xref: /netbsd-src/share/man/man9/uvm.9 (revision d48f14661dda8638fee055ba15d35bdfb29b9fa8)
1.\"	$NetBSD: uvm.9,v 1.74 2006/06/13 13:23:59 yamt Exp $
2.\"
3.\" Copyright (c) 1998 Matthew R. Green
4.\" All rights reserved.
5.\"
6.\" Redistribution and use in source and binary forms, with or without
7.\" modification, are permitted provided that the following conditions
8.\" are met:
9.\" 1. Redistributions of source code must retain the above copyright
10.\"    notice, this list of conditions and the following disclaimer.
11.\" 2. Redistributions in binary form must reproduce the above copyright
12.\"    notice, this list of conditions and the following disclaimer in the
13.\"    documentation and/or other materials provided with the distribution.
14.\" 3. The name of the author may not be used to endorse or promote products
15.\"    derived from this software without specific prior written permission.
16.\"
17.\" THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
18.\" IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
19.\" OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
20.\" IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
21.\" INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
22.\" BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
23.\" LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED
24.\" AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
25.\" OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
26.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
27.\" SUCH DAMAGE.
28.\"
29.Dd February 27, 2006
30.Dt UVM 9
31.Os
32.Sh NAME
33.Nm uvm
34.Nd virtual memory system external interface
35.Sh SYNOPSIS
36.In sys/param.h
37.In uvm/uvm.h
38.Sh DESCRIPTION
39The UVM virtual memory system manages access to the computer's memory
40resources.
41User processes and the kernel access these resources through
42UVM's external interface.
43UVM's external interface includes functions that:
44.Pp
45.Bl -hyphen -compact
46.It
47initialise UVM sub-systems
48.It
49manage virtual address spaces
50.It
51resolve page faults
52.It
53memory map files and devices
54.It
55perform uio-based I/O to virtual memory
56.It
57allocate and free kernel virtual memory
58.It
59allocate and free physical memory
60.El
61.Pp
62In addition to exporting these services, UVM has two kernel-level processes:
63pagedaemon and swapper.
64The pagedaemon process sleeps until physical memory becomes scarce.
65When that happens, pagedaemon is awoken.
66It scans physical memory, paging out and freeing memory that has not
67been recently used.
68The swapper process swaps in runnable processes that are currently swapped
69out, if there is room.
70.Pp
71There are also several miscellaneous functions.
72.Sh INITIALISATION
73.Ft void
74.br
75.Fn uvm_init "void" ;
76.Pp
77.Ft void
78.br
79.Fn uvm_init_limits "struct lwp *l" ;
80.Pp
81.Ft void
82.br
83.Fn uvm_setpagesize "void" ;
84.Pp
85.Ft void
86.br
87.Fn uvm_swap_init "void" ;
88.Pp
89.Fn uvm_init
90sets up the UVM system at system boot time, after the
91console has been setup.
92It initialises global state, the page, map, kernel virtual memory state,
93machine-dependent physical map, kernel memory allocator,
94pager and anonymous memory sub-systems, and then enables
95paging of kernel objects.
96.Pp
97.Fn uvm_init_limits
98initialises process limits for the named process.
99This is for use by the system startup for process zero, before any
100other processes are created.
101.Pp
102.Fn uvm_setpagesize
103initialises the uvmexp members pagesize (if not already done by
104machine-dependent code), pageshift and pagemask.
105It should be called by machine-dependent code early in the
106.Fn pmap_init
107call (see
108.Xr pmap 9 ) .
109.Pp
110.Fn uvm_swap_init
111initialises the swap sub-system.
112.Sh VIRTUAL ADDRESS SPACE MANAGEMENT
113.Ft int
114.br
115.Fn uvm_map "struct vm_map *map" "vaddr_t *startp" "vsize_t size" "struct uvm_object *uobj" "voff_t uoffset" "vsize_t align" "uvm_flag_t flags" ;
116.Pp
117.Ft void
118.br
119.Fn uvm_unmap "struct vm_map *map" "vaddr_t start" "vaddr_t end" ;
120.Pp
121.Ft int
122.br
123.Fn uvm_map_pageable "struct vm_map *map" "vaddr_t start" "vaddr_t end" "boolean_t new_pageable" "int lockflags" ;
124.Pp
125.Ft boolean_t
126.br
127.Fn uvm_map_checkprot "struct vm_map *map" "vaddr_t start" "vaddr_t end" "vm_prot_t protection" ;
128.Pp
129.Ft int
130.br
131.Fn uvm_map_protect "struct vm_map *map" "vaddr_t start" "vaddr_t end" "vm_prot_t new_prot" "boolean_t set_max" ;
132.Pp
133.Ft int
134.br
135.Fn uvm_deallocate "struct vm_map *map" "vaddr_t start" "vsize_t size" ;
136.Pp
137.Ft struct vmspace *
138.br
139.Fn uvmspace_alloc "vaddr_t min" "vaddr_t max" "int pageable" ;
140.Pp
141.Ft void
142.br
143.Fn uvmspace_exec "struct lwp *l" "vaddr_t start" "vaddr_t end" ;
144.Pp
145.Ft struct vmspace *
146.br
147.Fn uvmspace_fork "struct vmspace *vm" ;
148.Pp
149.Ft void
150.br
151.Fn uvmspace_free "struct vmspace *vm1" ;
152.Pp
153.Ft void
154.br
155.Fn uvmspace_share "struct proc *p1" "struct proc *p2" ;
156.Pp
157.Ft void
158.br
159.Fn uvmspace_unshare "struct lwp *l" ;
160.Pp
161.Ft boolean_t
162.br
163.Fn uvm_uarea_alloc "vaddr_t *uaddrp" ;
164.Pp
165.Ft void
166.br
167.Fn uvm_uarea_free "vaddr_t uaddr" ;
168.Pp
169.Fn uvm_map
170establishes a valid mapping in map
171.Fa map ,
172which must be unlocked.
173The new mapping has size
174.Fa size ,
175which must be a multiple of
176.Dv PAGE_SIZE .
177The
178.Fa uobj
179and
180.Fa uoffset
181arguments can have four meanings.
182When
183.Fa uobj
184is
185.Dv NULL
186and
187.Fa uoffset
188is
189.Dv UVM_UNKNOWN_OFFSET ,
190.Fn uvm_map
191does not use the machine-dependent
192.Dv PMAP_PREFER
193function.
194If
195.Fa uoffset
196is any other value, it is used as the hint to
197.Dv PMAP_PREFER .
198When
199.Fa uobj
200is not
201.Dv NULL
202and
203.Fa uoffset
204is
205.Dv UVM_UNKNOWN_OFFSET ,
206.Fn uvm_map
207finds the offset based upon the virtual address, passed as
208.Fa startp .
209If
210.Fa uoffset
211is any other value, we are doing a normal mapping at this offset.
212The start address of the map will be returned in
213.Fa startp .
214.Pp
215.Fa align
216specifies alignment of mapping unless
217.Dv UVM_FLAG_FIXED
218is specified in
219.Fa flags .
220.Fa align
221must be a power of 2.
222.Pp
223.Fa flags
224passed to
225.Fn uvm_map
226are typically created using the
227.Fn UVM_MAPFLAG "vm_prot_t prot" "vm_prot_t maxprot" "vm_inherit_t inh" "int advice" "int flags"
228macro, which uses the following values.
229The
230.Fa prot
231and
232.Fa maxprot
233can take are:
234.Bd -literal
235#define UVM_PROT_MASK   0x07    /* protection mask */
236#define UVM_PROT_NONE   0x00    /* protection none */
237#define UVM_PROT_ALL    0x07    /* everything */
238#define UVM_PROT_READ   0x01    /* read */
239#define UVM_PROT_WRITE  0x02    /* write */
240#define UVM_PROT_EXEC   0x04    /* exec */
241#define UVM_PROT_R      0x01    /* read */
242#define UVM_PROT_W      0x02    /* write */
243#define UVM_PROT_RW     0x03    /* read-write */
244#define UVM_PROT_X      0x04    /* exec */
245#define UVM_PROT_RX     0x05    /* read-exec */
246#define UVM_PROT_WX     0x06    /* write-exec */
247#define UVM_PROT_RWX    0x07    /* read-write-exec */
248.Ed
249.Pp
250The values that
251.Fa inh
252can take are:
253.Bd -literal
254#define UVM_INH_MASK    0x30    /* inherit mask */
255#define UVM_INH_SHARE   0x00    /* "share" */
256#define UVM_INH_COPY    0x10    /* "copy" */
257#define UVM_INH_NONE    0x20    /* "none" */
258#define UVM_INH_DONATE  0x30    /* "donate" \*[Lt]\*[Lt] not used */
259.Ed
260.Pp
261The values that
262.Fa advice
263can take are:
264.Bd -literal
265#define UVM_ADV_NORMAL     0x0  /* 'normal' */
266#define UVM_ADV_RANDOM     0x1  /* 'random' */
267#define UVM_ADV_SEQUENTIAL 0x2  /* 'sequential' */
268#define UVM_ADV_MASK       0x7  /* mask */
269.Ed
270.Pp
271The values that
272.Fa flags
273can take are:
274.Bd -literal
275#define UVM_FLAG_FIXED   0x010000 /* find space */
276#define UVM_FLAG_OVERLAY 0x020000 /* establish overlay */
277#define UVM_FLAG_NOMERGE 0x040000 /* don't merge map entries */
278#define UVM_FLAG_COPYONW 0x080000 /* set copy_on_write flag */
279#define UVM_FLAG_AMAPPAD 0x100000 /* for bss: pad amap to reduce malloc() */
280#define UVM_FLAG_TRYLOCK 0x200000 /* fail if we can not lock map */
281.Ed
282.Pp
283The
284.Dv UVM_MAPFLAG
285macro arguments can be combined with an or operator.
286There are several special purpose macros for checking protection
287combinations, e.g., the
288.Dv UVM_PROT_WX
289macro.
290There are also some additional macros to extract bits from the flags.
291The
292.Dv UVM_PROTECTION ,
293.Dv UVM_INHERIT ,
294.Dv UVM_MAXPROTECTION
295and
296.Dv UVM_ADVICE
297macros return the protection, inheritance, maximum protection and advice,
298respectively.
299.Fn uvm_map
300returns a standard UVM return value.
301.Pp
302.Fn uvm_unmap
303removes a valid mapping,
304from
305.Fa start
306to
307.Fa end ,
308in map
309.Fa map ,
310which must be unlocked.
311.Pp
312.Fn uvm_map_pageable
313changes the pageability of the pages in the range from
314.Fa start
315to
316.Fa end
317in map
318.Fa map
319to
320.Fa new_pageable .
321.Fn uvm_map_pageable
322returns a standard UVM return value.
323.Pp
324.Fn uvm_map_checkprot
325checks the protection of the range from
326.Fa start
327to
328.Fa end
329in map
330.Fa map
331against
332.Fa protection .
333This returns either
334.Dv TRUE
335or
336.Dv FALSE .
337.Pp
338.Fn uvm_map_protect
339changes the protection
340.Fa start
341to
342.Fa end
343in map
344.Fa map
345to
346.Fa new_prot ,
347also setting the maximum protection to the region to
348.Fa new_prot
349if
350.Fa set_max
351is non-zero.
352This function returns a standard UVM return value.
353.Pp
354.Fn uvm_deallocate
355deallocates kernel memory in map
356.Fa map
357from address
358.Fa start
359to
360.Fa start + size .
361.Pp
362.Fn uvmspace_alloc
363allocates and returns a new address space, with ranges from
364.Fa min
365to
366.Fa max ,
367setting the pageability of the address space to
368.Fa pageable .
369.Pp
370.Fn uvmspace_exec
371either reuses the address space of lwp
372.Fa l
373if there are no other references to it, or creates
374a new one with
375.Fn uvmspace_alloc .
376The range of valid addresses in the address space is reset to
377.Fa start
378through
379.Fa end .
380.Pp
381.Fn uvmspace_fork
382creates and returns a new address space based upon the
383.Fa vm1
384address space, typically used when allocating an address space for a
385child process.
386.Pp
387.Fn uvmspace_free
388lowers the reference count on the address space
389.Fa vm ,
390freeing the data structures if there are no other references.
391.Pp
392.Fn uvmspace_share
393causes process
394.Pa p2
395to share the address space of
396.Fa p1 .
397.Pp
398.Fn uvmspace_unshare
399ensures that lwp
400.Fa l
401has its own, unshared address space, by creating a new one if
402necessary by calling
403.Fn uvmspace_fork .
404.Pp
405.Fn uvm_uarea_alloc
406allocates virtual space for a u-area (i.e., a kernel stack) and stores
407its virtual address in
408.Fa *uaddrp .
409The return value is
410.Dv TRUE
411if the u-area is already backed by wired physical memory, otherwise
412.Dv FALSE .
413.Pp
414.Fn uvm_uarea_free
415frees a u-area allocated with
416.Fn uvm_uarea_alloc ,
417freeing both the virtual space and any physical pages which may have been
418allocated to back that virtual space later.
419.Sh PAGE FAULT HANDLING
420.Ft int
421.br
422.Fn uvm_fault "struct vm_map *orig_map" "vaddr_t vaddr" "vm_fault_t fault_type" "vm_prot_t access_type" ;
423.Pp
424.Fn uvm_fault
425is the main entry point for faults.
426It takes
427.Fa orig_map
428as the map the fault originated in, a
429.Fa vaddr
430offset into the map the fault occurred,
431.Fa fault_type
432describing the type of fault, and
433.Fa access_type
434describing the type of access requested.
435.Fn uvm_fault
436returns a standard UVM return value.
437.Sh MEMORY MAPPING FILES AND DEVICES
438.Ft struct uvm_object *
439.br
440.Fn uvn_attach "void *arg" "vm_prot_t accessprot" ;
441.Pp
442.Ft void
443.br
444.Fn uvm_vnp_setsize "struct vnode *vp" "voff_t newsize" ;
445.Pp
446.Ft void *
447.br
448.Fn ubc_alloc "struct uvm_object *uobj" "voff_t offset" "vsize_t *lenp" \
449"int advice" "int flags" ;
450.Pp
451.Ft void
452.br
453.Fn ubc_release "void *va" "int flags" ;
454.Pp
455.Fn uvn_attach
456attaches a UVM object to vnode
457.Fa arg ,
458creating the object if necessary.
459The object is returned.
460.Pp
461.Fn uvm_vnp_setsize
462sets the size of vnode
463.Fa vp
464to
465.Fa newsize .
466Caller must hold a reference to the vnode.
467If the vnode shrinks, pages no longer used are discarded.
468.Pp
469.Fn ubc_alloc
470creates a kernel mapping of
471.Fa uobj
472starting at offset
473.Fa offset .
474The desired length of the mapping is pointed to by
475.Fa lenp ,
476but the actual mapping may be smaller than this.
477.Fa lenp
478is updated to contain the actual length mapped.
479.Fa advice
480is the access pattern hint, which must be one of
481.Pp
482.Bl -tag -offset indent -width "UVM_ADV_SEQUENTIAL" -compact
483.It UVM_ADV_NORMAL
484No hint
485.It UVM_ADV_RANDOM
486Random access hint
487.It UVM_ADV_SEQUENTIAL
488Sequential access hint (from lower offset to higher offset)
489.El
490.Pp
491The flags must be one of
492.Bd -literal
493#define UBC_READ        0x01    /* mapping will be accessed for read */
494#define UBC_WRITE       0x02    /* mapping will be accessed for write */
495.Ed
496.Pp
497Currently,
498.Fa uobj
499must actually be a vnode object.
500Once the mapping is created, it must be accessed only by methods that can
501handle faults, such as
502.Fn uiomove
503or
504.Fn kcopy .
505Page faults on the mapping will result in the vnode's
506.Fn VOP_GETPAGES
507method being called to resolve the fault.
508.Pp
509.Fn ubc_release
510frees the mapping at
511.Fa va
512for reuse.
513The mapping may be cached to speed future accesses to the same region
514of the object.
515The flags can be any of
516.Bd -literal
517#define UBC_UNMAP       0x01    /* do not cache mapping */
518.Ed
519.Sh VIRTUAL MEMORY I/O
520.Ft int
521.br
522.Fn uvm_io "struct vm_map *map" "struct uio *uio" ;
523.Pp
524.Fn uvm_io
525performs the I/O described in
526.Fa uio
527on the memory described in
528.Fa map .
529.Sh ALLOCATION OF KERNEL MEMORY
530.Ft vaddr_t
531.br
532.Fn uvm_km_alloc "struct vm_map *map" "vsize_t size" "vsize_t align" "uvm_flag_t flags" ;
533.Pp
534.Ft void
535.br
536.Fn uvm_km_free "struct vm_map *map" "vaddr_t addr" "vsize_t size" "uvm_flag_t flags" ;
537.Pp
538.Ft struct vm_map *
539.br
540.Fn uvm_km_suballoc "struct vm_map *map" "vaddr_t *min" "vaddr_t *max" "vsize_t size" "boolean_t pageable" "boolean_t fixed" "struct vm_map *submap" ;
541.Pp
542.Fn uvm_km_alloc
543allocates
544.Fa size
545bytes of kernel memory in map
546.Fa map .
547The first address of the allocated memory range will be aligned according to the
548.Fa align
549argument
550.Pq specify 0 if no alignment is necessary .
551The alignment must be a multiple of page size.
552The
553.Fa flags
554is a bitwise inclusive OR of the allocation type and operation flags.
555.Pp
556The allocation type should be one of:
557.Bl -tag -width UVM_KMF_PAGEABLE
558.It UVM_KMF_WIRED
559Wired memory.
560.It UVM_KMF_PAGEABLE
561Demand-paged zero-filled memory.
562.It UVM_KMF_VAONLY
563Virtual address only.
564No physical pages are mapped in the allocated region.
565If necessary, it's the caller's responsibility to enter page mappings.
566It's also the caller's responsibility to clean up the mappings before freeing
567the address range.
568.El
569.Pp
570The following operation flags are available:
571.Bl -tag -width UVM_KMF_PAGEABLE
572.It UVM_KMF_CANFAIL
573Can fail even if
574.Dv UVM_KMF_NOWAIT
575is not specified and
576.Dv UVM_KMF_WAITVA
577is specified.
578.It UVM_KMF_ZERO
579Request zero-filled memory.
580Only supported for
581.Dv UVM_KMF_WIRED .
582Shouldn't be used with other types.
583.It UVM_KMF_TRYLOCK
584Fail if we can't lock the map.
585.It UVM_KMF_NOWAIT
586Fail immediately if no memory is available.
587.It UVM_KMF_WAITVA
588Sleep to wait for the virtual address resources if needed.
589.El
590.Pp
591(If neither
592.Dv UVM_KMF_NOWAIT
593nor
594.Dv UVM_KMF_CANFAIL
595are specified and
596.Dv UVM_KMF_WAITVA
597is specified,
598.Fn uvm_km_alloc
599will never fail, but rather sleep indefinitely until the allocation succeeds.)
600.Pp
601Pageability of the pages allocated with
602.Dv UVM_KMF_PAGEABLE
603can be changed by
604.Fn uvm_map_pageable .
605In that case, the entire range must be changed atomically.
606Changing a part of the range is not supported.
607.Pp
608.Fn uvm_km_free
609frees the memory range allocated by
610.Fn uvm_km_alloc .
611.Fa addr
612must be an address returned by
613.Fn uvm_km_alloc .
614.Fa map
615and
616.Fa size
617must be the same as the ones used for the corresponding
618.Fn uvm_km_alloc .
619.Fa flags
620must be the allocation type used for the corresponding
621.Fn uvm_km_alloc .
622.Pp
623.Fn uvm_km_free
624is the only way to free memory ranges allocated by
625.Fn uvm_km_alloc .
626.Fn uvm_unmap
627must not be used.
628.Pp
629.Fn uvm_km_suballoc
630allocates submap from
631.Fa map ,
632creating a new map if
633.Fa submap
634is
635.Dv NULL .
636The addresses of the submap can be specified exactly by setting the
637.Fa fixed
638argument to non-zero, which causes the
639.Fa min
640argument to specify the beginning of the address in the submap.
641If
642.Fa fixed
643is zero, any address of size
644.Fa size
645will be allocated from
646.Fa map
647and the start and end addresses returned in
648.Fa min
649and
650.Fa max .
651If
652.Fa pageable
653is non-zero, entries in the map may be paged out.
654.Sh ALLOCATION OF PHYSICAL MEMORY
655.Ft struct vm_page *
656.br
657.Fn uvm_pagealloc "struct uvm_object *uobj" "voff_t off" "struct vm_anon *anon" "int flags" ;
658.Pp
659.Ft void
660.br
661.Fn uvm_pagerealloc "struct vm_page *pg" "struct uvm_object *newobj" "voff_t newoff" ;
662.Pp
663.Ft void
664.br
665.Fn uvm_pagefree "struct vm_page *pg" ;
666.Pp
667.Ft int
668.br
669.Fn uvm_pglistalloc "psize_t size" "paddr_t low" "paddr_t high" "paddr_t alignment" "paddr_t boundary" "struct pglist *rlist" "int nsegs" "int waitok" ;
670.Pp
671.Ft void
672.br
673.Fn uvm_pglistfree "struct pglist *list" ;
674.Pp
675.Ft void
676.br
677.Fn uvm_page_physload "vaddr_t start" "vaddr_t end" "vaddr_t avail_start" "vaddr_t avail_end" "int free_list" ;
678.Pp
679.Fn uvm_pagealloc
680allocates a page of memory at virtual address
681.Fa off
682in either the object
683.Fa uobj
684or the anonymous memory
685.Fa anon ,
686which must be locked by the caller.
687Only one of
688.Fa uobj
689and
690.Fa anon
691can be non
692.Dv NULL .
693Returns
694.Dv NULL
695when no page can be found.
696The flags can be any of
697.Bd -literal
698#define UVM_PGA_USERESERVE      0x0001  /* ok to use reserve pages */
699#define UVM_PGA_ZERO            0x0002  /* returned page must be zero'd */
700.Ed
701.Pp
702.Dv UVM_PGA_USERESERVE
703means to allocate a page even if that will result in the number of free pages
704being lower than
705.Dv uvmexp.reserve_pagedaemon
706(if the current thread is the pagedaemon) or
707.Dv uvmexp.reserve_kernel
708(if the current thread is not the pagedaemon).
709.Dv UVM_PGA_ZERO
710causes the returned page to be filled with zeroes, either by allocating it
711from a pool of pre-zeroed pages or by zeroing it in-line as necessary.
712.Pp
713.Fn uvm_pagerealloc
714reallocates page
715.Fa pg
716to a new object
717.Fa newobj ,
718at a new offset
719.Fa newoff .
720.Pp
721.Fn uvm_pagefree
722frees the physical page
723.Fa pg .
724If the content of the page is known to be zero-filled,
725caller should set
726.Dv PG_ZERO
727in pg-\*[Gt]flags so that the page allocator will use
728the page to serve future
729.Dv UVM_PGA_ZERO
730requests efficiently.
731.Pp
732.Fn uvm_pglistalloc
733allocates a list of pages for size
734.Fa size
735byte under various constraints.
736.Fa low
737and
738.Fa high
739describe the lowest and highest addresses acceptable for the list.
740If
741.Fa alignment
742is non-zero, it describes the required alignment of the list, in
743power-of-two notation.
744If
745.Fa boundary
746is non-zero, no segment of the list may cross this power-of-two
747boundary, relative to zero.
748.Fa nsegs
749is the maximum number of physically contigous segments.
750If
751.Fa waitok
752is non-zero, the function may sleep until enough memory is available.
753(It also may give up in some situations, so a non-zero
754.Fa waitok
755does not imply that
756.Fn uvm_pglistalloc
757cannot return an error.)
758The allocated memory is returned in the
759.Fa rlist
760list; the caller has to provide storage only, the list is initialized by
761.Fn uvm_pglistalloc .
762.Pp
763.Fn uvm_pglistfree
764frees the list of pages pointed to by
765.Fa list .
766If the content of the page is known to be zero-filled,
767caller should set
768.Dv PG_ZERO
769in pg-\*[Gt]flags so that the page allocator will use
770the page to serve future
771.Dv UVM_PGA_ZERO
772requests efficiently.
773.Pp
774.Fn uvm_page_physload
775loads physical memory segments into VM space on the specified
776.Fa free_list .
777It must be called at system boot time to set up physical memory
778management pages.
779The arguments describe the
780.Fa start
781and
782.Fa end
783of the physical addresses of the segment, and the available start and end
784addresses of pages not already in use.
785.\" XXX expand on "system boot time"!
786.Sh PROCESSES
787.Ft void
788.br
789.Fn uvm_pageout "void" ;
790.Pp
791.Ft void
792.br
793.Fn uvm_scheduler "void" ;
794.Pp
795.Ft void
796.br
797.Fn uvm_swapin "struct lwp *l" ;
798.Pp
799.Fn uvm_pageout
800is the main loop for the page daemon.
801.Pp
802.Fn uvm_scheduler
803is the process zero main loop, which is to be called after the
804system has finished starting other processes.
805It handles the swapping in of runnable, swapped out processes in priority
806order.
807.Pp
808.Fn uvm_swapin
809swaps in the named lwp.
810.Sh PAGE LOAN
811.Ft int
812.br
813.Fn uvm_loan "struct vm_map *map" "vaddr_t start" "vsize_t len" "void *v" "int flags" ;
814.Pp
815.Ft void
816.br
817.Fn uvm_unloan "void *v" "int npages" "int flags" ;
818.Pp
819.Fn uvm_loan
820loans pages in a map out to anons or to the kernel.
821.Fa map
822should be unlocked,
823.Fa start
824and
825.Fa len
826should be multiples of
827.Dv PAGE_SIZE .
828Argument
829.Fa flags
830should be one of
831.Bd -literal
832#define UVM_LOAN_TOANON       0x01    /* loan to anons */
833#define UVM_LOAN_TOPAGE       0x02    /* loan to kernel */
834.Ed
835.Pp
836.Fa v
837should be pointer to array of pointers to
838.Li struct anon
839or
840.Li struct vm_page ,
841as appropriate.
842The caller has to allocate memory for the array and
843ensure it's big enough to hold
844.Fa len / PAGE_SIZE
845pointers.
846Returns 0 for success, or appropriate error number otherwise.
847Note that wired pages can't be loaned out and
848.Fn uvm_loan
849will fail in that case.
850.Pp
851.Fn uvm_unloan
852kills loans on pages or anons.
853The
854.Fa v
855must point to the array of pointers initialized by previous call to
856.Fn uvm_loan .
857.Fa npages
858should match number of pages allocated for loan, this also matches
859number of items in the array.
860Argument
861.Fa flags
862should be one of
863.Bd -literal
864#define UVM_LOAN_TOANON       0x01    /* loan to anons */
865#define UVM_LOAN_TOPAGE       0x02    /* loan to kernel */
866.Ed
867.Pp
868and should match what was used for previous call to
869.Fn uvm_loan .
870.Sh MISCELLANEOUS FUNCTIONS
871.Ft struct uvm_object *
872.br
873.Fn uao_create "vsize_t size" "int flags" ;
874.Pp
875.Ft void
876.br
877.Fn uao_detach "struct uvm_object *uobj" ;
878.Pp
879.Ft void
880.br
881.Fn uao_reference "struct uvm_object *uobj" ;
882.Pp
883.Ft boolean_t
884.br
885.Fn uvm_chgkprot "caddr_t addr" "size_t len" "int rw" ;
886.Pp
887.Ft void
888.br
889.Fn uvm_kernacc "caddr_t addr" "size_t len" "int rw" ;
890.Pp
891.Ft int
892.br
893.Fn uvm_vslock "struct proc *l" "caddr_t addr" "size_t len" "vm_prot_t prot" ;
894.Pp
895.Ft void
896.br
897.Fn uvm_vsunlock "struct proc *p" "caddr_t addr" "size_t len" ;
898.Pp
899.Ft void
900.br
901.Fn uvm_meter "void" ;
902.Pp
903.Ft void
904.br
905.Fn uvm_fork "struct lwp *l1" "struct lwp *l2" "boolean_t shared" ;
906.Pp
907.Ft int
908.br
909.Fn uvm_grow "struct proc *p" "vaddr_t sp" ;
910.Pp
911.Ft int
912.br
913.Fn uvm_coredump "struct proc *p" "struct vnode *vp" "struct ucred *cred" "struct core *chdr" ;
914.Pp
915.Ft void
916.br
917.Fn uvn_findpages "struct uvm_object *uobj" "voff_t offset" "int *npagesp" "struct vm_page **pps" "int flags" ;
918.Pp
919.Ft void
920.br
921.Fn uvm_swap_stats "int cmd" "struct swapent *sep" "int sec" "register_t *retval" ;
922.Pp
923The
924.Fn uao_create ,
925.Fn uao_detach ,
926and
927.Fn uao_reference
928functions operate on anonymous memory objects, such as those used to support
929System V shared memory.
930.Fn uao_create
931returns an object of size
932.Fa size
933with flags:
934.Bd -literal
935#define UAO_FLAG_KERNOBJ        0x1     /* create kernel object */
936#define UAO_FLAG_KERNSWAP       0x2     /* enable kernel swap */
937.Ed
938.Pp
939which can only be used once each at system boot time.
940.Fn uao_reference
941creates an additional reference to the named anonymous memory object.
942.Fn uao_detach
943removes a reference from the named anonymous memory object, destroying
944it if removing the last reference.
945.Pp
946.Fn uvm_chgkprot
947changes the protection of kernel memory from
948.Fa addr
949to
950.Fa addr + len
951to the value of
952.Fa rw .
953This is primarily useful for debuggers, for setting breakpoints.
954This function is only available with options
955.Dv KGDB .
956.Pp
957.Fn uvm_kernacc
958checks the access at address
959.Fa addr
960to
961.Fa addr + len
962for
963.Fa rw
964access in the kernel address space.
965.Pp
966.Fn uvm_vslock
967and
968.Fn uvm_vsunlock
969control the wiring and unwiring of pages for process
970.Fa p
971from
972.Fa addr
973to
974.Fa addr + len .
975These functions are normally used to wire memory for I/O.
976.Pp
977.Fn uvm_meter
978calculates the load average and wakes up the swapper if necessary.
979.Pp
980.Fn uvm_fork
981forks a virtual address space for process' (old)
982.Fa p1
983and (new)
984.Fa p2 .
985If the
986.Fa shared
987argument is non zero, p1 shares its address space with p2,
988otherwise a new address space is created.
989This function currently has no return value, and thus cannot fail.
990In the future, this function will be changed to allow it to
991fail in low memory conditions.
992.Pp
993.Fn uvm_grow
994increases the stack segment of process
995.Fa p
996to include
997.Fa sp .
998.Pp
999.Fn uvm_coredump
1000generates a coredump on vnode
1001.Fa vp
1002for process
1003.Fa p
1004with credentials
1005.Fa cred
1006and core header description in
1007.Fa chdr .
1008.Pp
1009.Fn uvn_findpages
1010looks up or creates pages in
1011.Fa uobj
1012at offset
1013.Fa offset ,
1014marks them busy and returns them in the
1015.Fa pps
1016array.
1017Currently
1018.Fa uobj
1019must be a vnode object.
1020The number of pages requested is pointed to by
1021.Fa npagesp ,
1022and this value is updated with the actual number of pages returned.
1023The flags can be
1024.Bd -literal
1025#define UFP_ALL         0x00    /* return all pages requested */
1026#define UFP_NOWAIT      0x01    /* don't sleep */
1027#define UFP_NOALLOC     0x02    /* don't allocate new pages */
1028#define UFP_NOCACHE     0x04    /* don't return pages which already exist */
1029#define UFP_NORDONLY    0x08    /* don't return PG_READONLY pages */
1030.Ed
1031.Pp
1032.Dv UFP_ALL
1033is a pseudo-flag meaning all requested pages should be returned.
1034.Dv UFP_NOWAIT
1035means that we must not sleep.
1036.Dv UFP_NOALLOC
1037causes any pages which do not already exist to be skipped.
1038.Dv UFP_NOCACHE
1039causes any pages which do already exist to be skipped.
1040.Dv UFP_NORDONLY
1041causes any pages which are marked PG_READONLY to be skipped.
1042.Pp
1043.Fn uvm_swap_stats
1044implements the
1045.Dv SWAP_STATS
1046and
1047.Dv SWAP_OSTATS
1048operation of the
1049.Xr swapctl 2
1050system call.
1051.Fa cmd
1052is the requested command,
1053.Dv SWAP_STATS
1054or
1055.Dv SWAP_OSTATS .
1056The function will copy no more than
1057.Fa sec
1058entries in the array pointed by
1059.Fa sep .
1060On return,
1061.Fa retval
1062holds the actual number of entries copied in the array.
1063.Sh SYSCTL
1064UVM provides support for the
1065.Dv CTL_VM
1066domain of the
1067.Xr sysctl 3
1068hierarchy.
1069It handles the
1070.Dv VM_LOADAVG ,
1071.Dv VM_METER ,
1072.Dv VM_UVMEXP ,
1073and
1074.Dv VM_UVMEXP2
1075nodes, which return the current load averages, calculates current VM
1076totals, returns the uvmexp structure, and a kernel version independent
1077view of the uvmexp structure, respectively.
1078It also exports a number of tunables that control how much VM space is
1079allowed to be consumed by various tasks.
1080The load averages are typically accessed from userland using the
1081.Xr getloadavg 3
1082function.
1083The uvmexp structure has all global state of the UVM system,
1084and has the following members:
1085.Bd -literal
1086/* vm_page constants */
1087int pagesize;   /* size of a page (PAGE_SIZE): must be power of 2 */
1088int pagemask;   /* page mask */
1089int pageshift;  /* page shift */
1090
1091/* vm_page counters */
1092int npages;     /* number of pages we manage */
1093int free;       /* number of free pages */
1094int active;     /* number of active pages */
1095int inactive;   /* number of pages that we free'd but may want back */
1096int paging;     /* number of pages in the process of being paged out */
1097int wired;      /* number of wired pages */
1098int reserve_pagedaemon; /* number of pages reserved for pagedaemon */
1099int reserve_kernel; /* number of pages reserved for kernel */
1100
1101/* pageout params */
1102int freemin;    /* min number of free pages */
1103int freetarg;   /* target number of free pages */
1104int inactarg;   /* target number of inactive pages */
1105int wiredmax;   /* max number of wired pages */
1106
1107/* swap */
1108int nswapdev;   /* number of configured swap devices in system */
1109int swpages;    /* number of PAGE_SIZE'ed swap pages */
1110int swpginuse;  /* number of swap pages in use */
1111int nswget;     /* number of times fault calls uvm_swap_get() */
1112int nanon;      /* number total of anon's in system */
1113int nfreeanon;  /* number of free anon's */
1114
1115/* stat counters */
1116int faults;             /* page fault count */
1117int traps;              /* trap count */
1118int intrs;              /* interrupt count */
1119int swtch;              /* context switch count */
1120int softs;              /* software interrupt count */
1121int syscalls;           /* system calls */
1122int pageins;            /* pagein operation count */
1123                        /* pageouts are in pdpageouts below */
1124int swapins;            /* swapins */
1125int swapouts;           /* swapouts */
1126int pgswapin;           /* pages swapped in */
1127int pgswapout;          /* pages swapped out */
1128int forks;              /* forks */
1129int forks_ppwait;       /* forks where parent waits */
1130int forks_sharevm;      /* forks where vmspace is shared */
1131
1132/* fault subcounters */
1133int fltnoram;   /* number of times fault was out of ram */
1134int fltnoanon;  /* number of times fault was out of anons */
1135int fltpgwait;  /* number of times fault had to wait on a page */
1136int fltpgrele;  /* number of times fault found a released page */
1137int fltrelck;   /* number of times fault relock called */
1138int fltrelckok; /* number of times fault relock is a success */
1139int fltanget;   /* number of times fault gets anon page */
1140int fltanretry; /* number of times fault retrys an anon get */
1141int fltamcopy;  /* number of times fault clears "needs copy" */
1142int fltnamap;   /* number of times fault maps a neighbor anon page */
1143int fltnomap;   /* number of times fault maps a neighbor obj page */
1144int fltlget;    /* number of times fault does a locked pgo_get */
1145int fltget;     /* number of times fault does an unlocked get */
1146int flt_anon;   /* number of times fault anon (case 1a) */
1147int flt_acow;   /* number of times fault anon cow (case 1b) */
1148int flt_obj;    /* number of times fault is on object page (2a) */
1149int flt_prcopy; /* number of times fault promotes with copy (2b) */
1150int flt_przero; /* number of times fault promotes with zerofill (2b) */
1151
1152/* daemon counters */
1153int pdwoke;     /* number of times daemon woke up */
1154int pdrevs;     /* number of times daemon rev'd clock hand */
1155int pdswout;    /* number of times daemon called for swapout */
1156int pdfreed;    /* number of pages daemon freed since boot */
1157int pdscans;    /* number of pages daemon scanned since boot */
1158int pdanscan;   /* number of anonymous pages scanned by daemon */
1159int pdobscan;   /* number of object pages scanned by daemon */
1160int pdreact;    /* number of pages daemon reactivated since boot */
1161int pdbusy;     /* number of times daemon found a busy page */
1162int pdpageouts; /* number of times daemon started a pageout */
1163int pdpending;  /* number of times daemon got a pending pageout */
1164int pddeact;    /* number of pages daemon deactivates */
1165.Ed
1166.Sh NOTES
1167.Fn uvm_chgkprot
1168is only available if the kernel has been compiled with options
1169.Dv KGDB .
1170.Pp
1171All structure and types whose names begin with
1172.Dq vm_
1173will be renamed to
1174.Dq uvm_ .
1175.Sh SEE ALSO
1176.Xr swapctl 2 ,
1177.Xr getloadavg 3 ,
1178.Xr kvm 3 ,
1179.Xr sysctl 3 ,
1180.Xr ddb 4 ,
1181.Xr options 4 ,
1182.Xr pmap 9
1183.Sh HISTORY
1184UVM is a new VM system developed at Washington University in St. Louis
1185(Missouri).
1186UVM's roots lie partly in the Mach-based
1187.Bx 4.4
1188VM system, the
1189.Fx
1190VM system, and the SunOS 4 VM system.
1191UVM's basic structure is based on the
1192.Bx 4.4
1193VM system.
1194UVM's new anonymous memory system is based on the
1195anonymous memory system found in the SunOS 4 VM (as described in papers
1196published by Sun Microsystems, Inc.).
1197UVM also includes a number of features new to
1198.Bx
1199including page loanout, map entry passing, simplified
1200copy-on-write, and clustered anonymous memory pageout.
1201UVM is also further documented in an August 1998 dissertation by
1202Charles D. Cranor.
1203.Pp
1204UVM appeared in
1205.Nx 1.4 .
1206.Sh AUTHORS
1207Charles D. Cranor
1208.Aq chuck@ccrc.wustl.edu
1209designed and implemented UVM.
1210.Pp
1211Matthew Green
1212.Aq mrg@eterna.com.au
1213wrote the swap-space management code and handled the logistical issues
1214involved with merging UVM into the
1215.Nx
1216source tree.
1217.Pp
1218Chuck Silvers
1219.Aq chuq@chuq.com
1220implemented the aobj pager, thus allowing UVM to support System V shared
1221memory and process swapping.
1222He also designed and implemented the UBC part of UVM, which uses UVM pages
1223to cache vnode data rather than the traditional buffer cache buffers.
1224