summaryrefslogtreecommitdiffstats
path: root/fs/ocfs2/cluster/netdebug.c
blob: cfb2be708abe33b255ed8f3208f93569a92339e8 (plain) (blame)
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
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
/* -*- mode: c; c-basic-offset: 8; -*-
 * vim: noexpandtab sw=8 ts=8 sts=0:
 *
 * netdebug.c
 *
 * debug functionality for o2net
 *
 * Copyright (C) 2005, 2008 Oracle.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * 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.
 *
 * You should have received a copy of the GNU General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 *
 */

#ifdef CONFIG_DEBUG_FS

#include <linux/module.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/idr.h>
#include <linux/kref.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>

#include <linux/uaccess.h>

#include "tcp.h"
#include "nodemanager.h"
#define MLOG_MASK_PREFIX ML_TCP
#include "masklog.h"

#include "tcp_internal.h"

#define O2NET_DEBUG_DIR		"o2net"
#define SC_DEBUG_NAME		"sock_containers"
#define NST_DEBUG_NAME		"send_tracking"

static struct dentry *o2net_dentry;
static struct dentry *sc_dentry;
static struct dentry *nst_dentry;

static DEFINE_SPINLOCK(o2net_debug_lock);

static LIST_HEAD(sock_containers);
static LIST_HEAD(send_tracking);

void o2net_debug_add_nst(struct o2net_send_tracking *nst)
{
	spin_lock(&o2net_debug_lock);
	list_add(&nst->st_net_debug_item, &send_tracking);
	spin_unlock(&o2net_debug_lock);
}

void o2net_debug_del_nst(struct o2net_send_tracking *nst)
{
	spin_lock(&o2net_debug_lock);
	if (!list_empty(&nst->st_net_debug_item))
		list_del_init(&nst->st_net_debug_item);
	spin_unlock(&o2net_debug_lock);
}

static struct o2net_send_tracking
			*next_nst(struct o2net_send_tracking *nst_start)
{
	struct o2net_send_tracking *nst, *ret = NULL;

	assert_spin_locked(&o2net_debug_lock);

	list_for_each_entry(nst, &nst_start->st_net_debug_item,
			    st_net_debug_item) {
		/* discover the head of the list */
		if (&nst->st_net_debug_item == &send_tracking)
			break;

		/* use st_task to detect real nsts in the list */
		if (nst->st_task != NULL) {
			ret = nst;
			break;
		}
	}

	return ret;
}

static void *nst_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct o2net_send_tracking *nst, *dummy_nst = seq->private;

	spin_lock(&o2net_debug_lock);
	nst = next_nst(dummy_nst);
	spin_unlock(&o2net_debug_lock);

	return nst;
}

static void *nst_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct o2net_send_tracking *nst, *dummy_nst = seq->private;

	spin_lock(&o2net_debug_lock);
	nst = next_nst(dummy_nst);
	list_del_init(&dummy_nst->st_net_debug_item);
	if (nst)
		list_add(&dummy_nst->st_net_debug_item,
			 &nst->st_net_debug_item);
	spin_unlock(&o2net_debug_lock);

	return nst; /* unused, just needs to be null when done */
}

static int nst_seq_show(struct seq_file *seq, void *v)
{
	struct o2net_send_tracking *nst, *dummy_nst = seq->private;

	spin_lock(&o2net_debug_lock);
	nst = next_nst(dummy_nst);

	if (nst != NULL) {
		/* get_task_comm isn't exported.  oh well. */
		seq_printf(seq, "%p:\n"
			   "  pid:          %lu\n"
			   "  tgid:         %lu\n"
			   "  process name: %s\n"
			   "  node:         %u\n"
			   "  sc:           %p\n"
			   "  message id:   %d\n"
			   "  message type: %u\n"
			   "  message key:  0x%08x\n"
			   "  sock acquiry: %lu.%ld\n"
			   "  send start:   %lu.%ld\n"
			   "  wait start:   %lu.%ld\n",
			   nst, (unsigned long)nst->st_task->pid,
			   (unsigned long)nst->st_task->tgid,
			   nst->st_task->comm, nst->st_node,
			   nst->st_sc, nst->st_id, nst->st_msg_type,
			   nst->st_msg_key,
			   nst->st_sock_time.tv_sec,
			   (long)nst->st_sock_time.tv_usec,
			   nst->st_send_time.tv_sec,
			   (long)nst->st_send_time.tv_usec,
			   nst->st_status_time.tv_sec,
			   (long)nst->st_status_time.tv_usec);
	}

	spin_unlock(&o2net_debug_lock);

	return 0;
}

static void nst_seq_stop(struct seq_file *seq, void *v)
{
}

static const struct seq_operations nst_seq_ops = {
	.start = nst_seq_start,
	.next = nst_seq_next,
	.stop = nst_seq_stop,
	.show = nst_seq_show,
};

static int nst_fop_open(struct inode *inode, struct file *file)
{
	struct o2net_send_tracking *dummy_nst;
	struct seq_file *seq;
	int ret;

	dummy_nst = kmalloc(sizeof(struct o2net_send_tracking), GFP_KERNEL);
	if (dummy_nst == NULL) {
		ret = -ENOMEM;
		goto out;
	}
	dummy_nst->st_task = NULL;

	ret = seq_open(file, &nst_seq_ops);
	if (ret)
		goto out;

	seq = file->private_data;
	seq->private = dummy_nst;
	o2net_debug_add_nst(dummy_nst);

	dummy_nst = NULL;

out:
	kfree(dummy_nst);
	return ret;
}

static int nst_fop_release(struct inode *inode, struct file *file)
{
	struct seq_file *seq = file->private_data;
	struct o2net_send_tracking *dummy_nst = seq->private;

	o2net_debug_del_nst(dummy_nst);
	return seq_release_private(inode, file);
}

static struct file_operations nst_seq_fops = {
	.open = nst_fop_open,
	.read = seq_read,
	.llseek = seq_lseek,
	.release = nst_fop_release,
};

void o2net_debug_add_sc(struct o2net_sock_container *sc)
{
	spin_lock(&o2net_debug_lock);
	list_add(&sc->sc_net_debug_item, &sock_containers);
	spin_unlock(&o2net_debug_lock);
}

void o2net_debug_del_sc(struct o2net_sock_container *sc)
{
	spin_lock(&o2net_debug_lock);
	list_del_init(&sc->sc_net_debug_item);
	spin_unlock(&o2net_debug_lock);
}

static struct o2net_sock_container
			*next_sc(struct o2net_sock_container *sc_start)
{
	struct o2net_sock_container *sc, *ret = NULL;

	assert_spin_locked(&o2net_debug_lock);

	list_for_each_entry(sc, &sc_start->sc_net_debug_item,
			    sc_net_debug_item) {
		/* discover the head of the list miscast as a sc */
		if (&sc->sc_net_debug_item == &sock_containers)
			break;

		/* use sc_page to detect real scs in the list */
		if (sc->sc_page != NULL) {
			ret = sc;
			break;
		}
	}

	return ret;
}

static void *sc_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct o2net_sock_container *sc, *dummy_sc = seq->private;

	spin_lock(&o2net_debug_lock);
	sc = next_sc(dummy_sc);
	spin_unlock(&o2net_debug_lock);

	return sc;
}

static void *sc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct o2net_sock_container *sc, *dummy_sc = seq->private;

	spin_lock(&o2net_debug_lock);
	sc = next_sc(dummy_sc);
	list_del_init(&dummy_sc->sc_net_debug_item);
	if (sc)
		list_add(&dummy_sc->sc_net_debug_item, &sc->sc_net_debug_item);
	spin_unlock(&o2net_debug_lock);

	return sc; /* unused, just needs to be null when done */
}

#define TV_SEC_USEC(TV) TV.tv_sec, (long)TV.tv_usec

static int sc_seq_show(struct seq_file *seq, void *v)
{
	struct o2net_sock_container *sc, *dummy_sc = seq->private;

	spin_lock(&o2net_debug_lock);
	sc = next_sc(dummy_sc);

	if (sc != NULL) {
		struct inet_sock *inet = NULL;

		__be32 saddr = 0, daddr = 0;
		__be16 sport = 0, dport = 0;

		if (sc->sc_sock) {
			inet = inet_sk(sc->sc_sock->sk);
			/* the stack's structs aren't sparse endian clean */
			saddr = (__force __be32)inet->saddr;
			daddr = (__force __be32)inet->daddr;
			sport = (__force __be16)inet->sport;
			dport = (__force __be16)inet->dport;
		}

		/* XXX sigh, inet-> doesn't have sparse annotation so any
		 * use of it here generates a warning with -Wbitwise */
		seq_printf(seq, "%p:\n"
			   "  krefs:           %d\n"
			   "  sock:            %pI4:%u -> "
					      "%pI4:%u\n"
			   "  remote node:     %s\n"
			   "  page off:        %zu\n"
			   "  handshake ok:    %u\n"
			   "  timer:           %lu.%ld\n"
			   "  data ready:      %lu.%ld\n"
			   "  advance start:   %lu.%ld\n"
			   "  advance stop:    %lu.%ld\n"
			   "  func start:      %lu.%ld\n"
			   "  func stop:       %lu.%ld\n"
			   "  func key:        %u\n"
			   "  func type:       %u\n",
			   sc,
			   atomic_read(&sc->sc_kref.refcount),
			   &saddr, inet ? ntohs(sport) : 0,
			   &daddr, inet ? ntohs(dport) : 0,
			   sc->sc_node->nd_name,
			   sc->sc_page_off,
			   sc->sc_handshake_ok,
			   TV_SEC_USEC(sc->sc_tv_timer),
			   TV_SEC_USEC(sc->sc_tv_data_ready),
			   TV_SEC_USEC(sc->sc_tv_advance_start),
			   TV_SEC_USEC(sc->sc_tv_advance_stop),
			   TV_SEC_USEC(sc->sc_tv_func_start),
			   TV_SEC_USEC(sc->sc_tv_func_stop),
			   sc->sc_msg_key,
			   sc->sc_msg_type);
	}


	spin_unlock(&o2net_debug_lock);

	return 0;
}

static void sc_seq_stop(struct seq_file *seq, void *v)
{
}

static const struct seq_operations sc_seq_ops = {
	.start = sc_seq_start,
	.next = sc_seq_next,
	.stop = sc_seq_stop,
	.show = sc_seq_show,
};

static int sc_fop_open(struct inode *inode, struct file *file)
{
	struct o2net_sock_container *dummy_sc;
	struct seq_file *seq;
	int ret;

	dummy_sc = kmalloc(sizeof(struct o2net_sock_container), GFP_KERNEL);
	if (dummy_sc == NULL) {
		ret = -ENOMEM;
		goto out;
	}
	dummy_sc->sc_page = NULL;

	ret = seq_open(file, &sc_seq_ops);
	if (ret)
		goto out;

	seq = file->private_data;
	seq->private = dummy_sc;
	o2net_debug_add_sc(dummy_sc);

	dummy_sc = NULL;

out:
	kfree(dummy_sc);
	return ret;
}

static int sc_fop_release(struct inode *inode, struct file *file)
{
	struct seq_file *seq = file->private_data;
	struct o2net_sock_container *dummy_sc = seq->private;

	o2net_debug_del_sc(dummy_sc);
	return seq_release_private(inode, file);
}

static struct file_operations sc_seq_fops = {
	.open = sc_fop_open,
	.read = seq_read,
	.llseek = seq_lseek,
	.release = sc_fop_release,
};

int o2net_debugfs_init(void)
{
	o2net_dentry = debugfs_create_dir(O2NET_DEBUG_DIR, NULL);
	if (!o2net_dentry) {
		mlog_errno(-ENOMEM);
		goto bail;
	}

	nst_dentry = debugfs_create_file(NST_DEBUG_NAME, S_IFREG|S_IRUSR,
					 o2net_dentry, NULL,
					 &nst_seq_fops);
	if (!nst_dentry) {
		mlog_errno(-ENOMEM);
		goto bail;
	}

	sc_dentry = debugfs_create_file(SC_DEBUG_NAME, S_IFREG|S_IRUSR,
					o2net_dentry, NULL,
					&sc_seq_fops);
	if (!sc_dentry) {
		mlog_errno(-ENOMEM);
		goto bail;
	}

	return 0;
bail:
	if (sc_dentry)
		debugfs_remove(sc_dentry);
	if (nst_dentry)
		debugfs_remove(nst_dentry);
	if (o2net_dentry)
		debugfs_remove(o2net_dentry);
	return -ENOMEM;
}

void o2net_debugfs_exit(void)
{
	if (sc_dentry)
		debugfs_remove(sc_dentry);
	if (nst_dentry)
		debugfs_remove(nst_dentry);
	if (o2net_dentry)
		debugfs_remove(o2net_dentry);
}

#endif	/* CONFIG_DEBUG_FS */
#ifdef CONFIG_RCU_BOOST seq_printf(m, "%sttb=%c ntb=%lu neb=%lu nnb=%lu j=%04x bt=%04x\n", " ", "B."[!rcu_preempt_ctrlblk.boost_tasks], rcu_preempt_ctrlblk.n_tasks_boosted, rcu_preempt_ctrlblk.n_exp_boosts, rcu_preempt_ctrlblk.n_normal_boosts, (int)(jiffies & 0xffff), (int)(rcu_preempt_ctrlblk.boost_time & 0xffff)); seq_printf(m, "%s: nt=%lu egt=%lu bt=%lu ny=%lu nos=%lu\n", " balk", rcu_preempt_ctrlblk.n_balk_blkd_tasks, rcu_preempt_ctrlblk.n_balk_exp_gp_tasks, rcu_preempt_ctrlblk.n_balk_boost_tasks, rcu_preempt_ctrlblk.n_balk_notyet, rcu_preempt_ctrlblk.n_balk_nos); #endif /* #ifdef CONFIG_RCU_BOOST */ } #endif /* #ifdef CONFIG_RCU_TRACE */ #ifdef CONFIG_RCU_BOOST #include "rtmutex_common.h" #define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO /* Controls for rcu_kthread() kthread. */ static struct task_struct *rcu_kthread_task; static DECLARE_WAIT_QUEUE_HEAD(rcu_kthread_wq); static unsigned long have_rcu_kthread_work; /* * Carry out RCU priority boosting on the task indicated by ->boost_tasks, * and advance ->boost_tasks to the next task in the ->blkd_tasks list. */ static int rcu_boost(void) { unsigned long flags; struct rt_mutex mtx; struct task_struct *t; struct list_head *tb; if (rcu_preempt_ctrlblk.boost_tasks == NULL && rcu_preempt_ctrlblk.exp_tasks == NULL) return 0; /* Nothing to boost. */ raw_local_irq_save(flags); /* * Recheck with irqs disabled: all tasks in need of boosting * might exit their RCU read-side critical sections on their own * if we are preempted just before disabling irqs. */ if (rcu_preempt_ctrlblk.boost_tasks == NULL && rcu_preempt_ctrlblk.exp_tasks == NULL) { raw_local_irq_restore(flags); return 0; } /* * Preferentially boost tasks blocking expedited grace periods. * This cannot starve the normal grace periods because a second * expedited grace period must boost all blocked tasks, including * those blocking the pre-existing normal grace period. */ if (rcu_preempt_ctrlblk.exp_tasks != NULL) { tb = rcu_preempt_ctrlblk.exp_tasks; RCU_TRACE(rcu_preempt_ctrlblk.n_exp_boosts++); } else { tb = rcu_preempt_ctrlblk.boost_tasks; RCU_TRACE(rcu_preempt_ctrlblk.n_normal_boosts++); } RCU_TRACE(rcu_preempt_ctrlblk.n_tasks_boosted++); /* * We boost task t by manufacturing an rt_mutex that appears to * be held by task t. We leave a pointer to that rt_mutex where * task t can find it, and task t will release the mutex when it * exits its outermost RCU read-side critical section. Then * simply acquiring this artificial rt_mutex will boost task * t's priority. (Thanks to tglx for suggesting this approach!) */ t = container_of(tb, struct task_struct, rcu_node_entry); rt_mutex_init_proxy_locked(&mtx, t); t->rcu_boost_mutex = &mtx; raw_local_irq_restore(flags); rt_mutex_lock(&mtx); rt_mutex_unlock(&mtx); /* Keep lockdep happy. */ return ACCESS_ONCE(rcu_preempt_ctrlblk.boost_tasks) != NULL || ACCESS_ONCE(rcu_preempt_ctrlblk.exp_tasks) != NULL; } /* * Check to see if it is now time to start boosting RCU readers blocking * the current grace period, and, if so, tell the rcu_kthread_task to * start boosting them. If there is an expedited boost in progress, * we wait for it to complete. * * If there are no blocked readers blocking the current grace period, * return 0 to let the caller know, otherwise return 1. Note that this * return value is independent of whether or not boosting was done. */ static int rcu_initiate_boost(void) { if (!rcu_preempt_blocked_readers_cgp() && rcu_preempt_ctrlblk.exp_tasks == NULL) { RCU_TRACE(rcu_preempt_ctrlblk.n_balk_exp_gp_tasks++); return 0; } if (rcu_preempt_ctrlblk.exp_tasks != NULL || (rcu_preempt_ctrlblk.gp_tasks != NULL && rcu_preempt_ctrlblk.boost_tasks == NULL && ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time))) { if (rcu_preempt_ctrlblk.exp_tasks == NULL) rcu_preempt_ctrlblk.boost_tasks = rcu_preempt_ctrlblk.gp_tasks; invoke_rcu_callbacks(); } else RCU_TRACE(rcu_initiate_boost_trace()); return 1; } #define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000) /* * Do priority-boost accounting for the start of a new grace period. */ static void rcu_preempt_boost_start_gp(void) { rcu_preempt_ctrlblk.boost_time = jiffies + RCU_BOOST_DELAY_JIFFIES; } #else /* #ifdef CONFIG_RCU_BOOST */ /* * If there is no RCU priority boosting, we don't initiate boosting, * but we do indicate whether there are blocked readers blocking the * current grace period. */ static int rcu_initiate_boost(void) { return rcu_preempt_blocked_readers_cgp(); } /* * If there is no RCU priority boosting, nothing to do at grace-period start. */ static void rcu_preempt_boost_start_gp(void) { } #endif /* else #ifdef CONFIG_RCU_BOOST */ /* * Record a preemptible-RCU quiescent state for the specified CPU. Note * that this just means that the task currently running on the CPU is * in a quiescent state. There might be any number of tasks blocked * while in an RCU read-side critical section. * * Unlike the other rcu_*_qs() functions, callers to this function * must disable irqs in order to protect the assignment to * ->rcu_read_unlock_special. * * Because this is a single-CPU implementation, the only way a grace * period can end is if the CPU is in a quiescent state. The reason is * that a blocked preemptible-RCU reader can exit its critical section * only if the CPU is running it at the time. Therefore, when the * last task blocking the current grace period exits its RCU read-side * critical section, neither the CPU nor blocked tasks will be stopping * the current grace period. (In contrast, SMP implementations * might have CPUs running in RCU read-side critical sections that * block later grace periods -- but this is not possible given only * one CPU.) */ static void rcu_preempt_cpu_qs(void) { /* Record both CPU and task as having responded to current GP. */ rcu_preempt_ctrlblk.gpcpu = rcu_preempt_ctrlblk.gpnum; current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS; /* If there is no GP then there is nothing more to do. */ if (!rcu_preempt_gp_in_progress()) return; /* * Check up on boosting. If there are readers blocking the * current grace period, leave. */ if (rcu_initiate_boost()) return; /* Advance callbacks. */ rcu_preempt_ctrlblk.completed = rcu_preempt_ctrlblk.gpnum; rcu_preempt_ctrlblk.rcb.donetail = rcu_preempt_ctrlblk.rcb.curtail; rcu_preempt_ctrlblk.rcb.curtail = rcu_preempt_ctrlblk.nexttail; /* If there are no blocked readers, next GP is done instantly. */ if (!rcu_preempt_blocked_readers_any()) rcu_preempt_ctrlblk.rcb.donetail = rcu_preempt_ctrlblk.nexttail; /* If there are done callbacks, cause them to be invoked. */ if (*rcu_preempt_ctrlblk.rcb.donetail != NULL) invoke_rcu_callbacks(); } /* * Start a new RCU grace period if warranted. Hard irqs must be disabled. */ static void rcu_preempt_start_gp(void) { if (!rcu_preempt_gp_in_progress() && rcu_preempt_needs_another_gp()) { /* Official start of GP. */ rcu_preempt_ctrlblk.gpnum++; RCU_TRACE(rcu_preempt_ctrlblk.n_grace_periods++); /* Any blocked RCU readers block new GP. */ if (rcu_preempt_blocked_readers_any()) rcu_preempt_ctrlblk.gp_tasks = rcu_preempt_ctrlblk.blkd_tasks.next; /* Set up for RCU priority boosting. */ rcu_preempt_boost_start_gp(); /* If there is no running reader, CPU is done with GP. */ if (!rcu_preempt_running_reader()) rcu_preempt_cpu_qs(); } } /* * We have entered the scheduler, and the current task might soon be * context-switched away from. If this task is in an RCU read-side * critical section, we will no longer be able to rely on the CPU to * record that fact, so we enqueue the task on the blkd_tasks list. * If the task started after the current grace period began, as recorded * by ->gpcpu, we enqueue at the beginning of the list. Otherwise * before the element referenced by ->gp_tasks (or at the tail if * ->gp_tasks is NULL) and point ->gp_tasks at the newly added element. * The task will dequeue itself when it exits the outermost enclosing * RCU read-side critical section. Therefore, the current grace period * cannot be permitted to complete until the ->gp_tasks pointer becomes * NULL. * * Caller must disable preemption. */ void rcu_preempt_note_context_switch(void) { struct task_struct *t = current; unsigned long flags; local_irq_save(flags); /* must exclude scheduler_tick(). */ if (rcu_preempt_running_reader() > 0 && (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) { /* Possibly blocking in an RCU read-side critical section. */ t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED; /* * If this CPU has already checked in, then this task * will hold up the next grace period rather than the * current grace period. Queue the task accordingly. * If the task is queued for the current grace period * (i.e., this CPU has not yet passed through a quiescent * state for the current grace period), then as long * as that task remains queued, the current grace period * cannot end. */ list_add(&t->rcu_node_entry, &rcu_preempt_ctrlblk.blkd_tasks); if (rcu_cpu_blocking_cur_gp()) rcu_preempt_ctrlblk.gp_tasks = &t->rcu_node_entry; } else if (rcu_preempt_running_reader() < 0 && t->rcu_read_unlock_special) { /* * Complete exit from RCU read-side critical section on * behalf of preempted instance of __rcu_read_unlock(). */ rcu_read_unlock_special(t); } /* * Either we were not in an RCU read-side critical section to * begin with, or we have now recorded that critical section * globally. Either way, we can now note a quiescent state * for this CPU. Again, if we were in an RCU read-side critical * section, and if that critical section was blocking the current * grace period, then the fact that the task has been enqueued * means that current grace period continues to be blocked. */ rcu_preempt_cpu_qs(); local_irq_restore(flags); } /* * Tiny-preemptible RCU implementation for rcu_read_lock(). * Just increment ->rcu_read_lock_nesting, shared state will be updated * if we block. */ void __rcu_read_lock(void) { current->rcu_read_lock_nesting++; barrier(); /* needed if we ever invoke rcu_read_lock in rcutiny.c */ } EXPORT_SYMBOL_GPL(__rcu_read_lock); /* * Handle special cases during rcu_read_unlock(), such as needing to * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ static noinline void rcu_read_unlock_special(struct task_struct *t) { int empty; int empty_exp; unsigned long flags; struct list_head *np; #ifdef CONFIG_RCU_BOOST struct rt_mutex *rbmp = NULL; #endif /* #ifdef CONFIG_RCU_BOOST */ int special; /* * NMI handlers cannot block and cannot safely manipulate state. * They therefore cannot possibly be special, so just leave. */ if (in_nmi()) return; local_irq_save(flags); /* * If RCU core is waiting for this CPU to exit critical section, * let it know that we have done so. */ special = t->rcu_read_unlock_special; if (special & RCU_READ_UNLOCK_NEED_QS) rcu_preempt_cpu_qs(); /* Hardware IRQ handlers cannot block. */ if (in_irq() || in_serving_softirq()) { local_irq_restore(flags); return; } /* Clean up if blocked during RCU read-side critical section. */ if (special & RCU_READ_UNLOCK_BLOCKED) { t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BLOCKED; /* * Remove this task from the ->blkd_tasks list and adjust * any pointers that might have been referencing it. */ empty = !rcu_preempt_blocked_readers_cgp(); empty_exp = rcu_preempt_ctrlblk.exp_tasks == NULL; np = rcu_next_node_entry(t); list_del_init(&t->rcu_node_entry); if (&t->rcu_node_entry == rcu_preempt_ctrlblk.gp_tasks) rcu_preempt_ctrlblk.gp_tasks = np; if (&t->rcu_node_entry == rcu_preempt_ctrlblk.exp_tasks) rcu_preempt_ctrlblk.exp_tasks = np; #ifdef CONFIG_RCU_BOOST if (&t->rcu_node_entry == rcu_preempt_ctrlblk.boost_tasks) rcu_preempt_ctrlblk.boost_tasks = np; #endif /* #ifdef CONFIG_RCU_BOOST */ /* * If this was the last task on the current list, and if * we aren't waiting on the CPU, report the quiescent state * and start a new grace period if needed. */ if (!empty && !rcu_preempt_blocked_readers_cgp()) { rcu_preempt_cpu_qs(); rcu_preempt_start_gp(); } /* * If this was the last task on the expedited lists, * then we need wake up the waiting task. */ if (!empty_exp && rcu_preempt_ctrlblk.exp_tasks == NULL) rcu_report_exp_done(); } #ifdef CONFIG_RCU_BOOST /* Unboost self if was boosted. */ if (t->rcu_boost_mutex != NULL) { rbmp = t->rcu_boost_mutex; t->rcu_boost_mutex = NULL; rt_mutex_unlock(rbmp); } #endif /* #ifdef CONFIG_RCU_BOOST */ local_irq_restore(flags); } /* * Tiny-preemptible RCU implementation for rcu_read_unlock(). * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then * invoke rcu_read_unlock_special() to clean up after a context switch * in an RCU read-side critical section and other special cases. */ void __rcu_read_unlock(void) { struct task_struct *t = current; barrier(); /* needed if we ever invoke rcu_read_unlock in rcutiny.c */ if (t->rcu_read_lock_nesting != 1) --t->rcu_read_lock_nesting; else { t->rcu_read_lock_nesting = INT_MIN; barrier(); /* assign before ->rcu_read_unlock_special load */ if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) rcu_read_unlock_special(t); barrier(); /* ->rcu_read_unlock_special load before assign */ t->rcu_read_lock_nesting = 0; } #ifdef CONFIG_PROVE_LOCKING { int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); } #endif /* #ifdef CONFIG_PROVE_LOCKING */ } EXPORT_SYMBOL_GPL(__rcu_read_unlock); /* * Check for a quiescent state from the current CPU. When a task blocks, * the task is recorded in the rcu_preempt_ctrlblk structure, which is * checked elsewhere. This is called from the scheduling-clock interrupt. * * Caller must disable hard irqs. */ static void rcu_preempt_check_callbacks(void) { struct task_struct *t = current; if (rcu_preempt_gp_in_progress() && (!rcu_preempt_running_reader() || !rcu_cpu_blocking_cur_gp())) rcu_preempt_cpu_qs(); if (&rcu_preempt_ctrlblk.rcb.rcucblist != rcu_preempt_ctrlblk.rcb.donetail) invoke_rcu_callbacks(); if (rcu_preempt_gp_in_progress() && rcu_cpu_blocking_cur_gp() && rcu_preempt_running_reader() > 0) t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS; } /* * TINY_PREEMPT_RCU has an extra callback-list tail pointer to * update, so this is invoked from rcu_process_callbacks() to * handle that case. Of course, it is invoked for all flavors of * RCU, but RCU callbacks can appear only on one of the lists, and * neither ->nexttail nor ->donetail can possibly be NULL, so there * is no need for an explicit check. */ static void rcu_preempt_remove_callbacks(struct rcu_ctrlblk *rcp) { if (rcu_preempt_ctrlblk.nexttail == rcp->donetail) rcu_preempt_ctrlblk.nexttail = &rcp->rcucblist; } /* * Process callbacks for preemptible RCU. */ static void rcu_preempt_process_callbacks(void) { __rcu_process_callbacks(&rcu_preempt_ctrlblk.rcb); } /* * Queue a preemptible -RCU callback for invocation after a grace period. */ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) { unsigned long flags; debug_rcu_head_queue(head); head->func = func; head->next = NULL; local_irq_save(flags); *rcu_preempt_ctrlblk.nexttail = head; rcu_preempt_ctrlblk.nexttail = &head->next; RCU_TRACE(rcu_preempt_ctrlblk.rcb.qlen++); rcu_preempt_start_gp(); /* checks to see if GP needed. */ local_irq_restore(flags); } EXPORT_SYMBOL_GPL(call_rcu); /* * synchronize_rcu - wait until a grace period has elapsed. * * Control will return to the caller some time after a full grace * period has elapsed, in other words after all currently executing RCU * read-side critical sections have completed. RCU read-side critical * sections are delimited by rcu_read_lock() and rcu_read_unlock(), * and may be nested. */ void synchronize_rcu(void) { rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && !lock_is_held(&rcu_lock_map) && !lock_is_held(&rcu_sched_lock_map), "Illegal synchronize_rcu() in RCU read-side critical section"); #ifdef CONFIG_DEBUG_LOCK_ALLOC if (!rcu_scheduler_active) return; #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ WARN_ON_ONCE(rcu_preempt_running_reader()); if (!rcu_preempt_blocked_readers_any()) return; /* Once we get past the fastpath checks, same code as rcu_barrier(). */ rcu_barrier(); } EXPORT_SYMBOL_GPL(synchronize_rcu); static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq); static unsigned long sync_rcu_preempt_exp_count; static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex); /* * Return non-zero if there are any tasks in RCU read-side critical * sections blocking the current preemptible-RCU expedited grace period. * If there is no preemptible-RCU expedited grace period currently in * progress, returns zero unconditionally. */ static int rcu_preempted_readers_exp(void) { return rcu_preempt_ctrlblk.exp_tasks != NULL; } /* * Report the exit from RCU read-side critical section for the last task * that queued itself during or before the current expedited preemptible-RCU * grace period. */ static void rcu_report_exp_done(void) { wake_up(&sync_rcu_preempt_exp_wq); } /* * Wait for an rcu-preempt grace period, but expedite it. The basic idea * is to rely in the fact that there is but one CPU, and that it is * illegal for a task to invoke synchronize_rcu_expedited() while in a * preemptible-RCU read-side critical section. Therefore, any such * critical sections must correspond to blocked tasks, which must therefore * be on the ->blkd_tasks list. So just record the current head of the * list in the ->exp_tasks pointer, and wait for all tasks including and * after the task pointed to by ->exp_tasks to drain. */ void synchronize_rcu_expedited(void) { unsigned long flags; struct rcu_preempt_ctrlblk *rpcp = &rcu_preempt_ctrlblk; unsigned long snap; barrier(); /* ensure prior action seen before grace period. */ WARN_ON_ONCE(rcu_preempt_running_reader()); /* * Acquire lock so that there is only one preemptible RCU grace * period in flight. Of course, if someone does the expedited * grace period for us while we are acquiring the lock, just leave. */ snap = sync_rcu_preempt_exp_count + 1; mutex_lock(&sync_rcu_preempt_exp_mutex); if (ULONG_CMP_LT(snap, sync_rcu_preempt_exp_count)) goto unlock_mb_ret; /* Others did our work for us. */ local_irq_save(flags); /* * All RCU readers have to already be on blkd_tasks because * we cannot legally be executing in an RCU read-side critical * section. */ /* Snapshot current head of ->blkd_tasks list. */ rpcp->exp_tasks = rpcp->blkd_tasks.next; if (rpcp->exp_tasks == &rpcp->blkd_tasks) rpcp->exp_tasks = NULL; /* Wait for tail of ->blkd_tasks list to drain. */ if (!rcu_preempted_readers_exp()) local_irq_restore(flags); else { rcu_initiate_boost(); local_irq_restore(flags); wait_event(sync_rcu_preempt_exp_wq, !rcu_preempted_readers_exp()); } /* Clean up and exit. */ barrier(); /* ensure expedited GP seen before counter increment. */ sync_rcu_preempt_exp_count++; unlock_mb_ret: mutex_unlock(&sync_rcu_preempt_exp_mutex); barrier(); /* ensure subsequent action seen after grace period. */ } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); /* * Does preemptible RCU need the CPU to stay out of dynticks mode? */ int rcu_preempt_needs_cpu(void) { if (!rcu_preempt_running_reader()) rcu_preempt_cpu_qs(); return rcu_preempt_ctrlblk.rcb.rcucblist != NULL; } /* * Check for a task exiting while in a preemptible -RCU read-side * critical section, clean up if so. No need to issue warnings, * as debug_check_no_locks_held() already does this if lockdep * is enabled. */ void exit_rcu(void) { struct task_struct *t = current; if (t->rcu_read_lock_nesting == 0) return; t->rcu_read_lock_nesting = 1; __rcu_read_unlock(); } #else /* #ifdef CONFIG_TINY_PREEMPT_RCU */ #ifdef CONFIG_RCU_TRACE /* * Because preemptible RCU does not exist, it is not necessary to * dump out its statistics. */ static void show_tiny_preempt_stats(struct seq_file *m) { } #endif /* #ifdef CONFIG_RCU_TRACE */ /* * Because preemptible RCU does not exist, it never has any callbacks * to check. */ static void rcu_preempt_check_callbacks(void) { } /* * Because preemptible RCU does not exist, it never has any callbacks * to remove. */ static void rcu_preempt_remove_callbacks(struct rcu_ctrlblk *rcp) { } /* * Because preemptible RCU does not exist, it never has any callbacks * to process. */ static void rcu_preempt_process_callbacks(void) { } #endif /* #else #ifdef CONFIG_TINY_PREEMPT_RCU */ #ifdef CONFIG_RCU_BOOST /* * Wake up rcu_kthread() to process callbacks now eligible for invocation * or to boost readers. */ static void invoke_rcu_callbacks(void) { have_rcu_kthread_work = 1; if (rcu_kthread_task != NULL) wake_up(&rcu_kthread_wq); } #ifdef CONFIG_RCU_TRACE /* * Is the current CPU running the RCU-callbacks kthread? * Caller must have preemption disabled. */ static bool rcu_is_callbacks_kthread(void) { return rcu_kthread_task == current; } #endif /* #ifdef CONFIG_RCU_TRACE */ /* * This kthread invokes RCU callbacks whose grace periods have * elapsed. It is awakened as needed, and takes the place of the * RCU_SOFTIRQ that is used for this purpose when boosting is disabled. * This is a kthread, but it is never stopped, at least not until * the system goes down. */ static int rcu_kthread(void *arg) { unsigned long work; unsigned long morework; unsigned long flags; for (;;) { wait_event_interruptible(rcu_kthread_wq, have_rcu_kthread_work != 0); morework = rcu_boost(); local_irq_save(flags); work = have_rcu_kthread_work; have_rcu_kthread_work = morework; local_irq_restore(flags); if (work) rcu_process_callbacks(NULL); schedule_timeout_interruptible(1); /* Leave CPU for others. */ } return 0; /* Not reached, but needed to shut gcc up. */ } /* * Spawn the kthread that invokes RCU callbacks. */ static int __init rcu_spawn_kthreads(void) { struct sched_param sp; rcu_kthread_task = kthread_run(rcu_kthread, NULL, "rcu_kthread"); sp.sched_priority = RCU_BOOST_PRIO; sched_setscheduler_nocheck(rcu_kthread_task, SCHED_FIFO, &sp); return 0; } early_initcall(rcu_spawn_kthreads); #else /* #ifdef CONFIG_RCU_BOOST */ /* Hold off callback invocation until early_initcall() time. */ static int rcu_scheduler_fully_active __read_mostly; /* * Start up softirq processing of callbacks. */ void invoke_rcu_callbacks(void) { if (rcu_scheduler_fully_active) raise_softirq(RCU_SOFTIRQ); } #ifdef CONFIG_RCU_TRACE /* * There is no callback kthread, so this thread is never it. */ static bool rcu_is_callbacks_kthread(void) { return false; } #endif /* #ifdef CONFIG_RCU_TRACE */ static int __init rcu_scheduler_really_started(void) { rcu_scheduler_fully_active = 1; open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); raise_softirq(RCU_SOFTIRQ); /* Invoke any callbacks from early boot. */ return 0; } early_initcall(rcu_scheduler_really_started); #endif /* #else #ifdef CONFIG_RCU_BOOST */ #ifdef CONFIG_DEBUG_LOCK_ALLOC #include <linux/kernel_stat.h> /* * During boot, we forgive RCU lockdep issues. After this function is * invoked, we start taking RCU lockdep issues seriously. */ void __init rcu_scheduler_starting(void) { WARN_ON(nr_context_switches() > 0); rcu_scheduler_active = 1; } #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_RCU_TRACE #ifdef CONFIG_RCU_BOOST static void rcu_initiate_boost_trace(void) { if (list_empty(&rcu_preempt_ctrlblk.blkd_tasks)) rcu_preempt_ctrlblk.n_balk_blkd_tasks++; else if (rcu_preempt_ctrlblk.gp_tasks == NULL && rcu_preempt_ctrlblk.exp_tasks == NULL) rcu_preempt_ctrlblk.n_balk_exp_gp_tasks++; else if (rcu_preempt_ctrlblk.boost_tasks != NULL) rcu_preempt_ctrlblk.n_balk_boost_tasks++; else if (!ULONG_CMP_GE(jiffies, rcu_preempt_ctrlblk.boost_time)) rcu_preempt_ctrlblk.n_balk_notyet++; else rcu_preempt_ctrlblk.n_balk_nos++; } #endif /* #ifdef CONFIG_RCU_BOOST */ static void rcu_trace_sub_qlen(struct rcu_ctrlblk *rcp, int n) { unsigned long flags; raw_local_irq_save(flags); rcp->qlen -= n; raw_local_irq_restore(flags); } /* * Dump statistics for TINY_RCU, such as they are. */ static int show_tiny_stats(struct seq_file *m, void *unused) { show_tiny_preempt_stats(m); seq_printf(m, "rcu_sched: qlen: %ld\n", rcu_sched_ctrlblk.qlen); seq_printf(m, "rcu_bh: qlen: %ld\n", rcu_bh_ctrlblk.qlen); return 0; } static int show_tiny_stats_open(struct inode *inode, struct file *file) { return single_open(file, show_tiny_stats, NULL); } static const struct file_operations show_tiny_stats_fops = { .owner = THIS_MODULE, .open = show_tiny_stats_open, .read = seq_read, .llseek = seq_lseek, .release = single_release, }; static struct dentry *rcudir; static int __init rcutiny_trace_init(void) { struct dentry *retval; rcudir = debugfs_create_dir("rcu", NULL); if (!rcudir) goto free_out; retval = debugfs_create_file("rcudata", 0444, rcudir, NULL, &show_tiny_stats_fops); if (!retval) goto free_out; return 0; free_out: debugfs_remove_recursive(rcudir); return 1; } static void __exit rcutiny_trace_cleanup(void) { debugfs_remove_recursive(rcudir); } module_init(rcutiny_trace_init); module_exit(rcutiny_trace_cleanup); MODULE_AUTHOR("Paul E. McKenney"); MODULE_DESCRIPTION("Read-Copy Update tracing for tiny implementation"); MODULE_LICENSE("GPL"); #endif /* #ifdef CONFIG_RCU_TRACE */