aboutsummaryrefslogtreecommitdiffstats
path: root/Documentation/RCU
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2009-01-08 18:52:13 -0500
committerLinus Torvalds <torvalds@linux-foundation.org>2009-01-08 18:52:13 -0500
commit1df2d017fe9d22a49bad157b4f5aa19212f29557 (patch)
tree8907fd08c5c367067768e79b3d98af2772cfa680 /Documentation/RCU
parent022992ee59e90fef719493c09988884be157fb73 (diff)
parentd5b524327b2a482dddae3839ced8f8825074730d (diff)
Merge branch 'docs-next' of git://git.lwn.net/linux-2.6
* 'docs-next' of git://git.lwn.net/linux-2.6: Fix a typo in the development process document. Document handling of bad memory Document RCU and unloadable modules
Diffstat (limited to 'Documentation/RCU')
-rw-r--r--Documentation/RCU/00-INDEX2
-rw-r--r--Documentation/RCU/rcubarrier.txt304
2 files changed, 306 insertions, 0 deletions
diff --git a/Documentation/RCU/00-INDEX b/Documentation/RCU/00-INDEX
index 7dc0695a8f90..9bb62f7b89c3 100644
--- a/Documentation/RCU/00-INDEX
+++ b/Documentation/RCU/00-INDEX
@@ -12,6 +12,8 @@ rcuref.txt
12 - Reference-count design for elements of lists/arrays protected by RCU 12 - Reference-count design for elements of lists/arrays protected by RCU
13rcu.txt 13rcu.txt
14 - RCU Concepts 14 - RCU Concepts
15rcubarrier.txt
16 - Unloading modules that use RCU callbacks
15RTFP.txt 17RTFP.txt
16 - List of RCU papers (bibliography) going back to 1980. 18 - List of RCU papers (bibliography) going back to 1980.
17torture.txt 19torture.txt
diff --git a/Documentation/RCU/rcubarrier.txt b/Documentation/RCU/rcubarrier.txt
new file mode 100644
index 000000000000..909602d409bb
--- /dev/null
+++ b/Documentation/RCU/rcubarrier.txt
@@ -0,0 +1,304 @@
1RCU and Unloadable Modules
2
3[Originally published in LWN Jan. 14, 2007: http://lwn.net/Articles/217484/]
4
5RCU (read-copy update) is a synchronization mechanism that can be thought
6of as a replacement for read-writer locking (among other things), but with
7very low-overhead readers that are immune to deadlock, priority inversion,
8and unbounded latency. RCU read-side critical sections are delimited
9by rcu_read_lock() and rcu_read_unlock(), which, in non-CONFIG_PREEMPT
10kernels, generate no code whatsoever.
11
12This means that RCU writers are unaware of the presence of concurrent
13readers, so that RCU updates to shared data must be undertaken quite
14carefully, leaving an old version of the data structure in place until all
15pre-existing readers have finished. These old versions are needed because
16such readers might hold a reference to them. RCU updates can therefore be
17rather expensive, and RCU is thus best suited for read-mostly situations.
18
19How can an RCU writer possibly determine when all readers are finished,
20given that readers might well leave absolutely no trace of their
21presence? There is a synchronize_rcu() primitive that blocks until all
22pre-existing readers have completed. An updater wishing to delete an
23element p from a linked list might do the following, while holding an
24appropriate lock, of course:
25
26 list_del_rcu(p);
27 synchronize_rcu();
28 kfree(p);
29
30But the above code cannot be used in IRQ context -- the call_rcu()
31primitive must be used instead. This primitive takes a pointer to an
32rcu_head struct placed within the RCU-protected data structure and
33another pointer to a function that may be invoked later to free that
34structure. Code to delete an element p from the linked list from IRQ
35context might then be as follows:
36
37 list_del_rcu(p);
38 call_rcu(&p->rcu, p_callback);
39
40Since call_rcu() never blocks, this code can safely be used from within
41IRQ context. The function p_callback() might be defined as follows:
42
43 static void p_callback(struct rcu_head *rp)
44 {
45 struct pstruct *p = container_of(rp, struct pstruct, rcu);
46
47 kfree(p);
48 }
49
50
51Unloading Modules That Use call_rcu()
52
53But what if p_callback is defined in an unloadable module?
54
55If we unload the module while some RCU callbacks are pending,
56the CPUs executing these callbacks are going to be severely
57disappointed when they are later invoked, as fancifully depicted at
58http://lwn.net/images/ns/kernel/rcu-drop.jpg.
59
60We could try placing a synchronize_rcu() in the module-exit code path,
61but this is not sufficient. Although synchronize_rcu() does wait for a
62grace period to elapse, it does not wait for the callbacks to complete.
63
64One might be tempted to try several back-to-back synchronize_rcu()
65calls, but this is still not guaranteed to work. If there is a very
66heavy RCU-callback load, then some of the callbacks might be deferred
67in order to allow other processing to proceed. Such deferral is required
68in realtime kernels in order to avoid excessive scheduling latencies.
69
70
71rcu_barrier()
72
73We instead need the rcu_barrier() primitive. This primitive is similar
74to synchronize_rcu(), but instead of waiting solely for a grace
75period to elapse, it also waits for all outstanding RCU callbacks to
76complete. Pseudo-code using rcu_barrier() is as follows:
77
78 1. Prevent any new RCU callbacks from being posted.
79 2. Execute rcu_barrier().
80 3. Allow the module to be unloaded.
81
82Quick Quiz #1: Why is there no srcu_barrier()?
83
84The rcutorture module makes use of rcu_barrier in its exit function
85as follows:
86
87 1 static void
88 2 rcu_torture_cleanup(void)
89 3 {
90 4 int i;
91 5
92 6 fullstop = 1;
93 7 if (shuffler_task != NULL) {
94 8 VERBOSE_PRINTK_STRING("Stopping rcu_torture_shuffle task");
95 9 kthread_stop(shuffler_task);
9610 }
9711 shuffler_task = NULL;
9812
9913 if (writer_task != NULL) {
10014 VERBOSE_PRINTK_STRING("Stopping rcu_torture_writer task");
10115 kthread_stop(writer_task);
10216 }
10317 writer_task = NULL;
10418
10519 if (reader_tasks != NULL) {
10620 for (i = 0; i < nrealreaders; i++) {
10721 if (reader_tasks[i] != NULL) {
10822 VERBOSE_PRINTK_STRING(
10923 "Stopping rcu_torture_reader task");
11024 kthread_stop(reader_tasks[i]);
11125 }
11226 reader_tasks[i] = NULL;
11327 }
11428 kfree(reader_tasks);
11529 reader_tasks = NULL;
11630 }
11731 rcu_torture_current = NULL;
11832
11933 if (fakewriter_tasks != NULL) {
12034 for (i = 0; i < nfakewriters; i++) {
12135 if (fakewriter_tasks[i] != NULL) {
12236 VERBOSE_PRINTK_STRING(
12337 "Stopping rcu_torture_fakewriter task");
12438 kthread_stop(fakewriter_tasks[i]);
12539 }
12640 fakewriter_tasks[i] = NULL;
12741 }
12842 kfree(fakewriter_tasks);
12943 fakewriter_tasks = NULL;
13044 }
13145
13246 if (stats_task != NULL) {
13347 VERBOSE_PRINTK_STRING("Stopping rcu_torture_stats task");
13448 kthread_stop(stats_task);
13549 }
13650 stats_task = NULL;
13751
13852 /* Wait for all RCU callbacks to fire. */
13953 rcu_barrier();
14054
14155 rcu_torture_stats_print(); /* -After- the stats thread is stopped! */
14256
14357 if (cur_ops->cleanup != NULL)
14458 cur_ops->cleanup();
14559 if (atomic_read(&n_rcu_torture_error))
14660 rcu_torture_print_module_parms("End of test: FAILURE");
14761 else
14862 rcu_torture_print_module_parms("End of test: SUCCESS");
14963 }
150
151Line 6 sets a global variable that prevents any RCU callbacks from
152re-posting themselves. This will not be necessary in most cases, since
153RCU callbacks rarely include calls to call_rcu(). However, the rcutorture
154module is an exception to this rule, and therefore needs to set this
155global variable.
156
157Lines 7-50 stop all the kernel tasks associated with the rcutorture
158module. Therefore, once execution reaches line 53, no more rcutorture
159RCU callbacks will be posted. The rcu_barrier() call on line 53 waits
160for any pre-existing callbacks to complete.
161
162Then lines 55-62 print status and do operation-specific cleanup, and
163then return, permitting the module-unload operation to be completed.
164
165Quick Quiz #2: Is there any other situation where rcu_barrier() might
166 be required?
167
168Your module might have additional complications. For example, if your
169module invokes call_rcu() from timers, you will need to first cancel all
170the timers, and only then invoke rcu_barrier() to wait for any remaining
171RCU callbacks to complete.
172
173
174Implementing rcu_barrier()
175
176Dipankar Sarma's implementation of rcu_barrier() makes use of the fact
177that RCU callbacks are never reordered once queued on one of the per-CPU
178queues. His implementation queues an RCU callback on each of the per-CPU
179callback queues, and then waits until they have all started executing, at
180which point, all earlier RCU callbacks are guaranteed to have completed.
181
182The original code for rcu_barrier() was as follows:
183
184 1 void rcu_barrier(void)
185 2 {
186 3 BUG_ON(in_interrupt());
187 4 /* Take cpucontrol mutex to protect against CPU hotplug */
188 5 mutex_lock(&rcu_barrier_mutex);
189 6 init_completion(&rcu_barrier_completion);
190 7 atomic_set(&rcu_barrier_cpu_count, 0);
191 8 on_each_cpu(rcu_barrier_func, NULL, 0, 1);
192 9 wait_for_completion(&rcu_barrier_completion);
19310 mutex_unlock(&rcu_barrier_mutex);
19411 }
195
196Line 3 verifies that the caller is in process context, and lines 5 and 10
197use rcu_barrier_mutex to ensure that only one rcu_barrier() is using the
198global completion and counters at a time, which are initialized on lines
1996 and 7. Line 8 causes each CPU to invoke rcu_barrier_func(), which is
200shown below. Note that the final "1" in on_each_cpu()'s argument list
201ensures that all the calls to rcu_barrier_func() will have completed
202before on_each_cpu() returns. Line 9 then waits for the completion.
203
204This code was rewritten in 2008 to support rcu_barrier_bh() and
205rcu_barrier_sched() in addition to the original rcu_barrier().
206
207The rcu_barrier_func() runs on each CPU, where it invokes call_rcu()
208to post an RCU callback, as follows:
209
210 1 static void rcu_barrier_func(void *notused)
211 2 {
212 3 int cpu = smp_processor_id();
213 4 struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
214 5 struct rcu_head *head;
215 6
216 7 head = &rdp->barrier;
217 8 atomic_inc(&rcu_barrier_cpu_count);
218 9 call_rcu(head, rcu_barrier_callback);
21910 }
220
221Lines 3 and 4 locate RCU's internal per-CPU rcu_data structure,
222which contains the struct rcu_head that needed for the later call to
223call_rcu(). Line 7 picks up a pointer to this struct rcu_head, and line
2248 increments a global counter. This counter will later be decremented
225by the callback. Line 9 then registers the rcu_barrier_callback() on
226the current CPU's queue.
227
228The rcu_barrier_callback() function simply atomically decrements the
229rcu_barrier_cpu_count variable and finalizes the completion when it
230reaches zero, as follows:
231
232 1 static void rcu_barrier_callback(struct rcu_head *notused)
233 2 {
234 3 if (atomic_dec_and_test(&rcu_barrier_cpu_count))
235 4 complete(&rcu_barrier_completion);
236 5 }
237
238Quick Quiz #3: What happens if CPU 0's rcu_barrier_func() executes
239 immediately (thus incrementing rcu_barrier_cpu_count to the
240 value one), but the other CPU's rcu_barrier_func() invocations
241 are delayed for a full grace period? Couldn't this result in
242 rcu_barrier() returning prematurely?
243
244
245rcu_barrier() Summary
246
247The rcu_barrier() primitive has seen relatively little use, since most
248code using RCU is in the core kernel rather than in modules. However, if
249you are using RCU from an unloadable module, you need to use rcu_barrier()
250so that your module may be safely unloaded.
251
252
253Answers to Quick Quizzes
254
255Quick Quiz #1: Why is there no srcu_barrier()?
256
257Answer: Since there is no call_srcu(), there can be no outstanding SRCU
258 callbacks. Therefore, there is no need to wait for them.
259
260Quick Quiz #2: Is there any other situation where rcu_barrier() might
261 be required?
262
263Answer: Interestingly enough, rcu_barrier() was not originally
264 implemented for module unloading. Nikita Danilov was using
265 RCU in a filesystem, which resulted in a similar situation at
266 filesystem-unmount time. Dipankar Sarma coded up rcu_barrier()
267 in response, so that Nikita could invoke it during the
268 filesystem-unmount process.
269
270 Much later, yours truly hit the RCU module-unload problem when
271 implementing rcutorture, and found that rcu_barrier() solves
272 this problem as well.
273
274Quick Quiz #3: What happens if CPU 0's rcu_barrier_func() executes
275 immediately (thus incrementing rcu_barrier_cpu_count to the
276 value one), but the other CPU's rcu_barrier_func() invocations
277 are delayed for a full grace period? Couldn't this result in
278 rcu_barrier() returning prematurely?
279
280Answer: This cannot happen. The reason is that on_each_cpu() has its last
281 argument, the wait flag, set to "1". This flag is passed through
282 to smp_call_function() and further to smp_call_function_on_cpu(),
283 causing this latter to spin until the cross-CPU invocation of
284 rcu_barrier_func() has completed. This by itself would prevent
285 a grace period from completing on non-CONFIG_PREEMPT kernels,
286 since each CPU must undergo a context switch (or other quiescent
287 state) before the grace period can complete. However, this is
288 of no use in CONFIG_PREEMPT kernels.
289
290 Therefore, on_each_cpu() disables preemption across its call
291 to smp_call_function() and also across the local call to
292 rcu_barrier_func(). This prevents the local CPU from context
293 switching, again preventing grace periods from completing. This
294 means that all CPUs have executed rcu_barrier_func() before
295 the first rcu_barrier_callback() can possibly execute, in turn
296 preventing rcu_barrier_cpu_count from prematurely reaching zero.
297
298 Currently, -rt implementations of RCU keep but a single global
299 queue for RCU callbacks, and thus do not suffer from this
300 problem. However, when the -rt RCU eventually does have per-CPU
301 callback queues, things will have to change. One simple change
302 is to add an rcu_read_lock() before line 8 of rcu_barrier()
303 and an rcu_read_unlock() after line 8 of this same function. If
304 you can think of a better change, please let me know!