xref: /freebsd/share/man/man9/atomic.9 (revision 817420dc8eac7df799c78f5309b75092b7f7cd40)
1.\" Copyright (c) 2000 John H. Baldwin
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.Fd #include <machine/atomic.h>
41.Ft void
42.Fn atomic_add{acq_,rel_,}_<type> "volatile <type> *p" "<type> v"
43.Ft void
44.Fn atomic_clear{acq_,rel_,}_<type> "volatile <type> *p" "<type> v"
45.Ft int
46.Fo atomic_cmpset{acq_,rel_,}_<type>
47.Fa "volatile <type> *dst"
48.Fa "<type> old"
49.Fa "<type> new"
50.Fc
51.Ft <type>
52.Fn atomic_load_acq_<type> "volatile <type> *p"
53.Ft <type>
54.Fn atomic_readandclear_<type> "volatile <type> *p"
55.Ft void
56.Fn atomic_set{acq_,rel_,}_<type> "volatile <type> *p" "<type> v"
57.Ft void
58.Fn atomic_subtract{acq_,rel_},_<type> "volatile <type> *p" "<type> v"
59.Ft void
60.Fn atomic_store_rel_<type> "volatile <type> *p" "<type> v"
61.Sh DESCRIPTION
62Each of the atomic operations is guaranteed to be atomic in the presence of
63interrupts.
64They can be used to implement reference counts or as building blocks for more
65advanced synchronization primitives such as mutexes.
66.Ss Types
67Each atomic operation operates on a specific type.
68The type to use is indicated in the function name.
69The available types that can be used are:
70.Bl -tag -offset indent -width short
71.It char
72unsigned character
73.It short
74unsigned short integer
75.It int
76unsigned integer
77.It long
78unsigned long integer
79.It ptr
80unsigned integer the size of a pointer
81.It 8
82unsigned 8-bit integer
83.It 16
84unsigned 16-bit integer
85.It 32
86unsigned 32-bit integer
87.It 64
88unsigned 64-bit integer
89.El
90.Pp
91For example, the function to atomically add two integers is called
92.Fn atomic_add_int .
93.Ss Memory Barriers
94Memory barriers are used to guarantee the order the order of data accesses in
95two ways.
96First, they specify hints to the compiler to not re-order or optimize the
97operations.
98Secondly, on architectures that do not guarantee ordered data accesses,
99special instructions or special variants of instructions are used to indicate
100to the processor that data accesses need to occur in a certain order.
101As a result, most of the atomic operations have three variants in order to
102include optional memory barriers.
103The first form just performs the operation without any explicit barriers.
104The second form uses a read memory barrier, and the final variant uses a write
105memory barrier.
106.Pp
107The second variant of each operation includes a read memory barrier.
108This barrier ensures that the effects of this operation are completed before the
109effects of any later data accesses.
110As a result, the operation is said to have acquire semantics as it acquires a
111pseudo-lock requiring further operations to wait until it has completed.
112To denote this, the suffix
113.Dq _acq
114is inserted into the function name immediately prior to the
115.Em _type
116suffix.
117For example, to subtract two integers ensuring that any later writes will
118happen after the subtraction is performed, use
119.Fn atomic_subtract_acq_int .
120.Pp
121The third variant of each operation includes a write memory barrier.
122This ensures that all effects of all previous data accesses are completed
123before this operation takes place.
124As a result, the operation is said to have release semantics as it releases
125any pending data accesses to be completed before its operation is performed.
126To denote this, the suffix
127.Dq _rel
128is inserted into the function name immediately prior to the
129.Em _type
130suffix.
131For example, to add two long integers ensuring that all previous
132writes will happen first, use
133.Fn atomic_add_rel_long .
134.Pp
135A practical example of using memory barriers is to ensure that data accesses
136that are protected by a lock are all performed while the lock is held.
137To achieve this, one would use a read barrier when acquiring the lock to
138guarantee that the lock is held before any protected operations are performed.
139Finally, one would use a write barrier when releasing the lock to ensure that
140all of the protected operations are completed before the lock is released.
141.Pp
142.Ss Multiple Processors
143The current set of atomic operations do not necessarily guarantee atomicity
144across multiple processors.
145To guarantee atomicity across processors, not only does the individual
146operation need to be atomic on the processor performing the operation, but the
147the result of the operation needs to be pushed out to stable storage and the
148caches of all other processors on the system need to invalidate any cache
149lines that include the affected memory region.
150On the
151.Tn i386
152architecture, the cache coherency model requires that the hardware perform
153this task, thus the atomic operations are atomic across multiple processors.
154On the
155.Tn ia64
156architecture, coherency is only guaranteed for pages that are configured to
157using a caching policy of either uncached or write back.
158.Ss Semantics
159This section describes the semantics of each operation using a C like notation.
160.Bl -hang
161.It Fn atomic_add "p" "v"
162.Bd -literal
163*p += v;
164.Ed
165.It Fn atomic_clear "p" "v"
166.Bd -literal
167*p &= ~v;
168.Ed
169.It Fn atomic_cmpset "dst" "old" "new"
170.Bd -literal
171if (*dst == old) {
172	*dst = new;
173	return 1;
174} else
175	return 0;
176.Ed
177.El
178.Pp
179The
180.Fn atomic_cmpset
181functions are not implemented for the types char, short, 8, and 16.
182.Bl -hang
183.It Fn atomic_load "addr"
184.Bd -literal
185return (*addr)
186.Ed
187.El
188.Pp
189The
190.Fn atomic_load
191functions always have acquire semantics.
192.Bl -hang
193.It Fn atomic_readandclear "addr"
194.Bd -literal
195temp = *addr;
196*addr = 0;
197return (temp);
198.Ed
199.El
200.Pp
201The
202.Fn atomic_readandclear
203functions are not implemented for the types char, short, ptr, 8, and 16 and do
204not have any variants with memory barriers at this time.
205.Bl -hang
206.It Fn atomic_set "p" "v"
207.Bd -literal
208*p |= v;
209.Ed
210.It Fn atomic_subtract "p" "v"
211.Bd -literal
212*p -= v;
213.Ed
214.It Fn atomic_store "p" "v"
215.Bd -literal
216*p = v;
217.Ed
218.El
219.Pp
220The
221.Fn atomic_store
222functions always have release semantics.
223.Pp
224The type
225.Dq 64
226is currently not implemented for any of the atomic operations on the
227.Tn i386
228architecture.
229.Sh RETURN VALUES
230.Fn atomic_cmpset
231returns the result of the compare operation.
232.Fn atomic_load
233and
234.Fn atomic_readandclear
235return the value at the specified address.
236.Sh EXAMPLES
237This example uses the
238.Fn atomic_cmpset_acq_ptr
239and
240.Fn atomic_set_ptr
241functions to obtain a sleep mutex and handle recursion.
242Since the
243.Va mtx_lock
244member of a
245.Li struct mtx
246is a pointer, the
247.Dq ptr
248type is used.
249.Bd -literal
250#define _obtain_lock(mp, tid)						\\
251	atomic_cmpset_acq_ptr(&(mp)->mtx_lock, (void *)MTX_UNOWNED, (tid))
252
253/* Get a sleep lock, deal with recursion inline. */
254#define	_getlock_sleep(mp, tid, type) do {				\\
255	if (!_obtain_lock(mp, tid)) {					\\
256		if (((mp)->mtx_lock & MTX_FLAGMASK) != ((uintptr_t)(tid)))\\
257			mtx_enter_hard(mp, (type) & MTX_HARDOPTS, 0);	\\
258		else {							\\
259			atomic_set_ptr(&(mp)->mtx_lock, MTX_RECURSE);	\\
260			(mp)->mtx_recurse++;				\\
261		}							\\
262	}								\\
263} while (0)
264.Ed
265.Sh HISTORY
266The
267.Fn atomic_add ,
268.Fn atomic_clear ,
269.Fn atomic_set ,
270and
271.Fn atomic_subtract
272operations were first introduced in
273.Fx 3.0 .
274This first set only suppored the types char, short, int, and long.
275The
276.Fn atomic_cmpset ,
277.Fn atomic_load ,
278.Fn atomic_readandclear ,
279and
280.Fn atomic_store
281operations were added in
282.Fx 5.0 .
283The types 8, 16, 32, 64, and ptr and all of the acquire and release variants
284were added in
285.Fx 5.0
286as well.
287