freebsd-dev/sys/vm/vm_object.h
Alan Cox 387aabc513 Long, long ago in r27464 special case code for mapping device-backed
memory with 4MB pages was added to pmap_object_init_pt().  This code
assumes that the pages of a OBJT_DEVICE object are always physically
contiguous.  Unfortunately, this is not always the case.  For example,
jhb@ informs me that the recently introduced /dev/ksyms driver creates
a OBJT_DEVICE object that violates this assumption.  Thus, this
revision modifies pmap_object_init_pt() to abort the mapping if the
OBJT_DEVICE object's pages are not physically contiguous.  This
revision also changes some inconsistent if not buggy behavior.  For
example, the i386 version aborts if the first 4MB virtual page that
would be mapped is already valid.  However, it incorrectly replaces
any subsequent 4MB virtual page mappings that it encounters,
potentially leaking a page table page.  The amd64 version has a bug of
my own creation.  It potentially busies the wrong page and always an
insufficent number of pages if it blocks allocating a page table page.

To my knowledge, there have been no reports of these bugs, hence,
their persistance.  I suspect that the existing restrictions that
pmap_object_init_pt() placed on the OBJT_DEVICE objects that it would
choose to map, for example, that the first page must be aligned on a 2
or 4MB physical boundary and that the size of the mapping must be a
multiple of the large page size, were enough to avoid triggering the
bug for drivers like ksyms.  However, one side effect of testing the
OBJT_DEVICE object's pages for physical contiguity is that a dubious
difference between pmap_object_init_pt() and the standard path for
mapping devices pages, i.e., vm_fault(), has been eliminated.
Previously, pmap_object_init_pt() would only instantiate the first
PG_FICTITOUS page being mapped because it never examined the rest.
Now, however, pmap_object_init_pt() uses the new function
vm_object_populate() to instantiate them all (in order to support
testing their physical contiguity).  These pages need to be
instantiated for the mechanism that I have prototyped for
automatically maintaining the consistency of the PAT settings across
multiple mappings, particularly, amd64's direct mapping, to work.
(Translation: This change is also being made to support jhb@'s work on
the Nvidia feature requests.)

Discussed with:	jhb@
2009-06-14 19:51:43 +00:00

221 lines
7.8 KiB
C

/*-
* Copyright (c) 1991, 1993
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* The Mach Operating System project at Carnegie-Mellon University.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* from: @(#)vm_object.h 8.3 (Berkeley) 1/12/94
*
*
* Copyright (c) 1987, 1990 Carnegie-Mellon University.
* All rights reserved.
*
* Authors: Avadis Tevanian, Jr., Michael Wayne Young
*
* Permission to use, copy, modify and distribute this software and
* its documentation is hereby granted, provided that both the copyright
* notice and this permission notice appear in all copies of the
* software, derivative works or modified versions, and any portions
* thereof, and that both notices appear in supporting documentation.
*
* CARNEGIE MELLON ALLOWS FREE USE OF THIS SOFTWARE IN ITS "AS IS"
* CONDITION. CARNEGIE MELLON DISCLAIMS ANY LIABILITY OF ANY KIND
* FOR ANY DAMAGES WHATSOEVER RESULTING FROM THE USE OF THIS SOFTWARE.
*
* Carnegie Mellon requests users of this software to return to
*
* Software Distribution Coordinator or Software.Distribution@CS.CMU.EDU
* School of Computer Science
* Carnegie Mellon University
* Pittsburgh PA 15213-3890
*
* any improvements or extensions that they make and grant Carnegie the
* rights to redistribute these changes.
*
* $FreeBSD$
*/
/*
* Virtual memory object module definitions.
*/
#ifndef _VM_OBJECT_
#define _VM_OBJECT_
#include <sys/queue.h>
#include <sys/_lock.h>
#include <sys/_mutex.h>
/*
* Types defined:
*
* vm_object_t Virtual memory object.
*
* List of locks
* (c) const until freed
*
*/
struct vm_object {
struct mtx mtx;
TAILQ_ENTRY(vm_object) object_list; /* list of all objects */
LIST_HEAD(, vm_object) shadow_head; /* objects that this is a shadow for */
LIST_ENTRY(vm_object) shadow_list; /* chain of shadow objects */
TAILQ_HEAD(, vm_page) memq; /* list of resident pages */
vm_page_t root; /* root of the resident page splay tree */
vm_pindex_t size; /* Object size */
int generation; /* generation ID */
int ref_count; /* How many refs?? */
int shadow_count; /* how many objects that this is a shadow for */
objtype_t type; /* type of pager */
u_short flags; /* see below */
u_short pg_color; /* (c) color of first page in obj */
u_short paging_in_progress; /* Paging (in or out) so don't collapse or destroy */
int resident_page_count; /* number of resident pages */
struct vm_object *backing_object; /* object that I'm a shadow of */
vm_ooffset_t backing_object_offset;/* Offset in backing object */
TAILQ_ENTRY(vm_object) pager_object_list; /* list of all objects of this pager type */
LIST_HEAD(, vm_reserv) rvq; /* list of reservations */
vm_page_t cache; /* root of the cache page splay tree */
void *handle;
union {
/*
* VNode pager
*
* vnp_size - current size of file
*/
struct {
off_t vnp_size;
} vnp;
/*
* Device pager
*
* devp_pglist - list of allocated pages
*/
struct {
TAILQ_HEAD(, vm_page) devp_pglist;
} devp;
/*
* Swap pager
*
* swp_bcount - number of swap 'swblock' metablocks, each
* contains up to 16 swapblk assignments.
* see vm/swap_pager.h
*/
struct {
int swp_bcount;
} swp;
} un_pager;
};
/*
* Flags
*/
#define OBJ_ACTIVE 0x0004 /* active objects */
#define OBJ_DEAD 0x0008 /* dead objects (during rundown) */
#define OBJ_NOSPLIT 0x0010 /* dont split this object */
#define OBJ_PIPWNT 0x0040 /* paging in progress wanted */
#define OBJ_MIGHTBEDIRTY 0x0100 /* object might be dirty */
#define OBJ_CLEANING 0x0200
#define OBJ_COLORED 0x1000 /* pg_color is defined */
#define OBJ_ONEMAPPING 0x2000 /* One USE (a single, non-forked) mapping flag */
#define OBJ_DISCONNECTWNT 0x4000 /* disconnect from vnode wanted */
#define IDX_TO_OFF(idx) (((vm_ooffset_t)(idx)) << PAGE_SHIFT)
#define OFF_TO_IDX(off) ((vm_pindex_t)(((vm_ooffset_t)(off)) >> PAGE_SHIFT))
#ifdef _KERNEL
#define OBJPC_SYNC 0x1 /* sync I/O */
#define OBJPC_INVAL 0x2 /* invalidate */
#define OBJPC_NOSYNC 0x4 /* skip if PG_NOSYNC */
TAILQ_HEAD(object_q, vm_object);
extern struct object_q vm_object_list; /* list of allocated objects */
extern struct mtx vm_object_list_mtx; /* lock for object list and count */
extern struct vm_object kernel_object_store;
extern struct vm_object kmem_object_store;
#define kernel_object (&kernel_object_store)
#define kmem_object (&kmem_object_store)
#define VM_OBJECT_LOCK(object) mtx_lock(&(object)->mtx)
#define VM_OBJECT_LOCK_ASSERT(object, type) \
mtx_assert(&(object)->mtx, (type))
#define VM_OBJECT_LOCK_INIT(object, type) \
mtx_init(&(object)->mtx, "vm object", \
(type), MTX_DEF | MTX_DUPOK)
#define VM_OBJECT_LOCKED(object) mtx_owned(&(object)->mtx)
#define VM_OBJECT_MTX(object) (&(object)->mtx)
#define VM_OBJECT_TRYLOCK(object) mtx_trylock(&(object)->mtx)
#define VM_OBJECT_UNLOCK(object) mtx_unlock(&(object)->mtx)
/*
* The object must be locked or thread private.
*/
static __inline void
vm_object_set_flag(vm_object_t object, u_short bits)
{
object->flags |= bits;
}
void vm_object_clear_flag(vm_object_t object, u_short bits);
void vm_object_pip_add(vm_object_t object, short i);
void vm_object_pip_subtract(vm_object_t object, short i);
void vm_object_pip_wakeup(vm_object_t object);
void vm_object_pip_wakeupn(vm_object_t object, short i);
void vm_object_pip_wait(vm_object_t object, char *waitid);
vm_object_t vm_object_allocate (objtype_t, vm_pindex_t);
void _vm_object_allocate (objtype_t, vm_pindex_t, vm_object_t);
boolean_t vm_object_coalesce(vm_object_t, vm_ooffset_t, vm_size_t, vm_size_t);
void vm_object_collapse (vm_object_t);
void vm_object_deallocate (vm_object_t);
void vm_object_destroy (vm_object_t);
void vm_object_terminate (vm_object_t);
void vm_object_set_writeable_dirty (vm_object_t);
void vm_object_init (void);
void vm_object_page_clean (vm_object_t, vm_pindex_t, vm_pindex_t, boolean_t);
void vm_object_page_remove (vm_object_t, vm_pindex_t, vm_pindex_t, boolean_t);
boolean_t vm_object_populate(vm_object_t, vm_pindex_t, vm_pindex_t);
void vm_object_reference (vm_object_t);
void vm_object_reference_locked(vm_object_t);
void vm_object_shadow (vm_object_t *, vm_ooffset_t *, vm_size_t);
void vm_object_split(vm_map_entry_t);
void vm_object_sync(vm_object_t, vm_ooffset_t, vm_size_t, boolean_t,
boolean_t);
void vm_object_madvise (vm_object_t, vm_pindex_t, int, int);
#endif /* _KERNEL */
#endif /* _VM_OBJECT_ */