1/*
2 * Copyright (c) 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/workqueue.h>
35#include <linux/module.h>
36
37#include "mlx4.h"
38
39enum {
40	MLX4_CATAS_POLL_INTERVAL	= 5 * HZ,
41};
42
43
44
45int mlx4_internal_err_reset = 1;
46module_param_named(internal_err_reset, mlx4_internal_err_reset,  int, 0644);
47MODULE_PARM_DESC(internal_err_reset,
48		 "Reset device on internal errors if non-zero (default 1)");
49
50static int read_vendor_id(struct mlx4_dev *dev)
51{
52	u16 vendor_id = 0;
53	int ret;
54
55	ret = pci_read_config_word(dev->persist->pdev, 0, &vendor_id);
56	if (ret) {
57		mlx4_err(dev, "Failed to read vendor ID, ret=%d\n", ret);
58		return ret;
59	}
60
61	if (vendor_id == 0xffff) {
62		mlx4_err(dev, "PCI can't be accessed to read vendor id\n");
63		return -EINVAL;
64	}
65
66	return 0;
67}
68
69static int mlx4_reset_master(struct mlx4_dev *dev)
70{
71	int err = 0;
72
73	if (mlx4_is_master(dev))
74		mlx4_report_internal_err_comm_event(dev);
75
76	if (!pci_channel_offline(dev->persist->pdev)) {
77		err = read_vendor_id(dev);
78		/* If PCI can't be accessed to read vendor ID we assume that its
79		 * link was disabled and chip was already reset.
80		 */
81		if (err)
82			return 0;
83
84		err = mlx4_reset(dev);
85		if (err)
86			mlx4_err(dev, "Fail to reset HCA\n");
87	}
88
89	return err;
90}
91
92static int mlx4_reset_slave(struct mlx4_dev *dev)
93{
94#define COM_CHAN_RST_REQ_OFFSET 0x10
95#define COM_CHAN_RST_ACK_OFFSET 0x08
96
97	u32 comm_flags;
98	u32 rst_req;
99	u32 rst_ack;
100	unsigned long end;
101	struct mlx4_priv *priv = mlx4_priv(dev);
102
103	if (pci_channel_offline(dev->persist->pdev))
104		return 0;
105
106	comm_flags = swab32(readl((__iomem char *)priv->mfunc.comm +
107				  MLX4_COMM_CHAN_FLAGS));
108	if (comm_flags == 0xffffffff) {
109		mlx4_err(dev, "VF reset is not needed\n");
110		return 0;
111	}
112
113	if (!(dev->caps.vf_caps & MLX4_VF_CAP_FLAG_RESET)) {
114		mlx4_err(dev, "VF reset is not supported\n");
115		return -EOPNOTSUPP;
116	}
117
118	rst_req = (comm_flags & (u32)(1 << COM_CHAN_RST_REQ_OFFSET)) >>
119		COM_CHAN_RST_REQ_OFFSET;
120	rst_ack = (comm_flags & (u32)(1 << COM_CHAN_RST_ACK_OFFSET)) >>
121		COM_CHAN_RST_ACK_OFFSET;
122	if (rst_req != rst_ack) {
123		mlx4_err(dev, "Communication channel isn't sync, fail to send reset\n");
124		return -EIO;
125	}
126
127	rst_req ^= 1;
128	mlx4_warn(dev, "VF is sending reset request to Firmware\n");
129	comm_flags = rst_req << COM_CHAN_RST_REQ_OFFSET;
130	__raw_writel((__force u32)cpu_to_be32(comm_flags),
131		     (__iomem char *)priv->mfunc.comm + MLX4_COMM_CHAN_FLAGS);
132
133	end = msecs_to_jiffies(MLX4_COMM_TIME) + jiffies;
134	while (time_before(jiffies, end)) {
135		comm_flags = swab32(readl((__iomem char *)priv->mfunc.comm +
136					  MLX4_COMM_CHAN_FLAGS));
137		rst_ack = (comm_flags & (u32)(1 << COM_CHAN_RST_ACK_OFFSET)) >>
138			COM_CHAN_RST_ACK_OFFSET;
139
140		/* Reading rst_req again since the communication channel can
141		 * be reset at any time by the PF and all its bits will be
142		 * set to zero.
143		 */
144		rst_req = (comm_flags & (u32)(1 << COM_CHAN_RST_REQ_OFFSET)) >>
145			COM_CHAN_RST_REQ_OFFSET;
146
147		if (rst_ack == rst_req) {
148			mlx4_warn(dev, "VF Reset succeed\n");
149			return 0;
150		}
151		cond_resched();
152	}
153	mlx4_err(dev, "Fail to send reset over the communication channel\n");
154	return -ETIMEDOUT;
155}
156
157int mlx4_comm_internal_err(u32 slave_read)
158{
159	return (u32)COMM_CHAN_EVENT_INTERNAL_ERR ==
160		(slave_read & (u32)COMM_CHAN_EVENT_INTERNAL_ERR) ? 1 : 0;
161}
162
163void mlx4_enter_error_state(struct mlx4_dev_persistent *persist)
164{
165	int err;
166	struct mlx4_dev *dev;
167
168	if (!mlx4_internal_err_reset)
169		return;
170
171	mutex_lock(&persist->device_state_mutex);
172	if (persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR)
173		goto out;
174
175	dev = persist->dev;
176	mlx4_err(dev, "device is going to be reset\n");
177	if (mlx4_is_slave(dev)) {
178		err = mlx4_reset_slave(dev);
179	} else {
180		mlx4_crdump_collect(dev);
181		err = mlx4_reset_master(dev);
182	}
183
184	if (!err) {
185		mlx4_err(dev, "device was reset successfully\n");
186	} else {
187		/* EEH could have disabled the PCI channel during reset. That's
188		 * recoverable and the PCI error flow will handle it.
189		 */
190		if (!pci_channel_offline(dev->persist->pdev))
191			BUG_ON(1);
192	}
193	dev->persist->state |= MLX4_DEVICE_STATE_INTERNAL_ERROR;
194	mutex_unlock(&persist->device_state_mutex);
195
196	/* At that step HW was already reset, now notify clients */
197	mlx4_dispatch_event(dev, MLX4_DEV_EVENT_CATASTROPHIC_ERROR, 0);
198	mlx4_cmd_wake_completions(dev);
199	return;
200
201out:
202	mutex_unlock(&persist->device_state_mutex);
203}
204
205static void mlx4_handle_error_state(struct mlx4_dev_persistent *persist)
206{
207	int err = 0;
208
209	mlx4_enter_error_state(persist);
210	mutex_lock(&persist->interface_state_mutex);
211	if (persist->interface_state & MLX4_INTERFACE_STATE_UP &&
212	    !(persist->interface_state & MLX4_INTERFACE_STATE_DELETION)) {
213		err = mlx4_restart_one(persist->pdev);
214		mlx4_info(persist->dev, "mlx4_restart_one was ended, ret=%d\n",
215			  err);
216	}
217	mutex_unlock(&persist->interface_state_mutex);
218}
219
220static void dump_err_buf(struct mlx4_dev *dev)
221{
222	struct mlx4_priv *priv = mlx4_priv(dev);
223
224	int i;
225
226	mlx4_err(dev, "Internal error detected:\n");
227	for (i = 0; i < priv->fw.catas_size; ++i)
228		mlx4_err(dev, "  buf[%02x]: %08x\n",
229			 i, swab32(readl(priv->catas_err.map + i)));
230}
231
232static void poll_catas(struct timer_list *t)
233{
234	struct mlx4_priv *priv = from_timer(priv, t, catas_err.timer);
235	struct mlx4_dev *dev = &priv->dev;
236	u32 slave_read;
237
238	if (mlx4_is_slave(dev)) {
239		slave_read = swab32(readl(&priv->mfunc.comm->slave_read));
240		if (mlx4_comm_internal_err(slave_read)) {
241			mlx4_warn(dev, "Internal error detected on the communication channel\n");
242			goto internal_err;
243		}
244	} else if (readl(priv->catas_err.map)) {
245		dump_err_buf(dev);
246		goto internal_err;
247	}
248
249	if (dev->persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR) {
250		mlx4_warn(dev, "Internal error mark was detected on device\n");
251		goto internal_err;
252	}
253
254	mod_timer(&priv->catas_err.timer,
255		  round_jiffies(jiffies + MLX4_CATAS_POLL_INTERVAL));
256	return;
257
258internal_err:
259	if (mlx4_internal_err_reset)
260		queue_work(dev->persist->catas_wq, &dev->persist->catas_work);
261}
262
263static void catas_reset(struct work_struct *work)
264{
265	struct mlx4_dev_persistent *persist =
266		container_of(work, struct mlx4_dev_persistent,
267			     catas_work);
268
269	mlx4_handle_error_state(persist);
270}
271
272void mlx4_start_catas_poll(struct mlx4_dev *dev)
273{
274	struct mlx4_priv *priv = mlx4_priv(dev);
275	phys_addr_t addr;
276
277	INIT_LIST_HEAD(&priv->catas_err.list);
278	timer_setup(&priv->catas_err.timer, poll_catas, 0);
279	priv->catas_err.map = NULL;
280
281	if (!mlx4_is_slave(dev)) {
282		addr = pci_resource_start(dev->persist->pdev,
283					  priv->fw.catas_bar) +
284					  priv->fw.catas_offset;
285
286		priv->catas_err.map = ioremap(addr, priv->fw.catas_size * 4);
287		if (!priv->catas_err.map) {
288			mlx4_warn(dev, "Failed to map internal error buffer at 0x%llx\n",
289				  (unsigned long long)addr);
290			return;
291		}
292	}
293
294	priv->catas_err.timer.expires  =
295		round_jiffies(jiffies + MLX4_CATAS_POLL_INTERVAL);
296	add_timer(&priv->catas_err.timer);
297}
298
299void mlx4_stop_catas_poll(struct mlx4_dev *dev)
300{
301	struct mlx4_priv *priv = mlx4_priv(dev);
302
303	del_timer_sync(&priv->catas_err.timer);
304
305	if (priv->catas_err.map) {
306		iounmap(priv->catas_err.map);
307		priv->catas_err.map = NULL;
308	}
309
310	if (dev->persist->interface_state & MLX4_INTERFACE_STATE_DELETION)
311		flush_workqueue(dev->persist->catas_wq);
312}
313
314int  mlx4_catas_init(struct mlx4_dev *dev)
315{
316	INIT_WORK(&dev->persist->catas_work, catas_reset);
317	dev->persist->catas_wq = create_singlethread_workqueue("mlx4_health");
318	if (!dev->persist->catas_wq)
319		return -ENOMEM;
320
321	return 0;
322}
323
324void mlx4_catas_end(struct mlx4_dev *dev)
325{
326	if (dev->persist->catas_wq) {
327		destroy_workqueue(dev->persist->catas_wq);
328		dev->persist->catas_wq = NULL;
329	}
330}
331