xref: /freebsd/share/man/man9/atomic.9 (revision f0adf7f5cdd241db2f2c817683191a6ef64a4e95)
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 October 27, 2000
27.Os
28.Dt ATOMIC 9
29.Sh NAME
30.Nm atomic_add ,
31.Nm atomic_clear ,
32.Nm atomic_cmpset ,
33.Nm atomic_load ,
34.Nm atomic_readandclear ,
35.Nm atomic_set ,
36.Nm atomic_subtract ,
37.Nm atomic_store
38.Nd atomic operations
39.Sh SYNOPSIS
40.In sys/types.h
41.In machine/atomic.h
42.Ft void
43.Fn atomic_add_[acq_|rel_]<type> "volatile <type> *p" "<type> v"
44.Ft void
45.Fn atomic_clear_[acq_|rel_]<type> "volatile <type> *p" "<type> v"
46.Ft int
47.Fo atomic_cmpset_[acq_|rel_]<type>
48.Fa "volatile <type> *dst"
49.Fa "<type> old"
50.Fa "<type> new"
51.Fc
52.Ft <type>
53.Fn atomic_load_acq_<type> "volatile <type> *p"
54.Ft <type>
55.Fn atomic_readandclear_<type> "volatile <type> *p"
56.Ft void
57.Fn atomic_set_[acq_|rel_]<type> "volatile <type> *p" "<type> v"
58.Ft void
59.Fn atomic_subtract_[acq_|rel_]<type> "volatile <type> *p" "<type> v"
60.Ft void
61.Fn atomic_store_rel_<type> "volatile <type> *p" "<type> v"
62.rm LB RB La Ra
63.Sh DESCRIPTION
64Each of the atomic operations is guaranteed to be atomic in the presence of
65interrupts.
66They can be used to implement reference counts or as building blocks for more
67advanced synchronization primitives such as mutexes.
68.Ss Types
69Each atomic operation operates on a specific
70.Fa type .
71The type to use is indicated in the function name.
72The available types that can be used are:
73.Pp
74.Bl -tag -offset indent -width short -compact
75.It Li int
76unsigned integer
77.It Li long
78unsigned long integer
79.It Li ptr
80unsigned integer the size of a pointer
81.It Li 32
82unsigned 32-bit integer
83.It Li 64
84unsigned 64-bit integer
85.El
86.Pp
87For example, the function to atomically add two integers is called
88.Fn atomic_add_int .
89.Pp
90Certain architectures also provide operations for types smaller than
91.Dq Li int .
92.Pp
93.Bl -tag -offset indent -width short -compact
94.It Li char
95unsigned character
96.It Li short
97unsigned short integer
98.It Li 8
99unsigned 8-bit integer
100.It Li 16
101unsigned 16-bit integer
102.El
103.Pp
104These must not be used in MI code because the instructions to implement them
105efficiently may not be available.
106.Ss Memory Barriers
107Memory barriers are used to guarantee the order of data accesses in
108two ways.
109First, they specify hints to the compiler to not re-order or optimize the
110operations.
111Second, on architectures that do not guarantee ordered data accesses,
112special instructions or special variants of instructions are used to indicate
113to the processor that data accesses need to occur in a certain order.
114As a result, most of the atomic operations have three variants in order to
115include optional memory barriers.
116The first form just performs the operation without any explicit barriers.
117The second form uses a read memory barrier, and the third variant uses a write
118memory barrier.
119.Pp
120The second variant of each operation includes a read memory barrier.
121This barrier ensures that the effects of this operation are completed before the
122effects of any later data accesses.
123As a result, the operation is said to have acquire semantics as it acquires a
124pseudo-lock requiring further operations to wait until it has completed.
125To denote this, the suffix
126.Dq Li _acq
127is inserted into the function name immediately prior to the
128.Dq Li _ Ns Aq Fa type
129suffix.
130For example, to subtract two integers ensuring that any later writes will
131happen after the subtraction is performed, use
132.Fn atomic_subtract_acq_int .
133.Pp
134The third variant of each operation includes a write memory barrier.
135This ensures that all effects of all previous data accesses are completed
136before this operation takes place.
137As a result, the operation is said to have release semantics as it releases
138any pending data accesses to be completed before its operation is performed.
139To denote this, the suffix
140.Dq Li _rel
141is inserted into the function name immediately prior to the
142.Dq Li _ Ns Aq Fa type
143suffix.
144For example, to add two long integers ensuring that all previous
145writes will happen first, use
146.Fn atomic_add_rel_long .
147.Pp
148A practical example of using memory barriers is to ensure that data accesses
149that are protected by a lock are all performed while the lock is held.
150To achieve this, one would use a read barrier when acquiring the lock to
151guarantee that the lock is held before any protected operations are performed.
152Finally, one would use a write barrier when releasing the lock to ensure that
153all of the protected operations are completed before the lock is released.
154.Ss Multiple Processors
155The current set of atomic operations do not necessarily guarantee atomicity
156across multiple processors.
157To guarantee atomicity across processors, not only does the individual
158operation need to be atomic on the processor performing the operation, but
159the result of the operation needs to be pushed out to stable storage and the
160caches of all other processors on the system need to invalidate any cache
161lines that include the affected memory region.
162On the
163.Tn i386
164architecture, the cache coherency model requires that the hardware perform
165this task, thus the atomic operations are atomic across multiple processors.
166On the
167.Tn ia64
168architecture, coherency is only guaranteed for pages that are configured to
169using a caching policy of either uncached or write back.
170.Ss Semantics
171This section describes the semantics of each operation using a C like notation.
172.Bl -hang
173.It Fn atomic_add p v
174.Bd -literal -compact
175*p += v;
176.Ed
177.It Fn atomic_clear p v
178.Bd -literal -compact
179*p &= ~v;
180.Ed
181.It Fn atomic_cmpset dst old new
182.Bd -literal -compact
183if (*dst == old) {
184	*dst = new;
185	return 1;
186} else
187	return 0;
188.Ed
189.El
190.Pp
191The
192.Fn atomic_cmpset
193functions are not implemented for the types
194.Dq Li char ,
195.Dq Li short ,
196.Dq Li 8 ,
197and
198.Dq Li 16 .
199.Bl -hang
200.It Fn atomic_load addr
201.Bd -literal -compact
202return (*addr)
203.Ed
204.El
205.Pp
206The
207.Fn atomic_load
208functions always have acquire semantics.
209.Bl -hang
210.It Fn atomic_readandclear addr
211.Bd -literal -compact
212temp = *addr;
213*addr = 0;
214return (temp);
215.Ed
216.El
217.Pp
218The
219.Fn atomic_readandclear
220functions are not implemented for the types
221.Dq Li char ,
222.Dq Li short ,
223.Dq Li ptr ,
224.Dq Li 8 ,
225and
226.Dq Li 16
227and do
228not have any variants with memory barriers at this time.
229.Bl -hang
230.It Fn atomic_set p v
231.Bd -literal -compact
232*p |= v;
233.Ed
234.It Fn atomic_subtract p v
235.Bd -literal -compact
236*p -= v;
237.Ed
238.It Fn atomic_store p v
239.Bd -literal -compact
240*p = v;
241.Ed
242.El
243.Pp
244The
245.Fn atomic_store
246functions always have release semantics.
247.Pp
248The type
249.Dq Li 64
250is currently not implemented for any of the atomic operations on the
251.Tn i386
252architecture.
253.Sh RETURN VALUES
254The
255.Fn atomic_cmpset
256function
257returns the result of the compare operation.
258The
259.Fn atomic_load
260and
261.Fn atomic_readandclear
262functions
263return the value at the specified address.
264.Sh EXAMPLES
265This example uses the
266.Fn atomic_cmpset_acq_ptr
267and
268.Fn atomic_set_ptr
269functions to obtain a sleep mutex and handle recursion.
270Since the
271.Va mtx_lock
272member of a
273.Vt "struct mtx"
274is a pointer, the
275.Dq Li ptr
276type is used.
277.Bd -literal
278#define _obtain_lock(mp, tid)						\\
279	atomic_cmpset_acq_ptr(&(mp)->mtx_lock, (void *)MTX_UNOWNED, (tid))
280
281/* Get a sleep lock, deal with recursion inline. */
282#define	_getlock_sleep(mp, tid, type) do {				\\
283	if (!_obtain_lock(mp, tid)) {					\\
284		if (((mp)->mtx_lock & MTX_FLAGMASK) != ((uintptr_t)(tid)))\\
285			mtx_enter_hard(mp, (type) & MTX_HARDOPTS, 0);	\\
286		else {							\\
287			atomic_set_ptr(&(mp)->mtx_lock, MTX_RECURSE);	\\
288			(mp)->mtx_recurse++;				\\
289		}							\\
290	}								\\
291} while (0)
292.Ed
293.Sh HISTORY
294The
295.Fn atomic_add ,
296.Fn atomic_clear ,
297.Fn atomic_set ,
298and
299.Fn atomic_subtract
300operations were first introduced in
301.Fx 3.0 .
302This first set only supported the types
303.Dq Li char ,
304.Dq Li short ,
305.Dq Li int ,
306and
307.Dq Li long .
308The
309.Fn atomic_cmpset ,
310.Fn atomic_load ,
311.Fn atomic_readandclear ,
312and
313.Fn atomic_store
314operations were added in
315.Fx 5.0 .
316The types
317.Dq Li 8 ,
318.Dq Li 16 ,
319.Dq Li 32 ,
320.Dq Li 64 ,
321and
322.Dq Li ptr ,
323and all of the acquire and release variants
324were added in
325.Fx 5.0
326as well.
327