xref: /freebsd/share/man/man9/atomic.9 (revision 2be1a816b9ff69588e55be0a84cbe2a31efc0f2f)
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.Os
28.Dt ATOMIC 9
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.rm LB RB La Ra
66.Sh DESCRIPTION
67Each of the atomic operations is guaranteed to be atomic in the presence of
68interrupts.
69They can be used to implement reference counts or as building blocks for more
70advanced synchronization primitives such as mutexes.
71.Ss Types
72Each atomic operation operates on a specific
73.Fa type .
74The type to use is indicated in the function name.
75The available types that can be used are:
76.Pp
77.Bl -tag -offset indent -width short -compact
78.It Li int
79unsigned integer
80.It Li long
81unsigned long integer
82.It Li ptr
83unsigned integer the size of a pointer
84.It Li 32
85unsigned 32-bit integer
86.It Li 64
87unsigned 64-bit integer
88.El
89.Pp
90For example, the function to atomically add two integers is called
91.Fn atomic_add_int .
92.Pp
93Certain architectures also provide operations for types smaller than
94.Dq Li int .
95.Pp
96.Bl -tag -offset indent -width short -compact
97.It Li char
98unsigned character
99.It Li short
100unsigned short integer
101.It Li 8
102unsigned 8-bit integer
103.It Li 16
104unsigned 16-bit integer
105.El
106.Pp
107These must not be used in MI code because the instructions to implement them
108efficiently may not be available.
109.Ss Memory Barriers
110Memory barriers are used to guarantee the order of data accesses in
111two ways.
112First, they specify hints to the compiler to not re-order or optimize the
113operations.
114Second, on architectures that do not guarantee ordered data accesses,
115special instructions or special variants of instructions are used to indicate
116to the processor that data accesses need to occur in a certain order.
117As a result, most of the atomic operations have three variants in order to
118include optional memory barriers.
119The first form just performs the operation without any explicit barriers.
120The second form uses a read memory barrier, and the third variant uses a write
121memory barrier.
122.Pp
123The second variant of each operation includes a read memory barrier.
124This barrier ensures that the effects of this operation are completed before the
125effects of any later data accesses.
126As a result, the operation is said to have acquire semantics as it acquires a
127pseudo-lock requiring further operations to wait until it has completed.
128To denote this, the suffix
129.Dq Li _acq
130is inserted into the function name immediately prior to the
131.Dq Li _ Ns Aq Fa type
132suffix.
133For example, to subtract two integers ensuring that any later writes will
134happen after the subtraction is performed, use
135.Fn atomic_subtract_acq_int .
136.Pp
137The third variant of each operation includes a write memory barrier.
138This ensures that all effects of all previous data accesses are completed
139before this operation takes place.
140As a result, the operation is said to have release semantics as it releases
141any pending data accesses to be completed before its operation is performed.
142To denote this, the suffix
143.Dq Li _rel
144is inserted into the function name immediately prior to the
145.Dq Li _ Ns Aq Fa type
146suffix.
147For example, to add two long integers ensuring that all previous
148writes will happen first, use
149.Fn atomic_add_rel_long .
150.Pp
151A practical example of using memory barriers is to ensure that data accesses
152that are protected by a lock are all performed while the lock is held.
153To achieve this, one would use a read barrier when acquiring the lock to
154guarantee that the lock is held before any protected operations are performed.
155Finally, one would use a write barrier when releasing the lock to ensure that
156all of the protected operations are completed before the lock is released.
157.Ss Multiple Processors
158The current set of atomic operations do not necessarily guarantee atomicity
159across multiple processors.
160To guarantee atomicity across processors, not only does the individual
161operation need to be atomic on the processor performing the operation, but
162the result of the operation needs to be pushed out to stable storage and the
163caches of all other processors on the system need to invalidate any cache
164lines that include the affected memory region.
165On the
166.Tn i386
167architecture, the cache coherency model requires that the hardware perform
168this task, thus the atomic operations are atomic across multiple processors.
169On the
170.Tn ia64
171architecture, coherency is only guaranteed for pages that are configured to
172using a caching policy of either uncached or write back.
173.Ss Semantics
174This section describes the semantics of each operation using a C like notation.
175.Bl -hang
176.It Fn atomic_add p v
177.Bd -literal -compact
178*p += v;
179.Ed
180.It Fn atomic_clear p v
181.Bd -literal -compact
182*p &= ~v;
183.Ed
184.It Fn atomic_cmpset dst old new
185.Bd -literal -compact
186if (*dst == old) {
187	*dst = new;
188	return 1;
189} else
190	return 0;
191.Ed
192.El
193.Pp
194The
195.Fn atomic_cmpset
196functions are not implemented for the types
197.Dq Li char ,
198.Dq Li short ,
199.Dq Li 8 ,
200and
201.Dq Li 16 .
202.Bl -hang
203.It Fn atomic_fetchadd p v
204.Bd -literal -compact
205tmp = *p;
206*p += v;
207return tmp;
208.Ed
209.El
210.Pp
211The
212.Fn atomic_fetchadd
213functions are only implemented for the types
214.Dq Li int ,
215.Dq Li long
216and
217.Dq Li 32
218and do not have any variants with memory barriers at this time.
219.Bl -hang
220.It Fn atomic_load addr
221.Bd -literal -compact
222return (*addr)
223.Ed
224.El
225.Pp
226The
227.Fn atomic_load
228functions always have acquire semantics.
229.Bl -hang
230.It Fn atomic_readandclear addr
231.Bd -literal -compact
232temp = *addr;
233*addr = 0;
234return (temp);
235.Ed
236.El
237.Pp
238The
239.Fn atomic_readandclear
240functions are not implemented for the types
241.Dq Li char ,
242.Dq Li short ,
243.Dq Li ptr ,
244.Dq Li 8 ,
245and
246.Dq Li 16
247and do
248not have any variants with memory barriers at this time.
249.Bl -hang
250.It Fn atomic_set p v
251.Bd -literal -compact
252*p |= v;
253.Ed
254.It Fn atomic_subtract p v
255.Bd -literal -compact
256*p -= v;
257.Ed
258.It Fn atomic_store p v
259.Bd -literal -compact
260*p = v;
261.Ed
262.El
263.Pp
264The
265.Fn atomic_store
266functions always have release semantics.
267.Pp
268The type
269.Dq Li 64
270is currently not implemented for any of the atomic operations on the
271.Tn arm ,
272.Tn i386 ,
273and
274.Tn powerpc
275architectures.
276.Sh RETURN VALUES
277The
278.Fn atomic_cmpset
279function
280returns the result of the compare operation.
281The
282.Fn atomic_fetchadd ,
283.Fn atomic_load ,
284and
285.Fn atomic_readandclear
286functions
287return the value at the specified address.
288.Sh EXAMPLES
289This example uses the
290.Fn atomic_cmpset_acq_ptr
291and
292.Fn atomic_set_ptr
293functions to obtain a sleep mutex and handle recursion.
294Since the
295.Va mtx_lock
296member of a
297.Vt "struct mtx"
298is a pointer, the
299.Dq Li ptr
300type is used.
301.Bd -literal
302/* Try to obtain mtx_lock once. */
303#define _obtain_lock(mp, tid)						\\
304	atomic_cmpset_acq_ptr(&(mp)->mtx_lock, MTX_UNOWNED, (tid))
305
306/* Get a sleep lock, deal with recursion inline. */
307#define _get_sleep_lock(mp, tid, opts, file, line) do {			\\
308	uintptr_t _tid = (uintptr_t)(tid);				\\
309									\\
310	if (!_obtain_lock(mp, tid)) {					\\
311		if (((mp)->mtx_lock & MTX_FLAGMASK) != _tid)		\\
312			_mtx_lock_sleep((mp), _tid, (opts), (file), (line));\\
313		else {							\\
314			atomic_set_ptr(&(mp)->mtx_lock, MTX_RECURSE);	\\
315			(mp)->mtx_recurse++;				\\
316		}							\\
317	}								\\
318} while (0)
319.Ed
320.Sh HISTORY
321The
322.Fn atomic_add ,
323.Fn atomic_clear ,
324.Fn atomic_set ,
325and
326.Fn atomic_subtract
327operations were first introduced in
328.Fx 3.0 .
329This first set only supported the types
330.Dq Li char ,
331.Dq Li short ,
332.Dq Li int ,
333and
334.Dq Li long .
335The
336.Fn atomic_cmpset ,
337.Fn atomic_load ,
338.Fn atomic_readandclear ,
339and
340.Fn atomic_store
341operations were added in
342.Fx 5.0 .
343The types
344.Dq Li 8 ,
345.Dq Li 16 ,
346.Dq Li 32 ,
347.Dq Li 64 ,
348and
349.Dq Li ptr
350and all of the acquire and release variants
351were added in
352.Fx 5.0
353as well.
354The
355.Fn atomic_fetchadd
356operations were added in
357.Fx 6.0 .
358