About Kernel Documentation Linux Kernel Contact Linux Resources Linux Blog

Documentation / RCU / whatisRCU.txt




Custom Search

Based on kernel version 4.13.3. Page generated on 2017-09-23 13:56 EST.

1	Please note that the "What is RCU?" LWN series is an excellent place
2	to start learning about RCU:
3	
4	1.	What is RCU, Fundamentally?  http://lwn.net/Articles/262464/
5	2.	What is RCU? Part 2: Usage   http://lwn.net/Articles/263130/
6	3.	RCU part 3: the RCU API      http://lwn.net/Articles/264090/
7	4.	The RCU API, 2010 Edition    http://lwn.net/Articles/418853/
8		2010 Big API Table           http://lwn.net/Articles/419086/
9	5.	The RCU API, 2014 Edition    http://lwn.net/Articles/609904/
10		2014 Big API Table           http://lwn.net/Articles/609973/
11	
12	
13	What is RCU?
14	
15	RCU is a synchronization mechanism that was added to the Linux kernel
16	during the 2.5 development effort that is optimized for read-mostly
17	situations.  Although RCU is actually quite simple once you understand it,
18	getting there can sometimes be a challenge.  Part of the problem is that
19	most of the past descriptions of RCU have been written with the mistaken
20	assumption that there is "one true way" to describe RCU.  Instead,
21	the experience has been that different people must take different paths
22	to arrive at an understanding of RCU.  This document provides several
23	different paths, as follows:
24	
25	1.	RCU OVERVIEW
26	2.	WHAT IS RCU'S CORE API?
27	3.	WHAT ARE SOME EXAMPLE USES OF CORE RCU API?
28	4.	WHAT IF MY UPDATING THREAD CANNOT BLOCK?
29	5.	WHAT ARE SOME SIMPLE IMPLEMENTATIONS OF RCU?
30	6.	ANALOGY WITH READER-WRITER LOCKING
31	7.	FULL LIST OF RCU APIs
32	8.	ANSWERS TO QUICK QUIZZES
33	
34	People who prefer starting with a conceptual overview should focus on
35	Section 1, though most readers will profit by reading this section at
36	some point.  People who prefer to start with an API that they can then
37	experiment with should focus on Section 2.  People who prefer to start
38	with example uses should focus on Sections 3 and 4.  People who need to
39	understand the RCU implementation should focus on Section 5, then dive
40	into the kernel source code.  People who reason best by analogy should
41	focus on Section 6.  Section 7 serves as an index to the docbook API
42	documentation, and Section 8 is the traditional answer key.
43	
44	So, start with the section that makes the most sense to you and your
45	preferred method of learning.  If you need to know everything about
46	everything, feel free to read the whole thing -- but if you are really
47	that type of person, you have perused the source code and will therefore
48	never need this document anyway.  ;-)
49	
50	
51	1.  RCU OVERVIEW
52	
53	The basic idea behind RCU is to split updates into "removal" and
54	"reclamation" phases.  The removal phase removes references to data items
55	within a data structure (possibly by replacing them with references to
56	new versions of these data items), and can run concurrently with readers.
57	The reason that it is safe to run the removal phase concurrently with
58	readers is the semantics of modern CPUs guarantee that readers will see
59	either the old or the new version of the data structure rather than a
60	partially updated reference.  The reclamation phase does the work of reclaiming
61	(e.g., freeing) the data items removed from the data structure during the
62	removal phase.  Because reclaiming data items can disrupt any readers
63	concurrently referencing those data items, the reclamation phase must
64	not start until readers no longer hold references to those data items.
65	
66	Splitting the update into removal and reclamation phases permits the
67	updater to perform the removal phase immediately, and to defer the
68	reclamation phase until all readers active during the removal phase have
69	completed, either by blocking until they finish or by registering a
70	callback that is invoked after they finish.  Only readers that are active
71	during the removal phase need be considered, because any reader starting
72	after the removal phase will be unable to gain a reference to the removed
73	data items, and therefore cannot be disrupted by the reclamation phase.
74	
75	So the typical RCU update sequence goes something like the following:
76	
77	a.	Remove pointers to a data structure, so that subsequent
78		readers cannot gain a reference to it.
79	
80	b.	Wait for all previous readers to complete their RCU read-side
81		critical sections.
82	
83	c.	At this point, there cannot be any readers who hold references
84		to the data structure, so it now may safely be reclaimed
85		(e.g., kfree()d).
86	
87	Step (b) above is the key idea underlying RCU's deferred destruction.
88	The ability to wait until all readers are done allows RCU readers to
89	use much lighter-weight synchronization, in some cases, absolutely no
90	synchronization at all.  In contrast, in more conventional lock-based
91	schemes, readers must use heavy-weight synchronization in order to
92	prevent an updater from deleting the data structure out from under them.
93	This is because lock-based updaters typically update data items in place,
94	and must therefore exclude readers.  In contrast, RCU-based updaters
95	typically take advantage of the fact that writes to single aligned
96	pointers are atomic on modern CPUs, allowing atomic insertion, removal,
97	and replacement of data items in a linked structure without disrupting
98	readers.  Concurrent RCU readers can then continue accessing the old
99	versions, and can dispense with the atomic operations, memory barriers,
100	and communications cache misses that are so expensive on present-day
101	SMP computer systems, even in absence of lock contention.
102	
103	In the three-step procedure shown above, the updater is performing both
104	the removal and the reclamation step, but it is often helpful for an
105	entirely different thread to do the reclamation, as is in fact the case
106	in the Linux kernel's directory-entry cache (dcache).  Even if the same
107	thread performs both the update step (step (a) above) and the reclamation
108	step (step (c) above), it is often helpful to think of them separately.
109	For example, RCU readers and updaters need not communicate at all,
110	but RCU provides implicit low-overhead communication between readers
111	and reclaimers, namely, in step (b) above.
112	
113	So how the heck can a reclaimer tell when a reader is done, given
114	that readers are not doing any sort of synchronization operations???
115	Read on to learn about how RCU's API makes this easy.
116	
117	
118	2.  WHAT IS RCU'S CORE API?
119	
120	The core RCU API is quite small:
121	
122	a.	rcu_read_lock()
123	b.	rcu_read_unlock()
124	c.	synchronize_rcu() / call_rcu()
125	d.	rcu_assign_pointer()
126	e.	rcu_dereference()
127	
128	There are many other members of the RCU API, but the rest can be
129	expressed in terms of these five, though most implementations instead
130	express synchronize_rcu() in terms of the call_rcu() callback API.
131	
132	The five core RCU APIs are described below, the other 18 will be enumerated
133	later.  See the kernel docbook documentation for more info, or look directly
134	at the function header comments.
135	
136	rcu_read_lock()
137	
138		void rcu_read_lock(void);
139	
140		Used by a reader to inform the reclaimer that the reader is
141		entering an RCU read-side critical section.  It is illegal
142		to block while in an RCU read-side critical section, though
143		kernels built with CONFIG_PREEMPT_RCU can preempt RCU
144		read-side critical sections.  Any RCU-protected data structure
145		accessed during an RCU read-side critical section is guaranteed to
146		remain unreclaimed for the full duration of that critical section.
147		Reference counts may be used in conjunction with RCU to maintain
148		longer-term references to data structures.
149	
150	rcu_read_unlock()
151	
152		void rcu_read_unlock(void);
153	
154		Used by a reader to inform the reclaimer that the reader is
155		exiting an RCU read-side critical section.  Note that RCU
156		read-side critical sections may be nested and/or overlapping.
157	
158	synchronize_rcu()
159	
160		void synchronize_rcu(void);
161	
162		Marks the end of updater code and the beginning of reclaimer
163		code.  It does this by blocking until all pre-existing RCU
164		read-side critical sections on all CPUs have completed.
165		Note that synchronize_rcu() will -not- necessarily wait for
166		any subsequent RCU read-side critical sections to complete.
167		For example, consider the following sequence of events:
168	
169		         CPU 0                  CPU 1                 CPU 2
170		     ----------------- ------------------------- ---------------
171		 1.  rcu_read_lock()
172		 2.                    enters synchronize_rcu()
173		 3.                                               rcu_read_lock()
174		 4.  rcu_read_unlock()
175		 5.                     exits synchronize_rcu()
176		 6.                                              rcu_read_unlock()
177	
178		To reiterate, synchronize_rcu() waits only for ongoing RCU
179		read-side critical sections to complete, not necessarily for
180		any that begin after synchronize_rcu() is invoked.
181	
182		Of course, synchronize_rcu() does not necessarily return
183		-immediately- after the last pre-existing RCU read-side critical
184		section completes.  For one thing, there might well be scheduling
185		delays.  For another thing, many RCU implementations process
186		requests in batches in order to improve efficiencies, which can
187		further delay synchronize_rcu().
188	
189		Since synchronize_rcu() is the API that must figure out when
190		readers are done, its implementation is key to RCU.  For RCU
191		to be useful in all but the most read-intensive situations,
192		synchronize_rcu()'s overhead must also be quite small.
193	
194		The call_rcu() API is a callback form of synchronize_rcu(),
195		and is described in more detail in a later section.  Instead of
196		blocking, it registers a function and argument which are invoked
197		after all ongoing RCU read-side critical sections have completed.
198		This callback variant is particularly useful in situations where
199		it is illegal to block or where update-side performance is
200		critically important.
201	
202		However, the call_rcu() API should not be used lightly, as use
203		of the synchronize_rcu() API generally results in simpler code.
204		In addition, the synchronize_rcu() API has the nice property
205		of automatically limiting update rate should grace periods
206		be delayed.  This property results in system resilience in face
207		of denial-of-service attacks.  Code using call_rcu() should limit
208		update rate in order to gain this same sort of resilience.  See
209		checklist.txt for some approaches to limiting the update rate.
210	
211	rcu_assign_pointer()
212	
213		typeof(p) rcu_assign_pointer(p, typeof(p) v);
214	
215		Yes, rcu_assign_pointer() -is- implemented as a macro, though it
216		would be cool to be able to declare a function in this manner.
217		(Compiler experts will no doubt disagree.)
218	
219		The updater uses this function to assign a new value to an
220		RCU-protected pointer, in order to safely communicate the change
221		in value from the updater to the reader.  This function returns
222		the new value, and also executes any memory-barrier instructions
223		required for a given CPU architecture.
224	
225		Perhaps just as important, it serves to document (1) which
226		pointers are protected by RCU and (2) the point at which a
227		given structure becomes accessible to other CPUs.  That said,
228		rcu_assign_pointer() is most frequently used indirectly, via
229		the _rcu list-manipulation primitives such as list_add_rcu().
230	
231	rcu_dereference()
232	
233		typeof(p) rcu_dereference(p);
234	
235		Like rcu_assign_pointer(), rcu_dereference() must be implemented
236		as a macro.
237	
238		The reader uses rcu_dereference() to fetch an RCU-protected
239		pointer, which returns a value that may then be safely
240		dereferenced.  Note that rcu_dereference() does not actually
241		dereference the pointer, instead, it protects the pointer for
242		later dereferencing.  It also executes any needed memory-barrier
243		instructions for a given CPU architecture.  Currently, only Alpha
244		needs memory barriers within rcu_dereference() -- on other CPUs,
245		it compiles to nothing, not even a compiler directive.
246	
247		Common coding practice uses rcu_dereference() to copy an
248		RCU-protected pointer to a local variable, then dereferences
249		this local variable, for example as follows:
250	
251			p = rcu_dereference(head.next);
252			return p->data;
253	
254		However, in this case, one could just as easily combine these
255		into one statement:
256	
257			return rcu_dereference(head.next)->data;
258	
259		If you are going to be fetching multiple fields from the
260		RCU-protected structure, using the local variable is of
261		course preferred.  Repeated rcu_dereference() calls look
262		ugly, do not guarantee that the same pointer will be returned
263		if an update happened while in the critical section, and incur
264		unnecessary overhead on Alpha CPUs.
265	
266		Note that the value returned by rcu_dereference() is valid
267		only within the enclosing RCU read-side critical section.
268		For example, the following is -not- legal:
269	
270			rcu_read_lock();
271			p = rcu_dereference(head.next);
272			rcu_read_unlock();
273			x = p->address;	/* BUG!!! */
274			rcu_read_lock();
275			y = p->data;	/* BUG!!! */
276			rcu_read_unlock();
277	
278		Holding a reference from one RCU read-side critical section
279		to another is just as illegal as holding a reference from
280		one lock-based critical section to another!  Similarly,
281		using a reference outside of the critical section in which
282		it was acquired is just as illegal as doing so with normal
283		locking.
284	
285		As with rcu_assign_pointer(), an important function of
286		rcu_dereference() is to document which pointers are protected by
287		RCU, in particular, flagging a pointer that is subject to changing
288		at any time, including immediately after the rcu_dereference().
289		And, again like rcu_assign_pointer(), rcu_dereference() is
290		typically used indirectly, via the _rcu list-manipulation
291		primitives, such as list_for_each_entry_rcu().
292	
293	The following diagram shows how each API communicates among the
294	reader, updater, and reclaimer.
295	
296	
297		    rcu_assign_pointer()
298		    			    +--------+
299		    +---------------------->| reader |---------+
300		    |                       +--------+         |
301		    |                           |              |
302		    |                           |              | Protect:
303		    |                           |              | rcu_read_lock()
304		    |                           |              | rcu_read_unlock()
305		    |        rcu_dereference()  |              |
306	       +---------+                      |              |
307	       | updater |<---------------------+              |
308	       +---------+                                     V
309		    |                                    +-----------+
310		    +----------------------------------->| reclaimer |
311		    				         +-----------+
312		      Defer:
313		      synchronize_rcu() & call_rcu()
314	
315	
316	The RCU infrastructure observes the time sequence of rcu_read_lock(),
317	rcu_read_unlock(), synchronize_rcu(), and call_rcu() invocations in
318	order to determine when (1) synchronize_rcu() invocations may return
319	to their callers and (2) call_rcu() callbacks may be invoked.  Efficient
320	implementations of the RCU infrastructure make heavy use of batching in
321	order to amortize their overhead over many uses of the corresponding APIs.
322	
323	There are no fewer than three RCU mechanisms in the Linux kernel; the
324	diagram above shows the first one, which is by far the most commonly used.
325	The rcu_dereference() and rcu_assign_pointer() primitives are used for
326	all three mechanisms, but different defer and protect primitives are
327	used as follows:
328	
329		Defer			Protect
330	
331	a.	synchronize_rcu()	rcu_read_lock() / rcu_read_unlock()
332		call_rcu()		rcu_dereference()
333	
334	b.	synchronize_rcu_bh()	rcu_read_lock_bh() / rcu_read_unlock_bh()
335		call_rcu_bh()		rcu_dereference_bh()
336	
337	c.	synchronize_sched()	rcu_read_lock_sched() / rcu_read_unlock_sched()
338		call_rcu_sched()	preempt_disable() / preempt_enable()
339					local_irq_save() / local_irq_restore()
340					hardirq enter / hardirq exit
341					NMI enter / NMI exit
342					rcu_dereference_sched()
343	
344	These three mechanisms are used as follows:
345	
346	a.	RCU applied to normal data structures.
347	
348	b.	RCU applied to networking data structures that may be subjected
349		to remote denial-of-service attacks.
350	
351	c.	RCU applied to scheduler and interrupt/NMI-handler tasks.
352	
353	Again, most uses will be of (a).  The (b) and (c) cases are important
354	for specialized uses, but are relatively uncommon.
355	
356	
357	3.  WHAT ARE SOME EXAMPLE USES OF CORE RCU API?
358	
359	This section shows a simple use of the core RCU API to protect a
360	global pointer to a dynamically allocated structure.  More-typical
361	uses of RCU may be found in listRCU.txt, arrayRCU.txt, and NMI-RCU.txt.
362	
363		struct foo {
364			int a;
365			char b;
366			long c;
367		};
368		DEFINE_SPINLOCK(foo_mutex);
369	
370		struct foo __rcu *gbl_foo;
371	
372		/*
373		 * Create a new struct foo that is the same as the one currently
374		 * pointed to by gbl_foo, except that field "a" is replaced
375		 * with "new_a".  Points gbl_foo to the new structure, and
376		 * frees up the old structure after a grace period.
377		 *
378		 * Uses rcu_assign_pointer() to ensure that concurrent readers
379		 * see the initialized version of the new structure.
380		 *
381		 * Uses synchronize_rcu() to ensure that any readers that might
382		 * have references to the old structure complete before freeing
383		 * the old structure.
384		 */
385		void foo_update_a(int new_a)
386		{
387			struct foo *new_fp;
388			struct foo *old_fp;
389	
390			new_fp = kmalloc(sizeof(*new_fp), GFP_KERNEL);
391			spin_lock(&foo_mutex);
392			old_fp = rcu_dereference_protected(gbl_foo, lockdep_is_held(&foo_mutex));
393			*new_fp = *old_fp;
394			new_fp->a = new_a;
395			rcu_assign_pointer(gbl_foo, new_fp);
396			spin_unlock(&foo_mutex);
397			synchronize_rcu();
398			kfree(old_fp);
399		}
400	
401		/*
402		 * Return the value of field "a" of the current gbl_foo
403		 * structure.  Use rcu_read_lock() and rcu_read_unlock()
404		 * to ensure that the structure does not get deleted out
405		 * from under us, and use rcu_dereference() to ensure that
406		 * we see the initialized version of the structure (important
407		 * for DEC Alpha and for people reading the code).
408		 */
409		int foo_get_a(void)
410		{
411			int retval;
412	
413			rcu_read_lock();
414			retval = rcu_dereference(gbl_foo)->a;
415			rcu_read_unlock();
416			return retval;
417		}
418	
419	So, to sum up:
420	
421	o	Use rcu_read_lock() and rcu_read_unlock() to guard RCU
422		read-side critical sections.
423	
424	o	Within an RCU read-side critical section, use rcu_dereference()
425		to dereference RCU-protected pointers.
426	
427	o	Use some solid scheme (such as locks or semaphores) to
428		keep concurrent updates from interfering with each other.
429	
430	o	Use rcu_assign_pointer() to update an RCU-protected pointer.
431		This primitive protects concurrent readers from the updater,
432		-not- concurrent updates from each other!  You therefore still
433		need to use locking (or something similar) to keep concurrent
434		rcu_assign_pointer() primitives from interfering with each other.
435	
436	o	Use synchronize_rcu() -after- removing a data element from an
437		RCU-protected data structure, but -before- reclaiming/freeing
438		the data element, in order to wait for the completion of all
439		RCU read-side critical sections that might be referencing that
440		data item.
441	
442	See checklist.txt for additional rules to follow when using RCU.
443	And again, more-typical uses of RCU may be found in listRCU.txt,
444	arrayRCU.txt, and NMI-RCU.txt.
445	
446	
447	4.  WHAT IF MY UPDATING THREAD CANNOT BLOCK?
448	
449	In the example above, foo_update_a() blocks until a grace period elapses.
450	This is quite simple, but in some cases one cannot afford to wait so
451	long -- there might be other high-priority work to be done.
452	
453	In such cases, one uses call_rcu() rather than synchronize_rcu().
454	The call_rcu() API is as follows:
455	
456		void call_rcu(struct rcu_head * head,
457			      void (*func)(struct rcu_head *head));
458	
459	This function invokes func(head) after a grace period has elapsed.
460	This invocation might happen from either softirq or process context,
461	so the function is not permitted to block.  The foo struct needs to
462	have an rcu_head structure added, perhaps as follows:
463	
464		struct foo {
465			int a;
466			char b;
467			long c;
468			struct rcu_head rcu;
469		};
470	
471	The foo_update_a() function might then be written as follows:
472	
473		/*
474		 * Create a new struct foo that is the same as the one currently
475		 * pointed to by gbl_foo, except that field "a" is replaced
476		 * with "new_a".  Points gbl_foo to the new structure, and
477		 * frees up the old structure after a grace period.
478		 *
479		 * Uses rcu_assign_pointer() to ensure that concurrent readers
480		 * see the initialized version of the new structure.
481		 *
482		 * Uses call_rcu() to ensure that any readers that might have
483		 * references to the old structure complete before freeing the
484		 * old structure.
485		 */
486		void foo_update_a(int new_a)
487		{
488			struct foo *new_fp;
489			struct foo *old_fp;
490	
491			new_fp = kmalloc(sizeof(*new_fp), GFP_KERNEL);
492			spin_lock(&foo_mutex);
493			old_fp = rcu_dereference_protected(gbl_foo, lockdep_is_held(&foo_mutex));
494			*new_fp = *old_fp;
495			new_fp->a = new_a;
496			rcu_assign_pointer(gbl_foo, new_fp);
497			spin_unlock(&foo_mutex);
498			call_rcu(&old_fp->rcu, foo_reclaim);
499		}
500	
501	The foo_reclaim() function might appear as follows:
502	
503		void foo_reclaim(struct rcu_head *rp)
504		{
505			struct foo *fp = container_of(rp, struct foo, rcu);
506	
507			foo_cleanup(fp->a);
508	
509			kfree(fp);
510		}
511	
512	The container_of() primitive is a macro that, given a pointer into a
513	struct, the type of the struct, and the pointed-to field within the
514	struct, returns a pointer to the beginning of the struct.
515	
516	The use of call_rcu() permits the caller of foo_update_a() to
517	immediately regain control, without needing to worry further about the
518	old version of the newly updated element.  It also clearly shows the
519	RCU distinction between updater, namely foo_update_a(), and reclaimer,
520	namely foo_reclaim().
521	
522	The summary of advice is the same as for the previous section, except
523	that we are now using call_rcu() rather than synchronize_rcu():
524	
525	o	Use call_rcu() -after- removing a data element from an
526		RCU-protected data structure in order to register a callback
527		function that will be invoked after the completion of all RCU
528		read-side critical sections that might be referencing that
529		data item.
530	
531	If the callback for call_rcu() is not doing anything more than calling
532	kfree() on the structure, you can use kfree_rcu() instead of call_rcu()
533	to avoid having to write your own callback:
534	
535		kfree_rcu(old_fp, rcu);
536	
537	Again, see checklist.txt for additional rules governing the use of RCU.
538	
539	
540	5.  WHAT ARE SOME SIMPLE IMPLEMENTATIONS OF RCU?
541	
542	One of the nice things about RCU is that it has extremely simple "toy"
543	implementations that are a good first step towards understanding the
544	production-quality implementations in the Linux kernel.  This section
545	presents two such "toy" implementations of RCU, one that is implemented
546	in terms of familiar locking primitives, and another that more closely
547	resembles "classic" RCU.  Both are way too simple for real-world use,
548	lacking both functionality and performance.  However, they are useful
549	in getting a feel for how RCU works.  See kernel/rcupdate.c for a
550	production-quality implementation, and see:
551	
552		http://www.rdrop.com/users/paulmck/RCU
553	
554	for papers describing the Linux kernel RCU implementation.  The OLS'01
555	and OLS'02 papers are a good introduction, and the dissertation provides
556	more details on the current implementation as of early 2004.
557	
558	
559	5A.  "TOY" IMPLEMENTATION #1: LOCKING
560	
561	This section presents a "toy" RCU implementation that is based on
562	familiar locking primitives.  Its overhead makes it a non-starter for
563	real-life use, as does its lack of scalability.  It is also unsuitable
564	for realtime use, since it allows scheduling latency to "bleed" from
565	one read-side critical section to another.  It also assumes recursive
566	reader-writer locks:  If you try this with non-recursive locks, and
567	you allow nested rcu_read_lock() calls, you can deadlock.
568	
569	However, it is probably the easiest implementation to relate to, so is
570	a good starting point.
571	
572	It is extremely simple:
573	
574		static DEFINE_RWLOCK(rcu_gp_mutex);
575	
576		void rcu_read_lock(void)
577		{
578			read_lock(&rcu_gp_mutex);
579		}
580	
581		void rcu_read_unlock(void)
582		{
583			read_unlock(&rcu_gp_mutex);
584		}
585	
586		void synchronize_rcu(void)
587		{
588			write_lock(&rcu_gp_mutex);
589			write_unlock(&rcu_gp_mutex);
590		}
591	
592	[You can ignore rcu_assign_pointer() and rcu_dereference() without missing
593	much.  But here are simplified versions anyway.  And whatever you do,
594	don't forget about them when submitting patches making use of RCU!]
595	
596		#define rcu_assign_pointer(p, v) \
597		({ \
598			smp_store_release(&(p), (v)); \
599		})
600	
601		#define rcu_dereference(p) \
602		({ \
603			typeof(p) _________p1 = p; \
604			smp_read_barrier_depends(); \
605			(_________p1); \
606		})
607	
608	
609	The rcu_read_lock() and rcu_read_unlock() primitive read-acquire
610	and release a global reader-writer lock.  The synchronize_rcu()
611	primitive write-acquires this same lock, then immediately releases
612	it.  This means that once synchronize_rcu() exits, all RCU read-side
613	critical sections that were in progress before synchronize_rcu() was
614	called are guaranteed to have completed -- there is no way that
615	synchronize_rcu() would have been able to write-acquire the lock
616	otherwise.
617	
618	It is possible to nest rcu_read_lock(), since reader-writer locks may
619	be recursively acquired.  Note also that rcu_read_lock() is immune
620	from deadlock (an important property of RCU).  The reason for this is
621	that the only thing that can block rcu_read_lock() is a synchronize_rcu().
622	But synchronize_rcu() does not acquire any locks while holding rcu_gp_mutex,
623	so there can be no deadlock cycle.
624	
625	Quick Quiz #1:	Why is this argument naive?  How could a deadlock
626			occur when using this algorithm in a real-world Linux
627			kernel?  How could this deadlock be avoided?
628	
629	
630	5B.  "TOY" EXAMPLE #2: CLASSIC RCU
631	
632	This section presents a "toy" RCU implementation that is based on
633	"classic RCU".  It is also short on performance (but only for updates) and
634	on features such as hotplug CPU and the ability to run in CONFIG_PREEMPT
635	kernels.  The definitions of rcu_dereference() and rcu_assign_pointer()
636	are the same as those shown in the preceding section, so they are omitted.
637	
638		void rcu_read_lock(void) { }
639	
640		void rcu_read_unlock(void) { }
641	
642		void synchronize_rcu(void)
643		{
644			int cpu;
645	
646			for_each_possible_cpu(cpu)
647				run_on(cpu);
648		}
649	
650	Note that rcu_read_lock() and rcu_read_unlock() do absolutely nothing.
651	This is the great strength of classic RCU in a non-preemptive kernel:
652	read-side overhead is precisely zero, at least on non-Alpha CPUs.
653	And there is absolutely no way that rcu_read_lock() can possibly
654	participate in a deadlock cycle!
655	
656	The implementation of synchronize_rcu() simply schedules itself on each
657	CPU in turn.  The run_on() primitive can be implemented straightforwardly
658	in terms of the sched_setaffinity() primitive.  Of course, a somewhat less
659	"toy" implementation would restore the affinity upon completion rather
660	than just leaving all tasks running on the last CPU, but when I said
661	"toy", I meant -toy-!
662	
663	So how the heck is this supposed to work???
664	
665	Remember that it is illegal to block while in an RCU read-side critical
666	section.  Therefore, if a given CPU executes a context switch, we know
667	that it must have completed all preceding RCU read-side critical sections.
668	Once -all- CPUs have executed a context switch, then -all- preceding
669	RCU read-side critical sections will have completed.
670	
671	So, suppose that we remove a data item from its structure and then invoke
672	synchronize_rcu().  Once synchronize_rcu() returns, we are guaranteed
673	that there are no RCU read-side critical sections holding a reference
674	to that data item, so we can safely reclaim it.
675	
676	Quick Quiz #2:	Give an example where Classic RCU's read-side
677			overhead is -negative-.
678	
679	Quick Quiz #3:  If it is illegal to block in an RCU read-side
680			critical section, what the heck do you do in
681			PREEMPT_RT, where normal spinlocks can block???
682	
683	
684	6.  ANALOGY WITH READER-WRITER LOCKING
685	
686	Although RCU can be used in many different ways, a very common use of
687	RCU is analogous to reader-writer locking.  The following unified
688	diff shows how closely related RCU and reader-writer locking can be.
689	
690		@@ -5,5 +5,5 @@ struct el {
691		 	int data;
692		 	/* Other data fields */
693		 };
694		-rwlock_t listmutex;
695		+spinlock_t listmutex;
696		 struct el head;
697	
698		@@ -13,15 +14,15 @@
699			struct list_head *lp;
700			struct el *p;
701	
702		-	read_lock(&listmutex);
703		-	list_for_each_entry(p, head, lp) {
704		+	rcu_read_lock();
705		+	list_for_each_entry_rcu(p, head, lp) {
706				if (p->key == key) {
707					*result = p->data;
708		-			read_unlock(&listmutex);
709		+			rcu_read_unlock();
710					return 1;
711				}
712			}
713		-	read_unlock(&listmutex);
714		+	rcu_read_unlock();
715			return 0;
716		 }
717	
718		@@ -29,15 +30,16 @@
719		 {
720			struct el *p;
721	
722		-	write_lock(&listmutex);
723		+	spin_lock(&listmutex);
724			list_for_each_entry(p, head, lp) {
725				if (p->key == key) {
726		-			list_del(&p->list);
727		-			write_unlock(&listmutex);
728		+			list_del_rcu(&p->list);
729		+			spin_unlock(&listmutex);
730		+			synchronize_rcu();
731					kfree(p);
732					return 1;
733				}
734			}
735		-	write_unlock(&listmutex);
736		+	spin_unlock(&listmutex);
737			return 0;
738		 }
739	
740	Or, for those who prefer a side-by-side listing:
741	
742	 1 struct el {                          1 struct el {
743	 2   struct list_head list;             2   struct list_head list;
744	 3   long key;                          3   long key;
745	 4   spinlock_t mutex;                  4   spinlock_t mutex;
746	 5   int data;                          5   int data;
747	 6   /* Other data fields */            6   /* Other data fields */
748	 7 };                                   7 };
749	 8 rwlock_t listmutex;                  8 spinlock_t listmutex;
750	 9 struct el head;                      9 struct el head;
751	
752	 1 int search(long key, int *result)    1 int search(long key, int *result)
753	 2 {                                    2 {
754	 3   struct list_head *lp;              3   struct list_head *lp;
755	 4   struct el *p;                      4   struct el *p;
756	 5                                      5
757	 6   read_lock(&listmutex);             6   rcu_read_lock();
758	 7   list_for_each_entry(p, head, lp) { 7   list_for_each_entry_rcu(p, head, lp) {
759	 8     if (p->key == key) {             8     if (p->key == key) {
760	 9       *result = p->data;             9       *result = p->data;
761	10       read_unlock(&listmutex);      10       rcu_read_unlock();
762	11       return 1;                     11       return 1;
763	12     }                               12     }
764	13   }                                 13   }
765	14   read_unlock(&listmutex);          14   rcu_read_unlock();
766	15   return 0;                         15   return 0;
767	16 }                                   16 }
768	
769	 1 int delete(long key)                 1 int delete(long key)
770	 2 {                                    2 {
771	 3   struct el *p;                      3   struct el *p;
772	 4                                      4
773	 5   write_lock(&listmutex);            5   spin_lock(&listmutex);
774	 6   list_for_each_entry(p, head, lp) { 6   list_for_each_entry(p, head, lp) {
775	 7     if (p->key == key) {             7     if (p->key == key) {
776	 8       list_del(&p->list);            8       list_del_rcu(&p->list);
777	 9       write_unlock(&listmutex);      9       spin_unlock(&listmutex);
778	                                       10       synchronize_rcu();
779	10       kfree(p);                     11       kfree(p);
780	11       return 1;                     12       return 1;
781	12     }                               13     }
782	13   }                                 14   }
783	14   write_unlock(&listmutex);         15   spin_unlock(&listmutex);
784	15   return 0;                         16   return 0;
785	16 }                                   17 }
786	
787	Either way, the differences are quite small.  Read-side locking moves
788	to rcu_read_lock() and rcu_read_unlock, update-side locking moves from
789	a reader-writer lock to a simple spinlock, and a synchronize_rcu()
790	precedes the kfree().
791	
792	However, there is one potential catch: the read-side and update-side
793	critical sections can now run concurrently.  In many cases, this will
794	not be a problem, but it is necessary to check carefully regardless.
795	For example, if multiple independent list updates must be seen as
796	a single atomic update, converting to RCU will require special care.
797	
798	Also, the presence of synchronize_rcu() means that the RCU version of
799	delete() can now block.  If this is a problem, there is a callback-based
800	mechanism that never blocks, namely call_rcu() or kfree_rcu(), that can
801	be used in place of synchronize_rcu().
802	
803	
804	7.  FULL LIST OF RCU APIs
805	
806	The RCU APIs are documented in docbook-format header comments in the
807	Linux-kernel source code, but it helps to have a full list of the
808	APIs, since there does not appear to be a way to categorize them
809	in docbook.  Here is the list, by category.
810	
811	RCU list traversal:
812	
813		list_entry_rcu
814		list_first_entry_rcu
815		list_next_rcu
816		list_for_each_entry_rcu
817		list_for_each_entry_continue_rcu
818		hlist_first_rcu
819		hlist_next_rcu
820		hlist_pprev_rcu
821		hlist_for_each_entry_rcu
822		hlist_for_each_entry_rcu_bh
823		hlist_for_each_entry_continue_rcu
824		hlist_for_each_entry_continue_rcu_bh
825		hlist_nulls_first_rcu
826		hlist_nulls_for_each_entry_rcu
827		hlist_bl_first_rcu
828		hlist_bl_for_each_entry_rcu
829	
830	RCU pointer/list update:
831	
832		rcu_assign_pointer
833		list_add_rcu
834		list_add_tail_rcu
835		list_del_rcu
836		list_replace_rcu
837		hlist_add_behind_rcu
838		hlist_add_before_rcu
839		hlist_add_head_rcu
840		hlist_del_rcu
841		hlist_del_init_rcu
842		hlist_replace_rcu
843		list_splice_init_rcu()
844		hlist_nulls_del_init_rcu
845		hlist_nulls_del_rcu
846		hlist_nulls_add_head_rcu
847		hlist_bl_add_head_rcu
848		hlist_bl_del_init_rcu
849		hlist_bl_del_rcu
850		hlist_bl_set_first_rcu
851	
852	RCU:	Critical sections	Grace period		Barrier
853	
854		rcu_read_lock		synchronize_net		rcu_barrier
855		rcu_read_unlock		synchronize_rcu
856		rcu_dereference		synchronize_rcu_expedited
857		rcu_read_lock_held	call_rcu
858		rcu_dereference_check	kfree_rcu
859		rcu_dereference_protected
860	
861	bh:	Critical sections	Grace period		Barrier
862	
863		rcu_read_lock_bh	call_rcu_bh		rcu_barrier_bh
864		rcu_read_unlock_bh	synchronize_rcu_bh
865		rcu_dereference_bh	synchronize_rcu_bh_expedited
866		rcu_dereference_bh_check
867		rcu_dereference_bh_protected
868		rcu_read_lock_bh_held
869	
870	sched:	Critical sections	Grace period		Barrier
871	
872		rcu_read_lock_sched	synchronize_sched	rcu_barrier_sched
873		rcu_read_unlock_sched	call_rcu_sched
874		[preempt_disable]	synchronize_sched_expedited
875		[and friends]
876		rcu_read_lock_sched_notrace
877		rcu_read_unlock_sched_notrace
878		rcu_dereference_sched
879		rcu_dereference_sched_check
880		rcu_dereference_sched_protected
881		rcu_read_lock_sched_held
882	
883	
884	SRCU:	Critical sections	Grace period		Barrier
885	
886		srcu_read_lock		synchronize_srcu	srcu_barrier
887		srcu_read_unlock	call_srcu
888		srcu_dereference	synchronize_srcu_expedited
889		srcu_dereference_check
890		srcu_read_lock_held
891	
892	SRCU:	Initialization/cleanup
893		init_srcu_struct
894		cleanup_srcu_struct
895	
896	All:  lockdep-checked RCU-protected pointer access
897	
898		rcu_access_pointer
899		rcu_dereference_raw
900		RCU_LOCKDEP_WARN
901		rcu_sleep_check
902		RCU_NONIDLE
903	
904	See the comment headers in the source code (or the docbook generated
905	from them) for more information.
906	
907	However, given that there are no fewer than four families of RCU APIs
908	in the Linux kernel, how do you choose which one to use?  The following
909	list can be helpful:
910	
911	a.	Will readers need to block?  If so, you need SRCU.
912	
913	b.	What about the -rt patchset?  If readers would need to block
914		in an non-rt kernel, you need SRCU.  If readers would block
915		in a -rt kernel, but not in a non-rt kernel, SRCU is not
916		necessary.
917	
918	c.	Do you need to treat NMI handlers, hardirq handlers,
919		and code segments with preemption disabled (whether
920		via preempt_disable(), local_irq_save(), local_bh_disable(),
921		or some other mechanism) as if they were explicit RCU readers?
922		If so, RCU-sched is the only choice that will work for you.
923	
924	d.	Do you need RCU grace periods to complete even in the face
925		of softirq monopolization of one or more of the CPUs?  For
926		example, is your code subject to network-based denial-of-service
927		attacks?  If so, you need RCU-bh.
928	
929	e.	Is your workload too update-intensive for normal use of
930		RCU, but inappropriate for other synchronization mechanisms?
931		If so, consider SLAB_TYPESAFE_BY_RCU (which was originally
932		named SLAB_DESTROY_BY_RCU).  But please be careful!
933	
934	f.	Do you need read-side critical sections that are respected
935		even though they are in the middle of the idle loop, during
936		user-mode execution, or on an offlined CPU?  If so, SRCU is the
937		only choice that will work for you.
938	
939	g.	Otherwise, use RCU.
940	
941	Of course, this all assumes that you have determined that RCU is in fact
942	the right tool for your job.
943	
944	
945	8.  ANSWERS TO QUICK QUIZZES
946	
947	Quick Quiz #1:	Why is this argument naive?  How could a deadlock
948			occur when using this algorithm in a real-world Linux
949			kernel?  [Referring to the lock-based "toy" RCU
950			algorithm.]
951	
952	Answer:		Consider the following sequence of events:
953	
954			1.	CPU 0 acquires some unrelated lock, call it
955				"problematic_lock", disabling irq via
956				spin_lock_irqsave().
957	
958			2.	CPU 1 enters synchronize_rcu(), write-acquiring
959				rcu_gp_mutex.
960	
961			3.	CPU 0 enters rcu_read_lock(), but must wait
962				because CPU 1 holds rcu_gp_mutex.
963	
964			4.	CPU 1 is interrupted, and the irq handler
965				attempts to acquire problematic_lock.
966	
967			The system is now deadlocked.
968	
969			One way to avoid this deadlock is to use an approach like
970			that of CONFIG_PREEMPT_RT, where all normal spinlocks
971			become blocking locks, and all irq handlers execute in
972			the context of special tasks.  In this case, in step 4
973			above, the irq handler would block, allowing CPU 1 to
974			release rcu_gp_mutex, avoiding the deadlock.
975	
976			Even in the absence of deadlock, this RCU implementation
977			allows latency to "bleed" from readers to other
978			readers through synchronize_rcu().  To see this,
979			consider task A in an RCU read-side critical section
980			(thus read-holding rcu_gp_mutex), task B blocked
981			attempting to write-acquire rcu_gp_mutex, and
982			task C blocked in rcu_read_lock() attempting to
983			read_acquire rcu_gp_mutex.  Task A's RCU read-side
984			latency is holding up task C, albeit indirectly via
985			task B.
986	
987			Realtime RCU implementations therefore use a counter-based
988			approach where tasks in RCU read-side critical sections
989			cannot be blocked by tasks executing synchronize_rcu().
990	
991	Quick Quiz #2:	Give an example where Classic RCU's read-side
992			overhead is -negative-.
993	
994	Answer:		Imagine a single-CPU system with a non-CONFIG_PREEMPT
995			kernel where a routing table is used by process-context
996			code, but can be updated by irq-context code (for example,
997			by an "ICMP REDIRECT" packet).	The usual way of handling
998			this would be to have the process-context code disable
999			interrupts while searching the routing table.  Use of
1000			RCU allows such interrupt-disabling to be dispensed with.
1001			Thus, without RCU, you pay the cost of disabling interrupts,
1002			and with RCU you don't.
1003	
1004			One can argue that the overhead of RCU in this
1005			case is negative with respect to the single-CPU
1006			interrupt-disabling approach.  Others might argue that
1007			the overhead of RCU is merely zero, and that replacing
1008			the positive overhead of the interrupt-disabling scheme
1009			with the zero-overhead RCU scheme does not constitute
1010			negative overhead.
1011	
1012			In real life, of course, things are more complex.  But
1013			even the theoretical possibility of negative overhead for
1014			a synchronization primitive is a bit unexpected.  ;-)
1015	
1016	Quick Quiz #3:  If it is illegal to block in an RCU read-side
1017			critical section, what the heck do you do in
1018			PREEMPT_RT, where normal spinlocks can block???
1019	
1020	Answer:		Just as PREEMPT_RT permits preemption of spinlock
1021			critical sections, it permits preemption of RCU
1022			read-side critical sections.  It also permits
1023			spinlocks blocking while in RCU read-side critical
1024			sections.
1025	
1026			Why the apparent inconsistency?  Because it is it
1027			possible to use priority boosting to keep the RCU
1028			grace periods short if need be (for example, if running
1029			short of memory).  In contrast, if blocking waiting
1030			for (say) network reception, there is no way to know
1031			what should be boosted.  Especially given that the
1032			process we need to boost might well be a human being
1033			who just went out for a pizza or something.  And although
1034			a computer-operated cattle prod might arouse serious
1035			interest, it might also provoke serious objections.
1036			Besides, how does the computer know what pizza parlor
1037			the human being went to???
1038	
1039	
1040	ACKNOWLEDGEMENTS
1041	
1042	My thanks to the people who helped make this human-readable, including
1043	Jon Walpole, Josh Triplett, Serge Hallyn, Suzanne Wood, and Alan Stern.
1044	
1045	
1046	For more information, see http://www.rdrop.com/users/paulmck/RCU.
Hide Line Numbers
About Kernel Documentation Linux Kernel Contact Linux Resources Linux Blog

Information is copyright its respective author. All material is available from the Linux Kernel Source distributed under a GPL License. This page is provided as a free service by mjmwired.net.