summaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw/hfi1/fault.c
blob: 93613e5def9b7bd4492e65494abd4d420fc5a6c1 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
/*
 * Copyright(c) 2018 Intel Corporation.
 *
 * This file is provided under a dual BSD/GPLv2 license.  When using or
 * redistributing this file, you may do so under either license.
 *
 * GPL LICENSE SUMMARY
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of version 2 of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * BSD LICENSE
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 *  - Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *  - Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *  - Neither the name of Intel Corporation nor the names of its
 *    contributors may be used to endorse or promote products derived
 *    from this software without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 */
#include <linux/debugfs.h>
#include <linux/seq_file.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/bitmap.h>

#include "debugfs.h"
#include "fault.h"
#include "trace.h"

#define HFI1_FAULT_DIR_TX   BIT(0)
#define HFI1_FAULT_DIR_RX   BIT(1)
#define HFI1_FAULT_DIR_TXRX (HFI1_FAULT_DIR_TX | HFI1_FAULT_DIR_RX)

static void *_fault_stats_seq_start(struct seq_file *s, loff_t *pos)
{
	struct hfi1_opcode_stats_perctx *opstats;

	if (*pos >= ARRAY_SIZE(opstats->stats))
		return NULL;
	return pos;
}

static void *_fault_stats_seq_next(struct seq_file *s, void *v, loff_t *pos)
{
	struct hfi1_opcode_stats_perctx *opstats;

	++*pos;
	if (*pos >= ARRAY_SIZE(opstats->stats))
		return NULL;
	return pos;
}

static void _fault_stats_seq_stop(struct seq_file *s, void *v)
{
}

static int _fault_stats_seq_show(struct seq_file *s, void *v)
{
	loff_t *spos = v;
	loff_t i = *spos, j;
	u64 n_packets = 0, n_bytes = 0;
	struct hfi1_ibdev *ibd = (struct hfi1_ibdev *)s->private;
	struct hfi1_devdata *dd = dd_from_dev(ibd);
	struct hfi1_ctxtdata *rcd;

	for (j = 0; j < dd->first_dyn_alloc_ctxt; j++) {
		rcd = hfi1_rcd_get_by_index(dd, j);
		if (rcd) {
			n_packets += rcd->opstats->stats[i].n_packets;
			n_bytes += rcd->opstats->stats[i].n_bytes;
		}
		hfi1_rcd_put(rcd);
	}
	for_each_possible_cpu(j) {
		struct hfi1_opcode_stats_perctx *sp =
			per_cpu_ptr(dd->tx_opstats, j);

		n_packets += sp->stats[i].n_packets;
		n_bytes += sp->stats[i].n_bytes;
	}
	if (!n_packets && !n_bytes)
		return SEQ_SKIP;
	if (!ibd->fault->n_rxfaults[i] && !ibd->fault->n_txfaults[i])
		return SEQ_SKIP;
	seq_printf(s, "%02llx %llu/%llu (faults rx:%llu faults: tx:%llu)\n", i,
		   (unsigned long long)n_packets,
		   (unsigned long long)n_bytes,
		   (unsigned long long)ibd->fault->n_rxfaults[i],
		   (unsigned long long)ibd->fault->n_txfaults[i]);
	return 0;
}

DEBUGFS_SEQ_FILE_OPS(fault_stats);
DEBUGFS_SEQ_FILE_OPEN(fault_stats);
DEBUGFS_FILE_OPS(fault_stats);

static int fault_opcodes_open(struct inode *inode, struct file *file)
{
	file->private_data = inode->i_private;
	return nonseekable_open(inode, file);
}

static ssize_t fault_opcodes_write(struct file *file, const char __user *buf,
				   size_t len, loff_t *pos)
{
	ssize_t ret = 0;
	/* 1280 = 256 opcodes * 4 chars/opcode + 255 commas + NULL */
	size_t copy, datalen = 1280;
	char *data, *token, *ptr, *end;
	struct fault *fault = file->private_data;

	data = kcalloc(datalen, sizeof(*data), GFP_KERNEL);
	if (!data)
		return -ENOMEM;
	copy = min(len, datalen - 1);
	if (copy_from_user(data, buf, copy))
		return -EFAULT;

	ret = debugfs_file_get(file->f_path.dentry);
	if (unlikely(ret))
		return ret;
	ptr = data;
	token = ptr;
	for (ptr = data; *ptr; ptr = end + 1, token = ptr) {
		char *dash;
		unsigned long range_start, range_end, i;
		bool remove = false;
		unsigned long bound = 1U << BITS_PER_BYTE;

		end = strchr(ptr, ',');
		if (end)
			*end = '\0';
		if (token[0] == '-') {
			remove = true;
			token++;
		}
		dash = strchr(token, '-');
		if (dash)
			*dash = '\0';
		if (kstrtoul(token, 0, &range_start))
			break;
		if (dash) {
			token = dash + 1;
			if (kstrtoul(token, 0, &range_end))
				break;
		} else {
			range_end = range_start;
		}
		if (range_start == range_end && range_start == -1UL) {
			bitmap_zero(fault->opcodes, sizeof(fault->opcodes) *
				    BITS_PER_BYTE);
			break;
		}
		/* Check the inputs */
		if (range_start >= bound || range_end >= bound)
			break;

		for (i = range_start; i <= range_end; i++) {
			if (remove)
				clear_bit(i, fault->opcodes);
			else
				set_bit(i, fault->opcodes);
		}
		if (!end)
			break;
	}
	ret = len;

	debugfs_file_put(file->f_path.dentry);
	kfree(data);
	return ret;
}

static ssize_t fault_opcodes_read(struct file *file, char __user *buf,
				  size_t len, loff_t *pos)
{
	ssize_t ret = 0;
	char *data;
	size_t datalen = 1280, size = 0; /* see fault_opcodes_write() */
	unsigned long bit = 0, zero = 0;
	struct fault *fault = file->private_data;
	size_t bitsize = sizeof(fault->opcodes) * BITS_PER_BYTE;

	data = kcalloc(datalen, sizeof(*data), GFP_KERNEL);
	if (!data)
		return -ENOMEM;
	ret = debugfs_file_get(file->f_path.dentry);
	if (unlikely(ret))
		return ret;
	bit = find_first_bit(fault->opcodes, bitsize);
	while (bit < bitsize) {
		zero = find_next_zero_bit(fault->opcodes, bitsize, bit);
		if (zero - 1 != bit)
			size += snprintf(data + size,
					 datalen - size - 1,
					 "0x%lx-0x%lx,", bit, zero - 1);
		else
			size += snprintf(data + size,
					 datalen - size - 1, "0x%lx,",
					 bit);
		bit = find_next_bit(fault->opcodes, bitsize, zero);
	}
	debugfs_file_put(file->f_path.dentry);
	data[size - 1] = '\n';
	data[size] = '\0';
	ret = simple_read_from_buffer(buf, len, pos, data, size);
	kfree(data);
	return ret;
}

static const struct file_operations __fault_opcodes_fops = {
	.owner = THIS_MODULE,
	.open = fault_opcodes_open,
	.read = fault_opcodes_read,
	.write = fault_opcodes_write,
	.llseek = no_llseek
};

void hfi1_fault_exit_debugfs(struct hfi1_ibdev *ibd)
{
	if (ibd->fault)
		debugfs_remove_recursive(ibd->fault->dir);
	kfree(ibd->fault);
	ibd->fault = NULL;
}

int hfi1_fault_init_debugfs(struct hfi1_ibdev *ibd)
{
	struct dentry *parent = ibd->hfi1_ibdev_dbg;
	struct dentry *fault_dir;

	ibd->fault = kzalloc(sizeof(*ibd->fault), GFP_KERNEL);
	if (!ibd->fault)
		return -ENOMEM;

	ibd->fault->attr.interval = 1;
	ibd->fault->attr.require_end = ULONG_MAX;
	ibd->fault->attr.stacktrace_depth = 32;
	ibd->fault->attr.dname = NULL;
	ibd->fault->attr.verbose = 0;
	ibd->fault->enable = false;
	ibd->fault->opcode = false;
	ibd->fault->fault_skip = 0;
	ibd->fault->skip = 0;
	ibd->fault->direction = HFI1_FAULT_DIR_TXRX;
	ibd->fault->suppress_err = false;
	bitmap_zero(ibd->fault->opcodes,
		    sizeof(ibd->fault->opcodes) * BITS_PER_BYTE);

	fault_dir =
		fault_create_debugfs_attr("fault", parent, &ibd->fault->attr);
	if (IS_ERR(fault_dir)) {
		kfree(ibd->fault);
		ibd->fault = NULL;
		return -ENOENT;
	}
	ibd->fault->dir = fault_dir;

	debugfs_create_file("fault_stats", 0444, fault_dir, ibd,
			    &_fault_stats_file_ops);
	debugfs_create_bool("enable", 0600, fault_dir, &ibd->fault->enable);
	debugfs_create_bool("suppress_err", 0600, fault_dir,
			    &ibd->fault->suppress_err);
	debugfs_create_bool("opcode_mode", 0600, fault_dir,
			    &ibd->fault->opcode);
	debugfs_create_file("opcodes", 0600, fault_dir, ibd->fault,
			    &__fault_opcodes_fops);
	debugfs_create_u64("skip_pkts", 0600, fault_dir,
			   &ibd->fault->fault_skip);
	debugfs_create_u64("skip_usec", 0600, fault_dir,
			   &ibd->fault->fault_skip_usec);
	debugfs_create_u8("direction", 0600, fault_dir, &ibd->fault->direction);

	return 0;
}

bool hfi1_dbg_fault_suppress_err(struct hfi1_ibdev *ibd)
{
	if (ibd->fault)
		return ibd->fault->suppress_err;
	return false;
}

static bool __hfi1_should_fault(struct hfi1_ibdev *ibd, u32 opcode,
				u8 direction)
{
	bool ret = false;

	if (!ibd->fault || !ibd->fault->enable)
		return false;
	if (!(ibd->fault->direction & direction))
		return false;
	if (ibd->fault->opcode) {
		if (bitmap_empty(ibd->fault->opcodes,
				 (sizeof(ibd->fault->opcodes) *
				  BITS_PER_BYTE)))
			return false;
		if (!(test_bit(opcode, ibd->fault->opcodes)))
			return false;
	}
	if (ibd->fault->fault_skip_usec &&
	    time_before(jiffies, ibd->fault->skip_usec))
		return false;
	if (ibd->fault->fault_skip && ibd->fault->skip) {
		ibd->fault->skip--;
		return false;
	}
	ret = should_fail(&ibd->fault->attr, 1);
	if (ret) {
		ibd->fault->skip = ibd->fault->fault_skip;
		ibd->fault->skip_usec = jiffies +
			usecs_to_jiffies(ibd->fault->fault_skip_usec);
	}
	return ret;
}

bool hfi1_dbg_should_fault_tx(struct rvt_qp *qp, u32 opcode)
{
	struct hfi1_ibdev *ibd = to_idev(qp->ibqp.device);

	if (__hfi1_should_fault(ibd, opcode, HFI1_FAULT_DIR_TX)) {
		trace_hfi1_fault_opcode(qp, opcode);
		ibd->fault->n_txfaults[opcode]++;
		return true;
	}
	return false;
}

bool hfi1_dbg_should_fault_rx(struct hfi1_packet *packet)
{
	struct hfi1_ibdev *ibd = &packet->rcd->dd->verbs_dev;

	if (__hfi1_should_fault(ibd, packet->opcode, HFI1_FAULT_DIR_RX)) {
		trace_hfi1_fault_packet(packet);
		ibd->fault->n_rxfaults[packet->opcode]++;
		return true;
	}
	return false;
}