xref: /freebsd/share/man/man9/atomic.9 (revision c6ec7d31830ab1c80edae95ad5e4b9dba10c47ac)
1.\" Copyright (c) 2000-2001 John H. Baldwin <jhb@FreeBSD.org>
2.\" All rights reserved.
3.\"
4.\" Redistribution and use in source and binary forms, with or without
5.\" modification, are permitted provided that the following conditions
6.\" are met:
7.\" 1. Redistributions of source code must retain the above copyright
8.\"    notice, this list of conditions and the following disclaimer.
9.\" 2. Redistributions in binary form must reproduce the above copyright
10.\"    notice, this list of conditions and the following disclaimer in the
11.\"    documentation and/or other materials provided with the distribution.
12.\"
13.\" THIS SOFTWARE IS PROVIDED BY THE DEVELOPERS ``AS IS'' AND ANY EXPRESS OR
14.\" IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
15.\" OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
16.\" IN NO EVENT SHALL THE DEVELOPERS BE LIABLE FOR ANY DIRECT, INDIRECT,
17.\" INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
18.\" NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
19.\" DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
20.\" THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
21.\" (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
22.\" THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
23.\"
24.\" $FreeBSD$
25.\"
26.Dd September 27, 2005
27.Dt ATOMIC 9
28.Os
29.Sh NAME
30.Nm atomic_add ,
31.Nm atomic_clear ,
32.Nm atomic_cmpset ,
33.Nm atomic_fetchadd ,
34.Nm atomic_load ,
35.Nm atomic_readandclear ,
36.Nm atomic_set ,
37.Nm atomic_subtract ,
38.Nm atomic_store
39.Nd atomic operations
40.Sh SYNOPSIS
41.In sys/types.h
42.In machine/atomic.h
43.Ft void
44.Fn atomic_add_[acq_|rel_]<type> "volatile <type> *p" "<type> v"
45.Ft void
46.Fn atomic_clear_[acq_|rel_]<type> "volatile <type> *p" "<type> v"
47.Ft int
48.Fo atomic_cmpset_[acq_|rel_]<type>
49.Fa "volatile <type> *dst"
50.Fa "<type> old"
51.Fa "<type> new"
52.Fc
53.Ft <type>
54.Fn atomic_fetchadd_<type> "volatile <type> *p" "<type> v"
55.Ft <type>
56.Fn atomic_load_acq_<type> "volatile <type> *p"
57.Ft <type>
58.Fn atomic_readandclear_<type> "volatile <type> *p"
59.Ft void
60.Fn atomic_set_[acq_|rel_]<type> "volatile <type> *p" "<type> v"
61.Ft void
62.Fn atomic_subtract_[acq_|rel_]<type> "volatile <type> *p" "<type> v"
63.Ft void
64.Fn atomic_store_rel_<type> "volatile <type> *p" "<type> v"
65.Sh DESCRIPTION
66Each of the atomic operations is guaranteed to be atomic in the presence of
67interrupts.
68They can be used to implement reference counts or as building blocks for more
69advanced synchronization primitives such as mutexes.
70.Ss Types
71Each atomic operation operates on a specific
72.Fa type .
73The type to use is indicated in the function name.
74The available types that can be used are:
75.Pp
76.Bl -tag -offset indent -width short -compact
77.It Li int
78unsigned integer
79.It Li long
80unsigned long integer
81.It Li ptr
82unsigned integer the size of a pointer
83.It Li 32
84unsigned 32-bit integer
85.It Li 64
86unsigned 64-bit integer
87.El
88.Pp
89For example, the function to atomically add two integers is called
90.Fn atomic_add_int .
91.Pp
92Certain architectures also provide operations for types smaller than
93.Dq Li int .
94.Pp
95.Bl -tag -offset indent -width short -compact
96.It Li char
97unsigned character
98.It Li short
99unsigned short integer
100.It Li 8
101unsigned 8-bit integer
102.It Li 16
103unsigned 16-bit integer
104.El
105.Pp
106These must not be used in MI code because the instructions to implement them
107efficiently may not be available.
108.Ss Memory Barriers
109Memory barriers are used to guarantee the order of data accesses in
110two ways.
111First, they specify hints to the compiler to not re-order or optimize the
112operations.
113Second, on architectures that do not guarantee ordered data accesses,
114special instructions or special variants of instructions are used to indicate
115to the processor that data accesses need to occur in a certain order.
116As a result, most of the atomic operations have three variants in order to
117include optional memory barriers.
118The first form just performs the operation without any explicit barriers.
119The second form uses a read memory barrier, and the third variant uses a write
120memory barrier.
121.Pp
122The second variant of each operation includes a read memory barrier.
123This barrier ensures that the effects of this operation are completed before the
124effects of any later data accesses.
125As a result, the operation is said to have acquire semantics as it acquires a
126pseudo-lock requiring further operations to wait until it has completed.
127To denote this, the suffix
128.Dq Li _acq
129is inserted into the function name immediately prior to the
130.Dq Li _ Ns Aq Fa type
131suffix.
132For example, to subtract two integers ensuring that any later writes will
133happen after the subtraction is performed, use
134.Fn atomic_subtract_acq_int .
135.Pp
136The third variant of each operation includes a write memory barrier.
137This ensures that all effects of all previous data accesses are completed
138before this operation takes place.
139As a result, the operation is said to have release semantics as it releases
140any pending data accesses to be completed before its operation is performed.
141To denote this, the suffix
142.Dq Li _rel
143is inserted into the function name immediately prior to the
144.Dq Li _ Ns Aq Fa type
145suffix.
146For example, to add two long integers ensuring that all previous
147writes will happen first, use
148.Fn atomic_add_rel_long .
149.Pp
150A practical example of using memory barriers is to ensure that data accesses
151that are protected by a lock are all performed while the lock is held.
152To achieve this, one would use a read barrier when acquiring the lock to
153guarantee that the lock is held before any protected operations are performed.
154Finally, one would use a write barrier when releasing the lock to ensure that
155all of the protected operations are completed before the lock is released.
156.Ss Multiple Processors
157The current set of atomic operations do not necessarily guarantee atomicity
158across multiple processors.
159To guarantee atomicity across processors, not only does the individual
160operation need to be atomic on the processor performing the operation, but
161the result of the operation needs to be pushed out to stable storage and the
162caches of all other processors on the system need to invalidate any cache
163lines that include the affected memory region.
164On the
165.Tn i386
166architecture, the cache coherency model requires that the hardware perform
167this task, thus the atomic operations are atomic across multiple processors.
168On the
169.Tn ia64
170architecture, coherency is only guaranteed for pages that are configured to
171using a caching policy of either uncached or write back.
172.Ss Semantics
173This section describes the semantics of each operation using a C like notation.
174.Bl -hang
175.It Fn atomic_add p v
176.Bd -literal -compact
177*p += v;
178.Ed
179.It Fn atomic_clear p v
180.Bd -literal -compact
181*p &= ~v;
182.Ed
183.It Fn atomic_cmpset dst old new
184.Bd -literal -compact
185if (*dst == old) {
186	*dst = new;
187	return 1;
188} else
189	return 0;
190.Ed
191.El
192.Pp
193The
194.Fn atomic_cmpset
195functions are not implemented for the types
196.Dq Li char ,
197.Dq Li short ,
198.Dq Li 8 ,
199and
200.Dq Li 16 .
201.Bl -hang
202.It Fn atomic_fetchadd p v
203.Bd -literal -compact
204tmp = *p;
205*p += v;
206return tmp;
207.Ed
208.El
209.Pp
210The
211.Fn atomic_fetchadd
212functions are only implemented for the types
213.Dq Li int ,
214.Dq Li long
215and
216.Dq Li 32
217and do not have any variants with memory barriers at this time.
218.Bl -hang
219.It Fn atomic_load addr
220.Bd -literal -compact
221return (*addr)
222.Ed
223.El
224.Pp
225The
226.Fn atomic_load
227functions are only provided with acquire memory barriers.
228.Bl -hang
229.It Fn atomic_readandclear addr
230.Bd -literal -compact
231temp = *addr;
232*addr = 0;
233return (temp);
234.Ed
235.El
236.Pp
237The
238.Fn atomic_readandclear
239functions are not implemented for the types
240.Dq Li char ,
241.Dq Li short ,
242.Dq Li ptr ,
243.Dq Li 8 ,
244and
245.Dq Li 16
246and do
247not have any variants with memory barriers at this time.
248.Bl -hang
249.It Fn atomic_set p v
250.Bd -literal -compact
251*p |= v;
252.Ed
253.It Fn atomic_subtract p v
254.Bd -literal -compact
255*p -= v;
256.Ed
257.It Fn atomic_store p v
258.Bd -literal -compact
259*p = v;
260.Ed
261.El
262.Pp
263The
264.Fn atomic_store
265functions are only provided with release memory barriers.
266.Pp
267The type
268.Dq Li 64
269is currently not implemented for any of the atomic operations on the
270.Tn arm ,
271.Tn i386 ,
272and
273.Tn powerpc
274architectures.
275.Sh RETURN VALUES
276The
277.Fn atomic_cmpset
278function
279returns the result of the compare operation.
280The
281.Fn atomic_fetchadd ,
282.Fn atomic_load ,
283and
284.Fn atomic_readandclear
285functions
286return the value at the specified address.
287.Sh EXAMPLES
288This example uses the
289.Fn atomic_cmpset_acq_ptr
290and
291.Fn atomic_set_ptr
292functions to obtain a sleep mutex and handle recursion.
293Since the
294.Va mtx_lock
295member of a
296.Vt "struct mtx"
297is a pointer, the
298.Dq Li ptr
299type is used.
300.Bd -literal
301/* Try to obtain mtx_lock once. */
302#define _obtain_lock(mp, tid)						\\
303	atomic_cmpset_acq_ptr(&(mp)->mtx_lock, MTX_UNOWNED, (tid))
304
305/* Get a sleep lock, deal with recursion inline. */
306#define _get_sleep_lock(mp, tid, opts, file, line) do {			\\
307	uintptr_t _tid = (uintptr_t)(tid);				\\
308									\\
309	if (!_obtain_lock(mp, tid)) {					\\
310		if (((mp)->mtx_lock & MTX_FLAGMASK) != _tid)		\\
311			_mtx_lock_sleep((mp), _tid, (opts), (file), (line));\\
312		else {							\\
313			atomic_set_ptr(&(mp)->mtx_lock, MTX_RECURSE);	\\
314			(mp)->mtx_recurse++;				\\
315		}							\\
316	}								\\
317} while (0)
318.Ed
319.Sh HISTORY
320The
321.Fn atomic_add ,
322.Fn atomic_clear ,
323.Fn atomic_set ,
324and
325.Fn atomic_subtract
326operations were first introduced in
327.Fx 3.0 .
328This first set only supported the types
329.Dq Li char ,
330.Dq Li short ,
331.Dq Li int ,
332and
333.Dq Li long .
334The
335.Fn atomic_cmpset ,
336.Fn atomic_load ,
337.Fn atomic_readandclear ,
338and
339.Fn atomic_store
340operations were added in
341.Fx 5.0 .
342The types
343.Dq Li 8 ,
344.Dq Li 16 ,
345.Dq Li 32 ,
346.Dq Li 64 ,
347and
348.Dq Li ptr
349and all of the acquire and release variants
350were added in
351.Fx 5.0
352as well.
353The
354.Fn atomic_fetchadd
355operations were added in
356.Fx 6.0 .
357