1 // SPDX-License-Identifier: GPL-2.0+
2 /*
3 * Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition.
4 *
5 * Copyright IBM Corporation, 2008
6 *
7 * Author: Paul E. McKenney <paulmck@linux.ibm.com>
8 *
9 * For detailed explanation of Read-Copy Update mechanism see -
10 * Documentation/RCU
11 */
12 #include <linux/completion.h>
13 #include <linux/interrupt.h>
14 #include <linux/notifier.h>
15 #include <linux/rcupdate_wait.h>
16 #include <linux/kernel.h>
17 #include <linux/export.h>
18 #include <linux/mutex.h>
19 #include <linux/sched.h>
20 #include <linux/types.h>
21 #include <linux/init.h>
22 #include <linux/time.h>
23 #include <linux/cpu.h>
24 #include <linux/prefetch.h>
25 #include <linux/slab.h>
26 #include <linux/mm.h>
27
28 #include "rcu.h"
29
30 /* Global control variables for rcupdate callback mechanism. */
31 struct rcu_ctrlblk {
32 struct rcu_head *rcucblist; /* List of pending callbacks (CBs). */
33 struct rcu_head **donetail; /* ->next pointer of last "done" CB. */
34 struct rcu_head **curtail; /* ->next pointer of last CB. */
35 unsigned long gp_seq; /* Grace-period counter. */
36 };
37
38 /* Definition for rcupdate control block. */
39 static struct rcu_ctrlblk rcu_ctrlblk = {
40 .donetail = &rcu_ctrlblk.rcucblist,
41 .curtail = &rcu_ctrlblk.rcucblist,
42 .gp_seq = 0 - 300UL,
43 };
44
rcu_barrier(void)45 void rcu_barrier(void)
46 {
47 wait_rcu_gp(call_rcu_hurry);
48 }
49 EXPORT_SYMBOL(rcu_barrier);
50
51 /* Record an rcu quiescent state. */
rcu_qs(void)52 void rcu_qs(void)
53 {
54 unsigned long flags;
55
56 local_irq_save(flags);
57 if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail) {
58 rcu_ctrlblk.donetail = rcu_ctrlblk.curtail;
59 raise_softirq_irqoff(RCU_SOFTIRQ);
60 }
61 WRITE_ONCE(rcu_ctrlblk.gp_seq, rcu_ctrlblk.gp_seq + 2);
62 local_irq_restore(flags);
63 }
64
65 /*
66 * Check to see if the scheduling-clock interrupt came from an extended
67 * quiescent state, and, if so, tell RCU about it. This function must
68 * be called from hardirq context. It is normally called from the
69 * scheduling-clock interrupt.
70 */
rcu_sched_clock_irq(int user)71 void rcu_sched_clock_irq(int user)
72 {
73 if (user) {
74 rcu_qs();
75 } else if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail) {
76 set_tsk_need_resched(current);
77 set_preempt_need_resched();
78 }
79 }
80
81 /*
82 * Reclaim the specified callback, either by invoking it for non-kfree cases or
83 * freeing it directly (for kfree). Return true if kfreeing, false otherwise.
84 */
rcu_reclaim_tiny(struct rcu_head * head)85 static inline bool rcu_reclaim_tiny(struct rcu_head *head)
86 {
87 rcu_callback_t f;
88 unsigned long offset = (unsigned long)head->func;
89
90 rcu_lock_acquire(&rcu_callback_map);
91 if (__is_kvfree_rcu_offset(offset)) {
92 trace_rcu_invoke_kvfree_callback("", head, offset);
93 kvfree((void *)head - offset);
94 rcu_lock_release(&rcu_callback_map);
95 return true;
96 }
97
98 trace_rcu_invoke_callback("", head);
99 f = head->func;
100 WRITE_ONCE(head->func, (rcu_callback_t)0L);
101 f(head);
102 rcu_lock_release(&rcu_callback_map);
103 return false;
104 }
105
106 /* Invoke the RCU callbacks whose grace period has elapsed. */
rcu_process_callbacks(struct softirq_action * unused)107 static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused)
108 {
109 struct rcu_head *next, *list;
110 unsigned long flags;
111
112 /* Move the ready-to-invoke callbacks to a local list. */
113 local_irq_save(flags);
114 if (rcu_ctrlblk.donetail == &rcu_ctrlblk.rcucblist) {
115 /* No callbacks ready, so just leave. */
116 local_irq_restore(flags);
117 return;
118 }
119 list = rcu_ctrlblk.rcucblist;
120 rcu_ctrlblk.rcucblist = *rcu_ctrlblk.donetail;
121 *rcu_ctrlblk.donetail = NULL;
122 if (rcu_ctrlblk.curtail == rcu_ctrlblk.donetail)
123 rcu_ctrlblk.curtail = &rcu_ctrlblk.rcucblist;
124 rcu_ctrlblk.donetail = &rcu_ctrlblk.rcucblist;
125 local_irq_restore(flags);
126
127 /* Invoke the callbacks on the local list. */
128 while (list) {
129 next = list->next;
130 prefetch(next);
131 debug_rcu_head_unqueue(list);
132 local_bh_disable();
133 rcu_reclaim_tiny(list);
134 local_bh_enable();
135 list = next;
136 }
137 }
138
139 /*
140 * Wait for a grace period to elapse. But it is illegal to invoke
141 * synchronize_rcu() from within an RCU read-side critical section.
142 * Therefore, any legal call to synchronize_rcu() is a quiescent state,
143 * and so on a UP system, synchronize_rcu() need do nothing, other than
144 * let the polled APIs know that another grace period elapsed.
145 *
146 * (But Lai Jiangshan points out the benefits of doing might_sleep()
147 * to reduce latency.)
148 *
149 * Cool, huh? (Due to Josh Triplett.)
150 */
synchronize_rcu(void)151 void synchronize_rcu(void)
152 {
153 RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
154 lock_is_held(&rcu_lock_map) ||
155 lock_is_held(&rcu_sched_lock_map),
156 "Illegal synchronize_rcu() in RCU read-side critical section");
157 WRITE_ONCE(rcu_ctrlblk.gp_seq, rcu_ctrlblk.gp_seq + 2);
158 }
159 EXPORT_SYMBOL_GPL(synchronize_rcu);
160
tiny_rcu_leak_callback(struct rcu_head * rhp)161 static void tiny_rcu_leak_callback(struct rcu_head *rhp)
162 {
163 }
164
165 /*
166 * Post an RCU callback to be invoked after the end of an RCU grace
167 * period. But since we have but one CPU, that would be after any
168 * quiescent state.
169 */
call_rcu(struct rcu_head * head,rcu_callback_t func)170 void call_rcu(struct rcu_head *head, rcu_callback_t func)
171 {
172 static atomic_t doublefrees;
173 unsigned long flags;
174
175 if (debug_rcu_head_queue(head)) {
176 if (atomic_inc_return(&doublefrees) < 4) {
177 pr_err("%s(): Double-freed CB %p->%pS()!!! ", __func__, head, head->func);
178 mem_dump_obj(head);
179 }
180
181 if (!__is_kvfree_rcu_offset((unsigned long)head->func))
182 WRITE_ONCE(head->func, tiny_rcu_leak_callback);
183 return;
184 }
185
186 head->func = func;
187 head->next = NULL;
188
189 local_irq_save(flags);
190 *rcu_ctrlblk.curtail = head;
191 rcu_ctrlblk.curtail = &head->next;
192 local_irq_restore(flags);
193
194 if (unlikely(is_idle_task(current))) {
195 /* force scheduling for rcu_qs() */
196 resched_cpu(0);
197 }
198 }
199 EXPORT_SYMBOL_GPL(call_rcu);
200
201 /*
202 * Store a grace-period-counter "cookie". For more information,
203 * see the Tree RCU header comment.
204 */
get_completed_synchronize_rcu_full(struct rcu_gp_oldstate * rgosp)205 void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp)
206 {
207 rgosp->rgos_norm = RCU_GET_STATE_COMPLETED;
208 }
209 EXPORT_SYMBOL_GPL(get_completed_synchronize_rcu_full);
210
211 /*
212 * Return a grace-period-counter "cookie". For more information,
213 * see the Tree RCU header comment.
214 */
get_state_synchronize_rcu(void)215 unsigned long get_state_synchronize_rcu(void)
216 {
217 return READ_ONCE(rcu_ctrlblk.gp_seq);
218 }
219 EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
220
221 /*
222 * Return a grace-period-counter "cookie" and ensure that a future grace
223 * period completes. For more information, see the Tree RCU header comment.
224 */
start_poll_synchronize_rcu(void)225 unsigned long start_poll_synchronize_rcu(void)
226 {
227 unsigned long gp_seq = get_state_synchronize_rcu();
228
229 if (unlikely(is_idle_task(current))) {
230 /* force scheduling for rcu_qs() */
231 resched_cpu(0);
232 }
233 return gp_seq;
234 }
235 EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu);
236
237 /*
238 * Return true if the grace period corresponding to oldstate has completed
239 * and false otherwise. For more information, see the Tree RCU header
240 * comment.
241 */
poll_state_synchronize_rcu(unsigned long oldstate)242 bool poll_state_synchronize_rcu(unsigned long oldstate)
243 {
244 return oldstate == RCU_GET_STATE_COMPLETED || READ_ONCE(rcu_ctrlblk.gp_seq) != oldstate;
245 }
246 EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu);
247
248 #ifdef CONFIG_KASAN_GENERIC
kvfree_call_rcu(struct rcu_head * head,void * ptr)249 void kvfree_call_rcu(struct rcu_head *head, void *ptr)
250 {
251 if (head)
252 kasan_record_aux_stack_noalloc(ptr);
253
254 __kvfree_call_rcu(head, ptr);
255 }
256 EXPORT_SYMBOL_GPL(kvfree_call_rcu);
257 #endif
258
rcu_init(void)259 void __init rcu_init(void)
260 {
261 open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
262 rcu_early_boot_tests();
263 }
264