1/* This file is part of the Emulex RoCE Device Driver for
2 * RoCE (RDMA over Converged Ethernet) adapters.
3 * Copyright (C) 2012-2015 Emulex. All rights reserved.
4 * EMULEX and SLI are trademarks of Emulex.
5 * www.emulex.com
6 *
7 * This software is available to you under a choice of one of two licenses.
8 * You may choose to be licensed under the terms of the GNU General Public
9 * License (GPL) Version 2, available from the file COPYING in the main
10 * directory of this source tree, or the BSD license below:
11 *
12 * Redistribution and use in source and binary forms, with or without
13 * modification, are permitted provided that the following conditions
14 * are met:
15 *
16 * - Redistributions of source code must retain the above copyright notice,
17 *   this list of conditions and the following disclaimer.
18 *
19 * - Redistributions in binary form must reproduce the above copyright
20 *   notice, this list of conditions and the following disclaimer in
21 *   the documentation and/or other materials provided with the distribution.
22 *
23 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
24 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
25 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
26 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
27 * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
28 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
29 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
30 * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
31 * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
32 * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
33 * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
34 *
35 * Contact Information:
36 * linux-drivers@emulex.com
37 *
38 * Emulex
39 * 3333 Susan Street
40 * Costa Mesa, CA 92626
41 */
42
43#include <linux/module.h>
44#include <linux/idr.h>
45#include <rdma/ib_verbs.h>
46#include <rdma/ib_user_verbs.h>
47#include <rdma/ib_addr.h>
48#include <rdma/ib_mad.h>
49
50#include <linux/netdevice.h>
51#include <net/addrconf.h>
52
53#include "ocrdma.h"
54#include "ocrdma_verbs.h"
55#include "ocrdma_ah.h"
56#include "be_roce.h"
57#include "ocrdma_hw.h"
58#include "ocrdma_stats.h"
59#include <rdma/ocrdma-abi.h>
60
61MODULE_DESCRIPTION(OCRDMA_ROCE_DRV_DESC " " OCRDMA_ROCE_DRV_VERSION);
62MODULE_AUTHOR("Emulex Corporation");
63MODULE_LICENSE("Dual BSD/GPL");
64
65void ocrdma_get_guid(struct ocrdma_dev *dev, u8 *guid)
66{
67	u8 mac_addr[6];
68
69	memcpy(&mac_addr[0], &dev->nic_info.mac_addr[0], ETH_ALEN);
70	guid[0] = mac_addr[0] ^ 2;
71	guid[1] = mac_addr[1];
72	guid[2] = mac_addr[2];
73	guid[3] = 0xff;
74	guid[4] = 0xfe;
75	guid[5] = mac_addr[3];
76	guid[6] = mac_addr[4];
77	guid[7] = mac_addr[5];
78}
79static enum rdma_link_layer ocrdma_link_layer(struct ib_device *device,
80					      u8 port_num)
81{
82	return IB_LINK_LAYER_ETHERNET;
83}
84
85static int ocrdma_port_immutable(struct ib_device *ibdev, u8 port_num,
86			         struct ib_port_immutable *immutable)
87{
88	struct ib_port_attr attr;
89	struct ocrdma_dev *dev;
90	int err;
91
92	dev = get_ocrdma_dev(ibdev);
93	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE;
94	if (ocrdma_is_udp_encap_supported(dev))
95		immutable->core_cap_flags |= RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP;
96
97	err = ib_query_port(ibdev, port_num, &attr);
98	if (err)
99		return err;
100
101	immutable->pkey_tbl_len = attr.pkey_tbl_len;
102	immutable->gid_tbl_len = attr.gid_tbl_len;
103	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
104
105	return 0;
106}
107
108static void get_dev_fw_str(struct ib_device *device, char *str)
109{
110	struct ocrdma_dev *dev = get_ocrdma_dev(device);
111
112	snprintf(str, IB_FW_VERSION_NAME_MAX, "%s", &dev->attr.fw_ver[0]);
113}
114
115/* OCRDMA sysfs interface */
116static ssize_t hw_rev_show(struct device *device,
117			   struct device_attribute *attr, char *buf)
118{
119	struct ocrdma_dev *dev =
120		rdma_device_to_drv_device(device, struct ocrdma_dev, ibdev);
121
122	return scnprintf(buf, PAGE_SIZE, "0x%x\n", dev->nic_info.pdev->vendor);
123}
124static DEVICE_ATTR_RO(hw_rev);
125
126static ssize_t hca_type_show(struct device *device,
127			     struct device_attribute *attr, char *buf)
128{
129	struct ocrdma_dev *dev =
130		rdma_device_to_drv_device(device, struct ocrdma_dev, ibdev);
131
132	return scnprintf(buf, PAGE_SIZE, "%s\n", &dev->model_number[0]);
133}
134static DEVICE_ATTR_RO(hca_type);
135
136static struct attribute *ocrdma_attributes[] = {
137	&dev_attr_hw_rev.attr,
138	&dev_attr_hca_type.attr,
139	NULL
140};
141
142static const struct attribute_group ocrdma_attr_group = {
143	.attrs = ocrdma_attributes,
144};
145
146static const struct ib_device_ops ocrdma_dev_ops = {
147	.owner = THIS_MODULE,
148	.driver_id = RDMA_DRIVER_OCRDMA,
149	.uverbs_abi_ver = OCRDMA_ABI_VERSION,
150
151	.alloc_mr = ocrdma_alloc_mr,
152	.alloc_pd = ocrdma_alloc_pd,
153	.alloc_ucontext = ocrdma_alloc_ucontext,
154	.create_ah = ocrdma_create_ah,
155	.create_cq = ocrdma_create_cq,
156	.create_qp = ocrdma_create_qp,
157	.dealloc_pd = ocrdma_dealloc_pd,
158	.dealloc_ucontext = ocrdma_dealloc_ucontext,
159	.dereg_mr = ocrdma_dereg_mr,
160	.destroy_ah = ocrdma_destroy_ah,
161	.destroy_cq = ocrdma_destroy_cq,
162	.destroy_qp = ocrdma_destroy_qp,
163	.get_dev_fw_str = get_dev_fw_str,
164	.get_dma_mr = ocrdma_get_dma_mr,
165	.get_link_layer = ocrdma_link_layer,
166	.get_port_immutable = ocrdma_port_immutable,
167	.map_mr_sg = ocrdma_map_mr_sg,
168	.mmap = ocrdma_mmap,
169	.modify_qp = ocrdma_modify_qp,
170	.poll_cq = ocrdma_poll_cq,
171	.post_recv = ocrdma_post_recv,
172	.post_send = ocrdma_post_send,
173	.process_mad = ocrdma_process_mad,
174	.query_ah = ocrdma_query_ah,
175	.query_device = ocrdma_query_device,
176	.query_pkey = ocrdma_query_pkey,
177	.query_port = ocrdma_query_port,
178	.query_qp = ocrdma_query_qp,
179	.reg_user_mr = ocrdma_reg_user_mr,
180	.req_notify_cq = ocrdma_arm_cq,
181	.resize_cq = ocrdma_resize_cq,
182
183	INIT_RDMA_OBJ_SIZE(ib_ah, ocrdma_ah, ibah),
184	INIT_RDMA_OBJ_SIZE(ib_cq, ocrdma_cq, ibcq),
185	INIT_RDMA_OBJ_SIZE(ib_pd, ocrdma_pd, ibpd),
186	INIT_RDMA_OBJ_SIZE(ib_ucontext, ocrdma_ucontext, ibucontext),
187};
188
189static const struct ib_device_ops ocrdma_dev_srq_ops = {
190	.create_srq = ocrdma_create_srq,
191	.destroy_srq = ocrdma_destroy_srq,
192	.modify_srq = ocrdma_modify_srq,
193	.post_srq_recv = ocrdma_post_srq_recv,
194	.query_srq = ocrdma_query_srq,
195
196	INIT_RDMA_OBJ_SIZE(ib_srq, ocrdma_srq, ibsrq),
197};
198
199static int ocrdma_register_device(struct ocrdma_dev *dev)
200{
201	int ret;
202
203	ocrdma_get_guid(dev, (u8 *)&dev->ibdev.node_guid);
204	BUILD_BUG_ON(sizeof(OCRDMA_NODE_DESC) > IB_DEVICE_NODE_DESC_MAX);
205	memcpy(dev->ibdev.node_desc, OCRDMA_NODE_DESC,
206	       sizeof(OCRDMA_NODE_DESC));
207	dev->ibdev.uverbs_cmd_mask =
208	    OCRDMA_UVERBS(GET_CONTEXT) |
209	    OCRDMA_UVERBS(QUERY_DEVICE) |
210	    OCRDMA_UVERBS(QUERY_PORT) |
211	    OCRDMA_UVERBS(ALLOC_PD) |
212	    OCRDMA_UVERBS(DEALLOC_PD) |
213	    OCRDMA_UVERBS(REG_MR) |
214	    OCRDMA_UVERBS(DEREG_MR) |
215	    OCRDMA_UVERBS(CREATE_COMP_CHANNEL) |
216	    OCRDMA_UVERBS(CREATE_CQ) |
217	    OCRDMA_UVERBS(RESIZE_CQ) |
218	    OCRDMA_UVERBS(DESTROY_CQ) |
219	    OCRDMA_UVERBS(REQ_NOTIFY_CQ) |
220	    OCRDMA_UVERBS(CREATE_QP) |
221	    OCRDMA_UVERBS(MODIFY_QP) |
222	    OCRDMA_UVERBS(QUERY_QP) |
223	    OCRDMA_UVERBS(DESTROY_QP) |
224	    OCRDMA_UVERBS(POLL_CQ) |
225	    OCRDMA_UVERBS(POST_SEND) |
226	    OCRDMA_UVERBS(POST_RECV);
227
228	dev->ibdev.uverbs_cmd_mask |=
229	    OCRDMA_UVERBS(CREATE_AH) |
230	     OCRDMA_UVERBS(MODIFY_AH) |
231	     OCRDMA_UVERBS(QUERY_AH) |
232	     OCRDMA_UVERBS(DESTROY_AH);
233
234	dev->ibdev.node_type = RDMA_NODE_IB_CA;
235	dev->ibdev.phys_port_cnt = 1;
236	dev->ibdev.num_comp_vectors = dev->eq_cnt;
237
238	/* mandatory to support user space verbs consumer. */
239	dev->ibdev.dev.parent = &dev->nic_info.pdev->dev;
240
241	ib_set_device_ops(&dev->ibdev, &ocrdma_dev_ops);
242
243	if (ocrdma_get_asic_type(dev) == OCRDMA_ASIC_GEN_SKH_R) {
244		dev->ibdev.uverbs_cmd_mask |=
245		     OCRDMA_UVERBS(CREATE_SRQ) |
246		     OCRDMA_UVERBS(MODIFY_SRQ) |
247		     OCRDMA_UVERBS(QUERY_SRQ) |
248		     OCRDMA_UVERBS(DESTROY_SRQ) |
249		     OCRDMA_UVERBS(POST_SRQ_RECV);
250
251		ib_set_device_ops(&dev->ibdev, &ocrdma_dev_srq_ops);
252	}
253	rdma_set_device_sysfs_group(&dev->ibdev, &ocrdma_attr_group);
254	ret = ib_device_set_netdev(&dev->ibdev, dev->nic_info.netdev, 1);
255	if (ret)
256		return ret;
257
258	dma_set_max_seg_size(&dev->nic_info.pdev->dev, UINT_MAX);
259	return ib_register_device(&dev->ibdev, "ocrdma%d",
260				  &dev->nic_info.pdev->dev);
261}
262
263static int ocrdma_alloc_resources(struct ocrdma_dev *dev)
264{
265	mutex_init(&dev->dev_lock);
266	dev->cq_tbl = kcalloc(OCRDMA_MAX_CQ, sizeof(struct ocrdma_cq *),
267			      GFP_KERNEL);
268	if (!dev->cq_tbl)
269		goto alloc_err;
270
271	if (dev->attr.max_qp) {
272		dev->qp_tbl = kcalloc(OCRDMA_MAX_QP,
273				      sizeof(struct ocrdma_qp *),
274				      GFP_KERNEL);
275		if (!dev->qp_tbl)
276			goto alloc_err;
277	}
278
279	dev->stag_arr = kcalloc(OCRDMA_MAX_STAG, sizeof(u64), GFP_KERNEL);
280	if (dev->stag_arr == NULL)
281		goto alloc_err;
282
283	ocrdma_alloc_pd_pool(dev);
284
285	if (!ocrdma_alloc_stats_resources(dev)) {
286		pr_err("%s: stats resource allocation failed\n", __func__);
287		goto alloc_err;
288	}
289
290	spin_lock_init(&dev->av_tbl.lock);
291	spin_lock_init(&dev->flush_q_lock);
292	return 0;
293alloc_err:
294	pr_err("%s(%d) error.\n", __func__, dev->id);
295	return -ENOMEM;
296}
297
298static void ocrdma_free_resources(struct ocrdma_dev *dev)
299{
300	ocrdma_release_stats_resources(dev);
301	kfree(dev->stag_arr);
302	kfree(dev->qp_tbl);
303	kfree(dev->cq_tbl);
304}
305
306static struct ocrdma_dev *ocrdma_add(struct be_dev_info *dev_info)
307{
308	int status = 0;
309	u8 lstate = 0;
310	struct ocrdma_dev *dev;
311
312	dev = ib_alloc_device(ocrdma_dev, ibdev);
313	if (!dev) {
314		pr_err("Unable to allocate ib device\n");
315		return NULL;
316	}
317
318	dev->mbx_cmd = kzalloc(sizeof(struct ocrdma_mqe_emb_cmd), GFP_KERNEL);
319	if (!dev->mbx_cmd)
320		goto init_err;
321
322	memcpy(&dev->nic_info, dev_info, sizeof(*dev_info));
323	dev->id = PCI_FUNC(dev->nic_info.pdev->devfn);
324	status = ocrdma_init_hw(dev);
325	if (status)
326		goto init_err;
327
328	status = ocrdma_alloc_resources(dev);
329	if (status)
330		goto alloc_err;
331
332	ocrdma_init_service_level(dev);
333	status = ocrdma_register_device(dev);
334	if (status)
335		goto alloc_err;
336
337	/* Query Link state and update */
338	status = ocrdma_mbx_get_link_speed(dev, NULL, &lstate);
339	if (!status)
340		ocrdma_update_link_state(dev, lstate);
341
342	/* Init stats */
343	ocrdma_add_port_stats(dev);
344	/* Interrupt Moderation */
345	INIT_DELAYED_WORK(&dev->eqd_work, ocrdma_eqd_set_task);
346	schedule_delayed_work(&dev->eqd_work, msecs_to_jiffies(1000));
347
348	pr_info("%s %s: %s \"%s\" port %d\n",
349		dev_name(&dev->nic_info.pdev->dev), hca_name(dev),
350		port_speed_string(dev), dev->model_number,
351		dev->hba_port_num);
352	pr_info("%s ocrdma%d driver loaded successfully\n",
353		dev_name(&dev->nic_info.pdev->dev), dev->id);
354	return dev;
355
356alloc_err:
357	ocrdma_free_resources(dev);
358	ocrdma_cleanup_hw(dev);
359init_err:
360	kfree(dev->mbx_cmd);
361	ib_dealloc_device(&dev->ibdev);
362	pr_err("%s() leaving. ret=%d\n", __func__, status);
363	return NULL;
364}
365
366static void ocrdma_remove_free(struct ocrdma_dev *dev)
367{
368
369	kfree(dev->mbx_cmd);
370	ib_dealloc_device(&dev->ibdev);
371}
372
373static void ocrdma_remove(struct ocrdma_dev *dev)
374{
375	/* first unregister with stack to stop all the active traffic
376	 * of the registered clients.
377	 */
378	cancel_delayed_work_sync(&dev->eqd_work);
379	ib_unregister_device(&dev->ibdev);
380
381	ocrdma_rem_port_stats(dev);
382	ocrdma_free_resources(dev);
383	ocrdma_cleanup_hw(dev);
384	ocrdma_remove_free(dev);
385}
386
387static int ocrdma_dispatch_port_active(struct ocrdma_dev *dev)
388{
389	struct ib_event port_event;
390
391	port_event.event = IB_EVENT_PORT_ACTIVE;
392	port_event.element.port_num = 1;
393	port_event.device = &dev->ibdev;
394	ib_dispatch_event(&port_event);
395	return 0;
396}
397
398static int ocrdma_dispatch_port_error(struct ocrdma_dev *dev)
399{
400	struct ib_event err_event;
401
402	err_event.event = IB_EVENT_PORT_ERR;
403	err_event.element.port_num = 1;
404	err_event.device = &dev->ibdev;
405	ib_dispatch_event(&err_event);
406	return 0;
407}
408
409static void ocrdma_shutdown(struct ocrdma_dev *dev)
410{
411	ocrdma_dispatch_port_error(dev);
412	ocrdma_remove(dev);
413}
414
415/* event handling via NIC driver ensures that all the NIC specific
416 * initialization done before RoCE driver notifies
417 * event to stack.
418 */
419static void ocrdma_event_handler(struct ocrdma_dev *dev, u32 event)
420{
421	switch (event) {
422	case BE_DEV_SHUTDOWN:
423		ocrdma_shutdown(dev);
424		break;
425	default:
426		break;
427	}
428}
429
430void ocrdma_update_link_state(struct ocrdma_dev *dev, u8 lstate)
431{
432	if (!(dev->flags & OCRDMA_FLAGS_LINK_STATUS_INIT)) {
433		dev->flags |= OCRDMA_FLAGS_LINK_STATUS_INIT;
434		if (!lstate)
435			return;
436	}
437
438	if (!lstate)
439		ocrdma_dispatch_port_error(dev);
440	else
441		ocrdma_dispatch_port_active(dev);
442}
443
444static struct ocrdma_driver ocrdma_drv = {
445	.name			= "ocrdma_driver",
446	.add			= ocrdma_add,
447	.remove			= ocrdma_remove,
448	.state_change_handler	= ocrdma_event_handler,
449	.be_abi_version		= OCRDMA_BE_ROCE_ABI_VERSION,
450};
451
452static int __init ocrdma_init_module(void)
453{
454	int status;
455
456	ocrdma_init_debugfs();
457
458	status = be_roce_register_driver(&ocrdma_drv);
459	if (status)
460		goto err_be_reg;
461
462	return 0;
463
464err_be_reg:
465
466	return status;
467}
468
469static void __exit ocrdma_exit_module(void)
470{
471	be_roce_unregister_driver(&ocrdma_drv);
472	ocrdma_rem_debugfs();
473}
474
475module_init(ocrdma_init_module);
476module_exit(ocrdma_exit_module);
477