1/*
2 * Copyright (c) 2012 Mellanox Technologies. All rights reserved.
3 *
4 * This software is available to you under a choice of one of two
5 * licenses.  You may choose to be licensed under the terms of the GNU
6 * General Public License (GPL) Version 2, available from the file
7 * COPYING in the main directory of this source tree, or the
8 * OpenIB.org BSD license below:
9 *
10 *     Redistribution and use in source and binary forms, with or
11 *     without modification, are permitted provided that the following
12 *     conditions are met:
13 *
14 *      - Redistributions of source code must retain the above
15 *        copyright notice, this list of conditions and the following
16 *        disclaimer.
17 *
18 *      - Redistributions in binary form must reproduce the above
19 *        copyright notice, this list of conditions and the following
20 *        disclaimer in the documentation and/or other materials
21 *        provided with the distribution.
22 *
23 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
24 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
25 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
26 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
27 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
28 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
29 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
30 * SOFTWARE.
31 */
32
33#include <rdma/ib_mad.h>
34#include <rdma/ib_smi.h>
35#include <rdma/ib_cache.h>
36#include <rdma/ib_sa.h>
37
38#include <linux/mlx4/cmd.h>
39#include <linux/rbtree.h>
40#include <linux/delay.h>
41
42#include "mlx4_ib.h"
43
44#define MAX_VFS		80
45#define MAX_PEND_REQS_PER_FUNC 4
46#define MAD_TIMEOUT_MS	2000
47
48#define mcg_warn(fmt, arg...)	pr_warn("MCG WARNING: " fmt, ##arg)
49#define mcg_error(fmt, arg...)	pr_err(fmt, ##arg)
50#define mcg_warn_group(group, format, arg...) \
51	pr_warn("%s-%d: %16s (port %d): WARNING: " format, __func__, __LINE__,\
52	(group)->name, group->demux->port, ## arg)
53
54#define mcg_debug_group(group, format, arg...) \
55	pr_debug("%s-%d: %16s (port %d): WARNING: " format, __func__, __LINE__,\
56		 (group)->name, (group)->demux->port, ## arg)
57
58#define mcg_error_group(group, format, arg...) \
59	pr_err("  %16s: " format, (group)->name, ## arg)
60
61
62static union ib_gid mgid0;
63
64static struct workqueue_struct *clean_wq;
65
66enum mcast_state {
67	MCAST_NOT_MEMBER = 0,
68	MCAST_MEMBER,
69};
70
71enum mcast_group_state {
72	MCAST_IDLE,
73	MCAST_JOIN_SENT,
74	MCAST_LEAVE_SENT,
75	MCAST_RESP_READY
76};
77
78struct mcast_member {
79	enum mcast_state state;
80	uint8_t			join_state;
81	int			num_pend_reqs;
82	struct list_head	pending;
83};
84
85struct ib_sa_mcmember_data {
86	union ib_gid	mgid;
87	union ib_gid	port_gid;
88	__be32		qkey;
89	__be16		mlid;
90	u8		mtusel_mtu;
91	u8		tclass;
92	__be16		pkey;
93	u8		ratesel_rate;
94	u8		lifetmsel_lifetm;
95	__be32		sl_flowlabel_hoplimit;
96	u8		scope_join_state;
97	u8		proxy_join;
98	u8		reserved[2];
99} __packed __aligned(4);
100
101struct mcast_group {
102	struct ib_sa_mcmember_data rec;
103	struct rb_node		node;
104	struct list_head	mgid0_list;
105	struct mlx4_ib_demux_ctx *demux;
106	struct mcast_member	func[MAX_VFS];
107	struct mutex		lock;
108	struct work_struct	work;
109	struct list_head	pending_list;
110	int			members[3];
111	enum mcast_group_state	state;
112	enum mcast_group_state	prev_state;
113	struct ib_sa_mad	response_sa_mad;
114	__be64			last_req_tid;
115
116	char			name[33]; /* MGID string */
117	struct device_attribute	dentry;
118
119	/* refcount is the reference count for the following:
120	   1. Each queued request
121	   2. Each invocation of the worker thread
122	   3. Membership of the port at the SA
123	*/
124	atomic_t		refcount;
125
126	/* delayed work to clean pending SM request */
127	struct delayed_work	timeout_work;
128	struct list_head	cleanup_list;
129};
130
131struct mcast_req {
132	int			func;
133	struct ib_sa_mad	sa_mad;
134	struct list_head	group_list;
135	struct list_head	func_list;
136	struct mcast_group	*group;
137	int			clean;
138};
139
140
141#define safe_atomic_dec(ref) \
142	do {\
143		if (atomic_dec_and_test(ref)) \
144			mcg_warn_group(group, "did not expect to reach zero\n"); \
145	} while (0)
146
147static const char *get_state_string(enum mcast_group_state state)
148{
149	switch (state) {
150	case MCAST_IDLE:
151		return "MCAST_IDLE";
152	case MCAST_JOIN_SENT:
153		return "MCAST_JOIN_SENT";
154	case MCAST_LEAVE_SENT:
155		return "MCAST_LEAVE_SENT";
156	case MCAST_RESP_READY:
157		return "MCAST_RESP_READY";
158	}
159	return "Invalid State";
160}
161
162static struct mcast_group *mcast_find(struct mlx4_ib_demux_ctx *ctx,
163				      union ib_gid *mgid)
164{
165	struct rb_node *node = ctx->mcg_table.rb_node;
166	struct mcast_group *group;
167	int ret;
168
169	while (node) {
170		group = rb_entry(node, struct mcast_group, node);
171		ret = memcmp(mgid->raw, group->rec.mgid.raw, sizeof *mgid);
172		if (!ret)
173			return group;
174
175		if (ret < 0)
176			node = node->rb_left;
177		else
178			node = node->rb_right;
179	}
180	return NULL;
181}
182
183static struct mcast_group *mcast_insert(struct mlx4_ib_demux_ctx *ctx,
184					struct mcast_group *group)
185{
186	struct rb_node **link = &ctx->mcg_table.rb_node;
187	struct rb_node *parent = NULL;
188	struct mcast_group *cur_group;
189	int ret;
190
191	while (*link) {
192		parent = *link;
193		cur_group = rb_entry(parent, struct mcast_group, node);
194
195		ret = memcmp(group->rec.mgid.raw, cur_group->rec.mgid.raw,
196			     sizeof group->rec.mgid);
197		if (ret < 0)
198			link = &(*link)->rb_left;
199		else if (ret > 0)
200			link = &(*link)->rb_right;
201		else
202			return cur_group;
203	}
204	rb_link_node(&group->node, parent, link);
205	rb_insert_color(&group->node, &ctx->mcg_table);
206	return NULL;
207}
208
209static int send_mad_to_wire(struct mlx4_ib_demux_ctx *ctx, struct ib_mad *mad)
210{
211	struct mlx4_ib_dev *dev = ctx->dev;
212	struct rdma_ah_attr	ah_attr;
213	unsigned long flags;
214
215	spin_lock_irqsave(&dev->sm_lock, flags);
216	if (!dev->sm_ah[ctx->port - 1]) {
217		/* port is not yet Active, sm_ah not ready */
218		spin_unlock_irqrestore(&dev->sm_lock, flags);
219		return -EAGAIN;
220	}
221	mlx4_ib_query_ah(dev->sm_ah[ctx->port - 1], &ah_attr);
222	spin_unlock_irqrestore(&dev->sm_lock, flags);
223	return mlx4_ib_send_to_wire(dev, mlx4_master_func_num(dev->dev),
224				    ctx->port, IB_QPT_GSI, 0, 1, IB_QP1_QKEY,
225				    &ah_attr, NULL, 0xffff, mad);
226}
227
228static int send_mad_to_slave(int slave, struct mlx4_ib_demux_ctx *ctx,
229			     struct ib_mad *mad)
230{
231	struct mlx4_ib_dev *dev = ctx->dev;
232	struct ib_mad_agent *agent = dev->send_agent[ctx->port - 1][1];
233	struct ib_wc wc;
234	struct rdma_ah_attr ah_attr;
235
236	/* Our agent might not yet be registered when mads start to arrive */
237	if (!agent)
238		return -EAGAIN;
239
240	rdma_query_ah(dev->sm_ah[ctx->port - 1], &ah_attr);
241
242	if (ib_find_cached_pkey(&dev->ib_dev, ctx->port, IB_DEFAULT_PKEY_FULL, &wc.pkey_index))
243		return -EINVAL;
244	wc.sl = 0;
245	wc.dlid_path_bits = 0;
246	wc.port_num = ctx->port;
247	wc.slid = rdma_ah_get_dlid(&ah_attr);  /* opensm lid */
248	wc.src_qp = 1;
249	return mlx4_ib_send_to_slave(dev, slave, ctx->port, IB_QPT_GSI, &wc, NULL, mad);
250}
251
252static int send_join_to_wire(struct mcast_group *group, struct ib_sa_mad *sa_mad)
253{
254	struct ib_sa_mad mad;
255	struct ib_sa_mcmember_data *sa_mad_data = (struct ib_sa_mcmember_data *)&mad.data;
256	int ret;
257
258	/* we rely on a mad request as arrived from a VF */
259	memcpy(&mad, sa_mad, sizeof mad);
260
261	/* fix port GID to be the real one (slave 0) */
262	sa_mad_data->port_gid.global.interface_id = group->demux->guid_cache[0];
263
264	/* assign our own TID */
265	mad.mad_hdr.tid = mlx4_ib_get_new_demux_tid(group->demux);
266	group->last_req_tid = mad.mad_hdr.tid; /* keep it for later validation */
267
268	ret = send_mad_to_wire(group->demux, (struct ib_mad *)&mad);
269	/* set timeout handler */
270	if (!ret) {
271		/* calls mlx4_ib_mcg_timeout_handler */
272		queue_delayed_work(group->demux->mcg_wq, &group->timeout_work,
273				msecs_to_jiffies(MAD_TIMEOUT_MS));
274	}
275
276	return ret;
277}
278
279static int send_leave_to_wire(struct mcast_group *group, u8 join_state)
280{
281	struct ib_sa_mad mad;
282	struct ib_sa_mcmember_data *sa_data = (struct ib_sa_mcmember_data *)&mad.data;
283	int ret;
284
285	memset(&mad, 0, sizeof mad);
286	mad.mad_hdr.base_version = 1;
287	mad.mad_hdr.mgmt_class = IB_MGMT_CLASS_SUBN_ADM;
288	mad.mad_hdr.class_version = 2;
289	mad.mad_hdr.method = IB_SA_METHOD_DELETE;
290	mad.mad_hdr.status = cpu_to_be16(0);
291	mad.mad_hdr.class_specific = cpu_to_be16(0);
292	mad.mad_hdr.tid = mlx4_ib_get_new_demux_tid(group->demux);
293	group->last_req_tid = mad.mad_hdr.tid; /* keep it for later validation */
294	mad.mad_hdr.attr_id = cpu_to_be16(IB_SA_ATTR_MC_MEMBER_REC);
295	mad.mad_hdr.attr_mod = cpu_to_be32(0);
296	mad.sa_hdr.sm_key = 0x0;
297	mad.sa_hdr.attr_offset = cpu_to_be16(7);
298	mad.sa_hdr.comp_mask = IB_SA_MCMEMBER_REC_MGID |
299		IB_SA_MCMEMBER_REC_PORT_GID | IB_SA_MCMEMBER_REC_JOIN_STATE;
300
301	*sa_data = group->rec;
302	sa_data->scope_join_state = join_state;
303
304	ret = send_mad_to_wire(group->demux, (struct ib_mad *)&mad);
305	if (ret)
306		group->state = MCAST_IDLE;
307
308	/* set timeout handler */
309	if (!ret) {
310		/* calls mlx4_ib_mcg_timeout_handler */
311		queue_delayed_work(group->demux->mcg_wq, &group->timeout_work,
312				msecs_to_jiffies(MAD_TIMEOUT_MS));
313	}
314
315	return ret;
316}
317
318static int send_reply_to_slave(int slave, struct mcast_group *group,
319		struct ib_sa_mad *req_sa_mad, u16 status)
320{
321	struct ib_sa_mad mad;
322	struct ib_sa_mcmember_data *sa_data = (struct ib_sa_mcmember_data *)&mad.data;
323	struct ib_sa_mcmember_data *req_sa_data = (struct ib_sa_mcmember_data *)&req_sa_mad->data;
324	int ret;
325
326	memset(&mad, 0, sizeof mad);
327	mad.mad_hdr.base_version = 1;
328	mad.mad_hdr.mgmt_class = IB_MGMT_CLASS_SUBN_ADM;
329	mad.mad_hdr.class_version = 2;
330	mad.mad_hdr.method = IB_MGMT_METHOD_GET_RESP;
331	mad.mad_hdr.status = cpu_to_be16(status);
332	mad.mad_hdr.class_specific = cpu_to_be16(0);
333	mad.mad_hdr.tid = req_sa_mad->mad_hdr.tid;
334	*(u8 *)&mad.mad_hdr.tid = 0; /* resetting tid to 0 */
335	mad.mad_hdr.attr_id = cpu_to_be16(IB_SA_ATTR_MC_MEMBER_REC);
336	mad.mad_hdr.attr_mod = cpu_to_be32(0);
337	mad.sa_hdr.sm_key = req_sa_mad->sa_hdr.sm_key;
338	mad.sa_hdr.attr_offset = cpu_to_be16(7);
339	mad.sa_hdr.comp_mask = 0; /* ignored on responses, see IBTA spec */
340
341	*sa_data = group->rec;
342
343	/* reconstruct VF's requested join_state and port_gid */
344	sa_data->scope_join_state &= 0xf0;
345	sa_data->scope_join_state |= (group->func[slave].join_state & 0x0f);
346	memcpy(&sa_data->port_gid, &req_sa_data->port_gid, sizeof req_sa_data->port_gid);
347
348	ret = send_mad_to_slave(slave, group->demux, (struct ib_mad *)&mad);
349	return ret;
350}
351
352static int check_selector(ib_sa_comp_mask comp_mask,
353			  ib_sa_comp_mask selector_mask,
354			  ib_sa_comp_mask value_mask,
355			  u8 src_value, u8 dst_value)
356{
357	int err;
358	u8 selector = dst_value >> 6;
359	dst_value &= 0x3f;
360	src_value &= 0x3f;
361
362	if (!(comp_mask & selector_mask) || !(comp_mask & value_mask))
363		return 0;
364
365	switch (selector) {
366	case IB_SA_GT:
367		err = (src_value <= dst_value);
368		break;
369	case IB_SA_LT:
370		err = (src_value >= dst_value);
371		break;
372	case IB_SA_EQ:
373		err = (src_value != dst_value);
374		break;
375	default:
376		err = 0;
377		break;
378	}
379
380	return err;
381}
382
383static u16 cmp_rec(struct ib_sa_mcmember_data *src,
384		   struct ib_sa_mcmember_data *dst, ib_sa_comp_mask comp_mask)
385{
386	/* src is group record, dst is request record */
387	/* MGID must already match */
388	/* Port_GID we always replace to our Port_GID, so it is a match */
389
390#define MAD_STATUS_REQ_INVALID 0x0200
391	if (comp_mask & IB_SA_MCMEMBER_REC_QKEY && src->qkey != dst->qkey)
392		return MAD_STATUS_REQ_INVALID;
393	if (comp_mask & IB_SA_MCMEMBER_REC_MLID && src->mlid != dst->mlid)
394		return MAD_STATUS_REQ_INVALID;
395	if (check_selector(comp_mask, IB_SA_MCMEMBER_REC_MTU_SELECTOR,
396				 IB_SA_MCMEMBER_REC_MTU,
397				 src->mtusel_mtu, dst->mtusel_mtu))
398		return MAD_STATUS_REQ_INVALID;
399	if (comp_mask & IB_SA_MCMEMBER_REC_TRAFFIC_CLASS &&
400	    src->tclass != dst->tclass)
401		return MAD_STATUS_REQ_INVALID;
402	if (comp_mask & IB_SA_MCMEMBER_REC_PKEY && src->pkey != dst->pkey)
403		return MAD_STATUS_REQ_INVALID;
404	if (check_selector(comp_mask, IB_SA_MCMEMBER_REC_RATE_SELECTOR,
405				 IB_SA_MCMEMBER_REC_RATE,
406				 src->ratesel_rate, dst->ratesel_rate))
407		return MAD_STATUS_REQ_INVALID;
408	if (check_selector(comp_mask,
409				 IB_SA_MCMEMBER_REC_PACKET_LIFE_TIME_SELECTOR,
410				 IB_SA_MCMEMBER_REC_PACKET_LIFE_TIME,
411				 src->lifetmsel_lifetm, dst->lifetmsel_lifetm))
412		return MAD_STATUS_REQ_INVALID;
413	if (comp_mask & IB_SA_MCMEMBER_REC_SL &&
414			(be32_to_cpu(src->sl_flowlabel_hoplimit) & 0xf0000000) !=
415			(be32_to_cpu(dst->sl_flowlabel_hoplimit) & 0xf0000000))
416		return MAD_STATUS_REQ_INVALID;
417	if (comp_mask & IB_SA_MCMEMBER_REC_FLOW_LABEL &&
418			(be32_to_cpu(src->sl_flowlabel_hoplimit) & 0x0fffff00) !=
419			(be32_to_cpu(dst->sl_flowlabel_hoplimit) & 0x0fffff00))
420		return MAD_STATUS_REQ_INVALID;
421	if (comp_mask & IB_SA_MCMEMBER_REC_HOP_LIMIT &&
422			(be32_to_cpu(src->sl_flowlabel_hoplimit) & 0x000000ff) !=
423			(be32_to_cpu(dst->sl_flowlabel_hoplimit) & 0x000000ff))
424		return MAD_STATUS_REQ_INVALID;
425	if (comp_mask & IB_SA_MCMEMBER_REC_SCOPE &&
426			(src->scope_join_state & 0xf0) !=
427			(dst->scope_join_state & 0xf0))
428		return MAD_STATUS_REQ_INVALID;
429
430	/* join_state checked separately, proxy_join ignored */
431
432	return 0;
433}
434
435/* release group, return 1 if this was last release and group is destroyed
436 * timout work is canceled sync */
437static int release_group(struct mcast_group *group, int from_timeout_handler)
438{
439	struct mlx4_ib_demux_ctx *ctx = group->demux;
440	int nzgroup;
441
442	mutex_lock(&ctx->mcg_table_lock);
443	mutex_lock(&group->lock);
444	if (atomic_dec_and_test(&group->refcount)) {
445		if (!from_timeout_handler) {
446			if (group->state != MCAST_IDLE &&
447			    !cancel_delayed_work(&group->timeout_work)) {
448				atomic_inc(&group->refcount);
449				mutex_unlock(&group->lock);
450				mutex_unlock(&ctx->mcg_table_lock);
451				return 0;
452			}
453		}
454
455		nzgroup = memcmp(&group->rec.mgid, &mgid0, sizeof mgid0);
456		if (nzgroup)
457			del_sysfs_port_mcg_attr(ctx->dev, ctx->port, &group->dentry.attr);
458		if (!list_empty(&group->pending_list))
459			mcg_warn_group(group, "releasing a group with non empty pending list\n");
460		if (nzgroup)
461			rb_erase(&group->node, &ctx->mcg_table);
462		list_del_init(&group->mgid0_list);
463		mutex_unlock(&group->lock);
464		mutex_unlock(&ctx->mcg_table_lock);
465		kfree(group);
466		return 1;
467	} else {
468		mutex_unlock(&group->lock);
469		mutex_unlock(&ctx->mcg_table_lock);
470	}
471	return 0;
472}
473
474static void adjust_membership(struct mcast_group *group, u8 join_state, int inc)
475{
476	int i;
477
478	for (i = 0; i < 3; i++, join_state >>= 1)
479		if (join_state & 0x1)
480			group->members[i] += inc;
481}
482
483static u8 get_leave_state(struct mcast_group *group)
484{
485	u8 leave_state = 0;
486	int i;
487
488	for (i = 0; i < 3; i++)
489		if (!group->members[i])
490			leave_state |= (1 << i);
491
492	return leave_state & (group->rec.scope_join_state & 0xf);
493}
494
495static int join_group(struct mcast_group *group, int slave, u8 join_mask)
496{
497	int ret = 0;
498	u8 join_state;
499
500	/* remove bits that slave is already member of, and adjust */
501	join_state = join_mask & (~group->func[slave].join_state);
502	adjust_membership(group, join_state, 1);
503	group->func[slave].join_state |= join_state;
504	if (group->func[slave].state != MCAST_MEMBER && join_state) {
505		group->func[slave].state = MCAST_MEMBER;
506		ret = 1;
507	}
508	return ret;
509}
510
511static int leave_group(struct mcast_group *group, int slave, u8 leave_state)
512{
513	int ret = 0;
514
515	adjust_membership(group, leave_state, -1);
516	group->func[slave].join_state &= ~leave_state;
517	if (!group->func[slave].join_state) {
518		group->func[slave].state = MCAST_NOT_MEMBER;
519		ret = 1;
520	}
521	return ret;
522}
523
524static int check_leave(struct mcast_group *group, int slave, u8 leave_mask)
525{
526	if (group->func[slave].state != MCAST_MEMBER)
527		return MAD_STATUS_REQ_INVALID;
528
529	/* make sure we're not deleting unset bits */
530	if (~group->func[slave].join_state & leave_mask)
531		return MAD_STATUS_REQ_INVALID;
532
533	if (!leave_mask)
534		return MAD_STATUS_REQ_INVALID;
535
536	return 0;
537}
538
539static void mlx4_ib_mcg_timeout_handler(struct work_struct *work)
540{
541	struct delayed_work *delay = to_delayed_work(work);
542	struct mcast_group *group;
543	struct mcast_req *req = NULL;
544
545	group = container_of(delay, typeof(*group), timeout_work);
546
547	mutex_lock(&group->lock);
548	if (group->state == MCAST_JOIN_SENT) {
549		if (!list_empty(&group->pending_list)) {
550			req = list_first_entry(&group->pending_list, struct mcast_req, group_list);
551			list_del(&req->group_list);
552			list_del(&req->func_list);
553			--group->func[req->func].num_pend_reqs;
554			mutex_unlock(&group->lock);
555			kfree(req);
556			if (memcmp(&group->rec.mgid, &mgid0, sizeof mgid0)) {
557				if (release_group(group, 1))
558					return;
559			} else {
560				kfree(group);
561				return;
562			}
563			mutex_lock(&group->lock);
564		} else
565			mcg_warn_group(group, "DRIVER BUG\n");
566	} else if (group->state == MCAST_LEAVE_SENT) {
567		if (group->rec.scope_join_state & 0xf)
568			group->rec.scope_join_state &= 0xf0;
569		group->state = MCAST_IDLE;
570		mutex_unlock(&group->lock);
571		if (release_group(group, 1))
572			return;
573		mutex_lock(&group->lock);
574	} else
575		mcg_warn_group(group, "invalid state %s\n", get_state_string(group->state));
576	group->state = MCAST_IDLE;
577	atomic_inc(&group->refcount);
578	if (!queue_work(group->demux->mcg_wq, &group->work))
579		safe_atomic_dec(&group->refcount);
580
581	mutex_unlock(&group->lock);
582}
583
584static int handle_leave_req(struct mcast_group *group, u8 leave_mask,
585			    struct mcast_req *req)
586{
587	u16 status;
588
589	if (req->clean)
590		leave_mask = group->func[req->func].join_state;
591
592	status = check_leave(group, req->func, leave_mask);
593	if (!status)
594		leave_group(group, req->func, leave_mask);
595
596	if (!req->clean)
597		send_reply_to_slave(req->func, group, &req->sa_mad, status);
598	--group->func[req->func].num_pend_reqs;
599	list_del(&req->group_list);
600	list_del(&req->func_list);
601	kfree(req);
602	return 1;
603}
604
605static int handle_join_req(struct mcast_group *group, u8 join_mask,
606			   struct mcast_req *req)
607{
608	u8 group_join_state = group->rec.scope_join_state & 0xf;
609	int ref = 0;
610	u16 status;
611	struct ib_sa_mcmember_data *sa_data = (struct ib_sa_mcmember_data *)req->sa_mad.data;
612
613	if (join_mask == (group_join_state & join_mask)) {
614		/* port's membership need not change */
615		status = cmp_rec(&group->rec, sa_data, req->sa_mad.sa_hdr.comp_mask);
616		if (!status)
617			join_group(group, req->func, join_mask);
618
619		--group->func[req->func].num_pend_reqs;
620		send_reply_to_slave(req->func, group, &req->sa_mad, status);
621		list_del(&req->group_list);
622		list_del(&req->func_list);
623		kfree(req);
624		++ref;
625	} else {
626		/* port's membership needs to be updated */
627		group->prev_state = group->state;
628		if (send_join_to_wire(group, &req->sa_mad)) {
629			--group->func[req->func].num_pend_reqs;
630			list_del(&req->group_list);
631			list_del(&req->func_list);
632			kfree(req);
633			ref = 1;
634			group->state = group->prev_state;
635		} else
636			group->state = MCAST_JOIN_SENT;
637	}
638
639	return ref;
640}
641
642static void mlx4_ib_mcg_work_handler(struct work_struct *work)
643{
644	struct mcast_group *group;
645	struct mcast_req *req = NULL;
646	struct ib_sa_mcmember_data *sa_data;
647	u8 req_join_state;
648	int rc = 1; /* release_count - this is for the scheduled work */
649	u16 status;
650	u8 method;
651
652	group = container_of(work, typeof(*group), work);
653
654	mutex_lock(&group->lock);
655
656	/* First, let's see if a response from SM is waiting regarding this group.
657	 * If so, we need to update the group's REC. If this is a bad response, we
658	 * may need to send a bad response to a VF waiting for it. If VF is waiting
659	 * and this is a good response, the VF will be answered later in this func. */
660	if (group->state == MCAST_RESP_READY) {
661		/* cancels mlx4_ib_mcg_timeout_handler */
662		cancel_delayed_work(&group->timeout_work);
663		status = be16_to_cpu(group->response_sa_mad.mad_hdr.status);
664		method = group->response_sa_mad.mad_hdr.method;
665		if (group->last_req_tid != group->response_sa_mad.mad_hdr.tid) {
666			mcg_warn_group(group, "Got MAD response to existing MGID but wrong TID, dropping. Resp TID=%llx, group TID=%llx\n",
667				be64_to_cpu(group->response_sa_mad.mad_hdr.tid),
668				be64_to_cpu(group->last_req_tid));
669			group->state = group->prev_state;
670			goto process_requests;
671		}
672		if (status) {
673			if (!list_empty(&group->pending_list))
674				req = list_first_entry(&group->pending_list,
675						struct mcast_req, group_list);
676			if (method == IB_MGMT_METHOD_GET_RESP) {
677					if (req) {
678						send_reply_to_slave(req->func, group, &req->sa_mad, status);
679						--group->func[req->func].num_pend_reqs;
680						list_del(&req->group_list);
681						list_del(&req->func_list);
682						kfree(req);
683						++rc;
684					} else
685						mcg_warn_group(group, "no request for failed join\n");
686			} else if (method == IB_SA_METHOD_DELETE_RESP && group->demux->flushing)
687				++rc;
688		} else {
689			u8 resp_join_state;
690			u8 cur_join_state;
691
692			resp_join_state = ((struct ib_sa_mcmember_data *)
693						group->response_sa_mad.data)->scope_join_state & 0xf;
694			cur_join_state = group->rec.scope_join_state & 0xf;
695
696			if (method == IB_MGMT_METHOD_GET_RESP) {
697				/* successfull join */
698				if (!cur_join_state && resp_join_state)
699					--rc;
700			} else if (!resp_join_state)
701					++rc;
702			memcpy(&group->rec, group->response_sa_mad.data, sizeof group->rec);
703		}
704		group->state = MCAST_IDLE;
705	}
706
707process_requests:
708	/* We should now go over pending join/leave requests, as long as we are idle. */
709	while (!list_empty(&group->pending_list) && group->state == MCAST_IDLE) {
710		req = list_first_entry(&group->pending_list, struct mcast_req,
711				       group_list);
712		sa_data = (struct ib_sa_mcmember_data *)req->sa_mad.data;
713		req_join_state = sa_data->scope_join_state & 0xf;
714
715		/* For a leave request, we will immediately answer the VF, and
716		 * update our internal counters. The actual leave will be sent
717		 * to SM later, if at all needed. We dequeue the request now. */
718		if (req->sa_mad.mad_hdr.method == IB_SA_METHOD_DELETE)
719			rc += handle_leave_req(group, req_join_state, req);
720		else
721			rc += handle_join_req(group, req_join_state, req);
722	}
723
724	/* Handle leaves */
725	if (group->state == MCAST_IDLE) {
726		req_join_state = get_leave_state(group);
727		if (req_join_state) {
728			group->rec.scope_join_state &= ~req_join_state;
729			group->prev_state = group->state;
730			if (send_leave_to_wire(group, req_join_state)) {
731				group->state = group->prev_state;
732				++rc;
733			} else
734				group->state = MCAST_LEAVE_SENT;
735		}
736	}
737
738	if (!list_empty(&group->pending_list) && group->state == MCAST_IDLE)
739		goto process_requests;
740	mutex_unlock(&group->lock);
741
742	while (rc--)
743		release_group(group, 0);
744}
745
746static struct mcast_group *search_relocate_mgid0_group(struct mlx4_ib_demux_ctx *ctx,
747						       __be64 tid,
748						       union ib_gid *new_mgid)
749{
750	struct mcast_group *group = NULL, *cur_group, *n;
751	struct mcast_req *req;
752
753	mutex_lock(&ctx->mcg_table_lock);
754	list_for_each_entry_safe(group, n, &ctx->mcg_mgid0_list, mgid0_list) {
755		mutex_lock(&group->lock);
756		if (group->last_req_tid == tid) {
757			if (memcmp(new_mgid, &mgid0, sizeof mgid0)) {
758				group->rec.mgid = *new_mgid;
759				sprintf(group->name, "%016llx%016llx",
760						be64_to_cpu(group->rec.mgid.global.subnet_prefix),
761						be64_to_cpu(group->rec.mgid.global.interface_id));
762				list_del_init(&group->mgid0_list);
763				cur_group = mcast_insert(ctx, group);
764				if (cur_group) {
765					/* A race between our code and SM. Silently cleaning the new one */
766					req = list_first_entry(&group->pending_list,
767							       struct mcast_req, group_list);
768					--group->func[req->func].num_pend_reqs;
769					list_del(&req->group_list);
770					list_del(&req->func_list);
771					kfree(req);
772					mutex_unlock(&group->lock);
773					mutex_unlock(&ctx->mcg_table_lock);
774					release_group(group, 0);
775					return NULL;
776				}
777
778				atomic_inc(&group->refcount);
779				add_sysfs_port_mcg_attr(ctx->dev, ctx->port, &group->dentry.attr);
780				mutex_unlock(&group->lock);
781				mutex_unlock(&ctx->mcg_table_lock);
782				return group;
783			} else {
784				struct mcast_req *tmp1, *tmp2;
785
786				list_del(&group->mgid0_list);
787				if (!list_empty(&group->pending_list) && group->state != MCAST_IDLE)
788					cancel_delayed_work_sync(&group->timeout_work);
789
790				list_for_each_entry_safe(tmp1, tmp2, &group->pending_list, group_list) {
791					list_del(&tmp1->group_list);
792					kfree(tmp1);
793				}
794				mutex_unlock(&group->lock);
795				mutex_unlock(&ctx->mcg_table_lock);
796				kfree(group);
797				return NULL;
798			}
799		}
800		mutex_unlock(&group->lock);
801	}
802	mutex_unlock(&ctx->mcg_table_lock);
803
804	return NULL;
805}
806
807static ssize_t sysfs_show_group(struct device *dev,
808		struct device_attribute *attr, char *buf);
809
810static struct mcast_group *acquire_group(struct mlx4_ib_demux_ctx *ctx,
811					 union ib_gid *mgid, int create)
812{
813	struct mcast_group *group, *cur_group;
814	int is_mgid0;
815	int i;
816
817	is_mgid0 = !memcmp(&mgid0, mgid, sizeof mgid0);
818	if (!is_mgid0) {
819		group = mcast_find(ctx, mgid);
820		if (group)
821			goto found;
822	}
823
824	if (!create)
825		return ERR_PTR(-ENOENT);
826
827	group = kzalloc(sizeof(*group), GFP_KERNEL);
828	if (!group)
829		return ERR_PTR(-ENOMEM);
830
831	group->demux = ctx;
832	group->rec.mgid = *mgid;
833	INIT_LIST_HEAD(&group->pending_list);
834	INIT_LIST_HEAD(&group->mgid0_list);
835	for (i = 0; i < MAX_VFS; ++i)
836		INIT_LIST_HEAD(&group->func[i].pending);
837	INIT_WORK(&group->work, mlx4_ib_mcg_work_handler);
838	INIT_DELAYED_WORK(&group->timeout_work, mlx4_ib_mcg_timeout_handler);
839	mutex_init(&group->lock);
840	sprintf(group->name, "%016llx%016llx",
841			be64_to_cpu(group->rec.mgid.global.subnet_prefix),
842			be64_to_cpu(group->rec.mgid.global.interface_id));
843	sysfs_attr_init(&group->dentry.attr);
844	group->dentry.show = sysfs_show_group;
845	group->dentry.store = NULL;
846	group->dentry.attr.name = group->name;
847	group->dentry.attr.mode = 0400;
848	group->state = MCAST_IDLE;
849
850	if (is_mgid0) {
851		list_add(&group->mgid0_list, &ctx->mcg_mgid0_list);
852		goto found;
853	}
854
855	cur_group = mcast_insert(ctx, group);
856	if (cur_group) {
857		mcg_warn("group just showed up %s - confused\n", cur_group->name);
858		kfree(group);
859		return ERR_PTR(-EINVAL);
860	}
861
862	add_sysfs_port_mcg_attr(ctx->dev, ctx->port, &group->dentry.attr);
863
864found:
865	atomic_inc(&group->refcount);
866	return group;
867}
868
869static void queue_req(struct mcast_req *req)
870{
871	struct mcast_group *group = req->group;
872
873	atomic_inc(&group->refcount); /* for the request */
874	atomic_inc(&group->refcount); /* for scheduling the work */
875	list_add_tail(&req->group_list, &group->pending_list);
876	list_add_tail(&req->func_list, &group->func[req->func].pending);
877	/* calls mlx4_ib_mcg_work_handler */
878	if (!queue_work(group->demux->mcg_wq, &group->work))
879		safe_atomic_dec(&group->refcount);
880}
881
882int mlx4_ib_mcg_demux_handler(struct ib_device *ibdev, int port, int slave,
883			      struct ib_sa_mad *mad)
884{
885	struct mlx4_ib_dev *dev = to_mdev(ibdev);
886	struct ib_sa_mcmember_data *rec = (struct ib_sa_mcmember_data *)mad->data;
887	struct mlx4_ib_demux_ctx *ctx = &dev->sriov.demux[port - 1];
888	struct mcast_group *group;
889
890	switch (mad->mad_hdr.method) {
891	case IB_MGMT_METHOD_GET_RESP:
892	case IB_SA_METHOD_DELETE_RESP:
893		mutex_lock(&ctx->mcg_table_lock);
894		group = acquire_group(ctx, &rec->mgid, 0);
895		mutex_unlock(&ctx->mcg_table_lock);
896		if (IS_ERR(group)) {
897			if (mad->mad_hdr.method == IB_MGMT_METHOD_GET_RESP) {
898				__be64 tid = mad->mad_hdr.tid;
899				*(u8 *)(&tid) = (u8)slave; /* in group we kept the modified TID */
900				group = search_relocate_mgid0_group(ctx, tid, &rec->mgid);
901			} else
902				group = NULL;
903		}
904
905		if (!group)
906			return 1;
907
908		mutex_lock(&group->lock);
909		group->response_sa_mad = *mad;
910		group->prev_state = group->state;
911		group->state = MCAST_RESP_READY;
912		/* calls mlx4_ib_mcg_work_handler */
913		atomic_inc(&group->refcount);
914		if (!queue_work(ctx->mcg_wq, &group->work))
915			safe_atomic_dec(&group->refcount);
916		mutex_unlock(&group->lock);
917		release_group(group, 0);
918		return 1; /* consumed */
919	case IB_MGMT_METHOD_SET:
920	case IB_SA_METHOD_GET_TABLE:
921	case IB_SA_METHOD_GET_TABLE_RESP:
922	case IB_SA_METHOD_DELETE:
923		return 0; /* not consumed, pass-through to guest over tunnel */
924	default:
925		mcg_warn("In demux, port %d: unexpected MCMember method: 0x%x, dropping\n",
926			port, mad->mad_hdr.method);
927		return 1; /* consumed */
928	}
929}
930
931int mlx4_ib_mcg_multiplex_handler(struct ib_device *ibdev, int port,
932				  int slave, struct ib_sa_mad *sa_mad)
933{
934	struct mlx4_ib_dev *dev = to_mdev(ibdev);
935	struct ib_sa_mcmember_data *rec = (struct ib_sa_mcmember_data *)sa_mad->data;
936	struct mlx4_ib_demux_ctx *ctx = &dev->sriov.demux[port - 1];
937	struct mcast_group *group;
938	struct mcast_req *req;
939	int may_create = 0;
940
941	if (ctx->flushing)
942		return -EAGAIN;
943
944	switch (sa_mad->mad_hdr.method) {
945	case IB_MGMT_METHOD_SET:
946		may_create = 1;
947		fallthrough;
948	case IB_SA_METHOD_DELETE:
949		req = kzalloc(sizeof *req, GFP_KERNEL);
950		if (!req)
951			return -ENOMEM;
952
953		req->func = slave;
954		req->sa_mad = *sa_mad;
955
956		mutex_lock(&ctx->mcg_table_lock);
957		group = acquire_group(ctx, &rec->mgid, may_create);
958		mutex_unlock(&ctx->mcg_table_lock);
959		if (IS_ERR(group)) {
960			kfree(req);
961			return PTR_ERR(group);
962		}
963		mutex_lock(&group->lock);
964		if (group->func[slave].num_pend_reqs > MAX_PEND_REQS_PER_FUNC) {
965			mutex_unlock(&group->lock);
966			mcg_debug_group(group, "Port %d, Func %d has too many pending requests (%d), dropping\n",
967					port, slave, MAX_PEND_REQS_PER_FUNC);
968			release_group(group, 0);
969			kfree(req);
970			return -ENOMEM;
971		}
972		++group->func[slave].num_pend_reqs;
973		req->group = group;
974		queue_req(req);
975		mutex_unlock(&group->lock);
976		release_group(group, 0);
977		return 1; /* consumed */
978	case IB_SA_METHOD_GET_TABLE:
979	case IB_MGMT_METHOD_GET_RESP:
980	case IB_SA_METHOD_GET_TABLE_RESP:
981	case IB_SA_METHOD_DELETE_RESP:
982		return 0; /* not consumed, pass-through */
983	default:
984		mcg_warn("In multiplex, port %d, func %d: unexpected MCMember method: 0x%x, dropping\n",
985			port, slave, sa_mad->mad_hdr.method);
986		return 1; /* consumed */
987	}
988}
989
990static ssize_t sysfs_show_group(struct device *dev,
991		struct device_attribute *attr, char *buf)
992{
993	struct mcast_group *group =
994		container_of(attr, struct mcast_group, dentry);
995	struct mcast_req *req = NULL;
996	char pending_str[40];
997	char state_str[40];
998	ssize_t len = 0;
999	int f;
1000
1001	if (group->state == MCAST_IDLE)
1002		sprintf(state_str, "%s", get_state_string(group->state));
1003	else
1004		sprintf(state_str, "%s(TID=0x%llx)",
1005				get_state_string(group->state),
1006				be64_to_cpu(group->last_req_tid));
1007	if (list_empty(&group->pending_list)) {
1008		sprintf(pending_str, "No");
1009	} else {
1010		req = list_first_entry(&group->pending_list, struct mcast_req, group_list);
1011		sprintf(pending_str, "Yes(TID=0x%llx)",
1012				be64_to_cpu(req->sa_mad.mad_hdr.tid));
1013	}
1014	len += sprintf(buf + len, "%1d [%02d,%02d,%02d] %4d %4s %5s     ",
1015			group->rec.scope_join_state & 0xf,
1016			group->members[2], group->members[1], group->members[0],
1017			atomic_read(&group->refcount),
1018			pending_str,
1019			state_str);
1020	for (f = 0; f < MAX_VFS; ++f)
1021		if (group->func[f].state == MCAST_MEMBER)
1022			len += sprintf(buf + len, "%d[%1x] ",
1023					f, group->func[f].join_state);
1024
1025	len += sprintf(buf + len, "\t\t(%4hx %4x %2x %2x %2x %2x %2x "
1026		"%4x %4x %2x %2x)\n",
1027		be16_to_cpu(group->rec.pkey),
1028		be32_to_cpu(group->rec.qkey),
1029		(group->rec.mtusel_mtu & 0xc0) >> 6,
1030		group->rec.mtusel_mtu & 0x3f,
1031		group->rec.tclass,
1032		(group->rec.ratesel_rate & 0xc0) >> 6,
1033		group->rec.ratesel_rate & 0x3f,
1034		(be32_to_cpu(group->rec.sl_flowlabel_hoplimit) & 0xf0000000) >> 28,
1035		(be32_to_cpu(group->rec.sl_flowlabel_hoplimit) & 0x0fffff00) >> 8,
1036		be32_to_cpu(group->rec.sl_flowlabel_hoplimit) & 0x000000ff,
1037		group->rec.proxy_join);
1038
1039	return len;
1040}
1041
1042int mlx4_ib_mcg_port_init(struct mlx4_ib_demux_ctx *ctx)
1043{
1044	char name[20];
1045
1046	atomic_set(&ctx->tid, 0);
1047	sprintf(name, "mlx4_ib_mcg%d", ctx->port);
1048	ctx->mcg_wq = alloc_ordered_workqueue(name, WQ_MEM_RECLAIM);
1049	if (!ctx->mcg_wq)
1050		return -ENOMEM;
1051
1052	mutex_init(&ctx->mcg_table_lock);
1053	ctx->mcg_table = RB_ROOT;
1054	INIT_LIST_HEAD(&ctx->mcg_mgid0_list);
1055	ctx->flushing = 0;
1056
1057	return 0;
1058}
1059
1060static void force_clean_group(struct mcast_group *group)
1061{
1062	struct mcast_req *req, *tmp
1063		;
1064	list_for_each_entry_safe(req, tmp, &group->pending_list, group_list) {
1065		list_del(&req->group_list);
1066		kfree(req);
1067	}
1068	del_sysfs_port_mcg_attr(group->demux->dev, group->demux->port, &group->dentry.attr);
1069	rb_erase(&group->node, &group->demux->mcg_table);
1070	kfree(group);
1071}
1072
1073static void _mlx4_ib_mcg_port_cleanup(struct mlx4_ib_demux_ctx *ctx, int destroy_wq)
1074{
1075	int i;
1076	struct rb_node *p;
1077	struct mcast_group *group;
1078	unsigned long end;
1079	int count;
1080
1081	for (i = 0; i < MAX_VFS; ++i)
1082		clean_vf_mcast(ctx, i);
1083
1084	end = jiffies + msecs_to_jiffies(MAD_TIMEOUT_MS + 3000);
1085	do {
1086		count = 0;
1087		mutex_lock(&ctx->mcg_table_lock);
1088		for (p = rb_first(&ctx->mcg_table); p; p = rb_next(p))
1089			++count;
1090		mutex_unlock(&ctx->mcg_table_lock);
1091		if (!count)
1092			break;
1093
1094		usleep_range(1000, 2000);
1095	} while (time_after(end, jiffies));
1096
1097	flush_workqueue(ctx->mcg_wq);
1098	if (destroy_wq)
1099		destroy_workqueue(ctx->mcg_wq);
1100
1101	mutex_lock(&ctx->mcg_table_lock);
1102	while ((p = rb_first(&ctx->mcg_table)) != NULL) {
1103		group = rb_entry(p, struct mcast_group, node);
1104		if (atomic_read(&group->refcount))
1105			mcg_debug_group(group, "group refcount %d!!! (pointer %p)\n",
1106					atomic_read(&group->refcount), group);
1107
1108		force_clean_group(group);
1109	}
1110	mutex_unlock(&ctx->mcg_table_lock);
1111}
1112
1113struct clean_work {
1114	struct work_struct work;
1115	struct mlx4_ib_demux_ctx *ctx;
1116	int destroy_wq;
1117};
1118
1119static void mcg_clean_task(struct work_struct *work)
1120{
1121	struct clean_work *cw = container_of(work, struct clean_work, work);
1122
1123	_mlx4_ib_mcg_port_cleanup(cw->ctx, cw->destroy_wq);
1124	cw->ctx->flushing = 0;
1125	kfree(cw);
1126}
1127
1128void mlx4_ib_mcg_port_cleanup(struct mlx4_ib_demux_ctx *ctx, int destroy_wq)
1129{
1130	struct clean_work *work;
1131
1132	if (ctx->flushing)
1133		return;
1134
1135	ctx->flushing = 1;
1136
1137	if (destroy_wq) {
1138		_mlx4_ib_mcg_port_cleanup(ctx, destroy_wq);
1139		ctx->flushing = 0;
1140		return;
1141	}
1142
1143	work = kmalloc(sizeof *work, GFP_KERNEL);
1144	if (!work) {
1145		ctx->flushing = 0;
1146		return;
1147	}
1148
1149	work->ctx = ctx;
1150	work->destroy_wq = destroy_wq;
1151	INIT_WORK(&work->work, mcg_clean_task);
1152	queue_work(clean_wq, &work->work);
1153}
1154
1155static void build_leave_mad(struct mcast_req *req)
1156{
1157	struct ib_sa_mad *mad = &req->sa_mad;
1158
1159	mad->mad_hdr.method = IB_SA_METHOD_DELETE;
1160}
1161
1162
1163static void clear_pending_reqs(struct mcast_group *group, int vf)
1164{
1165	struct mcast_req *req, *tmp, *group_first = NULL;
1166	int clear;
1167	int pend = 0;
1168
1169	if (!list_empty(&group->pending_list))
1170		group_first = list_first_entry(&group->pending_list, struct mcast_req, group_list);
1171
1172	list_for_each_entry_safe(req, tmp, &group->func[vf].pending, func_list) {
1173		clear = 1;
1174		if (group_first == req &&
1175		    (group->state == MCAST_JOIN_SENT ||
1176		     group->state == MCAST_LEAVE_SENT)) {
1177			clear = cancel_delayed_work(&group->timeout_work);
1178			pend = !clear;
1179			group->state = MCAST_IDLE;
1180		}
1181		if (clear) {
1182			--group->func[vf].num_pend_reqs;
1183			list_del(&req->group_list);
1184			list_del(&req->func_list);
1185			kfree(req);
1186			atomic_dec(&group->refcount);
1187		}
1188	}
1189
1190	if (!pend && (!list_empty(&group->func[vf].pending) || group->func[vf].num_pend_reqs)) {
1191		mcg_warn_group(group, "DRIVER BUG: list_empty %d, num_pend_reqs %d\n",
1192			       list_empty(&group->func[vf].pending), group->func[vf].num_pend_reqs);
1193	}
1194}
1195
1196static int push_deleteing_req(struct mcast_group *group, int slave)
1197{
1198	struct mcast_req *req;
1199	struct mcast_req *pend_req;
1200
1201	if (!group->func[slave].join_state)
1202		return 0;
1203
1204	req = kzalloc(sizeof *req, GFP_KERNEL);
1205	if (!req)
1206		return -ENOMEM;
1207
1208	if (!list_empty(&group->func[slave].pending)) {
1209		pend_req = list_entry(group->func[slave].pending.prev, struct mcast_req, group_list);
1210		if (pend_req->clean) {
1211			kfree(req);
1212			return 0;
1213		}
1214	}
1215
1216	req->clean = 1;
1217	req->func = slave;
1218	req->group = group;
1219	++group->func[slave].num_pend_reqs;
1220	build_leave_mad(req);
1221	queue_req(req);
1222	return 0;
1223}
1224
1225void clean_vf_mcast(struct mlx4_ib_demux_ctx *ctx, int slave)
1226{
1227	struct mcast_group *group;
1228	struct rb_node *p;
1229
1230	mutex_lock(&ctx->mcg_table_lock);
1231	for (p = rb_first(&ctx->mcg_table); p; p = rb_next(p)) {
1232		group = rb_entry(p, struct mcast_group, node);
1233		mutex_lock(&group->lock);
1234		if (atomic_read(&group->refcount)) {
1235			/* clear pending requests of this VF */
1236			clear_pending_reqs(group, slave);
1237			push_deleteing_req(group, slave);
1238		}
1239		mutex_unlock(&group->lock);
1240	}
1241	mutex_unlock(&ctx->mcg_table_lock);
1242}
1243
1244
1245int mlx4_ib_mcg_init(void)
1246{
1247	clean_wq = alloc_ordered_workqueue("mlx4_ib_mcg", WQ_MEM_RECLAIM);
1248	if (!clean_wq)
1249		return -ENOMEM;
1250
1251	return 0;
1252}
1253
1254void mlx4_ib_mcg_destroy(void)
1255{
1256	destroy_workqueue(clean_wq);
1257}
1258