <<  8)
#define MLX4_EQ_STATE_FIRED		(10 <<  8)

#define TASKLET_MAX_TIME 2
#define TASKLET_MAX_TIME_JIFFIES msecs_to_jiffies(TASKLET_MAX_TIME)

void mlx4_cq_tasklet_cb(struct tasklet_struct *t)
{
	unsigned long flags;
	unsigned long end = jiffies + TASKLET_MAX_TIME_JIFFIES;
	struct mlx4_eq_tasklet *ctx = from_tasklet(ctx, t, task);
	struct mlx4_cq *mcq, *temp;

	spin_lock_irqsave(&ctx->lock, flags);
	list_splice_tail_init(&ctx->list, &ctx->process_list);
	spin_unlock_irqrestore(&ctx->lock, flags);

	list_for_each_entry_safe(mcq, temp, &ctx->process_list, tasklet_ctx.list) {
		list_del_init(&mcq->tasklet_ctx.list);
		mcq->tasklet_ctx.comp(mcq);
		if (refcount_dec_and_test(&mcq->refcount))
			complete(&mcq->free);
		if (time_after(jiffies, end))
			break;
	}

	if (!list_empty(&ctx->process_list))
		tasklet_schedule(&ctx->task);
}

static void mlx4_add_cq_to_tasklet(struct mlx4_cq *cq)
{
	struct mlx4_eq_tasklet *tasklet_ctx = cq->tasklet_ctx.priv;
	unsigned long flags;
	bool kick;

	spin_lock_irqsave(&tasklet_ctx->lock, flags);
	/* When migrating CQs between EQs will be implemented, please note
	 * that you need to sync this point. It is possible that
	 * while migrating a CQ, completions on the old EQs could
	 * still arrive.
	 */
	if (list_empty_careful(&cq->tasklet_ctx.list)) {
		refcount_inc(&cq->refcount);
		kick = list_empty(&tasklet_ctx->list);
		list_add_tail(&cq->tasklet_ctx.list, &tasklet_ctx->list);
		if (kick)
			tasklet_schedule(&tasklet_ctx->task);
	}
	spin_unlock_irqrestore(&tasklet_ctx->lock, flags);
}

void mlx4_cq_completion(struct mlx4_dev *dev, u32 cqn)
{
	struct mlx4_cq *cq;

	rcu_read_lock();
	cq = radix_tree_lookup(&mlx4_priv(dev)->cq_table.tree,
			       cqn & (dev->caps.num_cqs - 1));
	rcu_read_unlock();

	if (!cq) {
		mlx4_dbg(dev, "Completion event for bogus CQ %08x\n", cqn);
		return;
	}

	/* Acessing the CQ outside of rcu_read_lock is safe, because
	 * the CQ is freed only after interrupt handling is completed.
	 */
	++cq->arm_sn;

	cq->comp(cq);
}

void mlx4_cq_event(struct mlx4_dev *dev, u32 cqn, int event_type)
{
	struct mlx4_cq_table *cq_table = &mlx4_priv(dev)->cq_table;
	struct mlx4_cq *cq;

	rcu_read_lock();
	cq = radix_tree_lookup(&cq_table->tree, cqn & (dev->caps.num_cqs - 1));
	rcu_read_unlock();

	if (!cq) {
		mlx4_dbg(dev, "Async event for bogus CQ %08x\n", cqn);
		return;
	}

	/* Acessing the CQ outside of rcu_read_lock is safe, because
	 * the CQ is freed only after interrupt handling is completed.
	 */
	cq->event(cq, event_type);
}

static int mlx4_SW2HW_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
			 int cq_num, u8 opmod)
{
	return mlx4_cmd(dev, mailbox->dma, cq_num, opmod,
			MLX4_CMD_SW2HW_CQ, MLX4_CMD_TIME_CLASS_A,
			MLX4_CMD_WRAPPED);
}

static int mlx4_MODIFY_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
			 int cq_num, u32 opmod)
{
	return mlx4_cmd(dev, mailbox->dma, cq_num, opmod, MLX4_CMD_MODIFY_CQ,
			MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
}

static int mlx4_HW2SW_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
			 int cq_num)
{
	return mlx4_cmd_box(dev, 0, mailbox ? mailbox->dma : 0,
			    cq_num, mailbox ? 0 : 1, MLX4_CMD_HW2SW_CQ,
			    MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
}

int mlx4_cq_modify(struct mlx4_dev *dev, struct mlx4_cq *cq,
		   u16 count, u16 period)
{
	struct mlx4_cmd_mailbox *mailbox;
	struct mlx4_cq_context *cq_context;
	int err;

	mailbox = mlx4_alloc_cmd_mailbox(dev);
	if (IS_ERR(mailbox))
		return PTR_ERR(mailbox);

	cq_context = mailbox->buf;
	cq_context->cq_max_count = cpu_to_be16(count);
	cq_context->cq_period    = cpu_to_be16(period);

	err = mlx4_MODIFY_CQ(dev, mailbox, cq->cqn, 1);

	mlx4_free_cmd_mailbox(dev, mailbox);
	return err;
}
EXPORT_SYMBOL_GPL(mlx4_cq_modify);

int mlx4_cq_resize(struct mlx4_dev *dev, struct mlx4_cq *cq,
		   int entries, struct mlx4_mtt *mtt)
{
	struct mlx4_cmd_mailbox *mailbox;
	struct mlx4_cq_context *cq_context;
	u64 mtt_addr;
	int err;

	mailbox = mlx4_alloc_cmd_mailbox(dev);
	if (IS_ERR(mailbox))
		return PTR_ERR(mailbox);

	cq_context = mailbox->buf;
	cq_context->logsize_usrpage = cpu_to_be32(ilog2(entries) << 24);
	cq_context->log_page_size   = mtt->page_shift - 12;
	mtt_addr = mlx4_mtt_addr(dev, mtt);
	cq_context->mtt_base_addr_h = mtt_addr >> 32;
	cq_context->mtt_base_addr_l = cpu_to_be32(mtt_addr & 0xffffffff);

	err = mlx4_MODIFY_CQ(dev, mailbox, cq->cqn, 0);

	mlx4_free_cmd_mailbox(dev, mailbox);
	return err;
}
EXPORT_SYMBOL_GPL(mlx4_cq_resize);

int __mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	struct mlx4_cq_table *cq_table = &priv->cq_table;
	int err;

	*cqn = mlx4_bitmap_alloc(&cq_table->bitmap);
	if (*cqn == -1)
		return -ENOMEM;

	err = mlx4_table_get(dev, &cq_table->table, *cqn);
	if (err)
		goto err_out;

	err = mlx4_table_get(dev, &cq_table->cmpt_table, *cqn);
	if (err)
		goto err_put;
	return 0;

err_put:
	mlx4_table_put(dev, &cq_table->table, *cqn);

err_out:
	mlx4_bitmap_free(&cq_table->bitmap, *cqn, MLX4_NO_RR);
	return err;
}

static int mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn, u8 usage)
{
	u32 in_modifier = RES_CQ | (((u32)usage & 3) << 30);
	u64 out_param;
	int err;

	if (mlx4_is_mfunc(dev)) {
		err = mlx4_cmd_imm(dev, 0, &out_param, in_modifier,
				   RES_OP_RESERVE_AND_MAP, MLX4_CMD_ALLOC_RES,
				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
		if (err)
			return err;
		else {
			*cqn = get_param_l(&out_param);
			return 0;
		}
	}
	return __mlx4_cq_alloc_icm(dev, cqn);
}

void __mlx4_cq_free_icm(struct mlx4_dev *dev, int cqn)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	struct mlx4_cq_table *cq_table = &priv->cq_table;

	mlx4_table_put(dev, &cq_table->cmpt_table, cqn);
	mlx4_table_put(dev, &cq_table->table, cqn);
	mlx4_bitmap_free(&cq_table->bitmap, cqn, MLX4_NO_RR);
}

static void mlx4_cq_free_icm(struct mlx4_dev *dev, int cqn)
{
	u64 in_param = 0;
	int err;

	if (mlx4_is_mfunc(dev)) {
		set_param_l(&in_param, cqn);
		err = mlx4_cmd(dev, in_param, RES_CQ, RES_OP_RESERVE_AND_MAP,
			       MLX4_CMD_FREE_RES,
			       MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
		if (err)
			mlx4_warn(dev, "Failed freeing cq:%d\n", cqn);
	} else
		__mlx4_cq_free_icm(dev, cqn);
}

static int mlx4_init_user_cqes(void *buf, int entries, int cqe_size)
{
	int entries_per_copy = PAGE_SIZE / cqe_size;
	void *init_ents;
	int err = 0;
	int i;

	init_ents = kmalloc(PAGE_SIZE, GFP_KERNEL);
	if (!init_ents)
		return -ENOMEM;

	/* Populate a list of CQ entries to reduce the number of
	 * copy_to_user calls. 0xcc is the initialization value
	 * required by the FW.
	 */
	memset(init_ents, 0xcc, PAGE_SIZE);

	if (entries_per_copy < entries) {
		for (i = 0; i < entries / entries_per_copy; i++) {
			err = copy_to_user((void __user *)buf, init_ents, PAGE_SIZE) ?
				-EFAULT : 0;
			if (err)
				goto out;

			buf += PAGE_SIZE;
		}
	} else {
		err = copy_to_user((void __user *)buf, init_ents, entries * cqe_size) ?
			-EFAULT : 0;
	}

out:
	kfree(init_ents);

	return err;
}

static void mlx4_init_kernel_cqes(struct mlx4_buf *buf,
				  int entries,
				  int cqe_size)
{
	int i;

	if (buf->nbufs == 1)
		memset(buf->direct.buf, 0xcc, entries * cqe_size);
	else
		for (i = 0; i < buf->npages; i++)
			memset(buf->page_list[i].buf, 0xcc,
			       1UL << buf->page_shift);
}

int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
		  struct mlx4_mtt *mtt, struct mlx4_uar *uar, u64 db_rec,
		  struct mlx4_cq *cq, unsigned vector, int collapsed,
		  int timestamp_en, void *buf_addr, bool user_cq)
{
	bool sw_cq_init = dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_SW_CQ_INIT;
	struct mlx4_priv *priv = mlx4_priv(dev);
	struct mlx4_cq_table *cq_table = &priv->cq_table;
	struct mlx4_cmd_mailbox *mailbox;
	struct mlx4_cq_context *cq_context;
	u64 mtt_addr;
	int err;

	if (vector >= dev->caps.num_comp_vectors)
		return -EINVAL;

	cq->vector = vector;

	err = mlx4_cq_alloc_icm(dev, &cq->cqn, cq->usage);
	if (err)
		return err;

	spin_lock(&cq_table->lock);
	err = radix_tree_insert(&cq_table->tree, cq->cqn, cq);
	spin_unlock(&cq_table->lock);
	if (err)
		goto err_icm;

	mailbox = mlx4_alloc_cmd_mailbox(dev);
	if (IS_ERR(mailbox)) {
		err = PTR_ERR(mailbox);
		goto err_radix;
	}

	cq_context = mailbox->buf;
	cq_context->flags	    = cpu_to_be32(!!collapsed << 18);
	if (timestamp_en)
		cq_context->flags  |= cpu_to_be32(1 << 19);

	cq_context->logsize_usrpage =
		cpu_to_be32((ilog2(nent) << 24) |
			    mlx4_to_hw_uar_index(dev, uar->index));
	cq_context->comp_eqn	    = priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].eqn;
	cq_context->log_page_size   = mtt->page_shift - MLX4_ICM_PAGE_SHIFT;

	mtt_addr = mlx4_mtt_addr(dev, mtt);
	cq_context->mtt_base_addr_h = mtt_addr >> 32;
	cq_context->mtt_base_addr_l = cpu_to_be32(mtt_addr & 0xffffffff);
	cq_context->db_rec_addr     = cpu_to_be64(db_rec);

	if (sw_cq_init) {
		if (user_cq) {
			err = mlx4_init_user_cqes(buf_addr, nent,
						  dev->caps.cqe_size);
			if (err)
				sw_cq_init = false;
		} else {
			mlx4_init_kernel_cqes(buf_addr, nent,
					      dev->caps.cqe_size);
		}
	}

	err = mlx4_SW2HW_CQ(dev, mailbox, cq->cqn, sw_cq_init);

	mlx4_free_cmd_mailbox(dev, mailbox);
	if (err)
		goto err_radix;

	cq->cons_index = 0;
	cq->arm_sn     = 1;
	cq->uar        = uar;
	refcount_set(&cq->refcount, 1);
	init_completion(&cq->free);
	cq->comp = mlx4_add_cq_to_tasklet;
	cq->tasklet_ctx.priv =
		&priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].tasklet_ctx;
	INIT_LIST_HEAD(&cq->tasklet_ctx.list);


	cq->irq = priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].irq;
	return 0;

err_radix:
	spin_lock(&cq_table->lock);
	radix_tree_delete(&cq_table->tree, cq->cqn);
	spin_unlock(&cq_table->lock);

err_icm:
	mlx4_cq_free_icm(dev, cq->cqn);

	return err;
}
EXPORT_SYMBOL_GPL(mlx4_cq_alloc);

void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	struct mlx4_cq_table *cq_table = &priv->cq_table;
	int err;

	err = mlx4_HW2SW_CQ(dev, NULL, cq->cqn);
	if (err)
		mlx4_warn(dev, "HW2SW_CQ failed (%d) for CQN %06x\n", err, cq->cqn);

	spin_lock(&cq_table->lock);
	radix_tree_delete(&cq_table->tree, cq->cqn);
	spin_unlock(&cq_table->lock);

	synchronize_irq(priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq);
	if (priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq !=
	    priv->eq_table.eq[MLX4_EQ_ASYNC].irq)
		synchronize_irq(priv->eq_table.eq[MLX4_EQ_ASYNC].irq);

	if (refcount_dec_and_test(&cq->refcount))
		complete(&cq->free);
	wait_for_completion(&cq->free);

	mlx4_cq_free_icm(dev, cq->cqn);
}
EXPORT_SYMBOL_GPL(mlx4_cq_free);

int mlx4_init_cq_table(struct mlx4_dev *dev)
{
	struct mlx4_cq_table *cq_table = &mlx4_priv(dev)->cq_table;
	int err;

	spin_lock_init(&cq_table->lock);
	INIT_RADIX_TREE(&cq_table->tree, GFP_ATOMIC);
	if (mlx4_is_slave(dev))
		return 0;

	err = mlx4_bitmap_init(&cq_table->bitmap, dev->caps.num_cqs,
			       dev->caps.num_cqs - 1, dev->caps.reserved_cqs, 0);
	if (err)
		return err;

	return 0;
}

void mlx4_cleanup_cq_table(struct mlx4_dev *dev)
{
	if (mlx4_is_slave(dev))
		return;
	/* Nothing to do to clean up radix_tree */
	mlx4_bitmap_cleanup(&mlx4_priv(dev)->cq_table.bitmap);
}