1// SPDX-License-Identifier: GPL-2.0-only
2/*
3 * Copyright (c) 2015 HGST, a Western Digital Company.
4 */
5#include <linux/module.h>
6#include <linux/err.h>
7#include <linux/slab.h>
8#include <rdma/ib_verbs.h>
9
10#include "core_priv.h"
11
12#include <trace/events/rdma_core.h>
13/* Max size for shared CQ, may require tuning */
14#define IB_MAX_SHARED_CQ_SZ		4096U
15
16/* # of WCs to poll for with a single call to ib_poll_cq */
17#define IB_POLL_BATCH			16
18#define IB_POLL_BATCH_DIRECT		8
19
20/* # of WCs to iterate over before yielding */
21#define IB_POLL_BUDGET_IRQ		256
22#define IB_POLL_BUDGET_WORKQUEUE	65536
23
24#define IB_POLL_FLAGS \
25	(IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS)
26
27static const struct dim_cq_moder
28rdma_dim_prof[RDMA_DIM_PARAMS_NUM_PROFILES] = {
29	{1,   0, 1,  0},
30	{1,   0, 4,  0},
31	{2,   0, 4,  0},
32	{2,   0, 8,  0},
33	{4,   0, 8,  0},
34	{16,  0, 8,  0},
35	{16,  0, 16, 0},
36	{32,  0, 16, 0},
37	{32,  0, 32, 0},
38};
39
40static void ib_cq_rdma_dim_work(struct work_struct *w)
41{
42	struct dim *dim = container_of(w, struct dim, work);
43	struct ib_cq *cq = dim->priv;
44
45	u16 usec = rdma_dim_prof[dim->profile_ix].usec;
46	u16 comps = rdma_dim_prof[dim->profile_ix].comps;
47
48	dim->state = DIM_START_MEASURE;
49
50	trace_cq_modify(cq, comps, usec);
51	cq->device->ops.modify_cq(cq, comps, usec);
52}
53
54static void rdma_dim_init(struct ib_cq *cq)
55{
56	struct dim *dim;
57
58	if (!cq->device->ops.modify_cq || !cq->device->use_cq_dim ||
59	    cq->poll_ctx == IB_POLL_DIRECT)
60		return;
61
62	dim = kzalloc(sizeof(struct dim), GFP_KERNEL);
63	if (!dim)
64		return;
65
66	dim->state = DIM_START_MEASURE;
67	dim->tune_state = DIM_GOING_RIGHT;
68	dim->profile_ix = RDMA_DIM_START_PROFILE;
69	dim->priv = cq;
70	cq->dim = dim;
71
72	INIT_WORK(&dim->work, ib_cq_rdma_dim_work);
73}
74
75static void rdma_dim_destroy(struct ib_cq *cq)
76{
77	if (!cq->dim)
78		return;
79
80	cancel_work_sync(&cq->dim->work);
81	kfree(cq->dim);
82}
83
84static int __poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc)
85{
86	int rc;
87
88	rc = ib_poll_cq(cq, num_entries, wc);
89	trace_cq_poll(cq, num_entries, rc);
90	return rc;
91}
92
93static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *wcs,
94			   int batch)
95{
96	int i, n, completed = 0;
97
98	trace_cq_process(cq);
99
100	/*
101	 * budget might be (-1) if the caller does not
102	 * want to bound this call, thus we need unsigned
103	 * minimum here.
104	 */
105	while ((n = __poll_cq(cq, min_t(u32, batch,
106					budget - completed), wcs)) > 0) {
107		for (i = 0; i < n; i++) {
108			struct ib_wc *wc = &wcs[i];
109
110			if (wc->wr_cqe)
111				wc->wr_cqe->done(cq, wc);
112			else
113				WARN_ON_ONCE(wc->status == IB_WC_SUCCESS);
114		}
115
116		completed += n;
117
118		if (n != batch || (budget != -1 && completed >= budget))
119			break;
120	}
121
122	return completed;
123}
124
125/**
126 * ib_process_direct_cq - process a CQ in caller context
127 * @cq:		CQ to process
128 * @budget:	number of CQEs to poll for
129 *
130 * This function is used to process all outstanding CQ entries.
131 * It does not offload CQ processing to a different context and does
132 * not ask for completion interrupts from the HCA.
133 * Using direct processing on CQ with non IB_POLL_DIRECT type may trigger
134 * concurrent processing.
135 *
136 * Note: do not pass -1 as %budget unless it is guaranteed that the number
137 * of completions that will be processed is small.
138 */
139int ib_process_cq_direct(struct ib_cq *cq, int budget)
140{
141	struct ib_wc wcs[IB_POLL_BATCH_DIRECT];
142
143	return __ib_process_cq(cq, budget, wcs, IB_POLL_BATCH_DIRECT);
144}
145EXPORT_SYMBOL(ib_process_cq_direct);
146
147static void ib_cq_completion_direct(struct ib_cq *cq, void *private)
148{
149	WARN_ONCE(1, "got unsolicited completion for CQ 0x%p\n", cq);
150}
151
152static int ib_poll_handler(struct irq_poll *iop, int budget)
153{
154	struct ib_cq *cq = container_of(iop, struct ib_cq, iop);
155	struct dim *dim = cq->dim;
156	int completed;
157
158	completed = __ib_process_cq(cq, budget, cq->wc, IB_POLL_BATCH);
159	if (completed < budget) {
160		irq_poll_complete(&cq->iop);
161		if (ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0) {
162			trace_cq_reschedule(cq);
163			irq_poll_sched(&cq->iop);
164		}
165	}
166
167	if (dim)
168		rdma_dim(dim, completed);
169
170	return completed;
171}
172
173static void ib_cq_completion_softirq(struct ib_cq *cq, void *private)
174{
175	trace_cq_schedule(cq);
176	irq_poll_sched(&cq->iop);
177}
178
179static void ib_cq_poll_work(struct work_struct *work)
180{
181	struct ib_cq *cq = container_of(work, struct ib_cq, work);
182	int completed;
183
184	completed = __ib_process_cq(cq, IB_POLL_BUDGET_WORKQUEUE, cq->wc,
185				    IB_POLL_BATCH);
186	if (completed >= IB_POLL_BUDGET_WORKQUEUE ||
187	    ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0)
188		queue_work(cq->comp_wq, &cq->work);
189	else if (cq->dim)
190		rdma_dim(cq->dim, completed);
191}
192
193static void ib_cq_completion_workqueue(struct ib_cq *cq, void *private)
194{
195	trace_cq_schedule(cq);
196	queue_work(cq->comp_wq, &cq->work);
197}
198
199/**
200 * __ib_alloc_cq        allocate a completion queue
201 * @dev:		device to allocate the CQ for
202 * @private:		driver private data, accessible from cq->cq_context
203 * @nr_cqe:		number of CQEs to allocate
204 * @comp_vector:	HCA completion vectors for this CQ
205 * @poll_ctx:		context to poll the CQ from.
206 * @caller:		module owner name.
207 *
208 * This is the proper interface to allocate a CQ for in-kernel users. A
209 * CQ allocated with this interface will automatically be polled from the
210 * specified context. The ULP must use wr->wr_cqe instead of wr->wr_id
211 * to use this CQ abstraction.
212 */
213struct ib_cq *__ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe,
214			    int comp_vector, enum ib_poll_context poll_ctx,
215			    const char *caller)
216{
217	struct ib_cq_init_attr cq_attr = {
218		.cqe		= nr_cqe,
219		.comp_vector	= comp_vector,
220	};
221	struct ib_cq *cq;
222	int ret = -ENOMEM;
223
224	cq = rdma_zalloc_drv_obj(dev, ib_cq);
225	if (!cq)
226		return ERR_PTR(ret);
227
228	cq->device = dev;
229	cq->cq_context = private;
230	cq->poll_ctx = poll_ctx;
231	atomic_set(&cq->usecnt, 0);
232	cq->comp_vector = comp_vector;
233
234	cq->wc = kmalloc_array(IB_POLL_BATCH, sizeof(*cq->wc), GFP_KERNEL);
235	if (!cq->wc)
236		goto out_free_cq;
237
238	rdma_restrack_new(&cq->res, RDMA_RESTRACK_CQ);
239	rdma_restrack_set_name(&cq->res, caller);
240
241	ret = dev->ops.create_cq(cq, &cq_attr, NULL);
242	if (ret)
243		goto out_free_wc;
244
245	rdma_dim_init(cq);
246
247	switch (cq->poll_ctx) {
248	case IB_POLL_DIRECT:
249		cq->comp_handler = ib_cq_completion_direct;
250		break;
251	case IB_POLL_SOFTIRQ:
252		cq->comp_handler = ib_cq_completion_softirq;
253
254		irq_poll_init(&cq->iop, IB_POLL_BUDGET_IRQ, ib_poll_handler);
255		ib_req_notify_cq(cq, IB_CQ_NEXT_COMP);
256		break;
257	case IB_POLL_WORKQUEUE:
258	case IB_POLL_UNBOUND_WORKQUEUE:
259		cq->comp_handler = ib_cq_completion_workqueue;
260		INIT_WORK(&cq->work, ib_cq_poll_work);
261		ib_req_notify_cq(cq, IB_CQ_NEXT_COMP);
262		cq->comp_wq = (cq->poll_ctx == IB_POLL_WORKQUEUE) ?
263				ib_comp_wq : ib_comp_unbound_wq;
264		break;
265	default:
266		ret = -EINVAL;
267		goto out_destroy_cq;
268	}
269
270	rdma_restrack_add(&cq->res);
271	trace_cq_alloc(cq, nr_cqe, comp_vector, poll_ctx);
272	return cq;
273
274out_destroy_cq:
275	rdma_dim_destroy(cq);
276	cq->device->ops.destroy_cq(cq, NULL);
277out_free_wc:
278	rdma_restrack_put(&cq->res);
279	kfree(cq->wc);
280out_free_cq:
281	kfree(cq);
282	trace_cq_alloc_error(nr_cqe, comp_vector, poll_ctx, ret);
283	return ERR_PTR(ret);
284}
285EXPORT_SYMBOL(__ib_alloc_cq);
286
287/**
288 * __ib_alloc_cq_any - allocate a completion queue
289 * @dev:		device to allocate the CQ for
290 * @private:		driver private data, accessible from cq->cq_context
291 * @nr_cqe:		number of CQEs to allocate
292 * @poll_ctx:		context to poll the CQ from
293 * @caller:		module owner name
294 *
295 * Attempt to spread ULP Completion Queues over each device's interrupt
296 * vectors. A simple best-effort mechanism is used.
297 */
298struct ib_cq *__ib_alloc_cq_any(struct ib_device *dev, void *private,
299				int nr_cqe, enum ib_poll_context poll_ctx,
300				const char *caller)
301{
302	static atomic_t counter;
303	int comp_vector = 0;
304
305	if (dev->num_comp_vectors > 1)
306		comp_vector =
307			atomic_inc_return(&counter) %
308			min_t(int, dev->num_comp_vectors, num_online_cpus());
309
310	return __ib_alloc_cq(dev, private, nr_cqe, comp_vector, poll_ctx,
311			     caller);
312}
313EXPORT_SYMBOL(__ib_alloc_cq_any);
314
315/**
316 * ib_free_cq - free a completion queue
317 * @cq:		completion queue to free.
318 */
319void ib_free_cq(struct ib_cq *cq)
320{
321	int ret;
322
323	if (WARN_ON_ONCE(atomic_read(&cq->usecnt)))
324		return;
325	if (WARN_ON_ONCE(cq->cqe_used))
326		return;
327
328	switch (cq->poll_ctx) {
329	case IB_POLL_DIRECT:
330		break;
331	case IB_POLL_SOFTIRQ:
332		irq_poll_disable(&cq->iop);
333		break;
334	case IB_POLL_WORKQUEUE:
335	case IB_POLL_UNBOUND_WORKQUEUE:
336		cancel_work_sync(&cq->work);
337		break;
338	default:
339		WARN_ON_ONCE(1);
340	}
341
342	rdma_dim_destroy(cq);
343	trace_cq_free(cq);
344	ret = cq->device->ops.destroy_cq(cq, NULL);
345	WARN_ONCE(ret, "Destroy of kernel CQ shouldn't fail");
346	rdma_restrack_del(&cq->res);
347	kfree(cq->wc);
348	kfree(cq);
349}
350EXPORT_SYMBOL(ib_free_cq);
351
352void ib_cq_pool_init(struct ib_device *dev)
353{
354	unsigned int i;
355
356	spin_lock_init(&dev->cq_pools_lock);
357	for (i = 0; i < ARRAY_SIZE(dev->cq_pools); i++)
358		INIT_LIST_HEAD(&dev->cq_pools[i]);
359}
360
361void ib_cq_pool_destroy(struct ib_device *dev)
362{
363	struct ib_cq *cq, *n;
364	unsigned int i;
365
366	for (i = 0; i < ARRAY_SIZE(dev->cq_pools); i++) {
367		list_for_each_entry_safe(cq, n, &dev->cq_pools[i],
368					 pool_entry) {
369			WARN_ON(cq->cqe_used);
370			cq->shared = false;
371			ib_free_cq(cq);
372		}
373	}
374}
375
376static int ib_alloc_cqs(struct ib_device *dev, unsigned int nr_cqes,
377			enum ib_poll_context poll_ctx)
378{
379	LIST_HEAD(tmp_list);
380	unsigned int nr_cqs, i;
381	struct ib_cq *cq, *n;
382	int ret;
383
384	if (poll_ctx > IB_POLL_LAST_POOL_TYPE) {
385		WARN_ON_ONCE(poll_ctx > IB_POLL_LAST_POOL_TYPE);
386		return -EINVAL;
387	}
388
389	/*
390	 * Allocate at least as many CQEs as requested, and otherwise
391	 * a reasonable batch size so that we can share CQs between
392	 * multiple users instead of allocating a larger number of CQs.
393	 */
394	nr_cqes = min_t(unsigned int, dev->attrs.max_cqe,
395			max(nr_cqes, IB_MAX_SHARED_CQ_SZ));
396	nr_cqs = min_t(unsigned int, dev->num_comp_vectors, num_online_cpus());
397	for (i = 0; i < nr_cqs; i++) {
398		cq = ib_alloc_cq(dev, NULL, nr_cqes, i, poll_ctx);
399		if (IS_ERR(cq)) {
400			ret = PTR_ERR(cq);
401			goto out_free_cqs;
402		}
403		cq->shared = true;
404		list_add_tail(&cq->pool_entry, &tmp_list);
405	}
406
407	spin_lock_irq(&dev->cq_pools_lock);
408	list_splice(&tmp_list, &dev->cq_pools[poll_ctx]);
409	spin_unlock_irq(&dev->cq_pools_lock);
410
411	return 0;
412
413out_free_cqs:
414	list_for_each_entry_safe(cq, n, &tmp_list, pool_entry) {
415		cq->shared = false;
416		ib_free_cq(cq);
417	}
418	return ret;
419}
420
421/**
422 * ib_cq_pool_get() - Find the least used completion queue that matches
423 *   a given cpu hint (or least used for wild card affinity) and fits
424 *   nr_cqe.
425 * @dev: rdma device
426 * @nr_cqe: number of needed cqe entries
427 * @comp_vector_hint: completion vector hint (-1) for the driver to assign
428 *   a comp vector based on internal counter
429 * @poll_ctx: cq polling context
430 *
431 * Finds a cq that satisfies @comp_vector_hint and @nr_cqe requirements and
432 * claim entries in it for us.  In case there is no available cq, allocate
433 * a new cq with the requirements and add it to the device pool.
434 * IB_POLL_DIRECT cannot be used for shared cqs so it is not a valid value
435 * for @poll_ctx.
436 */
437struct ib_cq *ib_cq_pool_get(struct ib_device *dev, unsigned int nr_cqe,
438			     int comp_vector_hint,
439			     enum ib_poll_context poll_ctx)
440{
441	static unsigned int default_comp_vector;
442	unsigned int vector, num_comp_vectors;
443	struct ib_cq *cq, *found = NULL;
444	int ret;
445
446	if (poll_ctx > IB_POLL_LAST_POOL_TYPE) {
447		WARN_ON_ONCE(poll_ctx > IB_POLL_LAST_POOL_TYPE);
448		return ERR_PTR(-EINVAL);
449	}
450
451	num_comp_vectors =
452		min_t(unsigned int, dev->num_comp_vectors, num_online_cpus());
453	/* Project the affinty to the device completion vector range */
454	if (comp_vector_hint < 0) {
455		comp_vector_hint =
456			(READ_ONCE(default_comp_vector) + 1) % num_comp_vectors;
457		WRITE_ONCE(default_comp_vector, comp_vector_hint);
458	}
459	vector = comp_vector_hint % num_comp_vectors;
460
461	/*
462	 * Find the least used CQ with correct affinity and
463	 * enough free CQ entries
464	 */
465	while (!found) {
466		spin_lock_irq(&dev->cq_pools_lock);
467		list_for_each_entry(cq, &dev->cq_pools[poll_ctx],
468				    pool_entry) {
469			/*
470			 * Check to see if we have found a CQ with the
471			 * correct completion vector
472			 */
473			if (vector != cq->comp_vector)
474				continue;
475			if (cq->cqe_used + nr_cqe > cq->cqe)
476				continue;
477			found = cq;
478			break;
479		}
480
481		if (found) {
482			found->cqe_used += nr_cqe;
483			spin_unlock_irq(&dev->cq_pools_lock);
484
485			return found;
486		}
487		spin_unlock_irq(&dev->cq_pools_lock);
488
489		/*
490		 * Didn't find a match or ran out of CQs in the device
491		 * pool, allocate a new array of CQs.
492		 */
493		ret = ib_alloc_cqs(dev, nr_cqe, poll_ctx);
494		if (ret)
495			return ERR_PTR(ret);
496	}
497
498	return found;
499}
500EXPORT_SYMBOL(ib_cq_pool_get);
501
502/**
503 * ib_cq_pool_put - Return a CQ taken from a shared pool.
504 * @cq: The CQ to return.
505 * @nr_cqe: The max number of cqes that the user had requested.
506 */
507void ib_cq_pool_put(struct ib_cq *cq, unsigned int nr_cqe)
508{
509	if (WARN_ON_ONCE(nr_cqe > cq->cqe_used))
510		return;
511
512	spin_lock_irq(&cq->device->cq_pools_lock);
513	cq->cqe_used -= nr_cqe;
514	spin_unlock_irq(&cq->device->cq_pools_lock);
515}
516EXPORT_SYMBOL(ib_cq_pool_put);
517