1/*
2 * Copyright (c) 2006, 2007 Cisco Systems, Inc. All rights reserved.
3 * Copyright (c) 2007, 2008 Mellanox Technologies. All rights reserved.
4 *
5 * This software is available to you under a choice of one of two
6 * licenses.  You may choose to be licensed under the terms of the GNU
7 * General Public License (GPL) Version 2, available from the file
8 * COPYING in the main directory of this source tree, or the
9 * OpenIB.org BSD license below:
10 *
11 *     Redistribution and use in source and binary forms, with or
12 *     without modification, are permitted provided that the following
13 *     conditions are met:
14 *
15 *      - Redistributions of source code must retain the above
16 *        copyright notice, this list of conditions and the following
17 *        disclaimer.
18 *
19 *      - Redistributions in binary form must reproduce the above
20 *        copyright notice, this list of conditions and the following
21 *        disclaimer in the documentation and/or other materials
22 *        provided with the distribution.
23 *
24 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
25 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
26 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
27 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
28 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
29 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
30 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
31 * SOFTWARE.
32 */
33
34#include <linux/module.h>
35#include <linux/init.h>
36#include <linux/slab.h>
37#include <linux/errno.h>
38#include <linux/netdevice.h>
39#include <linux/inetdevice.h>
40#include <linux/rtnetlink.h>
41#include <linux/if_vlan.h>
42#include <linux/sched/mm.h>
43#include <linux/sched/task.h>
44
45#include <net/ipv6.h>
46#include <net/addrconf.h>
47#include <net/devlink.h>
48
49#include <rdma/ib_smi.h>
50#include <rdma/ib_user_verbs.h>
51#include <rdma/ib_addr.h>
52#include <rdma/ib_cache.h>
53
54#include <net/bonding.h>
55
56#include <linux/mlx4/driver.h>
57#include <linux/mlx4/cmd.h>
58#include <linux/mlx4/qp.h>
59
60#include "mlx4_ib.h"
61#include <rdma/mlx4-abi.h>
62
63#define DRV_NAME	MLX4_IB_DRV_NAME
64#define DRV_VERSION	"4.0-0"
65
66#define MLX4_IB_FLOW_MAX_PRIO 0xFFF
67#define MLX4_IB_FLOW_QPN_MASK 0xFFFFFF
68#define MLX4_IB_CARD_REV_A0   0xA0
69
70MODULE_AUTHOR("Roland Dreier");
71MODULE_DESCRIPTION("Mellanox ConnectX HCA InfiniBand driver");
72MODULE_LICENSE("Dual BSD/GPL");
73
74int mlx4_ib_sm_guid_assign = 0;
75module_param_named(sm_guid_assign, mlx4_ib_sm_guid_assign, int, 0444);
76MODULE_PARM_DESC(sm_guid_assign, "Enable SM alias_GUID assignment if sm_guid_assign > 0 (Default: 0)");
77
78static const char mlx4_ib_version[] =
79	DRV_NAME ": Mellanox ConnectX InfiniBand driver v"
80	DRV_VERSION "\n";
81
82static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init);
83static enum rdma_link_layer mlx4_ib_port_link_layer(struct ib_device *device,
84						    u8 port_num);
85
86static struct workqueue_struct *wq;
87
88static void init_query_mad(struct ib_smp *mad)
89{
90	mad->base_version  = 1;
91	mad->mgmt_class    = IB_MGMT_CLASS_SUBN_LID_ROUTED;
92	mad->class_version = 1;
93	mad->method	   = IB_MGMT_METHOD_GET;
94}
95
96static int check_flow_steering_support(struct mlx4_dev *dev)
97{
98	int eth_num_ports = 0;
99	int ib_num_ports = 0;
100
101	int dmfs = dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED;
102
103	if (dmfs) {
104		int i;
105		mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH)
106			eth_num_ports++;
107		mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
108			ib_num_ports++;
109		dmfs &= (!ib_num_ports ||
110			 (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DMFS_IPOIB)) &&
111			(!eth_num_ports ||
112			 (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FS_EN));
113		if (ib_num_ports && mlx4_is_mfunc(dev)) {
114			pr_warn("Device managed flow steering is unavailable for IB port in multifunction env.\n");
115			dmfs = 0;
116		}
117	}
118	return dmfs;
119}
120
121static int num_ib_ports(struct mlx4_dev *dev)
122{
123	int ib_ports = 0;
124	int i;
125
126	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
127		ib_ports++;
128
129	return ib_ports;
130}
131
132static struct net_device *mlx4_ib_get_netdev(struct ib_device *device, u8 port_num)
133{
134	struct mlx4_ib_dev *ibdev = to_mdev(device);
135	struct net_device *dev;
136
137	rcu_read_lock();
138	dev = mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port_num);
139
140	if (dev) {
141		if (mlx4_is_bonded(ibdev->dev)) {
142			struct net_device *upper = NULL;
143
144			upper = netdev_master_upper_dev_get_rcu(dev);
145			if (upper) {
146				struct net_device *active;
147
148				active = bond_option_active_slave_get_rcu(netdev_priv(upper));
149				if (active)
150					dev = active;
151			}
152		}
153	}
154	if (dev)
155		dev_hold(dev);
156
157	rcu_read_unlock();
158	return dev;
159}
160
161static int mlx4_ib_update_gids_v1(struct gid_entry *gids,
162				  struct mlx4_ib_dev *ibdev,
163				  u8 port_num)
164{
165	struct mlx4_cmd_mailbox *mailbox;
166	int err;
167	struct mlx4_dev *dev = ibdev->dev;
168	int i;
169	union ib_gid *gid_tbl;
170
171	mailbox = mlx4_alloc_cmd_mailbox(dev);
172	if (IS_ERR(mailbox))
173		return -ENOMEM;
174
175	gid_tbl = mailbox->buf;
176
177	for (i = 0; i < MLX4_MAX_PORT_GIDS; ++i)
178		memcpy(&gid_tbl[i], &gids[i].gid, sizeof(union ib_gid));
179
180	err = mlx4_cmd(dev, mailbox->dma,
181		       MLX4_SET_PORT_GID_TABLE << 8 | port_num,
182		       1, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B,
183		       MLX4_CMD_WRAPPED);
184	if (mlx4_is_bonded(dev))
185		err += mlx4_cmd(dev, mailbox->dma,
186				MLX4_SET_PORT_GID_TABLE << 8 | 2,
187				1, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B,
188				MLX4_CMD_WRAPPED);
189
190	mlx4_free_cmd_mailbox(dev, mailbox);
191	return err;
192}
193
194static int mlx4_ib_update_gids_v1_v2(struct gid_entry *gids,
195				     struct mlx4_ib_dev *ibdev,
196				     u8 port_num)
197{
198	struct mlx4_cmd_mailbox *mailbox;
199	int err;
200	struct mlx4_dev *dev = ibdev->dev;
201	int i;
202	struct {
203		union ib_gid	gid;
204		__be32		rsrvd1[2];
205		__be16		rsrvd2;
206		u8		type;
207		u8		version;
208		__be32		rsrvd3;
209	} *gid_tbl;
210
211	mailbox = mlx4_alloc_cmd_mailbox(dev);
212	if (IS_ERR(mailbox))
213		return -ENOMEM;
214
215	gid_tbl = mailbox->buf;
216	for (i = 0; i < MLX4_MAX_PORT_GIDS; ++i) {
217		memcpy(&gid_tbl[i].gid, &gids[i].gid, sizeof(union ib_gid));
218		if (gids[i].gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) {
219			gid_tbl[i].version = 2;
220			if (!ipv6_addr_v4mapped((struct in6_addr *)&gids[i].gid))
221				gid_tbl[i].type = 1;
222		}
223	}
224
225	err = mlx4_cmd(dev, mailbox->dma,
226		       MLX4_SET_PORT_ROCE_ADDR << 8 | port_num,
227		       1, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B,
228		       MLX4_CMD_WRAPPED);
229	if (mlx4_is_bonded(dev))
230		err += mlx4_cmd(dev, mailbox->dma,
231				MLX4_SET_PORT_ROCE_ADDR << 8 | 2,
232				1, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B,
233				MLX4_CMD_WRAPPED);
234
235	mlx4_free_cmd_mailbox(dev, mailbox);
236	return err;
237}
238
239static int mlx4_ib_update_gids(struct gid_entry *gids,
240			       struct mlx4_ib_dev *ibdev,
241			       u8 port_num)
242{
243	if (ibdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ROCE_V1_V2)
244		return mlx4_ib_update_gids_v1_v2(gids, ibdev, port_num);
245
246	return mlx4_ib_update_gids_v1(gids, ibdev, port_num);
247}
248
249static void free_gid_entry(struct gid_entry *entry)
250{
251	memset(&entry->gid, 0, sizeof(entry->gid));
252	kfree(entry->ctx);
253	entry->ctx = NULL;
254}
255
256static int mlx4_ib_add_gid(const struct ib_gid_attr *attr, void **context)
257{
258	struct mlx4_ib_dev *ibdev = to_mdev(attr->device);
259	struct mlx4_ib_iboe *iboe = &ibdev->iboe;
260	struct mlx4_port_gid_table   *port_gid_table;
261	int free = -1, found = -1;
262	int ret = 0;
263	int hw_update = 0;
264	int i;
265	struct gid_entry *gids = NULL;
266	u16 vlan_id = 0xffff;
267	u8 mac[ETH_ALEN];
268
269	if (!rdma_cap_roce_gid_table(attr->device, attr->port_num))
270		return -EINVAL;
271
272	if (attr->port_num > MLX4_MAX_PORTS)
273		return -EINVAL;
274
275	if (!context)
276		return -EINVAL;
277
278	ret = rdma_read_gid_l2_fields(attr, &vlan_id, &mac[0]);
279	if (ret)
280		return ret;
281	port_gid_table = &iboe->gids[attr->port_num - 1];
282	spin_lock_bh(&iboe->lock);
283	for (i = 0; i < MLX4_MAX_PORT_GIDS; ++i) {
284		if (!memcmp(&port_gid_table->gids[i].gid,
285			    &attr->gid, sizeof(attr->gid)) &&
286		    port_gid_table->gids[i].gid_type == attr->gid_type &&
287		    port_gid_table->gids[i].vlan_id == vlan_id)  {
288			found = i;
289			break;
290		}
291		if (free < 0 && rdma_is_zero_gid(&port_gid_table->gids[i].gid))
292			free = i; /* HW has space */
293	}
294
295	if (found < 0) {
296		if (free < 0) {
297			ret = -ENOSPC;
298		} else {
299			port_gid_table->gids[free].ctx = kmalloc(sizeof(*port_gid_table->gids[free].ctx), GFP_ATOMIC);
300			if (!port_gid_table->gids[free].ctx) {
301				ret = -ENOMEM;
302			} else {
303				*context = port_gid_table->gids[free].ctx;
304				memcpy(&port_gid_table->gids[free].gid,
305				       &attr->gid, sizeof(attr->gid));
306				port_gid_table->gids[free].gid_type = attr->gid_type;
307				port_gid_table->gids[free].vlan_id = vlan_id;
308				port_gid_table->gids[free].ctx->real_index = free;
309				port_gid_table->gids[free].ctx->refcount = 1;
310				hw_update = 1;
311			}
312		}
313	} else {
314		struct gid_cache_context *ctx = port_gid_table->gids[found].ctx;
315		*context = ctx;
316		ctx->refcount++;
317	}
318	if (!ret && hw_update) {
319		gids = kmalloc_array(MLX4_MAX_PORT_GIDS, sizeof(*gids),
320				     GFP_ATOMIC);
321		if (!gids) {
322			ret = -ENOMEM;
323			*context = NULL;
324			free_gid_entry(&port_gid_table->gids[free]);
325		} else {
326			for (i = 0; i < MLX4_MAX_PORT_GIDS; i++) {
327				memcpy(&gids[i].gid, &port_gid_table->gids[i].gid, sizeof(union ib_gid));
328				gids[i].gid_type = port_gid_table->gids[i].gid_type;
329			}
330		}
331	}
332	spin_unlock_bh(&iboe->lock);
333
334	if (!ret && hw_update) {
335		ret = mlx4_ib_update_gids(gids, ibdev, attr->port_num);
336		if (ret) {
337			spin_lock_bh(&iboe->lock);
338			*context = NULL;
339			free_gid_entry(&port_gid_table->gids[free]);
340			spin_unlock_bh(&iboe->lock);
341		}
342		kfree(gids);
343	}
344
345	return ret;
346}
347
348static int mlx4_ib_del_gid(const struct ib_gid_attr *attr, void **context)
349{
350	struct gid_cache_context *ctx = *context;
351	struct mlx4_ib_dev *ibdev = to_mdev(attr->device);
352	struct mlx4_ib_iboe *iboe = &ibdev->iboe;
353	struct mlx4_port_gid_table   *port_gid_table;
354	int ret = 0;
355	int hw_update = 0;
356	struct gid_entry *gids = NULL;
357
358	if (!rdma_cap_roce_gid_table(attr->device, attr->port_num))
359		return -EINVAL;
360
361	if (attr->port_num > MLX4_MAX_PORTS)
362		return -EINVAL;
363
364	port_gid_table = &iboe->gids[attr->port_num - 1];
365	spin_lock_bh(&iboe->lock);
366	if (ctx) {
367		ctx->refcount--;
368		if (!ctx->refcount) {
369			unsigned int real_index = ctx->real_index;
370
371			free_gid_entry(&port_gid_table->gids[real_index]);
372			hw_update = 1;
373		}
374	}
375	if (!ret && hw_update) {
376		int i;
377
378		gids = kmalloc_array(MLX4_MAX_PORT_GIDS, sizeof(*gids),
379				     GFP_ATOMIC);
380		if (!gids) {
381			ret = -ENOMEM;
382		} else {
383			for (i = 0; i < MLX4_MAX_PORT_GIDS; i++) {
384				memcpy(&gids[i].gid,
385				       &port_gid_table->gids[i].gid,
386				       sizeof(union ib_gid));
387				gids[i].gid_type =
388				    port_gid_table->gids[i].gid_type;
389			}
390		}
391	}
392	spin_unlock_bh(&iboe->lock);
393
394	if (!ret && hw_update) {
395		ret = mlx4_ib_update_gids(gids, ibdev, attr->port_num);
396		kfree(gids);
397	}
398	return ret;
399}
400
401int mlx4_ib_gid_index_to_real_index(struct mlx4_ib_dev *ibdev,
402				    const struct ib_gid_attr *attr)
403{
404	struct mlx4_ib_iboe *iboe = &ibdev->iboe;
405	struct gid_cache_context *ctx = NULL;
406	struct mlx4_port_gid_table   *port_gid_table;
407	int real_index = -EINVAL;
408	int i;
409	unsigned long flags;
410	u8 port_num = attr->port_num;
411
412	if (port_num > MLX4_MAX_PORTS)
413		return -EINVAL;
414
415	if (mlx4_is_bonded(ibdev->dev))
416		port_num = 1;
417
418	if (!rdma_cap_roce_gid_table(&ibdev->ib_dev, port_num))
419		return attr->index;
420
421	spin_lock_irqsave(&iboe->lock, flags);
422	port_gid_table = &iboe->gids[port_num - 1];
423
424	for (i = 0; i < MLX4_MAX_PORT_GIDS; ++i)
425		if (!memcmp(&port_gid_table->gids[i].gid,
426			    &attr->gid, sizeof(attr->gid)) &&
427		    attr->gid_type == port_gid_table->gids[i].gid_type) {
428			ctx = port_gid_table->gids[i].ctx;
429			break;
430		}
431	if (ctx)
432		real_index = ctx->real_index;
433	spin_unlock_irqrestore(&iboe->lock, flags);
434	return real_index;
435}
436
437static int mlx4_ib_query_device(struct ib_device *ibdev,
438				struct ib_device_attr *props,
439				struct ib_udata *uhw)
440{
441	struct mlx4_ib_dev *dev = to_mdev(ibdev);
442	struct ib_smp *in_mad  = NULL;
443	struct ib_smp *out_mad = NULL;
444	int err;
445	int have_ib_ports;
446	struct mlx4_uverbs_ex_query_device cmd;
447	struct mlx4_uverbs_ex_query_device_resp resp = {};
448	struct mlx4_clock_params clock_params;
449
450	if (uhw->inlen) {
451		if (uhw->inlen < sizeof(cmd))
452			return -EINVAL;
453
454		err = ib_copy_from_udata(&cmd, uhw, sizeof(cmd));
455		if (err)
456			return err;
457
458		if (cmd.comp_mask)
459			return -EINVAL;
460
461		if (cmd.reserved)
462			return -EINVAL;
463	}
464
465	resp.response_length = offsetof(typeof(resp), response_length) +
466		sizeof(resp.response_length);
467	in_mad  = kzalloc(sizeof *in_mad, GFP_KERNEL);
468	out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
469	err = -ENOMEM;
470	if (!in_mad || !out_mad)
471		goto out;
472
473	init_query_mad(in_mad);
474	in_mad->attr_id = IB_SMP_ATTR_NODE_INFO;
475
476	err = mlx4_MAD_IFC(to_mdev(ibdev), MLX4_MAD_IFC_IGNORE_KEYS,
477			   1, NULL, NULL, in_mad, out_mad);
478	if (err)
479		goto out;
480
481	memset(props, 0, sizeof *props);
482
483	have_ib_ports = num_ib_ports(dev->dev);
484
485	props->fw_ver = dev->dev->caps.fw_ver;
486	props->device_cap_flags    = IB_DEVICE_CHANGE_PHY_PORT |
487		IB_DEVICE_PORT_ACTIVE_EVENT		|
488		IB_DEVICE_SYS_IMAGE_GUID		|
489		IB_DEVICE_RC_RNR_NAK_GEN		|
490		IB_DEVICE_BLOCK_MULTICAST_LOOPBACK;
491	if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_BAD_PKEY_CNTR)
492		props->device_cap_flags |= IB_DEVICE_BAD_PKEY_CNTR;
493	if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_BAD_QKEY_CNTR)
494		props->device_cap_flags |= IB_DEVICE_BAD_QKEY_CNTR;
495	if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_APM && have_ib_ports)
496		props->device_cap_flags |= IB_DEVICE_AUTO_PATH_MIG;
497	if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_UD_AV_PORT)
498		props->device_cap_flags |= IB_DEVICE_UD_AV_PORT_ENFORCE;
499	if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_IPOIB_CSUM)
500		props->device_cap_flags |= IB_DEVICE_UD_IP_CSUM;
501	if (dev->dev->caps.max_gso_sz &&
502	    (dev->dev->rev_id != MLX4_IB_CARD_REV_A0) &&
503	    (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_BLH))
504		props->device_cap_flags |= IB_DEVICE_UD_TSO;
505	if (dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_RESERVED_LKEY)
506		props->device_cap_flags |= IB_DEVICE_LOCAL_DMA_LKEY;
507	if ((dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_LOCAL_INV) &&
508	    (dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_REMOTE_INV) &&
509	    (dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_FAST_REG_WR))
510		props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS;
511	if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC)
512		props->device_cap_flags |= IB_DEVICE_XRC;
513	if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW)
514		props->device_cap_flags |= IB_DEVICE_MEM_WINDOW;
515	if (dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN) {
516		if (dev->dev->caps.bmme_flags & MLX4_BMME_FLAG_WIN_TYPE_2B)
517			props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2B;
518		else
519			props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2A;
520	}
521	if (dev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED)
522		props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
523
524	props->device_cap_flags |= IB_DEVICE_RAW_IP_CSUM;
525
526	props->vendor_id	   = be32_to_cpup((__be32 *) (out_mad->data + 36)) &
527		0xffffff;
528	props->vendor_part_id	   = dev->dev->persist->pdev->device;
529	props->hw_ver		   = be32_to_cpup((__be32 *) (out_mad->data + 32));
530	memcpy(&props->sys_image_guid, out_mad->data +	4, 8);
531
532	props->max_mr_size	   = ~0ull;
533	props->page_size_cap	   = dev->dev->caps.page_size_cap;
534	props->max_qp		   = dev->dev->quotas.qp;
535	props->max_qp_wr	   = dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE;
536	props->max_send_sge =
537		min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg);
538	props->max_recv_sge =
539		min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg);
540	props->max_sge_rd = MLX4_MAX_SGE_RD;
541	props->max_cq		   = dev->dev->quotas.cq;
542	props->max_cqe		   = dev->dev->caps.max_cqes;
543	props->max_mr		   = dev->dev->quotas.mpt;
544	props->max_pd		   = dev->dev->caps.num_pds - dev->dev->caps.reserved_pds;
545	props->max_qp_rd_atom	   = dev->dev->caps.max_qp_dest_rdma;
546	props->max_qp_init_rd_atom = dev->dev->caps.max_qp_init_rdma;
547	props->max_res_rd_atom	   = props->max_qp_rd_atom * props->max_qp;
548	props->max_srq		   = dev->dev->quotas.srq;
549	props->max_srq_wr	   = dev->dev->caps.max_srq_wqes - 1;
550	props->max_srq_sge	   = dev->dev->caps.max_srq_sge;
551	props->max_fast_reg_page_list_len = MLX4_MAX_FAST_REG_PAGES;
552	props->local_ca_ack_delay  = dev->dev->caps.local_ca_ack_delay;
553	props->atomic_cap	   = dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_ATOMIC ?
554		IB_ATOMIC_HCA : IB_ATOMIC_NONE;
555	props->masked_atomic_cap   = props->atomic_cap;
556	props->max_pkeys	   = dev->dev->caps.pkey_table_len[1];
557	props->max_mcast_grp	   = dev->dev->caps.num_mgms + dev->dev->caps.num_amgms;
558	props->max_mcast_qp_attach = dev->dev->caps.num_qp_per_mgm;
559	props->max_total_mcast_qp_attach = props->max_mcast_qp_attach *
560					   props->max_mcast_grp;
561	props->hca_core_clock = dev->dev->caps.hca_core_clock * 1000UL;
562	props->timestamp_mask = 0xFFFFFFFFFFFFULL;
563	props->max_ah = INT_MAX;
564
565	if (mlx4_ib_port_link_layer(ibdev, 1) == IB_LINK_LAYER_ETHERNET ||
566	    mlx4_ib_port_link_layer(ibdev, 2) == IB_LINK_LAYER_ETHERNET) {
567		if (dev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS) {
568			props->rss_caps.max_rwq_indirection_tables =
569				props->max_qp;
570			props->rss_caps.max_rwq_indirection_table_size =
571				dev->dev->caps.max_rss_tbl_sz;
572			props->rss_caps.supported_qpts = 1 << IB_QPT_RAW_PACKET;
573			props->max_wq_type_rq = props->max_qp;
574		}
575
576		if (dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_FCS_KEEP)
577			props->raw_packet_caps |= IB_RAW_PACKET_CAP_SCATTER_FCS;
578	}
579
580	props->cq_caps.max_cq_moderation_count = MLX4_MAX_CQ_COUNT;
581	props->cq_caps.max_cq_moderation_period = MLX4_MAX_CQ_PERIOD;
582
583	if (uhw->outlen >= resp.response_length + sizeof(resp.hca_core_clock_offset)) {
584		resp.response_length += sizeof(resp.hca_core_clock_offset);
585		if (!mlx4_get_internal_clock_params(dev->dev, &clock_params)) {
586			resp.comp_mask |= MLX4_IB_QUERY_DEV_RESP_MASK_CORE_CLOCK_OFFSET;
587			resp.hca_core_clock_offset = clock_params.offset % PAGE_SIZE;
588		}
589	}
590
591	if (uhw->outlen >= resp.response_length +
592	    sizeof(resp.max_inl_recv_sz)) {
593		resp.response_length += sizeof(resp.max_inl_recv_sz);
594		resp.max_inl_recv_sz  = dev->dev->caps.max_rq_sg *
595			sizeof(struct mlx4_wqe_data_seg);
596	}
597
598	if (offsetofend(typeof(resp), rss_caps) <= uhw->outlen) {
599		if (props->rss_caps.supported_qpts) {
600			resp.rss_caps.rx_hash_function =
601				MLX4_IB_RX_HASH_FUNC_TOEPLITZ;
602
603			resp.rss_caps.rx_hash_fields_mask =
604				MLX4_IB_RX_HASH_SRC_IPV4 |
605				MLX4_IB_RX_HASH_DST_IPV4 |
606				MLX4_IB_RX_HASH_SRC_IPV6 |
607				MLX4_IB_RX_HASH_DST_IPV6 |
608				MLX4_IB_RX_HASH_SRC_PORT_TCP |
609				MLX4_IB_RX_HASH_DST_PORT_TCP |
610				MLX4_IB_RX_HASH_SRC_PORT_UDP |
611				MLX4_IB_RX_HASH_DST_PORT_UDP;
612
613			if (dev->dev->caps.tunnel_offload_mode ==
614			    MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
615				resp.rss_caps.rx_hash_fields_mask |=
616					MLX4_IB_RX_HASH_INNER;
617		}
618		resp.response_length = offsetof(typeof(resp), rss_caps) +
619				       sizeof(resp.rss_caps);
620	}
621
622	if (offsetofend(typeof(resp), tso_caps) <= uhw->outlen) {
623		if (dev->dev->caps.max_gso_sz &&
624		    ((mlx4_ib_port_link_layer(ibdev, 1) ==
625		    IB_LINK_LAYER_ETHERNET) ||
626		    (mlx4_ib_port_link_layer(ibdev, 2) ==
627		    IB_LINK_LAYER_ETHERNET))) {
628			resp.tso_caps.max_tso = dev->dev->caps.max_gso_sz;
629			resp.tso_caps.supported_qpts |=
630				1 << IB_QPT_RAW_PACKET;
631		}
632		resp.response_length = offsetof(typeof(resp), tso_caps) +
633				       sizeof(resp.tso_caps);
634	}
635
636	if (uhw->outlen) {
637		err = ib_copy_to_udata(uhw, &resp, resp.response_length);
638		if (err)
639			goto out;
640	}
641out:
642	kfree(in_mad);
643	kfree(out_mad);
644
645	return err;
646}
647
648static enum rdma_link_layer
649mlx4_ib_port_link_layer(struct ib_device *device, u8 port_num)
650{
651	struct mlx4_dev *dev = to_mdev(device)->dev;
652
653	return dev->caps.port_mask[port_num] == MLX4_PORT_TYPE_IB ?
654		IB_LINK_LAYER_INFINIBAND : IB_LINK_LAYER_ETHERNET;
655}
656
657static int ib_link_query_port(struct ib_device *ibdev, u8 port,
658			      struct ib_port_attr *props, int netw_view)
659{
660	struct ib_smp *in_mad  = NULL;
661	struct ib_smp *out_mad = NULL;
662	int ext_active_speed;
663	int mad_ifc_flags = MLX4_MAD_IFC_IGNORE_KEYS;
664	int err = -ENOMEM;
665
666	in_mad  = kzalloc(sizeof *in_mad, GFP_KERNEL);
667	out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
668	if (!in_mad || !out_mad)
669		goto out;
670
671	init_query_mad(in_mad);
672	in_mad->attr_id  = IB_SMP_ATTR_PORT_INFO;
673	in_mad->attr_mod = cpu_to_be32(port);
674
675	if (mlx4_is_mfunc(to_mdev(ibdev)->dev) && netw_view)
676		mad_ifc_flags |= MLX4_MAD_IFC_NET_VIEW;
677
678	err = mlx4_MAD_IFC(to_mdev(ibdev), mad_ifc_flags, port, NULL, NULL,
679				in_mad, out_mad);
680	if (err)
681		goto out;
682
683
684	props->lid		= be16_to_cpup((__be16 *) (out_mad->data + 16));
685	props->lmc		= out_mad->data[34] & 0x7;
686	props->sm_lid		= be16_to_cpup((__be16 *) (out_mad->data + 18));
687	props->sm_sl		= out_mad->data[36] & 0xf;
688	props->state		= out_mad->data[32] & 0xf;
689	props->phys_state	= out_mad->data[33] >> 4;
690	props->port_cap_flags	= be32_to_cpup((__be32 *) (out_mad->data + 20));
691	if (netw_view)
692		props->gid_tbl_len = out_mad->data[50];
693	else
694		props->gid_tbl_len = to_mdev(ibdev)->dev->caps.gid_table_len[port];
695	props->max_msg_sz	= to_mdev(ibdev)->dev->caps.max_msg_sz;
696	props->pkey_tbl_len	= to_mdev(ibdev)->dev->caps.pkey_table_len[port];
697	props->bad_pkey_cntr	= be16_to_cpup((__be16 *) (out_mad->data + 46));
698	props->qkey_viol_cntr	= be16_to_cpup((__be16 *) (out_mad->data + 48));
699	props->active_width	= out_mad->data[31] & 0xf;
700	props->active_speed	= out_mad->data[35] >> 4;
701	props->max_mtu		= out_mad->data[41] & 0xf;
702	props->active_mtu	= out_mad->data[36] >> 4;
703	props->subnet_timeout	= out_mad->data[51] & 0x1f;
704	props->max_vl_num	= out_mad->data[37] >> 4;
705	props->init_type_reply	= out_mad->data[41] >> 4;
706
707	/* Check if extended speeds (EDR/FDR/...) are supported */
708	if (props->port_cap_flags & IB_PORT_EXTENDED_SPEEDS_SUP) {
709		ext_active_speed = out_mad->data[62] >> 4;
710
711		switch (ext_active_speed) {
712		case 1:
713			props->active_speed = IB_SPEED_FDR;
714			break;
715		case 2:
716			props->active_speed = IB_SPEED_EDR;
717			break;
718		}
719	}
720
721	/* If reported active speed is QDR, check if is FDR-10 */
722	if (props->active_speed == IB_SPEED_QDR) {
723		init_query_mad(in_mad);
724		in_mad->attr_id = MLX4_ATTR_EXTENDED_PORT_INFO;
725		in_mad->attr_mod = cpu_to_be32(port);
726
727		err = mlx4_MAD_IFC(to_mdev(ibdev), mad_ifc_flags, port,
728				   NULL, NULL, in_mad, out_mad);
729		if (err)
730			goto out;
731
732		/* Checking LinkSpeedActive for FDR-10 */
733		if (out_mad->data[15] & 0x1)
734			props->active_speed = IB_SPEED_FDR10;
735	}
736
737	/* Avoid wrong speed value returned by FW if the IB link is down. */
738	if (props->state == IB_PORT_DOWN)
739		 props->active_speed = IB_SPEED_SDR;
740
741out:
742	kfree(in_mad);
743	kfree(out_mad);
744	return err;
745}
746
747static u8 state_to_phys_state(enum ib_port_state state)
748{
749	return state == IB_PORT_ACTIVE ?
750		IB_PORT_PHYS_STATE_LINK_UP : IB_PORT_PHYS_STATE_DISABLED;
751}
752
753static int eth_link_query_port(struct ib_device *ibdev, u8 port,
754			       struct ib_port_attr *props)
755{
756
757	struct mlx4_ib_dev *mdev = to_mdev(ibdev);
758	struct mlx4_ib_iboe *iboe = &mdev->iboe;
759	struct net_device *ndev;
760	enum ib_mtu tmp;
761	struct mlx4_cmd_mailbox *mailbox;
762	int err = 0;
763	int is_bonded = mlx4_is_bonded(mdev->dev);
764
765	mailbox = mlx4_alloc_cmd_mailbox(mdev->dev);
766	if (IS_ERR(mailbox))
767		return PTR_ERR(mailbox);
768
769	err = mlx4_cmd_box(mdev->dev, 0, mailbox->dma, port, 0,
770			   MLX4_CMD_QUERY_PORT, MLX4_CMD_TIME_CLASS_B,
771			   MLX4_CMD_WRAPPED);
772	if (err)
773		goto out;
774
775	props->active_width	=  (((u8 *)mailbox->buf)[5] == 0x40) ||
776				   (((u8 *)mailbox->buf)[5] == 0x20 /*56Gb*/) ?
777					   IB_WIDTH_4X : IB_WIDTH_1X;
778	props->active_speed	=  (((u8 *)mailbox->buf)[5] == 0x20 /*56Gb*/) ?
779					   IB_SPEED_FDR : IB_SPEED_QDR;
780	props->port_cap_flags	= IB_PORT_CM_SUP;
781	props->ip_gids = true;
782	props->gid_tbl_len	= mdev->dev->caps.gid_table_len[port];
783	props->max_msg_sz	= mdev->dev->caps.max_msg_sz;
784	if (mdev->dev->caps.pkey_table_len[port])
785		props->pkey_tbl_len = 1;
786	props->max_mtu		= IB_MTU_4096;
787	props->max_vl_num	= 2;
788	props->state		= IB_PORT_DOWN;
789	props->phys_state	= state_to_phys_state(props->state);
790	props->active_mtu	= IB_MTU_256;
791	spin_lock_bh(&iboe->lock);
792	ndev = iboe->netdevs[port - 1];
793	if (ndev && is_bonded) {
794		rcu_read_lock(); /* required to get upper dev */
795		ndev = netdev_master_upper_dev_get_rcu(ndev);
796		rcu_read_unlock();
797	}
798	if (!ndev)
799		goto out_unlock;
800
801	tmp = iboe_get_mtu(ndev->mtu);
802	props->active_mtu = tmp ? min(props->max_mtu, tmp) : IB_MTU_256;
803
804	props->state		= (netif_running(ndev) && netif_carrier_ok(ndev)) ?
805					IB_PORT_ACTIVE : IB_PORT_DOWN;
806	props->phys_state	= state_to_phys_state(props->state);
807out_unlock:
808	spin_unlock_bh(&iboe->lock);
809out:
810	mlx4_free_cmd_mailbox(mdev->dev, mailbox);
811	return err;
812}
813
814int __mlx4_ib_query_port(struct ib_device *ibdev, u8 port,
815			 struct ib_port_attr *props, int netw_view)
816{
817	int err;
818
819	/* props being zeroed by the caller, avoid zeroing it here */
820
821	err = mlx4_ib_port_link_layer(ibdev, port) == IB_LINK_LAYER_INFINIBAND ?
822		ib_link_query_port(ibdev, port, props, netw_view) :
823				eth_link_query_port(ibdev, port, props);
824
825	return err;
826}
827
828static int mlx4_ib_query_port(struct ib_device *ibdev, u8 port,
829			      struct ib_port_attr *props)
830{
831	/* returns host view */
832	return __mlx4_ib_query_port(ibdev, port, props, 0);
833}
834
835int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
836			union ib_gid *gid, int netw_view)
837{
838	struct ib_smp *in_mad  = NULL;
839	struct ib_smp *out_mad = NULL;
840	int err = -ENOMEM;
841	struct mlx4_ib_dev *dev = to_mdev(ibdev);
842	int clear = 0;
843	int mad_ifc_flags = MLX4_MAD_IFC_IGNORE_KEYS;
844
845	in_mad  = kzalloc(sizeof *in_mad, GFP_KERNEL);
846	out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
847	if (!in_mad || !out_mad)
848		goto out;
849
850	init_query_mad(in_mad);
851	in_mad->attr_id  = IB_SMP_ATTR_PORT_INFO;
852	in_mad->attr_mod = cpu_to_be32(port);
853
854	if (mlx4_is_mfunc(dev->dev) && netw_view)
855		mad_ifc_flags |= MLX4_MAD_IFC_NET_VIEW;
856
857	err = mlx4_MAD_IFC(dev, mad_ifc_flags, port, NULL, NULL, in_mad, out_mad);
858	if (err)
859		goto out;
860
861	memcpy(gid->raw, out_mad->data + 8, 8);
862
863	if (mlx4_is_mfunc(dev->dev) && !netw_view) {
864		if (index) {
865			/* For any index > 0, return the null guid */
866			err = 0;
867			clear = 1;
868			goto out;
869		}
870	}
871
872	init_query_mad(in_mad);
873	in_mad->attr_id  = IB_SMP_ATTR_GUID_INFO;
874	in_mad->attr_mod = cpu_to_be32(index / 8);
875
876	err = mlx4_MAD_IFC(dev, mad_ifc_flags, port,
877			   NULL, NULL, in_mad, out_mad);
878	if (err)
879		goto out;
880
881	memcpy(gid->raw + 8, out_mad->data + (index % 8) * 8, 8);
882
883out:
884	if (clear)
885		memset(gid->raw + 8, 0, 8);
886	kfree(in_mad);
887	kfree(out_mad);
888	return err;
889}
890
891static int mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
892			     union ib_gid *gid)
893{
894	if (rdma_protocol_ib(ibdev, port))
895		return __mlx4_ib_query_gid(ibdev, port, index, gid, 0);
896	return 0;
897}
898
899static int mlx4_ib_query_sl2vl(struct ib_device *ibdev, u8 port, u64 *sl2vl_tbl)
900{
901	union sl2vl_tbl_to_u64 sl2vl64;
902	struct ib_smp *in_mad  = NULL;
903	struct ib_smp *out_mad = NULL;
904	int mad_ifc_flags = MLX4_MAD_IFC_IGNORE_KEYS;
905	int err = -ENOMEM;
906	int jj;
907
908	if (mlx4_is_slave(to_mdev(ibdev)->dev)) {
909		*sl2vl_tbl = 0;
910		return 0;
911	}
912
913	in_mad  = kzalloc(sizeof(*in_mad), GFP_KERNEL);
914	out_mad = kmalloc(sizeof(*out_mad), GFP_KERNEL);
915	if (!in_mad || !out_mad)
916		goto out;
917
918	init_query_mad(in_mad);
919	in_mad->attr_id  = IB_SMP_ATTR_SL_TO_VL_TABLE;
920	in_mad->attr_mod = 0;
921
922	if (mlx4_is_mfunc(to_mdev(ibdev)->dev))
923		mad_ifc_flags |= MLX4_MAD_IFC_NET_VIEW;
924
925	err = mlx4_MAD_IFC(to_mdev(ibdev), mad_ifc_flags, port, NULL, NULL,
926			   in_mad, out_mad);
927	if (err)
928		goto out;
929
930	for (jj = 0; jj < 8; jj++)
931		sl2vl64.sl8[jj] = ((struct ib_smp *)out_mad)->data[jj];
932	*sl2vl_tbl = sl2vl64.sl64;
933
934out:
935	kfree(in_mad);
936	kfree(out_mad);
937	return err;
938}
939
940static void mlx4_init_sl2vl_tbl(struct mlx4_ib_dev *mdev)
941{
942	u64 sl2vl;
943	int i;
944	int err;
945
946	for (i = 1; i <= mdev->dev->caps.num_ports; i++) {
947		if (mdev->dev->caps.port_type[i] == MLX4_PORT_TYPE_ETH)
948			continue;
949		err = mlx4_ib_query_sl2vl(&mdev->ib_dev, i, &sl2vl);
950		if (err) {
951			pr_err("Unable to get default sl to vl mapping for port %d.  Using all zeroes (%d)\n",
952			       i, err);
953			sl2vl = 0;
954		}
955		atomic64_set(&mdev->sl2vl[i - 1], sl2vl);
956	}
957}
958
959int __mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index,
960			 u16 *pkey, int netw_view)
961{
962	struct ib_smp *in_mad  = NULL;
963	struct ib_smp *out_mad = NULL;
964	int mad_ifc_flags = MLX4_MAD_IFC_IGNORE_KEYS;
965	int err = -ENOMEM;
966
967	in_mad  = kzalloc(sizeof *in_mad, GFP_KERNEL);
968	out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
969	if (!in_mad || !out_mad)
970		goto out;
971
972	init_query_mad(in_mad);
973	in_mad->attr_id  = IB_SMP_ATTR_PKEY_TABLE;
974	in_mad->attr_mod = cpu_to_be32(index / 32);
975
976	if (mlx4_is_mfunc(to_mdev(ibdev)->dev) && netw_view)
977		mad_ifc_flags |= MLX4_MAD_IFC_NET_VIEW;
978
979	err = mlx4_MAD_IFC(to_mdev(ibdev), mad_ifc_flags, port, NULL, NULL,
980			   in_mad, out_mad);
981	if (err)
982		goto out;
983
984	*pkey = be16_to_cpu(((__be16 *) out_mad->data)[index % 32]);
985
986out:
987	kfree(in_mad);
988	kfree(out_mad);
989	return err;
990}
991
992static int mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index, u16 *pkey)
993{
994	return __mlx4_ib_query_pkey(ibdev, port, index, pkey, 0);
995}
996
997static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask,
998				 struct ib_device_modify *props)
999{
1000	struct mlx4_cmd_mailbox *mailbox;
1001	unsigned long flags;
1002
1003	if (mask & ~IB_DEVICE_MODIFY_NODE_DESC)
1004		return -EOPNOTSUPP;
1005
1006	if (!(mask & IB_DEVICE_MODIFY_NODE_DESC))
1007		return 0;
1008
1009	if (mlx4_is_slave(to_mdev(ibdev)->dev))
1010		return -EOPNOTSUPP;
1011
1012	spin_lock_irqsave(&to_mdev(ibdev)->sm_lock, flags);
1013	memcpy(ibdev->node_desc, props->node_desc, IB_DEVICE_NODE_DESC_MAX);
1014	spin_unlock_irqrestore(&to_mdev(ibdev)->sm_lock, flags);
1015
1016	/*
1017	 * If possible, pass node desc to FW, so it can generate
1018	 * a 144 trap.  If cmd fails, just ignore.
1019	 */
1020	mailbox = mlx4_alloc_cmd_mailbox(to_mdev(ibdev)->dev);
1021	if (IS_ERR(mailbox))
1022		return 0;
1023
1024	memcpy(mailbox->buf, props->node_desc, IB_DEVICE_NODE_DESC_MAX);
1025	mlx4_cmd(to_mdev(ibdev)->dev, mailbox->dma, 1, 0,
1026		 MLX4_CMD_SET_NODE, MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
1027
1028	mlx4_free_cmd_mailbox(to_mdev(ibdev)->dev, mailbox);
1029
1030	return 0;
1031}
1032
1033static int mlx4_ib_SET_PORT(struct mlx4_ib_dev *dev, u8 port, int reset_qkey_viols,
1034			    u32 cap_mask)
1035{
1036	struct mlx4_cmd_mailbox *mailbox;
1037	int err;
1038
1039	mailbox = mlx4_alloc_cmd_mailbox(dev->dev);
1040	if (IS_ERR(mailbox))
1041		return PTR_ERR(mailbox);
1042
1043	if (dev->dev->flags & MLX4_FLAG_OLD_PORT_CMDS) {
1044		*(u8 *) mailbox->buf	     = !!reset_qkey_viols << 6;
1045		((__be32 *) mailbox->buf)[2] = cpu_to_be32(cap_mask);
1046	} else {
1047		((u8 *) mailbox->buf)[3]     = !!reset_qkey_viols;
1048		((__be32 *) mailbox->buf)[1] = cpu_to_be32(cap_mask);
1049	}
1050
1051	err = mlx4_cmd(dev->dev, mailbox->dma, port, MLX4_SET_PORT_IB_OPCODE,
1052		       MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B,
1053		       MLX4_CMD_WRAPPED);
1054
1055	mlx4_free_cmd_mailbox(dev->dev, mailbox);
1056	return err;
1057}
1058
1059static int mlx4_ib_modify_port(struct ib_device *ibdev, u8 port, int mask,
1060			       struct ib_port_modify *props)
1061{
1062	struct mlx4_ib_dev *mdev = to_mdev(ibdev);
1063	u8 is_eth = mdev->dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH;
1064	struct ib_port_attr attr;
1065	u32 cap_mask;
1066	int err;
1067
1068	/* return OK if this is RoCE. CM calls ib_modify_port() regardless
1069	 * of whether port link layer is ETH or IB. For ETH ports, qkey
1070	 * violations and port capabilities are not meaningful.
1071	 */
1072	if (is_eth)
1073		return 0;
1074
1075	mutex_lock(&mdev->cap_mask_mutex);
1076
1077	err = ib_query_port(ibdev, port, &attr);
1078	if (err)
1079		goto out;
1080
1081	cap_mask = (attr.port_cap_flags | props->set_port_cap_mask) &
1082		~props->clr_port_cap_mask;
1083
1084	err = mlx4_ib_SET_PORT(mdev, port,
1085			       !!(mask & IB_PORT_RESET_QKEY_CNTR),
1086			       cap_mask);
1087
1088out:
1089	mutex_unlock(&to_mdev(ibdev)->cap_mask_mutex);
1090	return err;
1091}
1092
1093static int mlx4_ib_alloc_ucontext(struct ib_ucontext *uctx,
1094				  struct ib_udata *udata)
1095{
1096	struct ib_device *ibdev = uctx->device;
1097	struct mlx4_ib_dev *dev = to_mdev(ibdev);
1098	struct mlx4_ib_ucontext *context = to_mucontext(uctx);
1099	struct mlx4_ib_alloc_ucontext_resp_v3 resp_v3;
1100	struct mlx4_ib_alloc_ucontext_resp resp;
1101	int err;
1102
1103	if (!dev->ib_active)
1104		return -EAGAIN;
1105
1106	if (ibdev->ops.uverbs_abi_ver ==
1107	    MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION) {
1108		resp_v3.qp_tab_size      = dev->dev->caps.num_qps;
1109		resp_v3.bf_reg_size      = dev->dev->caps.bf_reg_size;
1110		resp_v3.bf_regs_per_page = dev->dev->caps.bf_regs_per_page;
1111	} else {
1112		resp.dev_caps	      = dev->dev->caps.userspace_caps;
1113		resp.qp_tab_size      = dev->dev->caps.num_qps;
1114		resp.bf_reg_size      = dev->dev->caps.bf_reg_size;
1115		resp.bf_regs_per_page = dev->dev->caps.bf_regs_per_page;
1116		resp.cqe_size	      = dev->dev->caps.cqe_size;
1117	}
1118
1119	err = mlx4_uar_alloc(to_mdev(ibdev)->dev, &context->uar);
1120	if (err)
1121		return err;
1122
1123	INIT_LIST_HEAD(&context->db_page_list);
1124	mutex_init(&context->db_page_mutex);
1125
1126	INIT_LIST_HEAD(&context->wqn_ranges_list);
1127	mutex_init(&context->wqn_ranges_mutex);
1128
1129	if (ibdev->ops.uverbs_abi_ver == MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION)
1130		err = ib_copy_to_udata(udata, &resp_v3, sizeof(resp_v3));
1131	else
1132		err = ib_copy_to_udata(udata, &resp, sizeof(resp));
1133
1134	if (err) {
1135		mlx4_uar_free(to_mdev(ibdev)->dev, &context->uar);
1136		return -EFAULT;
1137	}
1138
1139	return err;
1140}
1141
1142static void mlx4_ib_dealloc_ucontext(struct ib_ucontext *ibcontext)
1143{
1144	struct mlx4_ib_ucontext *context = to_mucontext(ibcontext);
1145
1146	mlx4_uar_free(to_mdev(ibcontext->device)->dev, &context->uar);
1147}
1148
1149static void mlx4_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
1150{
1151}
1152
1153static int mlx4_ib_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
1154{
1155	struct mlx4_ib_dev *dev = to_mdev(context->device);
1156
1157	switch (vma->vm_pgoff) {
1158	case 0:
1159		return rdma_user_mmap_io(context, vma,
1160					 to_mucontext(context)->uar.pfn,
1161					 PAGE_SIZE,
1162					 pgprot_noncached(vma->vm_page_prot),
1163					 NULL);
1164
1165	case 1:
1166		if (dev->dev->caps.bf_reg_size == 0)
1167			return -EINVAL;
1168		return rdma_user_mmap_io(
1169			context, vma,
1170			to_mucontext(context)->uar.pfn +
1171				dev->dev->caps.num_uars,
1172			PAGE_SIZE, pgprot_writecombine(vma->vm_page_prot),
1173			NULL);
1174
1175	case 3: {
1176		struct mlx4_clock_params params;
1177		int ret;
1178
1179		ret = mlx4_get_internal_clock_params(dev->dev, &params);
1180		if (ret)
1181			return ret;
1182
1183		return rdma_user_mmap_io(
1184			context, vma,
1185			(pci_resource_start(dev->dev->persist->pdev,
1186					    params.bar) +
1187			 params.offset) >>
1188				PAGE_SHIFT,
1189			PAGE_SIZE, pgprot_noncached(vma->vm_page_prot),
1190			NULL);
1191	}
1192
1193	default:
1194		return -EINVAL;
1195	}
1196}
1197
1198static int mlx4_ib_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
1199{
1200	struct mlx4_ib_pd *pd = to_mpd(ibpd);
1201	struct ib_device *ibdev = ibpd->device;
1202	int err;
1203
1204	err = mlx4_pd_alloc(to_mdev(ibdev)->dev, &pd->pdn);
1205	if (err)
1206		return err;
1207
1208	if (udata && ib_copy_to_udata(udata, &pd->pdn, sizeof(__u32))) {
1209		mlx4_pd_free(to_mdev(ibdev)->dev, pd->pdn);
1210		return -EFAULT;
1211	}
1212	return 0;
1213}
1214
1215static int mlx4_ib_dealloc_pd(struct ib_pd *pd, struct ib_udata *udata)
1216{
1217	mlx4_pd_free(to_mdev(pd->device)->dev, to_mpd(pd)->pdn);
1218	return 0;
1219}
1220
1221static int mlx4_ib_alloc_xrcd(struct ib_xrcd *ibxrcd, struct ib_udata *udata)
1222{
1223	struct mlx4_ib_dev *dev = to_mdev(ibxrcd->device);
1224	struct mlx4_ib_xrcd *xrcd = to_mxrcd(ibxrcd);
1225	struct ib_cq_init_attr cq_attr = {};
1226	int err;
1227
1228	if (!(dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC))
1229		return -EOPNOTSUPP;
1230
1231	err = mlx4_xrcd_alloc(dev->dev, &xrcd->xrcdn);
1232	if (err)
1233		return err;
1234
1235	xrcd->pd = ib_alloc_pd(ibxrcd->device, 0);
1236	if (IS_ERR(xrcd->pd)) {
1237		err = PTR_ERR(xrcd->pd);
1238		goto err2;
1239	}
1240
1241	cq_attr.cqe = 1;
1242	xrcd->cq = ib_create_cq(ibxrcd->device, NULL, NULL, xrcd, &cq_attr);
1243	if (IS_ERR(xrcd->cq)) {
1244		err = PTR_ERR(xrcd->cq);
1245		goto err3;
1246	}
1247
1248	return 0;
1249
1250err3:
1251	ib_dealloc_pd(xrcd->pd);
1252err2:
1253	mlx4_xrcd_free(dev->dev, xrcd->xrcdn);
1254	return err;
1255}
1256
1257static int mlx4_ib_dealloc_xrcd(struct ib_xrcd *xrcd, struct ib_udata *udata)
1258{
1259	ib_destroy_cq(to_mxrcd(xrcd)->cq);
1260	ib_dealloc_pd(to_mxrcd(xrcd)->pd);
1261	mlx4_xrcd_free(to_mdev(xrcd->device)->dev, to_mxrcd(xrcd)->xrcdn);
1262	return 0;
1263}
1264
1265static int add_gid_entry(struct ib_qp *ibqp, union ib_gid *gid)
1266{
1267	struct mlx4_ib_qp *mqp = to_mqp(ibqp);
1268	struct mlx4_ib_dev *mdev = to_mdev(ibqp->device);
1269	struct mlx4_ib_gid_entry *ge;
1270
1271	ge = kzalloc(sizeof *ge, GFP_KERNEL);
1272	if (!ge)
1273		return -ENOMEM;
1274
1275	ge->gid = *gid;
1276	if (mlx4_ib_add_mc(mdev, mqp, gid)) {
1277		ge->port = mqp->port;
1278		ge->added = 1;
1279	}
1280
1281	mutex_lock(&mqp->mutex);
1282	list_add_tail(&ge->list, &mqp->gid_list);
1283	mutex_unlock(&mqp->mutex);
1284
1285	return 0;
1286}
1287
1288static void mlx4_ib_delete_counters_table(struct mlx4_ib_dev *ibdev,
1289					  struct mlx4_ib_counters *ctr_table)
1290{
1291	struct counter_index *counter, *tmp_count;
1292
1293	mutex_lock(&ctr_table->mutex);
1294	list_for_each_entry_safe(counter, tmp_count, &ctr_table->counters_list,
1295				 list) {
1296		if (counter->allocated)
1297			mlx4_counter_free(ibdev->dev, counter->index);
1298		list_del(&counter->list);
1299		kfree(counter);
1300	}
1301	mutex_unlock(&ctr_table->mutex);
1302}
1303
1304int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
1305		   union ib_gid *gid)
1306{
1307	struct net_device *ndev;
1308	int ret = 0;
1309
1310	if (!mqp->port)
1311		return 0;
1312
1313	spin_lock_bh(&mdev->iboe.lock);
1314	ndev = mdev->iboe.netdevs[mqp->port - 1];
1315	if (ndev)
1316		dev_hold(ndev);
1317	spin_unlock_bh(&mdev->iboe.lock);
1318
1319	if (ndev) {
1320		ret = 1;
1321		dev_put(ndev);
1322	}
1323
1324	return ret;
1325}
1326
1327struct mlx4_ib_steering {
1328	struct list_head list;
1329	struct mlx4_flow_reg_id reg_id;
1330	union ib_gid gid;
1331};
1332
1333#define LAST_ETH_FIELD vlan_tag
1334#define LAST_IB_FIELD sl
1335#define LAST_IPV4_FIELD dst_ip
1336#define LAST_TCP_UDP_FIELD src_port
1337
1338/* Field is the last supported field */
1339#define FIELDS_NOT_SUPPORTED(filter, field)\
1340	memchr_inv((void *)&filter.field  +\
1341		   sizeof(filter.field), 0,\
1342		   sizeof(filter) -\
1343		   offsetof(typeof(filter), field) -\
1344		   sizeof(filter.field))
1345
1346static int parse_flow_attr(struct mlx4_dev *dev,
1347			   u32 qp_num,
1348			   union ib_flow_spec *ib_spec,
1349			   struct _rule_hw *mlx4_spec)
1350{
1351	enum mlx4_net_trans_rule_id type;
1352
1353	switch (ib_spec->type) {
1354	case IB_FLOW_SPEC_ETH:
1355		if (FIELDS_NOT_SUPPORTED(ib_spec->eth.mask, LAST_ETH_FIELD))
1356			return -ENOTSUPP;
1357
1358		type = MLX4_NET_TRANS_RULE_ID_ETH;
1359		memcpy(mlx4_spec->eth.dst_mac, ib_spec->eth.val.dst_mac,
1360		       ETH_ALEN);
1361		memcpy(mlx4_spec->eth.dst_mac_msk, ib_spec->eth.mask.dst_mac,
1362		       ETH_ALEN);
1363		mlx4_spec->eth.vlan_tag = ib_spec->eth.val.vlan_tag;
1364		mlx4_spec->eth.vlan_tag_msk = ib_spec->eth.mask.vlan_tag;
1365		break;
1366	case IB_FLOW_SPEC_IB:
1367		if (FIELDS_NOT_SUPPORTED(ib_spec->ib.mask, LAST_IB_FIELD))
1368			return -ENOTSUPP;
1369
1370		type = MLX4_NET_TRANS_RULE_ID_IB;
1371		mlx4_spec->ib.l3_qpn =
1372			cpu_to_be32(qp_num);
1373		mlx4_spec->ib.qpn_mask =
1374			cpu_to_be32(MLX4_IB_FLOW_QPN_MASK);
1375		break;
1376
1377
1378	case IB_FLOW_SPEC_IPV4:
1379		if (FIELDS_NOT_SUPPORTED(ib_spec->ipv4.mask, LAST_IPV4_FIELD))
1380			return -ENOTSUPP;
1381
1382		type = MLX4_NET_TRANS_RULE_ID_IPV4;
1383		mlx4_spec->ipv4.src_ip = ib_spec->ipv4.val.src_ip;
1384		mlx4_spec->ipv4.src_ip_msk = ib_spec->ipv4.mask.src_ip;
1385		mlx4_spec->ipv4.dst_ip = ib_spec->ipv4.val.dst_ip;
1386		mlx4_spec->ipv4.dst_ip_msk = ib_spec->ipv4.mask.dst_ip;
1387		break;
1388
1389	case IB_FLOW_SPEC_TCP:
1390	case IB_FLOW_SPEC_UDP:
1391		if (FIELDS_NOT_SUPPORTED(ib_spec->tcp_udp.mask, LAST_TCP_UDP_FIELD))
1392			return -ENOTSUPP;
1393
1394		type = ib_spec->type == IB_FLOW_SPEC_TCP ?
1395					MLX4_NET_TRANS_RULE_ID_TCP :
1396					MLX4_NET_TRANS_RULE_ID_UDP;
1397		mlx4_spec->tcp_udp.dst_port = ib_spec->tcp_udp.val.dst_port;
1398		mlx4_spec->tcp_udp.dst_port_msk = ib_spec->tcp_udp.mask.dst_port;
1399		mlx4_spec->tcp_udp.src_port = ib_spec->tcp_udp.val.src_port;
1400		mlx4_spec->tcp_udp.src_port_msk = ib_spec->tcp_udp.mask.src_port;
1401		break;
1402
1403	default:
1404		return -EINVAL;
1405	}
1406	if (mlx4_map_sw_to_hw_steering_id(dev, type) < 0 ||
1407	    mlx4_hw_rule_sz(dev, type) < 0)
1408		return -EINVAL;
1409	mlx4_spec->id = cpu_to_be16(mlx4_map_sw_to_hw_steering_id(dev, type));
1410	mlx4_spec->size = mlx4_hw_rule_sz(dev, type) >> 2;
1411	return mlx4_hw_rule_sz(dev, type);
1412}
1413
1414struct default_rules {
1415	__u32 mandatory_fields[IB_FLOW_SPEC_SUPPORT_LAYERS];
1416	__u32 mandatory_not_fields[IB_FLOW_SPEC_SUPPORT_LAYERS];
1417	__u32 rules_create_list[IB_FLOW_SPEC_SUPPORT_LAYERS];
1418	__u8  link_layer;
1419};
1420static const struct default_rules default_table[] = {
1421	{
1422		.mandatory_fields = {IB_FLOW_SPEC_IPV4},
1423		.mandatory_not_fields = {IB_FLOW_SPEC_ETH},
1424		.rules_create_list = {IB_FLOW_SPEC_IB},
1425		.link_layer = IB_LINK_LAYER_INFINIBAND
1426	}
1427};
1428
1429static int __mlx4_ib_default_rules_match(struct ib_qp *qp,
1430					 struct ib_flow_attr *flow_attr)
1431{
1432	int i, j, k;
1433	void *ib_flow;
1434	const struct default_rules *pdefault_rules = default_table;
1435	u8 link_layer = rdma_port_get_link_layer(qp->device, flow_attr->port);
1436
1437	for (i = 0; i < ARRAY_SIZE(default_table); i++, pdefault_rules++) {
1438		__u32 field_types[IB_FLOW_SPEC_SUPPORT_LAYERS];
1439		memset(&field_types, 0, sizeof(field_types));
1440
1441		if (link_layer != pdefault_rules->link_layer)
1442			continue;
1443
1444		ib_flow = flow_attr + 1;
1445		/* we assume the specs are sorted */
1446		for (j = 0, k = 0; k < IB_FLOW_SPEC_SUPPORT_LAYERS &&
1447		     j < flow_attr->num_of_specs; k++) {
1448			union ib_flow_spec *current_flow =
1449				(union ib_flow_spec *)ib_flow;
1450
1451			/* same layer but different type */
1452			if (((current_flow->type & IB_FLOW_SPEC_LAYER_MASK) ==
1453			     (pdefault_rules->mandatory_fields[k] &
1454			      IB_FLOW_SPEC_LAYER_MASK)) &&
1455			    (current_flow->type !=
1456			     pdefault_rules->mandatory_fields[k]))
1457				goto out;
1458
1459			/* same layer, try match next one */
1460			if (current_flow->type ==
1461			    pdefault_rules->mandatory_fields[k]) {
1462				j++;
1463				ib_flow +=
1464					((union ib_flow_spec *)ib_flow)->size;
1465			}
1466		}
1467
1468		ib_flow = flow_attr + 1;
1469		for (j = 0; j < flow_attr->num_of_specs;
1470		     j++, ib_flow += ((union ib_flow_spec *)ib_flow)->size)
1471			for (k = 0; k < IB_FLOW_SPEC_SUPPORT_LAYERS; k++)
1472				/* same layer and same type */
1473				if (((union ib_flow_spec *)ib_flow)->type ==
1474				    pdefault_rules->mandatory_not_fields[k])
1475					goto out;
1476
1477		return i;
1478	}
1479out:
1480	return -1;
1481}
1482
1483static int __mlx4_ib_create_default_rules(
1484		struct mlx4_ib_dev *mdev,
1485		struct ib_qp *qp,
1486		const struct default_rules *pdefault_rules,
1487		struct _rule_hw *mlx4_spec) {
1488	int size = 0;
1489	int i;
1490
1491	for (i = 0; i < ARRAY_SIZE(pdefault_rules->rules_create_list); i++) {
1492		union ib_flow_spec ib_spec = {};
1493		int ret;
1494
1495		switch (pdefault_rules->rules_create_list[i]) {
1496		case 0:
1497			/* no rule */
1498			continue;
1499		case IB_FLOW_SPEC_IB:
1500			ib_spec.type = IB_FLOW_SPEC_IB;
1501			ib_spec.size = sizeof(struct ib_flow_spec_ib);
1502
1503			break;
1504		default:
1505			/* invalid rule */
1506			return -EINVAL;
1507		}
1508		/* We must put empty rule, qpn is being ignored */
1509		ret = parse_flow_attr(mdev->dev, 0, &ib_spec,
1510				      mlx4_spec);
1511		if (ret < 0) {
1512			pr_info("invalid parsing\n");
1513			return -EINVAL;
1514		}
1515
1516		mlx4_spec = (void *)mlx4_spec + ret;
1517		size += ret;
1518	}
1519	return size;
1520}
1521
1522static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_attr,
1523			  int domain,
1524			  enum mlx4_net_trans_promisc_mode flow_type,
1525			  u64 *reg_id)
1526{
1527	int ret, i;
1528	int size = 0;
1529	void *ib_flow;
1530	struct mlx4_ib_dev *mdev = to_mdev(qp->device);
1531	struct mlx4_cmd_mailbox *mailbox;
1532	struct mlx4_net_trans_rule_hw_ctrl *ctrl;
1533	int default_flow;
1534
1535	if (flow_attr->priority > MLX4_IB_FLOW_MAX_PRIO) {
1536		pr_err("Invalid priority value %d\n", flow_attr->priority);
1537		return -EINVAL;
1538	}
1539
1540	if (mlx4_map_sw_to_hw_steering_mode(mdev->dev, flow_type) < 0)
1541		return -EINVAL;
1542
1543	mailbox = mlx4_alloc_cmd_mailbox(mdev->dev);
1544	if (IS_ERR(mailbox))
1545		return PTR_ERR(mailbox);
1546	ctrl = mailbox->buf;
1547
1548	ctrl->prio = cpu_to_be16(domain | flow_attr->priority);
1549	ctrl->type = mlx4_map_sw_to_hw_steering_mode(mdev->dev, flow_type);
1550	ctrl->port = flow_attr->port;
1551	ctrl->qpn = cpu_to_be32(qp->qp_num);
1552
1553	ib_flow = flow_attr + 1;
1554	size += sizeof(struct mlx4_net_trans_rule_hw_ctrl);
1555	/* Add default flows */
1556	default_flow = __mlx4_ib_default_rules_match(qp, flow_attr);
1557	if (default_flow >= 0) {
1558		ret = __mlx4_ib_create_default_rules(
1559				mdev, qp, default_table + default_flow,
1560				mailbox->buf + size);
1561		if (ret < 0) {
1562			mlx4_free_cmd_mailbox(mdev->dev, mailbox);
1563			return -EINVAL;
1564		}
1565		size += ret;
1566	}
1567	for (i = 0; i < flow_attr->num_of_specs; i++) {
1568		ret = parse_flow_attr(mdev->dev, qp->qp_num, ib_flow,
1569				      mailbox->buf + size);
1570		if (ret < 0) {
1571			mlx4_free_cmd_mailbox(mdev->dev, mailbox);
1572			return -EINVAL;
1573		}
1574		ib_flow += ((union ib_flow_spec *) ib_flow)->size;
1575		size += ret;
1576	}
1577
1578	if (mlx4_is_master(mdev->dev) && flow_type == MLX4_FS_REGULAR &&
1579	    flow_attr->num_of_specs == 1) {
1580		struct _rule_hw *rule_header = (struct _rule_hw *)(ctrl + 1);
1581		enum ib_flow_spec_type header_spec =
1582			((union ib_flow_spec *)(flow_attr + 1))->type;
1583
1584		if (header_spec == IB_FLOW_SPEC_ETH)
1585			mlx4_handle_eth_header_mcast_prio(ctrl, rule_header);
1586	}
1587
1588	ret = mlx4_cmd_imm(mdev->dev, mailbox->dma, reg_id, size >> 2, 0,
1589			   MLX4_QP_FLOW_STEERING_ATTACH, MLX4_CMD_TIME_CLASS_A,
1590			   MLX4_CMD_NATIVE);
1591	if (ret == -ENOMEM)
1592		pr_err("mcg table is full. Fail to register network rule.\n");
1593	else if (ret == -ENXIO)
1594		pr_err("Device managed flow steering is disabled. Fail to register network rule.\n");
1595	else if (ret)
1596		pr_err("Invalid argument. Fail to register network rule.\n");
1597
1598	mlx4_free_cmd_mailbox(mdev->dev, mailbox);
1599	return ret;
1600}
1601
1602static int __mlx4_ib_destroy_flow(struct mlx4_dev *dev, u64 reg_id)
1603{
1604	int err;
1605	err = mlx4_cmd(dev, reg_id, 0, 0,
1606		       MLX4_QP_FLOW_STEERING_DETACH, MLX4_CMD_TIME_CLASS_A,
1607		       MLX4_CMD_NATIVE);
1608	if (err)
1609		pr_err("Fail to detach network rule. registration id = 0x%llx\n",
1610		       reg_id);
1611	return err;
1612}
1613
1614static int mlx4_ib_tunnel_steer_add(struct ib_qp *qp, struct ib_flow_attr *flow_attr,
1615				    u64 *reg_id)
1616{
1617	void *ib_flow;
1618	union ib_flow_spec *ib_spec;
1619	struct mlx4_dev	*dev = to_mdev(qp->device)->dev;
1620	int err = 0;
1621
1622	if (dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN ||
1623	    dev->caps.dmfs_high_steer_mode == MLX4_STEERING_DMFS_A0_STATIC)
1624		return 0; /* do nothing */
1625
1626	ib_flow = flow_attr + 1;
1627	ib_spec = (union ib_flow_spec *)ib_flow;
1628
1629	if (ib_spec->type !=  IB_FLOW_SPEC_ETH || flow_attr->num_of_specs != 1)
1630		return 0; /* do nothing */
1631
1632	err = mlx4_tunnel_steer_add(to_mdev(qp->device)->dev, ib_spec->eth.val.dst_mac,
1633				    flow_attr->port, qp->qp_num,
1634				    MLX4_DOMAIN_UVERBS | (flow_attr->priority & 0xff),
1635				    reg_id);
1636	return err;
1637}
1638
1639static int mlx4_ib_add_dont_trap_rule(struct mlx4_dev *dev,
1640				      struct ib_flow_attr *flow_attr,
1641				      enum mlx4_net_trans_promisc_mode *type)
1642{
1643	int err = 0;
1644
1645	if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DMFS_UC_MC_SNIFFER) ||
1646	    (dev->caps.dmfs_high_steer_mode == MLX4_STEERING_DMFS_A0_STATIC) ||
1647	    (flow_attr->num_of_specs > 1) || (flow_attr->priority != 0)) {
1648		return -EOPNOTSUPP;
1649	}
1650
1651	if (flow_attr->num_of_specs == 0) {
1652		type[0] = MLX4_FS_MC_SNIFFER;
1653		type[1] = MLX4_FS_UC_SNIFFER;
1654	} else {
1655		union ib_flow_spec *ib_spec;
1656
1657		ib_spec = (union ib_flow_spec *)(flow_attr + 1);
1658		if (ib_spec->type !=  IB_FLOW_SPEC_ETH)
1659			return -EINVAL;
1660
1661		/* if all is zero than MC and UC */
1662		if (is_zero_ether_addr(ib_spec->eth.mask.dst_mac)) {
1663			type[0] = MLX4_FS_MC_SNIFFER;
1664			type[1] = MLX4_FS_UC_SNIFFER;
1665		} else {
1666			u8 mac[ETH_ALEN] = {ib_spec->eth.mask.dst_mac[0] ^ 0x01,
1667					    ib_spec->eth.mask.dst_mac[1],
1668					    ib_spec->eth.mask.dst_mac[2],
1669					    ib_spec->eth.mask.dst_mac[3],
1670					    ib_spec->eth.mask.dst_mac[4],
1671					    ib_spec->eth.mask.dst_mac[5]};
1672
1673			/* Above xor was only on MC bit, non empty mask is valid
1674			 * only if this bit is set and rest are zero.
1675			 */
1676			if (!is_zero_ether_addr(&mac[0]))
1677				return -EINVAL;
1678
1679			if (is_multicast_ether_addr(ib_spec->eth.val.dst_mac))
1680				type[0] = MLX4_FS_MC_SNIFFER;
1681			else
1682				type[0] = MLX4_FS_UC_SNIFFER;
1683		}
1684	}
1685
1686	return err;
1687}
1688
1689static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
1690					   struct ib_flow_attr *flow_attr,
1691					   struct ib_udata *udata)
1692{
1693	int err = 0, i = 0, j = 0;
1694	struct mlx4_ib_flow *mflow;
1695	enum mlx4_net_trans_promisc_mode type[2];
1696	struct mlx4_dev *dev = (to_mdev(qp->device))->dev;
1697	int is_bonded = mlx4_is_bonded(dev);
1698
1699	if (flow_attr->port < 1 || flow_attr->port > qp->device->phys_port_cnt)
1700		return ERR_PTR(-EINVAL);
1701
1702	if (flow_attr->flags & ~IB_FLOW_ATTR_FLAGS_DONT_TRAP)
1703		return ERR_PTR(-EOPNOTSUPP);
1704
1705	if ((flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP) &&
1706	    (flow_attr->type != IB_FLOW_ATTR_NORMAL))
1707		return ERR_PTR(-EOPNOTSUPP);
1708
1709	if (udata &&
1710	    udata->inlen && !ib_is_udata_cleared(udata, 0, udata->inlen))
1711		return ERR_PTR(-EOPNOTSUPP);
1712
1713	memset(type, 0, sizeof(type));
1714
1715	mflow = kzalloc(sizeof(*mflow), GFP_KERNEL);
1716	if (!mflow) {
1717		err = -ENOMEM;
1718		goto err_free;
1719	}
1720
1721	switch (flow_attr->type) {
1722	case IB_FLOW_ATTR_NORMAL:
1723		/* If dont trap flag (continue match) is set, under specific
1724		 * condition traffic be replicated to given qp,
1725		 * without stealing it
1726		 */
1727		if (unlikely(flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP)) {
1728			err = mlx4_ib_add_dont_trap_rule(dev,
1729							 flow_attr,
1730							 type);
1731			if (err)
1732				goto err_free;
1733		} else {
1734			type[0] = MLX4_FS_REGULAR;
1735		}
1736		break;
1737
1738	case IB_FLOW_ATTR_ALL_DEFAULT:
1739		type[0] = MLX4_FS_ALL_DEFAULT;
1740		break;
1741
1742	case IB_FLOW_ATTR_MC_DEFAULT:
1743		type[0] = MLX4_FS_MC_DEFAULT;
1744		break;
1745
1746	case IB_FLOW_ATTR_SNIFFER:
1747		type[0] = MLX4_FS_MIRROR_RX_PORT;
1748		type[1] = MLX4_FS_MIRROR_SX_PORT;
1749		break;
1750
1751	default:
1752		err = -EINVAL;
1753		goto err_free;
1754	}
1755
1756	while (i < ARRAY_SIZE(type) && type[i]) {
1757		err = __mlx4_ib_create_flow(qp, flow_attr, MLX4_DOMAIN_UVERBS,
1758					    type[i], &mflow->reg_id[i].id);
1759		if (err)
1760			goto err_create_flow;
1761		if (is_bonded) {
1762			/* Application always sees one port so the mirror rule
1763			 * must be on port #2
1764			 */
1765			flow_attr->port = 2;
1766			err = __mlx4_ib_create_flow(qp, flow_attr,
1767						    MLX4_DOMAIN_UVERBS, type[j],
1768						    &mflow->reg_id[j].mirror);
1769			flow_attr->port = 1;
1770			if (err)
1771				goto err_create_flow;
1772			j++;
1773		}
1774
1775		i++;
1776	}
1777
1778	if (i < ARRAY_SIZE(type) && flow_attr->type == IB_FLOW_ATTR_NORMAL) {
1779		err = mlx4_ib_tunnel_steer_add(qp, flow_attr,
1780					       &mflow->reg_id[i].id);
1781		if (err)
1782			goto err_create_flow;
1783
1784		if (is_bonded) {
1785			flow_attr->port = 2;
1786			err = mlx4_ib_tunnel_steer_add(qp, flow_attr,
1787						       &mflow->reg_id[j].mirror);
1788			flow_attr->port = 1;
1789			if (err)
1790				goto err_create_flow;
1791			j++;
1792		}
1793		/* function to create mirror rule */
1794		i++;
1795	}
1796
1797	return &mflow->ibflow;
1798
1799err_create_flow:
1800	while (i) {
1801		(void)__mlx4_ib_destroy_flow(to_mdev(qp->device)->dev,
1802					     mflow->reg_id[i].id);
1803		i--;
1804	}
1805
1806	while (j) {
1807		(void)__mlx4_ib_destroy_flow(to_mdev(qp->device)->dev,
1808					     mflow->reg_id[j].mirror);
1809		j--;
1810	}
1811err_free:
1812	kfree(mflow);
1813	return ERR_PTR(err);
1814}
1815
1816static int mlx4_ib_destroy_flow(struct ib_flow *flow_id)
1817{
1818	int err, ret = 0;
1819	int i = 0;
1820	struct mlx4_ib_dev *mdev = to_mdev(flow_id->qp->device);
1821	struct mlx4_ib_flow *mflow = to_mflow(flow_id);
1822
1823	while (i < ARRAY_SIZE(mflow->reg_id) && mflow->reg_id[i].id) {
1824		err = __mlx4_ib_destroy_flow(mdev->dev, mflow->reg_id[i].id);
1825		if (err)
1826			ret = err;
1827		if (mflow->reg_id[i].mirror) {
1828			err = __mlx4_ib_destroy_flow(mdev->dev,
1829						     mflow->reg_id[i].mirror);
1830			if (err)
1831				ret = err;
1832		}
1833		i++;
1834	}
1835
1836	kfree(mflow);
1837	return ret;
1838}
1839
1840static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
1841{
1842	int err;
1843	struct mlx4_ib_dev *mdev = to_mdev(ibqp->device);
1844	struct mlx4_dev	*dev = mdev->dev;
1845	struct mlx4_ib_qp *mqp = to_mqp(ibqp);
1846	struct mlx4_ib_steering *ib_steering = NULL;
1847	enum mlx4_protocol prot = MLX4_PROT_IB_IPV6;
1848	struct mlx4_flow_reg_id	reg_id;
1849
1850	if (mdev->dev->caps.steering_mode ==
1851	    MLX4_STEERING_MODE_DEVICE_MANAGED) {
1852		ib_steering = kmalloc(sizeof(*ib_steering), GFP_KERNEL);
1853		if (!ib_steering)
1854			return -ENOMEM;
1855	}
1856
1857	err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw, mqp->port,
1858				    !!(mqp->flags &
1859				       MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK),
1860				    prot, &reg_id.id);
1861	if (err) {
1862		pr_err("multicast attach op failed, err %d\n", err);
1863		goto err_malloc;
1864	}
1865
1866	reg_id.mirror = 0;
1867	if (mlx4_is_bonded(dev)) {
1868		err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw,
1869					    (mqp->port == 1) ? 2 : 1,
1870					    !!(mqp->flags &
1871					    MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK),
1872					    prot, &reg_id.mirror);
1873		if (err)
1874			goto err_add;
1875	}
1876
1877	err = add_gid_entry(ibqp, gid);
1878	if (err)
1879		goto err_add;
1880
1881	if (ib_steering) {
1882		memcpy(ib_steering->gid.raw, gid->raw, 16);
1883		ib_steering->reg_id = reg_id;
1884		mutex_lock(&mqp->mutex);
1885		list_add(&ib_steering->list, &mqp->steering_rules);
1886		mutex_unlock(&mqp->mutex);
1887	}
1888	return 0;
1889
1890err_add:
1891	mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw,
1892			      prot, reg_id.id);
1893	if (reg_id.mirror)
1894		mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw,
1895				      prot, reg_id.mirror);
1896err_malloc:
1897	kfree(ib_steering);
1898
1899	return err;
1900}
1901
1902static struct mlx4_ib_gid_entry *find_gid_entry(struct mlx4_ib_qp *qp, u8 *raw)
1903{
1904	struct mlx4_ib_gid_entry *ge;
1905	struct mlx4_ib_gid_entry *tmp;
1906	struct mlx4_ib_gid_entry *ret = NULL;
1907
1908	list_for_each_entry_safe(ge, tmp, &qp->gid_list, list) {
1909		if (!memcmp(raw, ge->gid.raw, 16)) {
1910			ret = ge;
1911			break;
1912		}
1913	}
1914
1915	return ret;
1916}
1917
1918static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
1919{
1920	int err;
1921	struct mlx4_ib_dev *mdev = to_mdev(ibqp->device);
1922	struct mlx4_dev *dev = mdev->dev;
1923	struct mlx4_ib_qp *mqp = to_mqp(ibqp);
1924	struct net_device *ndev;
1925	struct mlx4_ib_gid_entry *ge;
1926	struct mlx4_flow_reg_id reg_id = {0, 0};
1927	enum mlx4_protocol prot =  MLX4_PROT_IB_IPV6;
1928
1929	if (mdev->dev->caps.steering_mode ==
1930	    MLX4_STEERING_MODE_DEVICE_MANAGED) {
1931		struct mlx4_ib_steering *ib_steering;
1932
1933		mutex_lock(&mqp->mutex);
1934		list_for_each_entry(ib_steering, &mqp->steering_rules, list) {
1935			if (!memcmp(ib_steering->gid.raw, gid->raw, 16)) {
1936				list_del(&ib_steering->list);
1937				break;
1938			}
1939		}
1940		mutex_unlock(&mqp->mutex);
1941		if (&ib_steering->list == &mqp->steering_rules) {
1942			pr_err("Couldn't find reg_id for mgid. Steering rule is left attached\n");
1943			return -EINVAL;
1944		}
1945		reg_id = ib_steering->reg_id;
1946		kfree(ib_steering);
1947	}
1948
1949	err = mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw,
1950				    prot, reg_id.id);
1951	if (err)
1952		return err;
1953
1954	if (mlx4_is_bonded(dev)) {
1955		err = mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw,
1956					    prot, reg_id.mirror);
1957		if (err)
1958			return err;
1959	}
1960
1961	mutex_lock(&mqp->mutex);
1962	ge = find_gid_entry(mqp, gid->raw);
1963	if (ge) {
1964		spin_lock_bh(&mdev->iboe.lock);
1965		ndev = ge->added ? mdev->iboe.netdevs[ge->port - 1] : NULL;
1966		if (ndev)
1967			dev_hold(ndev);
1968		spin_unlock_bh(&mdev->iboe.lock);
1969		if (ndev)
1970			dev_put(ndev);
1971		list_del(&ge->list);
1972		kfree(ge);
1973	} else
1974		pr_warn("could not find mgid entry\n");
1975
1976	mutex_unlock(&mqp->mutex);
1977
1978	return 0;
1979}
1980
1981static int init_node_data(struct mlx4_ib_dev *dev)
1982{
1983	struct ib_smp *in_mad  = NULL;
1984	struct ib_smp *out_mad = NULL;
1985	int mad_ifc_flags = MLX4_MAD_IFC_IGNORE_KEYS;
1986	int err = -ENOMEM;
1987
1988	in_mad  = kzalloc(sizeof *in_mad, GFP_KERNEL);
1989	out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
1990	if (!in_mad || !out_mad)
1991		goto out;
1992
1993	init_query_mad(in_mad);
1994	in_mad->attr_id = IB_SMP_ATTR_NODE_DESC;
1995	if (mlx4_is_master(dev->dev))
1996		mad_ifc_flags |= MLX4_MAD_IFC_NET_VIEW;
1997
1998	err = mlx4_MAD_IFC(dev, mad_ifc_flags, 1, NULL, NULL, in_mad, out_mad);
1999	if (err)
2000		goto out;
2001
2002	memcpy(dev->ib_dev.node_desc, out_mad->data, IB_DEVICE_NODE_DESC_MAX);
2003
2004	in_mad->attr_id = IB_SMP_ATTR_NODE_INFO;
2005
2006	err = mlx4_MAD_IFC(dev, mad_ifc_flags, 1, NULL, NULL, in_mad, out_mad);
2007	if (err)
2008		goto out;
2009
2010	dev->dev->rev_id = be32_to_cpup((__be32 *) (out_mad->data + 32));
2011	memcpy(&dev->ib_dev.node_guid, out_mad->data + 12, 8);
2012
2013out:
2014	kfree(in_mad);
2015	kfree(out_mad);
2016	return err;
2017}
2018
2019static ssize_t hca_type_show(struct device *device,
2020			     struct device_attribute *attr, char *buf)
2021{
2022	struct mlx4_ib_dev *dev =
2023		rdma_device_to_drv_device(device, struct mlx4_ib_dev, ib_dev);
2024	return sprintf(buf, "MT%d\n", dev->dev->persist->pdev->device);
2025}
2026static DEVICE_ATTR_RO(hca_type);
2027
2028static ssize_t hw_rev_show(struct device *device,
2029			   struct device_attribute *attr, char *buf)
2030{
2031	struct mlx4_ib_dev *dev =
2032		rdma_device_to_drv_device(device, struct mlx4_ib_dev, ib_dev);
2033	return sprintf(buf, "%x\n", dev->dev->rev_id);
2034}
2035static DEVICE_ATTR_RO(hw_rev);
2036
2037static ssize_t board_id_show(struct device *device,
2038			     struct device_attribute *attr, char *buf)
2039{
2040	struct mlx4_ib_dev *dev =
2041		rdma_device_to_drv_device(device, struct mlx4_ib_dev, ib_dev);
2042
2043	return sprintf(buf, "%.*s\n", MLX4_BOARD_ID_LEN,
2044		       dev->dev->board_id);
2045}
2046static DEVICE_ATTR_RO(board_id);
2047
2048static struct attribute *mlx4_class_attributes[] = {
2049	&dev_attr_hw_rev.attr,
2050	&dev_attr_hca_type.attr,
2051	&dev_attr_board_id.attr,
2052	NULL
2053};
2054
2055static const struct attribute_group mlx4_attr_group = {
2056	.attrs = mlx4_class_attributes,
2057};
2058
2059struct diag_counter {
2060	const char *name;
2061	u32 offset;
2062};
2063
2064#define DIAG_COUNTER(_name, _offset)			\
2065	{ .name = #_name, .offset = _offset }
2066
2067static const struct diag_counter diag_basic[] = {
2068	DIAG_COUNTER(rq_num_lle, 0x00),
2069	DIAG_COUNTER(sq_num_lle, 0x04),
2070	DIAG_COUNTER(rq_num_lqpoe, 0x08),
2071	DIAG_COUNTER(sq_num_lqpoe, 0x0C),
2072	DIAG_COUNTER(rq_num_lpe, 0x18),
2073	DIAG_COUNTER(sq_num_lpe, 0x1C),
2074	DIAG_COUNTER(rq_num_wrfe, 0x20),
2075	DIAG_COUNTER(sq_num_wrfe, 0x24),
2076	DIAG_COUNTER(sq_num_mwbe, 0x2C),
2077	DIAG_COUNTER(sq_num_bre, 0x34),
2078	DIAG_COUNTER(sq_num_rire, 0x44),
2079	DIAG_COUNTER(rq_num_rire, 0x48),
2080	DIAG_COUNTER(sq_num_rae, 0x4C),
2081	DIAG_COUNTER(rq_num_rae, 0x50),
2082	DIAG_COUNTER(sq_num_roe, 0x54),
2083	DIAG_COUNTER(sq_num_tree, 0x5C),
2084	DIAG_COUNTER(sq_num_rree, 0x64),
2085	DIAG_COUNTER(rq_num_rnr, 0x68),
2086	DIAG_COUNTER(sq_num_rnr, 0x6C),
2087	DIAG_COUNTER(rq_num_oos, 0x100),
2088	DIAG_COUNTER(sq_num_oos, 0x104),
2089};
2090
2091static const struct diag_counter diag_ext[] = {
2092	DIAG_COUNTER(rq_num_dup, 0x130),
2093	DIAG_COUNTER(sq_num_to, 0x134),
2094};
2095
2096static const struct diag_counter diag_device_only[] = {
2097	DIAG_COUNTER(num_cqovf, 0x1A0),
2098	DIAG_COUNTER(rq_num_udsdprd, 0x118),
2099};
2100
2101static struct rdma_hw_stats *mlx4_ib_alloc_hw_stats(struct ib_device *ibdev,
2102						    u8 port_num)
2103{
2104	struct mlx4_ib_dev *dev = to_mdev(ibdev);
2105	struct mlx4_ib_diag_counters *diag = dev->diag_counters;
2106
2107	if (!diag[!!port_num].name)
2108		return NULL;
2109
2110	return rdma_alloc_hw_stats_struct(diag[!!port_num].name,
2111					  diag[!!port_num].num_counters,
2112					  RDMA_HW_STATS_DEFAULT_LIFESPAN);
2113}
2114
2115static int mlx4_ib_get_hw_stats(struct ib_device *ibdev,
2116				struct rdma_hw_stats *stats,
2117				u8 port, int index)
2118{
2119	struct mlx4_ib_dev *dev = to_mdev(ibdev);
2120	struct mlx4_ib_diag_counters *diag = dev->diag_counters;
2121	u32 hw_value[ARRAY_SIZE(diag_device_only) +
2122		ARRAY_SIZE(diag_ext) + ARRAY_SIZE(diag_basic)] = {};
2123	int ret;
2124	int i;
2125
2126	ret = mlx4_query_diag_counters(dev->dev,
2127				       MLX4_OP_MOD_QUERY_TRANSPORT_CI_ERRORS,
2128				       diag[!!port].offset, hw_value,
2129				       diag[!!port].num_counters, port);
2130
2131	if (ret)
2132		return ret;
2133
2134	for (i = 0; i < diag[!!port].num_counters; i++)
2135		stats->value[i] = hw_value[i];
2136
2137	return diag[!!port].num_counters;
2138}
2139
2140static int __mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev,
2141					 const char ***name,
2142					 u32 **offset,
2143					 u32 *num,
2144					 bool port)
2145{
2146	u32 num_counters;
2147
2148	num_counters = ARRAY_SIZE(diag_basic);
2149
2150	if (ibdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT)
2151		num_counters += ARRAY_SIZE(diag_ext);
2152
2153	if (!port)
2154		num_counters += ARRAY_SIZE(diag_device_only);
2155
2156	*name = kcalloc(num_counters, sizeof(**name), GFP_KERNEL);
2157	if (!*name)
2158		return -ENOMEM;
2159
2160	*offset = kcalloc(num_counters, sizeof(**offset), GFP_KERNEL);
2161	if (!*offset)
2162		goto err_name;
2163
2164	*num = num_counters;
2165
2166	return 0;
2167
2168err_name:
2169	kfree(*name);
2170	return -ENOMEM;
2171}
2172
2173static void mlx4_ib_fill_diag_counters(struct mlx4_ib_dev *ibdev,
2174				       const char **name,
2175				       u32 *offset,
2176				       bool port)
2177{
2178	int i;
2179	int j;
2180
2181	for (i = 0, j = 0; i < ARRAY_SIZE(diag_basic); i++, j++) {
2182		name[i] = diag_basic[i].name;
2183		offset[i] = diag_basic[i].offset;
2184	}
2185
2186	if (ibdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT) {
2187		for (i = 0; i < ARRAY_SIZE(diag_ext); i++, j++) {
2188			name[j] = diag_ext[i].name;
2189			offset[j] = diag_ext[i].offset;
2190		}
2191	}
2192
2193	if (!port) {
2194		for (i = 0; i < ARRAY_SIZE(diag_device_only); i++, j++) {
2195			name[j] = diag_device_only[i].name;
2196			offset[j] = diag_device_only[i].offset;
2197		}
2198	}
2199}
2200
2201static const struct ib_device_ops mlx4_ib_hw_stats_ops = {
2202	.alloc_hw_stats = mlx4_ib_alloc_hw_stats,
2203	.get_hw_stats = mlx4_ib_get_hw_stats,
2204};
2205
2206static int mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev)
2207{
2208	struct mlx4_ib_diag_counters *diag = ibdev->diag_counters;
2209	int i;
2210	int ret;
2211	bool per_port = !!(ibdev->dev->caps.flags2 &
2212		MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT);
2213
2214	if (mlx4_is_slave(ibdev->dev))
2215		return 0;
2216
2217	for (i = 0; i < MLX4_DIAG_COUNTERS_TYPES; i++) {
2218		/* i == 1 means we are building port counters */
2219		if (i && !per_port)
2220			continue;
2221
2222		ret = __mlx4_ib_alloc_diag_counters(ibdev, &diag[i].name,
2223						    &diag[i].offset,
2224						    &diag[i].num_counters, i);
2225		if (ret)
2226			goto err_alloc;
2227
2228		mlx4_ib_fill_diag_counters(ibdev, diag[i].name,
2229					   diag[i].offset, i);
2230	}
2231
2232	ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_hw_stats_ops);
2233
2234	return 0;
2235
2236err_alloc:
2237	if (i) {
2238		kfree(diag[i - 1].name);
2239		kfree(diag[i - 1].offset);
2240	}
2241
2242	return ret;
2243}
2244
2245static void mlx4_ib_diag_cleanup(struct mlx4_ib_dev *ibdev)
2246{
2247	int i;
2248
2249	for (i = 0; i < MLX4_DIAG_COUNTERS_TYPES; i++) {
2250		kfree(ibdev->diag_counters[i].offset);
2251		kfree(ibdev->diag_counters[i].name);
2252	}
2253}
2254
2255#define MLX4_IB_INVALID_MAC	((u64)-1)
2256static void mlx4_ib_update_qps(struct mlx4_ib_dev *ibdev,
2257			       struct net_device *dev,
2258			       int port)
2259{
2260	u64 new_smac = 0;
2261	u64 release_mac = MLX4_IB_INVALID_MAC;
2262	struct mlx4_ib_qp *qp;
2263
2264	read_lock(&dev_base_lock);
2265	new_smac = mlx4_mac_to_u64(dev->dev_addr);
2266	read_unlock(&dev_base_lock);
2267
2268	atomic64_set(&ibdev->iboe.mac[port - 1], new_smac);
2269
2270	/* no need for update QP1 and mac registration in non-SRIOV */
2271	if (!mlx4_is_mfunc(ibdev->dev))
2272		return;
2273
2274	mutex_lock(&ibdev->qp1_proxy_lock[port - 1]);
2275	qp = ibdev->qp1_proxy[port - 1];
2276	if (qp) {
2277		int new_smac_index;
2278		u64 old_smac;
2279		struct mlx4_update_qp_params update_params;
2280
2281		mutex_lock(&qp->mutex);
2282		old_smac = qp->pri.smac;
2283		if (new_smac == old_smac)
2284			goto unlock;
2285
2286		new_smac_index = mlx4_register_mac(ibdev->dev, port, new_smac);
2287
2288		if (new_smac_index < 0)
2289			goto unlock;
2290
2291		update_params.smac_index = new_smac_index;
2292		if (mlx4_update_qp(ibdev->dev, qp->mqp.qpn, MLX4_UPDATE_QP_SMAC,
2293				   &update_params)) {
2294			release_mac = new_smac;
2295			goto unlock;
2296		}
2297		/* if old port was zero, no mac was yet registered for this QP */
2298		if (qp->pri.smac_port)
2299			release_mac = old_smac;
2300		qp->pri.smac = new_smac;
2301		qp->pri.smac_port = port;
2302		qp->pri.smac_index = new_smac_index;
2303	}
2304
2305unlock:
2306	if (release_mac != MLX4_IB_INVALID_MAC)
2307		mlx4_unregister_mac(ibdev->dev, port, release_mac);
2308	if (qp)
2309		mutex_unlock(&qp->mutex);
2310	mutex_unlock(&ibdev->qp1_proxy_lock[port - 1]);
2311}
2312
2313static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev,
2314				 struct net_device *dev,
2315				 unsigned long event)
2316
2317{
2318	struct mlx4_ib_iboe *iboe;
2319	int update_qps_port = -1;
2320	int port;
2321
2322	ASSERT_RTNL();
2323
2324	iboe = &ibdev->iboe;
2325
2326	spin_lock_bh(&iboe->lock);
2327	mlx4_foreach_ib_transport_port(port, ibdev->dev) {
2328
2329		iboe->netdevs[port - 1] =
2330			mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port);
2331
2332		if (dev == iboe->netdevs[port - 1] &&
2333		    (event == NETDEV_CHANGEADDR || event == NETDEV_REGISTER ||
2334		     event == NETDEV_UP || event == NETDEV_CHANGE))
2335			update_qps_port = port;
2336
2337		if (dev == iboe->netdevs[port - 1] &&
2338		    (event == NETDEV_UP || event == NETDEV_DOWN)) {
2339			enum ib_port_state port_state;
2340			struct ib_event ibev = { };
2341
2342			if (ib_get_cached_port_state(&ibdev->ib_dev, port,
2343						     &port_state))
2344				continue;
2345
2346			if (event == NETDEV_UP &&
2347			    (port_state != IB_PORT_ACTIVE ||
2348			     iboe->last_port_state[port - 1] != IB_PORT_DOWN))
2349				continue;
2350			if (event == NETDEV_DOWN &&
2351			    (port_state != IB_PORT_DOWN ||
2352			     iboe->last_port_state[port - 1] != IB_PORT_ACTIVE))
2353				continue;
2354			iboe->last_port_state[port - 1] = port_state;
2355
2356			ibev.device = &ibdev->ib_dev;
2357			ibev.element.port_num = port;
2358			ibev.event = event == NETDEV_UP ? IB_EVENT_PORT_ACTIVE :
2359							  IB_EVENT_PORT_ERR;
2360			ib_dispatch_event(&ibev);
2361		}
2362
2363	}
2364	spin_unlock_bh(&iboe->lock);
2365
2366	if (update_qps_port > 0)
2367		mlx4_ib_update_qps(ibdev, dev, update_qps_port);
2368}
2369
2370static int mlx4_ib_netdev_event(struct notifier_block *this,
2371				unsigned long event, void *ptr)
2372{
2373	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
2374	struct mlx4_ib_dev *ibdev;
2375
2376	if (!net_eq(dev_net(dev), &init_net))
2377		return NOTIFY_DONE;
2378
2379	ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb);
2380	mlx4_ib_scan_netdevs(ibdev, dev, event);
2381
2382	return NOTIFY_DONE;
2383}
2384
2385static void init_pkeys(struct mlx4_ib_dev *ibdev)
2386{
2387	int port;
2388	int slave;
2389	int i;
2390
2391	if (mlx4_is_master(ibdev->dev)) {
2392		for (slave = 0; slave <= ibdev->dev->persist->num_vfs;
2393		     ++slave) {
2394			for (port = 1; port <= ibdev->dev->caps.num_ports; ++port) {
2395				for (i = 0;
2396				     i < ibdev->dev->phys_caps.pkey_phys_table_len[port];
2397				     ++i) {
2398					ibdev->pkeys.virt2phys_pkey[slave][port - 1][i] =
2399					/* master has the identity virt2phys pkey mapping */
2400						(slave == mlx4_master_func_num(ibdev->dev) || !i) ? i :
2401							ibdev->dev->phys_caps.pkey_phys_table_len[port] - 1;
2402					mlx4_sync_pkey_table(ibdev->dev, slave, port, i,
2403							     ibdev->pkeys.virt2phys_pkey[slave][port - 1][i]);
2404				}
2405			}
2406		}
2407		/* initialize pkey cache */
2408		for (port = 1; port <= ibdev->dev->caps.num_ports; ++port) {
2409			for (i = 0;
2410			     i < ibdev->dev->phys_caps.pkey_phys_table_len[port];
2411			     ++i)
2412				ibdev->pkeys.phys_pkey_cache[port-1][i] =
2413					(i) ? 0 : 0xFFFF;
2414		}
2415	}
2416}
2417
2418static void mlx4_ib_alloc_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
2419{
2420	int i, j, eq = 0, total_eqs = 0;
2421
2422	ibdev->eq_table = kcalloc(dev->caps.num_comp_vectors,
2423				  sizeof(ibdev->eq_table[0]), GFP_KERNEL);
2424	if (!ibdev->eq_table)
2425		return;
2426
2427	for (i = 1; i <= dev->caps.num_ports; i++) {
2428		for (j = 0; j < mlx4_get_eqs_per_port(dev, i);
2429		     j++, total_eqs++) {
2430			if (i > 1 &&  mlx4_is_eq_shared(dev, total_eqs))
2431				continue;
2432			ibdev->eq_table[eq] = total_eqs;
2433			if (!mlx4_assign_eq(dev, i,
2434					    &ibdev->eq_table[eq]))
2435				eq++;
2436			else
2437				ibdev->eq_table[eq] = -1;
2438		}
2439	}
2440
2441	for (i = eq; i < dev->caps.num_comp_vectors;
2442	     ibdev->eq_table[i++] = -1)
2443		;
2444
2445	/* Advertise the new number of EQs to clients */
2446	ibdev->ib_dev.num_comp_vectors = eq;
2447}
2448
2449static void mlx4_ib_free_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
2450{
2451	int i;
2452	int total_eqs = ibdev->ib_dev.num_comp_vectors;
2453
2454	/* no eqs were allocated */
2455	if (!ibdev->eq_table)
2456		return;
2457
2458	/* Reset the advertised EQ number */
2459	ibdev->ib_dev.num_comp_vectors = 0;
2460
2461	for (i = 0; i < total_eqs; i++)
2462		mlx4_release_eq(dev, ibdev->eq_table[i]);
2463
2464	kfree(ibdev->eq_table);
2465	ibdev->eq_table = NULL;
2466}
2467
2468static int mlx4_port_immutable(struct ib_device *ibdev, u8 port_num,
2469			       struct ib_port_immutable *immutable)
2470{
2471	struct ib_port_attr attr;
2472	struct mlx4_ib_dev *mdev = to_mdev(ibdev);
2473	int err;
2474
2475	if (mlx4_ib_port_link_layer(ibdev, port_num) == IB_LINK_LAYER_INFINIBAND) {
2476		immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB;
2477		immutable->max_mad_size = IB_MGMT_MAD_SIZE;
2478	} else {
2479		if (mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE)
2480			immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE;
2481		if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ROCE_V1_V2)
2482			immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE |
2483				RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP;
2484		immutable->core_cap_flags |= RDMA_CORE_PORT_RAW_PACKET;
2485		if (immutable->core_cap_flags & (RDMA_CORE_PORT_IBA_ROCE |
2486		    RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP))
2487			immutable->max_mad_size = IB_MGMT_MAD_SIZE;
2488	}
2489
2490	err = ib_query_port(ibdev, port_num, &attr);
2491	if (err)
2492		return err;
2493
2494	immutable->pkey_tbl_len = attr.pkey_tbl_len;
2495	immutable->gid_tbl_len = attr.gid_tbl_len;
2496
2497	return 0;
2498}
2499
2500static void get_fw_ver_str(struct ib_device *device, char *str)
2501{
2502	struct mlx4_ib_dev *dev =
2503		container_of(device, struct mlx4_ib_dev, ib_dev);
2504	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d",
2505		 (int) (dev->dev->caps.fw_ver >> 32),
2506		 (int) (dev->dev->caps.fw_ver >> 16) & 0xffff,
2507		 (int) dev->dev->caps.fw_ver & 0xffff);
2508}
2509
2510static const struct ib_device_ops mlx4_ib_dev_ops = {
2511	.owner = THIS_MODULE,
2512	.driver_id = RDMA_DRIVER_MLX4,
2513	.uverbs_abi_ver = MLX4_IB_UVERBS_ABI_VERSION,
2514
2515	.add_gid = mlx4_ib_add_gid,
2516	.alloc_mr = mlx4_ib_alloc_mr,
2517	.alloc_pd = mlx4_ib_alloc_pd,
2518	.alloc_ucontext = mlx4_ib_alloc_ucontext,
2519	.attach_mcast = mlx4_ib_mcg_attach,
2520	.create_ah = mlx4_ib_create_ah,
2521	.create_cq = mlx4_ib_create_cq,
2522	.create_qp = mlx4_ib_create_qp,
2523	.create_srq = mlx4_ib_create_srq,
2524	.dealloc_pd = mlx4_ib_dealloc_pd,
2525	.dealloc_ucontext = mlx4_ib_dealloc_ucontext,
2526	.del_gid = mlx4_ib_del_gid,
2527	.dereg_mr = mlx4_ib_dereg_mr,
2528	.destroy_ah = mlx4_ib_destroy_ah,
2529	.destroy_cq = mlx4_ib_destroy_cq,
2530	.destroy_qp = mlx4_ib_destroy_qp,
2531	.destroy_srq = mlx4_ib_destroy_srq,
2532	.detach_mcast = mlx4_ib_mcg_detach,
2533	.disassociate_ucontext = mlx4_ib_disassociate_ucontext,
2534	.drain_rq = mlx4_ib_drain_rq,
2535	.drain_sq = mlx4_ib_drain_sq,
2536	.get_dev_fw_str = get_fw_ver_str,
2537	.get_dma_mr = mlx4_ib_get_dma_mr,
2538	.get_link_layer = mlx4_ib_port_link_layer,
2539	.get_netdev = mlx4_ib_get_netdev,
2540	.get_port_immutable = mlx4_port_immutable,
2541	.map_mr_sg = mlx4_ib_map_mr_sg,
2542	.mmap = mlx4_ib_mmap,
2543	.modify_cq = mlx4_ib_modify_cq,
2544	.modify_device = mlx4_ib_modify_device,
2545	.modify_port = mlx4_ib_modify_port,
2546	.modify_qp = mlx4_ib_modify_qp,
2547	.modify_srq = mlx4_ib_modify_srq,
2548	.poll_cq = mlx4_ib_poll_cq,
2549	.post_recv = mlx4_ib_post_recv,
2550	.post_send = mlx4_ib_post_send,
2551	.post_srq_recv = mlx4_ib_post_srq_recv,
2552	.process_mad = mlx4_ib_process_mad,
2553	.query_ah = mlx4_ib_query_ah,
2554	.query_device = mlx4_ib_query_device,
2555	.query_gid = mlx4_ib_query_gid,
2556	.query_pkey = mlx4_ib_query_pkey,
2557	.query_port = mlx4_ib_query_port,
2558	.query_qp = mlx4_ib_query_qp,
2559	.query_srq = mlx4_ib_query_srq,
2560	.reg_user_mr = mlx4_ib_reg_user_mr,
2561	.req_notify_cq = mlx4_ib_arm_cq,
2562	.rereg_user_mr = mlx4_ib_rereg_user_mr,
2563	.resize_cq = mlx4_ib_resize_cq,
2564
2565	INIT_RDMA_OBJ_SIZE(ib_ah, mlx4_ib_ah, ibah),
2566	INIT_RDMA_OBJ_SIZE(ib_cq, mlx4_ib_cq, ibcq),
2567	INIT_RDMA_OBJ_SIZE(ib_pd, mlx4_ib_pd, ibpd),
2568	INIT_RDMA_OBJ_SIZE(ib_srq, mlx4_ib_srq, ibsrq),
2569	INIT_RDMA_OBJ_SIZE(ib_ucontext, mlx4_ib_ucontext, ibucontext),
2570};
2571
2572static const struct ib_device_ops mlx4_ib_dev_wq_ops = {
2573	.create_rwq_ind_table = mlx4_ib_create_rwq_ind_table,
2574	.create_wq = mlx4_ib_create_wq,
2575	.destroy_rwq_ind_table = mlx4_ib_destroy_rwq_ind_table,
2576	.destroy_wq = mlx4_ib_destroy_wq,
2577	.modify_wq = mlx4_ib_modify_wq,
2578
2579	INIT_RDMA_OBJ_SIZE(ib_rwq_ind_table, mlx4_ib_rwq_ind_table,
2580			   ib_rwq_ind_tbl),
2581};
2582
2583static const struct ib_device_ops mlx4_ib_dev_mw_ops = {
2584	.alloc_mw = mlx4_ib_alloc_mw,
2585	.dealloc_mw = mlx4_ib_dealloc_mw,
2586
2587	INIT_RDMA_OBJ_SIZE(ib_mw, mlx4_ib_mw, ibmw),
2588};
2589
2590static const struct ib_device_ops mlx4_ib_dev_xrc_ops = {
2591	.alloc_xrcd = mlx4_ib_alloc_xrcd,
2592	.dealloc_xrcd = mlx4_ib_dealloc_xrcd,
2593
2594	INIT_RDMA_OBJ_SIZE(ib_xrcd, mlx4_ib_xrcd, ibxrcd),
2595};
2596
2597static const struct ib_device_ops mlx4_ib_dev_fs_ops = {
2598	.create_flow = mlx4_ib_create_flow,
2599	.destroy_flow = mlx4_ib_destroy_flow,
2600};
2601
2602static void *mlx4_ib_add(struct mlx4_dev *dev)
2603{
2604	struct mlx4_ib_dev *ibdev;
2605	int num_ports = 0;
2606	int i, j;
2607	int err;
2608	struct mlx4_ib_iboe *iboe;
2609	int ib_num_ports = 0;
2610	int num_req_counters;
2611	int allocated;
2612	u32 counter_index;
2613	struct counter_index *new_counter_index = NULL;
2614
2615	pr_info_once("%s", mlx4_ib_version);
2616
2617	num_ports = 0;
2618	mlx4_foreach_ib_transport_port(i, dev)
2619		num_ports++;
2620
2621	/* No point in registering a device with no ports... */
2622	if (num_ports == 0)
2623		return NULL;
2624
2625	ibdev = ib_alloc_device(mlx4_ib_dev, ib_dev);
2626	if (!ibdev) {
2627		dev_err(&dev->persist->pdev->dev,
2628			"Device struct alloc failed\n");
2629		return NULL;
2630	}
2631
2632	iboe = &ibdev->iboe;
2633
2634	if (mlx4_pd_alloc(dev, &ibdev->priv_pdn))
2635		goto err_dealloc;
2636
2637	if (mlx4_uar_alloc(dev, &ibdev->priv_uar))
2638		goto err_pd;
2639
2640	ibdev->uar_map = ioremap((phys_addr_t) ibdev->priv_uar.pfn << PAGE_SHIFT,
2641				 PAGE_SIZE);
2642	if (!ibdev->uar_map)
2643		goto err_uar;
2644	MLX4_INIT_DOORBELL_LOCK(&ibdev->uar_lock);
2645
2646	ibdev->dev = dev;
2647	ibdev->bond_next_port	= 0;
2648
2649	ibdev->ib_dev.node_type		= RDMA_NODE_IB_CA;
2650	ibdev->ib_dev.local_dma_lkey	= dev->caps.reserved_lkey;
2651	ibdev->num_ports		= num_ports;
2652	ibdev->ib_dev.phys_port_cnt     = mlx4_is_bonded(dev) ?
2653						1 : ibdev->num_ports;
2654	ibdev->ib_dev.num_comp_vectors	= dev->caps.num_comp_vectors;
2655	ibdev->ib_dev.dev.parent	= &dev->persist->pdev->dev;
2656
2657	ibdev->ib_dev.uverbs_cmd_mask	=
2658		(1ull << IB_USER_VERBS_CMD_GET_CONTEXT)		|
2659		(1ull << IB_USER_VERBS_CMD_QUERY_DEVICE)	|
2660		(1ull << IB_USER_VERBS_CMD_QUERY_PORT)		|
2661		(1ull << IB_USER_VERBS_CMD_ALLOC_PD)		|
2662		(1ull << IB_USER_VERBS_CMD_DEALLOC_PD)		|
2663		(1ull << IB_USER_VERBS_CMD_REG_MR)		|
2664		(1ull << IB_USER_VERBS_CMD_REREG_MR)		|
2665		(1ull << IB_USER_VERBS_CMD_DEREG_MR)		|
2666		(1ull << IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL)	|
2667		(1ull << IB_USER_VERBS_CMD_CREATE_CQ)		|
2668		(1ull << IB_USER_VERBS_CMD_RESIZE_CQ)		|
2669		(1ull << IB_USER_VERBS_CMD_DESTROY_CQ)		|
2670		(1ull << IB_USER_VERBS_CMD_CREATE_QP)		|
2671		(1ull << IB_USER_VERBS_CMD_MODIFY_QP)		|
2672		(1ull << IB_USER_VERBS_CMD_QUERY_QP)		|
2673		(1ull << IB_USER_VERBS_CMD_DESTROY_QP)		|
2674		(1ull << IB_USER_VERBS_CMD_ATTACH_MCAST)	|
2675		(1ull << IB_USER_VERBS_CMD_DETACH_MCAST)	|
2676		(1ull << IB_USER_VERBS_CMD_CREATE_SRQ)		|
2677		(1ull << IB_USER_VERBS_CMD_MODIFY_SRQ)		|
2678		(1ull << IB_USER_VERBS_CMD_QUERY_SRQ)		|
2679		(1ull << IB_USER_VERBS_CMD_DESTROY_SRQ)		|
2680		(1ull << IB_USER_VERBS_CMD_CREATE_XSRQ)		|
2681		(1ull << IB_USER_VERBS_CMD_OPEN_QP);
2682
2683	ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_ops);
2684	ibdev->ib_dev.uverbs_ex_cmd_mask |=
2685		(1ull << IB_USER_VERBS_EX_CMD_CREATE_CQ) |
2686		(1ull << IB_USER_VERBS_EX_CMD_CREATE_QP);
2687
2688	if ((dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS) &&
2689	    ((mlx4_ib_port_link_layer(&ibdev->ib_dev, 1) ==
2690	    IB_LINK_LAYER_ETHERNET) ||
2691	    (mlx4_ib_port_link_layer(&ibdev->ib_dev, 2) ==
2692	    IB_LINK_LAYER_ETHERNET)))
2693		ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_wq_ops);
2694
2695	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW ||
2696	    dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN) {
2697		ibdev->ib_dev.uverbs_cmd_mask |=
2698			(1ull << IB_USER_VERBS_CMD_ALLOC_MW) |
2699			(1ull << IB_USER_VERBS_CMD_DEALLOC_MW);
2700		ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_mw_ops);
2701	}
2702
2703	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) {
2704		ibdev->ib_dev.uverbs_cmd_mask |=
2705			(1ull << IB_USER_VERBS_CMD_OPEN_XRCD) |
2706			(1ull << IB_USER_VERBS_CMD_CLOSE_XRCD);
2707		ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_xrc_ops);
2708	}
2709
2710	if (check_flow_steering_support(dev)) {
2711		ibdev->steering_support = MLX4_STEERING_MODE_DEVICE_MANAGED;
2712		ib_set_device_ops(&ibdev->ib_dev, &mlx4_ib_dev_fs_ops);
2713	}
2714
2715	if (!dev->caps.userspace_caps)
2716		ibdev->ib_dev.ops.uverbs_abi_ver =
2717			MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION;
2718
2719	mlx4_ib_alloc_eqs(dev, ibdev);
2720
2721	spin_lock_init(&iboe->lock);
2722
2723	if (init_node_data(ibdev))
2724		goto err_map;
2725	mlx4_init_sl2vl_tbl(ibdev);
2726
2727	for (i = 0; i < ibdev->num_ports; ++i) {
2728		mutex_init(&ibdev->counters_table[i].mutex);
2729		INIT_LIST_HEAD(&ibdev->counters_table[i].counters_list);
2730		iboe->last_port_state[i] = IB_PORT_DOWN;
2731	}
2732
2733	num_req_counters = mlx4_is_bonded(dev) ? 1 : ibdev->num_ports;
2734	for (i = 0; i < num_req_counters; ++i) {
2735		mutex_init(&ibdev->qp1_proxy_lock[i]);
2736		allocated = 0;
2737		if (mlx4_ib_port_link_layer(&ibdev->ib_dev, i + 1) ==
2738						IB_LINK_LAYER_ETHERNET) {
2739			err = mlx4_counter_alloc(ibdev->dev, &counter_index,
2740						 MLX4_RES_USAGE_DRIVER);
2741			/* if failed to allocate a new counter, use default */
2742			if (err)
2743				counter_index =
2744					mlx4_get_default_counter_index(dev,
2745								       i + 1);
2746			else
2747				allocated = 1;
2748		} else { /* IB_LINK_LAYER_INFINIBAND use the default counter */
2749			counter_index = mlx4_get_default_counter_index(dev,
2750								       i + 1);
2751		}
2752		new_counter_index = kmalloc(sizeof(*new_counter_index),
2753					    GFP_KERNEL);
2754		if (!new_counter_index) {
2755			if (allocated)
2756				mlx4_counter_free(ibdev->dev, counter_index);
2757			goto err_counter;
2758		}
2759		new_counter_index->index = counter_index;
2760		new_counter_index->allocated = allocated;
2761		list_add_tail(&new_counter_index->list,
2762			      &ibdev->counters_table[i].counters_list);
2763		ibdev->counters_table[i].default_counter = counter_index;
2764		pr_info("counter index %d for port %d allocated %d\n",
2765			counter_index, i + 1, allocated);
2766	}
2767	if (mlx4_is_bonded(dev))
2768		for (i = 1; i < ibdev->num_ports ; ++i) {
2769			new_counter_index =
2770					kmalloc(sizeof(struct counter_index),
2771						GFP_KERNEL);
2772			if (!new_counter_index)
2773				goto err_counter;
2774			new_counter_index->index = counter_index;
2775			new_counter_index->allocated = 0;
2776			list_add_tail(&new_counter_index->list,
2777				      &ibdev->counters_table[i].counters_list);
2778			ibdev->counters_table[i].default_counter =
2779								counter_index;
2780		}
2781
2782	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
2783		ib_num_ports++;
2784
2785	spin_lock_init(&ibdev->sm_lock);
2786	mutex_init(&ibdev->cap_mask_mutex);
2787	INIT_LIST_HEAD(&ibdev->qp_list);
2788	spin_lock_init(&ibdev->reset_flow_resource_lock);
2789
2790	if (ibdev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED &&
2791	    ib_num_ports) {
2792		ibdev->steer_qpn_count = MLX4_IB_UC_MAX_NUM_QPS;
2793		err = mlx4_qp_reserve_range(dev, ibdev->steer_qpn_count,
2794					    MLX4_IB_UC_STEER_QPN_ALIGN,
2795					    &ibdev->steer_qpn_base, 0,
2796					    MLX4_RES_USAGE_DRIVER);
2797		if (err)
2798			goto err_counter;
2799
2800		ibdev->ib_uc_qpns_bitmap =
2801			kmalloc_array(BITS_TO_LONGS(ibdev->steer_qpn_count),
2802				      sizeof(long),
2803				      GFP_KERNEL);
2804		if (!ibdev->ib_uc_qpns_bitmap)
2805			goto err_steer_qp_release;
2806
2807		if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DMFS_IPOIB) {
2808			bitmap_zero(ibdev->ib_uc_qpns_bitmap,
2809				    ibdev->steer_qpn_count);
2810			err = mlx4_FLOW_STEERING_IB_UC_QP_RANGE(
2811					dev, ibdev->steer_qpn_base,
2812					ibdev->steer_qpn_base +
2813					ibdev->steer_qpn_count - 1);
2814			if (err)
2815				goto err_steer_free_bitmap;
2816		} else {
2817			bitmap_fill(ibdev->ib_uc_qpns_bitmap,
2818				    ibdev->steer_qpn_count);
2819		}
2820	}
2821
2822	for (j = 1; j <= ibdev->dev->caps.num_ports; j++)
2823		atomic64_set(&iboe->mac[j - 1], ibdev->dev->caps.def_mac[j]);
2824
2825	if (mlx4_ib_alloc_diag_counters(ibdev))
2826		goto err_steer_free_bitmap;
2827
2828	rdma_set_device_sysfs_group(&ibdev->ib_dev, &mlx4_attr_group);
2829	if (ib_register_device(&ibdev->ib_dev, "mlx4_%d",
2830			       &dev->persist->pdev->dev))
2831		goto err_diag_counters;
2832
2833	if (mlx4_ib_mad_init(ibdev))
2834		goto err_reg;
2835
2836	if (mlx4_ib_init_sriov(ibdev))
2837		goto err_mad;
2838
2839	if (!iboe->nb.notifier_call) {
2840		iboe->nb.notifier_call = mlx4_ib_netdev_event;
2841		err = register_netdevice_notifier(&iboe->nb);
2842		if (err) {
2843			iboe->nb.notifier_call = NULL;
2844			goto err_notif;
2845		}
2846	}
2847	if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ROCE_V1_V2) {
2848		err = mlx4_config_roce_v2_port(dev, ROCE_V2_UDP_DPORT);
2849		if (err)
2850			goto err_notif;
2851	}
2852
2853	ibdev->ib_active = true;
2854	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
2855		devlink_port_type_ib_set(mlx4_get_devlink_port(dev, i),
2856					 &ibdev->ib_dev);
2857
2858	if (mlx4_is_mfunc(ibdev->dev))
2859		init_pkeys(ibdev);
2860
2861	/* create paravirt contexts for any VFs which are active */
2862	if (mlx4_is_master(ibdev->dev)) {
2863		for (j = 0; j < MLX4_MFUNC_MAX; j++) {
2864			if (j == mlx4_master_func_num(ibdev->dev))
2865				continue;
2866			if (mlx4_is_slave_active(ibdev->dev, j))
2867				do_slave_init(ibdev, j, 1);
2868		}
2869	}
2870	return ibdev;
2871
2872err_notif:
2873	if (ibdev->iboe.nb.notifier_call) {
2874		if (unregister_netdevice_notifier(&ibdev->iboe.nb))
2875			pr_warn("failure unregistering notifier\n");
2876		ibdev->iboe.nb.notifier_call = NULL;
2877	}
2878	flush_workqueue(wq);
2879
2880	mlx4_ib_close_sriov(ibdev);
2881
2882err_mad:
2883	mlx4_ib_mad_cleanup(ibdev);
2884
2885err_reg:
2886	ib_unregister_device(&ibdev->ib_dev);
2887
2888err_diag_counters:
2889	mlx4_ib_diag_cleanup(ibdev);
2890
2891err_steer_free_bitmap:
2892	kfree(ibdev->ib_uc_qpns_bitmap);
2893
2894err_steer_qp_release:
2895	mlx4_qp_release_range(dev, ibdev->steer_qpn_base,
2896			      ibdev->steer_qpn_count);
2897err_counter:
2898	for (i = 0; i < ibdev->num_ports; ++i)
2899		mlx4_ib_delete_counters_table(ibdev, &ibdev->counters_table[i]);
2900
2901err_map:
2902	mlx4_ib_free_eqs(dev, ibdev);
2903	iounmap(ibdev->uar_map);
2904
2905err_uar:
2906	mlx4_uar_free(dev, &ibdev->priv_uar);
2907
2908err_pd:
2909	mlx4_pd_free(dev, ibdev->priv_pdn);
2910
2911err_dealloc:
2912	ib_dealloc_device(&ibdev->ib_dev);
2913
2914	return NULL;
2915}
2916
2917int mlx4_ib_steer_qp_alloc(struct mlx4_ib_dev *dev, int count, int *qpn)
2918{
2919	int offset;
2920
2921	WARN_ON(!dev->ib_uc_qpns_bitmap);
2922
2923	offset = bitmap_find_free_region(dev->ib_uc_qpns_bitmap,
2924					 dev->steer_qpn_count,
2925					 get_count_order(count));
2926	if (offset < 0)
2927		return offset;
2928
2929	*qpn = dev->steer_qpn_base + offset;
2930	return 0;
2931}
2932
2933void mlx4_ib_steer_qp_free(struct mlx4_ib_dev *dev, u32 qpn, int count)
2934{
2935	if (!qpn ||
2936	    dev->steering_support != MLX4_STEERING_MODE_DEVICE_MANAGED)
2937		return;
2938
2939	if (WARN(qpn < dev->steer_qpn_base, "qpn = %u, steer_qpn_base = %u\n",
2940		 qpn, dev->steer_qpn_base))
2941		/* not supposed to be here */
2942		return;
2943
2944	bitmap_release_region(dev->ib_uc_qpns_bitmap,
2945			      qpn - dev->steer_qpn_base,
2946			      get_count_order(count));
2947}
2948
2949int mlx4_ib_steer_qp_reg(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
2950			 int is_attach)
2951{
2952	int err;
2953	size_t flow_size;
2954	struct ib_flow_attr *flow = NULL;
2955	struct ib_flow_spec_ib *ib_spec;
2956
2957	if (is_attach) {
2958		flow_size = sizeof(struct ib_flow_attr) +
2959			    sizeof(struct ib_flow_spec_ib);
2960		flow = kzalloc(flow_size, GFP_KERNEL);
2961		if (!flow)
2962			return -ENOMEM;
2963		flow->port = mqp->port;
2964		flow->num_of_specs = 1;
2965		flow->size = flow_size;
2966		ib_spec = (struct ib_flow_spec_ib *)(flow + 1);
2967		ib_spec->type = IB_FLOW_SPEC_IB;
2968		ib_spec->size = sizeof(struct ib_flow_spec_ib);
2969		/* Add an empty rule for IB L2 */
2970		memset(&ib_spec->mask, 0, sizeof(ib_spec->mask));
2971
2972		err = __mlx4_ib_create_flow(&mqp->ibqp, flow, MLX4_DOMAIN_NIC,
2973					    MLX4_FS_REGULAR, &mqp->reg_id);
2974	} else {
2975		err = __mlx4_ib_destroy_flow(mdev->dev, mqp->reg_id);
2976	}
2977	kfree(flow);
2978	return err;
2979}
2980
2981static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
2982{
2983	struct mlx4_ib_dev *ibdev = ibdev_ptr;
2984	int p;
2985	int i;
2986
2987	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
2988		devlink_port_type_clear(mlx4_get_devlink_port(dev, i));
2989	ibdev->ib_active = false;
2990	flush_workqueue(wq);
2991
2992	if (ibdev->iboe.nb.notifier_call) {
2993		if (unregister_netdevice_notifier(&ibdev->iboe.nb))
2994			pr_warn("failure unregistering notifier\n");
2995		ibdev->iboe.nb.notifier_call = NULL;
2996	}
2997
2998	mlx4_ib_close_sriov(ibdev);
2999	mlx4_ib_mad_cleanup(ibdev);
3000	ib_unregister_device(&ibdev->ib_dev);
3001	mlx4_ib_diag_cleanup(ibdev);
3002
3003	mlx4_qp_release_range(dev, ibdev->steer_qpn_base,
3004			      ibdev->steer_qpn_count);
3005	kfree(ibdev->ib_uc_qpns_bitmap);
3006
3007	iounmap(ibdev->uar_map);
3008	for (p = 0; p < ibdev->num_ports; ++p)
3009		mlx4_ib_delete_counters_table(ibdev, &ibdev->counters_table[p]);
3010
3011	mlx4_foreach_port(p, dev, MLX4_PORT_TYPE_IB)
3012		mlx4_CLOSE_PORT(dev, p);
3013
3014	mlx4_ib_free_eqs(dev, ibdev);
3015
3016	mlx4_uar_free(dev, &ibdev->priv_uar);
3017	mlx4_pd_free(dev, ibdev->priv_pdn);
3018	ib_dealloc_device(&ibdev->ib_dev);
3019}
3020
3021static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init)
3022{
3023	struct mlx4_ib_demux_work **dm = NULL;
3024	struct mlx4_dev *dev = ibdev->dev;
3025	int i;
3026	unsigned long flags;
3027	struct mlx4_active_ports actv_ports;
3028	unsigned int ports;
3029	unsigned int first_port;
3030
3031	if (!mlx4_is_master(dev))
3032		return;
3033
3034	actv_ports = mlx4_get_active_ports(dev, slave);
3035	ports = bitmap_weight(actv_ports.ports, dev->caps.num_ports);
3036	first_port = find_first_bit(actv_ports.ports, dev->caps.num_ports);
3037
3038	dm = kcalloc(ports, sizeof(*dm), GFP_ATOMIC);
3039	if (!dm)
3040		return;
3041
3042	for (i = 0; i < ports; i++) {
3043		dm[i] = kmalloc(sizeof (struct mlx4_ib_demux_work), GFP_ATOMIC);
3044		if (!dm[i]) {
3045			while (--i >= 0)
3046				kfree(dm[i]);
3047			goto out;
3048		}
3049		INIT_WORK(&dm[i]->work, mlx4_ib_tunnels_update_work);
3050		dm[i]->port = first_port + i + 1;
3051		dm[i]->slave = slave;
3052		dm[i]->do_init = do_init;
3053		dm[i]->dev = ibdev;
3054	}
3055	/* initialize or tear down tunnel QPs for the slave */
3056	spin_lock_irqsave(&ibdev->sriov.going_down_lock, flags);
3057	if (!ibdev->sriov.is_going_down) {
3058		for (i = 0; i < ports; i++)
3059			queue_work(ibdev->sriov.demux[i].ud_wq, &dm[i]->work);
3060		spin_unlock_irqrestore(&ibdev->sriov.going_down_lock, flags);
3061	} else {
3062		spin_unlock_irqrestore(&ibdev->sriov.going_down_lock, flags);
3063		for (i = 0; i < ports; i++)
3064			kfree(dm[i]);
3065	}
3066out:
3067	kfree(dm);
3068	return;
3069}
3070
3071static void mlx4_ib_handle_catas_error(struct mlx4_ib_dev *ibdev)
3072{
3073	struct mlx4_ib_qp *mqp;
3074	unsigned long flags_qp;
3075	unsigned long flags_cq;
3076	struct mlx4_ib_cq *send_mcq, *recv_mcq;
3077	struct list_head    cq_notify_list;
3078	struct mlx4_cq *mcq;
3079	unsigned long flags;
3080
3081	pr_warn("mlx4_ib_handle_catas_error was started\n");
3082	INIT_LIST_HEAD(&cq_notify_list);
3083
3084	/* Go over qp list reside on that ibdev, sync with create/destroy qp.*/
3085	spin_lock_irqsave(&ibdev->reset_flow_resource_lock, flags);
3086
3087	list_for_each_entry(mqp, &ibdev->qp_list, qps_list) {
3088		spin_lock_irqsave(&mqp->sq.lock, flags_qp);
3089		if (mqp->sq.tail != mqp->sq.head) {
3090			send_mcq = to_mcq(mqp->ibqp.send_cq);
3091			spin_lock_irqsave(&send_mcq->lock, flags_cq);
3092			if (send_mcq->mcq.comp &&
3093			    mqp->ibqp.send_cq->comp_handler) {
3094				if (!send_mcq->mcq.reset_notify_added) {
3095					send_mcq->mcq.reset_notify_added = 1;
3096					list_add_tail(&send_mcq->mcq.reset_notify,
3097						      &cq_notify_list);
3098				}
3099			}
3100			spin_unlock_irqrestore(&send_mcq->lock, flags_cq);
3101		}
3102		spin_unlock_irqrestore(&mqp->sq.lock, flags_qp);
3103		/* Now, handle the QP's receive queue */
3104		spin_lock_irqsave(&mqp->rq.lock, flags_qp);
3105		/* no handling is needed for SRQ */
3106		if (!mqp->ibqp.srq) {
3107			if (mqp->rq.tail != mqp->rq.head) {
3108				recv_mcq = to_mcq(mqp->ibqp.recv_cq);
3109				spin_lock_irqsave(&recv_mcq->lock, flags_cq);
3110				if (recv_mcq->mcq.comp &&
3111				    mqp->ibqp.recv_cq->comp_handler) {
3112					if (!recv_mcq->mcq.reset_notify_added) {
3113						recv_mcq->mcq.reset_notify_added = 1;
3114						list_add_tail(&recv_mcq->mcq.reset_notify,
3115							      &cq_notify_list);
3116					}
3117				}
3118				spin_unlock_irqrestore(&recv_mcq->lock,
3119						       flags_cq);
3120			}
3121		}
3122		spin_unlock_irqrestore(&mqp->rq.lock, flags_qp);
3123	}
3124
3125	list_for_each_entry(mcq, &cq_notify_list, reset_notify) {
3126		mcq->comp(mcq);
3127	}
3128	spin_unlock_irqrestore(&ibdev->reset_flow_resource_lock, flags);
3129	pr_warn("mlx4_ib_handle_catas_error ended\n");
3130}
3131
3132static void handle_bonded_port_state_event(struct work_struct *work)
3133{
3134	struct ib_event_work *ew =
3135		container_of(work, struct ib_event_work, work);
3136	struct mlx4_ib_dev *ibdev = ew->ib_dev;
3137	enum ib_port_state bonded_port_state = IB_PORT_NOP;
3138	int i;
3139	struct ib_event ibev;
3140
3141	kfree(ew);
3142	spin_lock_bh(&ibdev->iboe.lock);
3143	for (i = 0; i < MLX4_MAX_PORTS; ++i) {
3144		struct net_device *curr_netdev = ibdev->iboe.netdevs[i];
3145		enum ib_port_state curr_port_state;
3146
3147		if (!curr_netdev)
3148			continue;
3149
3150		curr_port_state =
3151			(netif_running(curr_netdev) &&
3152			 netif_carrier_ok(curr_netdev)) ?
3153			IB_PORT_ACTIVE : IB_PORT_DOWN;
3154
3155		bonded_port_state = (bonded_port_state != IB_PORT_ACTIVE) ?
3156			curr_port_state : IB_PORT_ACTIVE;
3157	}
3158	spin_unlock_bh(&ibdev->iboe.lock);
3159
3160	ibev.device = &ibdev->ib_dev;
3161	ibev.element.port_num = 1;
3162	ibev.event = (bonded_port_state == IB_PORT_ACTIVE) ?
3163		IB_EVENT_PORT_ACTIVE : IB_EVENT_PORT_ERR;
3164
3165	ib_dispatch_event(&ibev);
3166}
3167
3168void mlx4_ib_sl2vl_update(struct mlx4_ib_dev *mdev, int port)
3169{
3170	u64 sl2vl;
3171	int err;
3172
3173	err = mlx4_ib_query_sl2vl(&mdev->ib_dev, port, &sl2vl);
3174	if (err) {
3175		pr_err("Unable to get current sl to vl mapping for port %d.  Using all zeroes (%d)\n",
3176		       port, err);
3177		sl2vl = 0;
3178	}
3179	atomic64_set(&mdev->sl2vl[port - 1], sl2vl);
3180}
3181
3182static void ib_sl2vl_update_work(struct work_struct *work)
3183{
3184	struct ib_event_work *ew = container_of(work, struct ib_event_work, work);
3185	struct mlx4_ib_dev *mdev = ew->ib_dev;
3186	int port = ew->port;
3187
3188	mlx4_ib_sl2vl_update(mdev, port);
3189
3190	kfree(ew);
3191}
3192
3193void mlx4_sched_ib_sl2vl_update_work(struct mlx4_ib_dev *ibdev,
3194				     int port)
3195{
3196	struct ib_event_work *ew;
3197
3198	ew = kmalloc(sizeof(*ew), GFP_ATOMIC);
3199	if (ew) {
3200		INIT_WORK(&ew->work, ib_sl2vl_update_work);
3201		ew->port = port;
3202		ew->ib_dev = ibdev;
3203		queue_work(wq, &ew->work);
3204	}
3205}
3206
3207static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
3208			  enum mlx4_dev_event event, unsigned long param)
3209{
3210	struct ib_event ibev;
3211	struct mlx4_ib_dev *ibdev = to_mdev((struct ib_device *) ibdev_ptr);
3212	struct mlx4_eqe *eqe = NULL;
3213	struct ib_event_work *ew;
3214	int p = 0;
3215
3216	if (mlx4_is_bonded(dev) &&
3217	    ((event == MLX4_DEV_EVENT_PORT_UP) ||
3218	    (event == MLX4_DEV_EVENT_PORT_DOWN))) {
3219		ew = kmalloc(sizeof(*ew), GFP_ATOMIC);
3220		if (!ew)
3221			return;
3222		INIT_WORK(&ew->work, handle_bonded_port_state_event);
3223		ew->ib_dev = ibdev;
3224		queue_work(wq, &ew->work);
3225		return;
3226	}
3227
3228	if (event == MLX4_DEV_EVENT_PORT_MGMT_CHANGE)
3229		eqe = (struct mlx4_eqe *)param;
3230	else
3231		p = (int) param;
3232
3233	switch (event) {
3234	case MLX4_DEV_EVENT_PORT_UP:
3235		if (p > ibdev->num_ports)
3236			return;
3237		if (!mlx4_is_slave(dev) &&
3238		    rdma_port_get_link_layer(&ibdev->ib_dev, p) ==
3239			IB_LINK_LAYER_INFINIBAND) {
3240			if (mlx4_is_master(dev))
3241				mlx4_ib_invalidate_all_guid_record(ibdev, p);
3242			if (ibdev->dev->flags & MLX4_FLAG_SECURE_HOST &&
3243			    !(ibdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_SL_TO_VL_CHANGE_EVENT))
3244				mlx4_sched_ib_sl2vl_update_work(ibdev, p);
3245		}
3246		ibev.event = IB_EVENT_PORT_ACTIVE;
3247		break;
3248
3249	case MLX4_DEV_EVENT_PORT_DOWN:
3250		if (p > ibdev->num_ports)
3251			return;
3252		ibev.event = IB_EVENT_PORT_ERR;
3253		break;
3254
3255	case MLX4_DEV_EVENT_CATASTROPHIC_ERROR:
3256		ibdev->ib_active = false;
3257		ibev.event = IB_EVENT_DEVICE_FATAL;
3258		mlx4_ib_handle_catas_error(ibdev);
3259		break;
3260
3261	case MLX4_DEV_EVENT_PORT_MGMT_CHANGE:
3262		ew = kmalloc(sizeof *ew, GFP_ATOMIC);
3263		if (!ew)
3264			return;
3265
3266		INIT_WORK(&ew->work, handle_port_mgmt_change_event);
3267		memcpy(&ew->ib_eqe, eqe, sizeof *eqe);
3268		ew->ib_dev = ibdev;
3269		/* need to queue only for port owner, which uses GEN_EQE */
3270		if (mlx4_is_master(dev))
3271			queue_work(wq, &ew->work);
3272		else
3273			handle_port_mgmt_change_event(&ew->work);
3274		return;
3275
3276	case MLX4_DEV_EVENT_SLAVE_INIT:
3277		/* here, p is the slave id */
3278		do_slave_init(ibdev, p, 1);
3279		if (mlx4_is_master(dev)) {
3280			int i;
3281
3282			for (i = 1; i <= ibdev->num_ports; i++) {
3283				if (rdma_port_get_link_layer(&ibdev->ib_dev, i)
3284					== IB_LINK_LAYER_INFINIBAND)
3285					mlx4_ib_slave_alias_guid_event(ibdev,
3286								       p, i,
3287								       1);
3288			}
3289		}
3290		return;
3291
3292	case MLX4_DEV_EVENT_SLAVE_SHUTDOWN:
3293		if (mlx4_is_master(dev)) {
3294			int i;
3295
3296			for (i = 1; i <= ibdev->num_ports; i++) {
3297				if (rdma_port_get_link_layer(&ibdev->ib_dev, i)
3298					== IB_LINK_LAYER_INFINIBAND)
3299					mlx4_ib_slave_alias_guid_event(ibdev,
3300								       p, i,
3301								       0);
3302			}
3303		}
3304		/* here, p is the slave id */
3305		do_slave_init(ibdev, p, 0);
3306		return;
3307
3308	default:
3309		return;
3310	}
3311
3312	ibev.device	      = ibdev_ptr;
3313	ibev.element.port_num = mlx4_is_bonded(ibdev->dev) ? 1 : (u8)p;
3314
3315	ib_dispatch_event(&ibev);
3316}
3317
3318static struct mlx4_interface mlx4_ib_interface = {
3319	.add		= mlx4_ib_add,
3320	.remove		= mlx4_ib_remove,
3321	.event		= mlx4_ib_event,
3322	.protocol	= MLX4_PROT_IB_IPV6,
3323	.flags		= MLX4_INTFF_BONDING
3324};
3325
3326static int __init mlx4_ib_init(void)
3327{
3328	int err;
3329
3330	wq = alloc_ordered_workqueue("mlx4_ib", WQ_MEM_RECLAIM);
3331	if (!wq)
3332		return -ENOMEM;
3333
3334	err = mlx4_ib_mcg_init();
3335	if (err)
3336		goto clean_wq;
3337
3338	err = mlx4_register_interface(&mlx4_ib_interface);
3339	if (err)
3340		goto clean_mcg;
3341
3342	return 0;
3343
3344clean_mcg:
3345	mlx4_ib_mcg_destroy();
3346
3347clean_wq:
3348	destroy_workqueue(wq);
3349	return err;
3350}
3351
3352static void __exit mlx4_ib_cleanup(void)
3353{
3354	mlx4_unregister_interface(&mlx4_ib_interface);
3355	mlx4_ib_mcg_destroy();
3356	destroy_workqueue(wq);
3357}
3358
3359module_init(mlx4_ib_init);
3360module_exit(mlx4_ib_cleanup);
3361