2 .\" Copyright (c) 2001 Dag-Erling Coïdan Smørgrav
3 .\" All rights reserved.
5 .\" Redistribution and use in source and binary forms, with or without
6 .\" modification, are permitted provided that the following conditions
8 .\" 1. Redistributions of source code must retain the above copyright
9 .\" notice, this list of conditions and the following disclaimer.
10 .\" 2. Redistributions in binary form must reproduce the above copyright
11 .\" notice, this list of conditions and the following disclaimer in the
12 .\" documentation and/or other materials provided with the distribution.
14 .\" THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
15 .\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
16 .\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
17 .\" ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
18 .\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
19 .\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
20 .\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
21 .\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
22 .\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
23 .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
42 .Nm uma_zone_set_warning
50 .Fa "char *name" "int size"
51 .Fa "uma_ctor ctor" "uma_dtor dtor" "uma_init uminit" "uma_fini fini"
52 .Fa "int align" "uint16_t flags"
55 .Fn uma_zalloc "uma_zone_t zone" "int flags"
57 .Fn uma_zalloc_arg "uma_zone_t zone" "void *arg" "int flags"
59 .Fn uma_zfree "uma_zone_t zone" "void *item"
61 .Fn uma_zfree_arg "uma_zone_t zone" "void *item" "void *arg"
63 .Fn uma_find_refcnt "uma_zone_t zone" "void *item"
65 .Fn uma_zdestroy "uma_zone_t zone"
67 .Fn uma_zone_set_max "uma_zone_t zone" "int nitems"
69 .Fn uma_zone_get_max "uma_zone_t zone"
71 .Fn uma_zone_get_cur "uma_zone_t zone"
73 .Fn uma_zone_set_warning "uma_zone_t zone" "const char *warning"
75 The zone allocator provides an efficient interface for managing
76 dynamically-sized collections of items of similar size.
77 The zone allocator can work with preallocated zones as well as with
78 runtime-allocated ones, and is therefore available much earlier in the
79 boot process than other memory management routines.
81 A zone is an extensible collection of items of identical size.
82 The zone allocator keeps track of which items are in use and which
83 are not, and provides functions for allocating items from the zone and
84 for releasing them back (which makes them available for later use).
86 After the first allocation of an item,
87 it will have been cleared to zeroes, however subsequent allocations
88 will retain the contents as of the last free.
92 function creates a new zone from which items may then be allocated from.
95 argument is a text name of the zone for debugging and stats; this memory
96 should not be freed until the zone has been deallocated.
102 arguments are callback functions that are called by
103 the uma subsystem at the time of the call to
108 Their purpose is to provide hooks for initializing or
109 destroying things that need to be done at the time of the allocation
110 or release of a resource.
116 might be to adjust a global count of the number of objects allocated.
122 arguments are used to optimize the allocation of
123 objects from the zone.
124 They are called by the uma subsystem whenever
125 it needs to allocate or free several items to satisfy requests or memory
131 callbacks might be to
132 initialize and destroy mutexes contained within the object.
134 allow one to re-use already initialized mutexes when an object is returned
135 from the uma subsystem's object cache.
136 They are not called on each call to
140 but rather in a batch mode on several objects.
146 is a subset of the following flags:
147 .Bl -tag -width "foo"
148 .It Dv UMA_ZONE_NOFREE
149 Slabs of the zone are never returned back to VM.
150 .It Dv UMA_ZONE_REFCNT
151 Each item in the zone would have internal reference counter associated with it.
153 .Fn uma_find_refcnt .
154 .It Dv UMA_ZONE_NODUMP
155 Pages belonging to the zone will not be included into mini-dumps.
157 An allocation from zone would have
159 shadow copies, that are privately assigned to CPUs.
160 A CPU can address its private copy using base allocation address plus
161 multiple of current CPU id and
162 .Fn sizeof "struct pcpu" :
163 .Bd -literal -offset indent
164 foo_zone = uma_zcreate(..., UMA_ZONE_PCPU);
166 foo_base = uma_zalloc(foo_zone, ...);
169 foo_pcpu = (foo_t *)zpcpu_get(foo_base);
170 /* do something with foo_pcpu */
173 .It Dv UMA_ZONE_OFFPAGE
174 By default book-keeping of items within a slab is done in the slab page itself.
175 This flag explicitly tells subsystem that book-keeping structure should be
176 allocated separately from special internal zone.
177 This flag requires either
181 since subsystem requires a mechanism to find a book-keeping structure
182 to an item beeing freed.
183 The subsystem may choose to prefer offpage book-keeping for certain zones
185 .It Dv UMA_ZONE_ZINIT
186 The zone will have its
188 method set to internal method that initializes a new allocated slab
196 flag would not return zeroed memory on every
199 The zone should use an internal hash table to find slab book-keeping
200 structure where an allocation being freed belongs to.
201 .It Dv UMA_ZONE_VTOSLAB
202 The zone should use special field of
204 to find slab book-keeping structure where an allocation being freed belongs to.
205 .It Dv UMA_ZONE_MALLOC
210 The zone is for the VM subsystem.
213 To allocate an item from a zone, simply call
215 with a pointer to that zone
218 argument to selected flags as documented in
220 It will return a pointer to an item if successful,
223 in the rare case where all items in the zone are in use and the
224 allocator is unable to grow the zone
229 Items are released back to the zone from which they were allocated by
232 with a pointer to the zone and a pointer to the item.
246 specify an argument for the
250 functions, respectively.
252 If zone was created with
254 flag, then pointer to reference counter for an item can be retrieved with
261 can be destroyed using
263 freeing all memory that was allocated for the zone.
264 All items allocated from the zone with
266 must have been freed with
272 function limits the number of items
273 .Pq and therefore memory
274 that can be allocated to
278 argument specifies the requested upper limit number of items.
279 The effective limit is returned to the caller, as it may end up being higher
280 than requested due to the implementation rounding up to ensure all memory pages
281 allocated to the zone are utilised to capacity.
282 The limit applies to the total number of items in the zone, which includes
283 allocated items, free items and free items in the per-cpu caches.
284 On systems with more than one CPU it may not be possible to allocate
285 the specified number of items even when there is no shortage of memory,
286 because all of the remaining free items may be in the caches of the
287 other CPUs when the limit is hit.
291 function returns the effective upper limit number of items for a zone.
295 function returns the approximate current occupancy of the zone.
296 The returned value is approximate because appropriate synchronisation to
297 determine an exact value is not performed by the implementation.
298 This ensures low overhead at the expense of potentially stale data being used
302 .Fn uma_zone_set_warning
303 function sets a warning that will be printed on the system console when the
304 given zone becomes full and fails to allocate an item.
305 The warning will be printed not often than every five minutes.
306 Warnings can be turned off globally by setting the
313 function returns a pointer to an item, or
315 if the zone ran out of unused items
322 The zone allocator first appeared in
324 It was radically changed in
326 to function as a slab allocator.
329 The zone allocator was written by
331 The zone allocator was rewritten in large parts by
332 .An Jeff Roberson Aq jeff@FreeBSD.org
333 to function as a slab allocator.
335 This manual page was written by
336 .An Dag-Erling Sm\(/orgrav Aq des@FreeBSD.org .
338 .An Jeroen Ruigrok van der Werven Aq asmodai@FreeBSD.org .