freebsd-skq/sys/vm/vm_pager.h

229 lines
7.4 KiB
C
Raw Normal View History

/*-
1994-05-24 10:09:53 +00:00
* Copyright (c) 1990 University of Utah.
* 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 Systems Programming Group of the University of Utah Computer
* Science Department.
*
* 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.
*
* @(#)vm_pager.h 8.4 (Berkeley) 1/12/94
1999-08-28 01:08:13 +00:00
* $FreeBSD$
1994-05-24 10:09:53 +00:00
*/
/*
* Pager routine interface definition.
*/
#ifndef _VM_PAGER_
#define _VM_PAGER_
#include <sys/queue.h>
TAILQ_HEAD(pagerlst, vm_object);
1994-05-24 10:09:53 +00:00
typedef void pgo_init_t(void);
typedef vm_object_t pgo_alloc_t(void *, vm_ooffset_t, vm_prot_t, vm_ooffset_t,
struct ucred *);
typedef void pgo_dealloc_t(vm_object_t);
typedef int pgo_getpages_t(vm_object_t, vm_page_t *, int, int);
typedef void pgo_getpages_iodone_t(void *, vm_page_t *, int, int);
typedef int pgo_getpages_async_t(vm_object_t, vm_page_t *, int, int,
pgo_getpages_iodone_t, void *);
typedef void pgo_putpages_t(vm_object_t, vm_page_t *, int, int, int *);
typedef boolean_t pgo_haspage_t(vm_object_t, vm_pindex_t, int *, int *);
typedef void pgo_pageunswapped_t(vm_page_t);
These changes embody the support of the fully coherent merged VM buffer cache, much higher filesystem I/O performance, and much better paging performance. It represents the culmination of over 6 months of R&D. The majority of the merged VM/cache work is by John Dyson. The following highlights the most significant changes. Additionally, there are (mostly minor) changes to the various filesystem modules (nfs, msdosfs, etc) to support the new VM/buffer scheme. vfs_bio.c: Significant rewrite of most of vfs_bio to support the merged VM buffer cache scheme. The scheme is almost fully compatible with the old filesystem interface. Significant improvement in the number of opportunities for write clustering. vfs_cluster.c, vfs_subr.c Upgrade and performance enhancements in vfs layer code to support merged VM/buffer cache. Fixup of vfs_cluster to eliminate the bogus pagemove stuff. vm_object.c: Yet more improvements in the collapse code. Elimination of some windows that can cause list corruption. vm_pageout.c: Fixed it, it really works better now. Somehow in 2.0, some "enhancements" broke the code. This code has been reworked from the ground-up. vm_fault.c, vm_page.c, pmap.c, vm_object.c Support for small-block filesystems with merged VM/buffer cache scheme. pmap.c vm_map.c Dynamic kernel VM size, now we dont have to pre-allocate excessive numbers of kernel PTs. vm_glue.c Much simpler and more effective swapping code. No more gratuitous swapping. proc.h Fixed the problem that the p_lock flag was not being cleared on a fork. swap_pager.c, vnode_pager.c Removal of old vfs_bio cruft to support the past pseudo-coherency. Now the code doesn't need it anymore. machdep.c Changes to better support the parameter values for the merged VM/buffer cache scheme. machdep.c, kern_exec.c, vm_glue.c Implemented a seperate submap for temporary exec string space and another one to contain process upages. This eliminates all map fragmentation problems that previously existed. ffs_inode.c, ufs_inode.c, ufs_readwrite.c Changes for merged VM/buffer cache. Add "bypass" support for sneaking in on busy buffers. Submitted by: John Dyson and David Greenman
1995-01-09 16:06:02 +00:00
struct pagerops {
2014-11-14 18:15:35 +00:00
pgo_init_t *pgo_init; /* Initialize pager. */
pgo_alloc_t *pgo_alloc; /* Allocate pager. */
pgo_dealloc_t *pgo_dealloc; /* Disassociate. */
pgo_getpages_t *pgo_getpages; /* Get (read) page. */
pgo_getpages_async_t *pgo_getpages_async; /* Get page asyncly. */
2014-11-14 18:15:35 +00:00
pgo_putpages_t *pgo_putpages; /* Put (write) page. */
pgo_haspage_t *pgo_haspage; /* Query page. */
2014-11-14 18:00:00 +00:00
pgo_pageunswapped_t *pgo_pageunswapped;
1994-05-24 10:09:53 +00:00
};
extern struct pagerops defaultpagerops;
extern struct pagerops swappagerops;
extern struct pagerops vnodepagerops;
extern struct pagerops devicepagerops;
extern struct pagerops physpagerops;
extern struct pagerops sgpagerops;
extern struct pagerops mgtdevicepagerops;
1994-05-24 10:09:53 +00:00
/*
* get/put return values
* OK operation was successful
* BAD specified data was out of the accepted range
* FAIL specified data was in range, but doesn't exist
* PEND operations was initiated but not completed
* ERROR error while accessing data that is in range and exists
* AGAIN temporary resource shortage prevented operation from happening
*/
#define VM_PAGER_OK 0
#define VM_PAGER_BAD 1
#define VM_PAGER_FAIL 2
#define VM_PAGER_PEND 3
#define VM_PAGER_ERROR 4
#define VM_PAGER_AGAIN 5
#define VM_PAGER_PUT_SYNC 0x0001
#define VM_PAGER_PUT_INVAL 0x0002
#define VM_PAGER_CLUSTER_OK 0x0008
This mega-commit is meant to fix numerous interrelated problems. There has been some bitrot and incorrect assumptions in the vfs_bio code. These problems have manifest themselves worse on NFS type filesystems, but can still affect local filesystems under certain circumstances. Most of the problems have involved mmap consistancy, and as a side-effect broke the vfs.ioopt code. This code might have been committed seperately, but almost everything is interrelated. 1) Allow (pmap_object_init_pt) prefaulting of buffer-busy pages that are fully valid. 2) Rather than deactivating erroneously read initial (header) pages in kern_exec, we now free them. 3) Fix the rundown of non-VMIO buffers that are in an inconsistent (missing vp) state. 4) Fix the disassociation of pages from buffers in brelse. The previous code had rotted and was faulty in a couple of important circumstances. 5) Remove a gratuitious buffer wakeup in vfs_vmio_release. 6) Remove a crufty and currently unused cluster mechanism for VBLK files in vfs_bio_awrite. When the code is functional, I'll add back a cleaner version. 7) The page busy count wakeups assocated with the buffer cache usage were incorrectly cleaned up in a previous commit by me. Revert to the original, correct version, but with a cleaner implementation. 8) The cluster read code now tries to keep data associated with buffers more aggressively (without breaking the heuristics) when it is presumed that the read data (buffers) will be soon needed. 9) Change to filesystem lockmgr locks so that they use LK_NOPAUSE. The delay loop waiting is not useful for filesystem locks, due to the length of the time intervals. 10) Correct and clean-up spec_getpages. 11) Implement a fully functional nfs_getpages, nfs_putpages. 12) Fix nfs_write so that modifications are coherent with the NFS data on the server disk (at least as well as NFS seems to allow.) 13) Properly support MS_INVALIDATE on NFS. 14) Properly pass down MS_INVALIDATE to lower levels of the VM code from vm_map_clean. 15) Better support the notion of pages being busy but valid, so that fewer in-transit waits occur. (use p->busy more for pageouts instead of PG_BUSY.) Since the page is fully valid, it is still usable for reads. 16) It is possible (in error) for cached pages to be busy. Make the page allocation code handle that case correctly. (It should probably be a printf or panic, but I want the system to handle coding errors robustly. I'll probably add a printf.) 17) Correct the design and usage of vm_page_sleep. It didn't handle consistancy problems very well, so make the design a little less lofty. After vm_page_sleep, if it ever blocked, it is still important to relookup the page (if the object generation count changed), and verify it's status (always.) 18) In vm_pageout.c, vm_pageout_clean had rotted, so clean that up. 19) Push the page busy for writes and VM_PROT_READ into vm_pageout_flush. 20) Fix vm_pager_put_pages and it's descendents to support an int flag instead of a boolean, so that we can pass down the invalidate bit.
1998-03-07 21:37:31 +00:00
#ifdef _KERNEL
extern struct pagerops *pagertab[];
extern struct mtx_padalign pbuf_mtx;
vm_object_t vm_pager_allocate(objtype_t, void *, vm_ooffset_t, vm_prot_t,
vm_ooffset_t, struct ucred *);
2002-03-19 22:20:14 +00:00
void vm_pager_bufferinit(void);
void vm_pager_deallocate(vm_object_t);
static __inline int vm_pager_get_pages(vm_object_t, vm_page_t *, int, int);
static inline int vm_pager_get_pages_async(vm_object_t, vm_page_t *, int,
int, pgo_getpages_iodone_t, void *);
2002-03-19 22:20:14 +00:00
static __inline boolean_t vm_pager_has_page(vm_object_t, vm_pindex_t, int *, int *);
void vm_pager_init(void);
vm_object_t vm_pager_object_lookup(struct pagerlst *, void *);
void vm_pager_free_nonreq(vm_object_t object, vm_page_t ma[], int reqpage,
int npages);
The VFS/BIO subsystem contained a number of hacks in order to optimize piecemeal, middle-of-file writes for NFS. These hacks have caused no end of trouble, especially when combined with mmap(). I've removed them. Instead, NFS will issue a read-before-write to fully instantiate the struct buf containing the write. NFS does, however, optimize piecemeal appends to files. For most common file operations, you will not notice the difference. The sole remaining fragment in the VFS/BIO system is b_dirtyoff/end, which NFS uses to avoid cache coherency issues with read-merge-write style operations. NFS also optimizes the write-covers-entire-buffer case by avoiding the read-before-write. There is quite a bit of room for further optimization in these areas. The VM system marks pages fully-valid (AKA vm_page_t->valid = VM_PAGE_BITS_ALL) in several places, most noteably in vm_fault. This is not correct operation. The vm_pager_get_pages() code is now responsible for marking VM pages all-valid. A number of VM helper routines have been added to aid in zeroing-out the invalid portions of a VM page prior to the page being marked all-valid. This operation is necessary to properly support mmap(). The zeroing occurs most often when dealing with file-EOF situations. Several bugs have been fixed in the NFS subsystem, including bits handling file and directory EOF situations and buf->b_flags consistancy issues relating to clearing B_ERROR & B_INVAL, and handling B_DONE. getblk() and allocbuf() have been rewritten. B_CACHE operation is now formally defined in comments and more straightforward in implementation. B_CACHE for VMIO buffers is based on the validity of the backing store. B_CACHE for non-VMIO buffers is based simply on whether the buffer is B_INVAL or not (B_CACHE set if B_INVAL clear, and vise-versa). biodone() is now responsible for setting B_CACHE when a successful read completes. B_CACHE is also set when a bdwrite() is initiated and when a bwrite() is initiated. VFS VOP_BWRITE routines (there are only two - nfs_bwrite() and bwrite()) are now expected to set B_CACHE. This means that bowrite() and bawrite() also set B_CACHE indirectly. There are a number of places in the code which were previously using buf->b_bufsize (which is DEV_BSIZE aligned) when they should have been using buf->b_bcount. These have been fixed. getblk() now clears B_DONE on return because the rest of the system is so bad about dealing with B_DONE. Major fixes to NFS/TCP have been made. A server-side bug could cause requests to be lost by the server due to nfs_realign() overwriting other rpc's in the same TCP mbuf chain. The server's kernel must be recompiled to get the benefit of the fixes. Submitted by: Matthew Dillon <dillon@apollo.backplane.com>
1999-05-02 23:57:16 +00:00
/*
* vm_page_get_pages:
*
* Retrieve pages from the VM system in order to map them into an object
* ( or into VM space somewhere ). If the pagein was successful, we
* must fully validate it.
*/
static __inline int
vm_pager_get_pages(
vm_object_t object,
vm_page_t *m,
int count,
int reqpage
) {
The VFS/BIO subsystem contained a number of hacks in order to optimize piecemeal, middle-of-file writes for NFS. These hacks have caused no end of trouble, especially when combined with mmap(). I've removed them. Instead, NFS will issue a read-before-write to fully instantiate the struct buf containing the write. NFS does, however, optimize piecemeal appends to files. For most common file operations, you will not notice the difference. The sole remaining fragment in the VFS/BIO system is b_dirtyoff/end, which NFS uses to avoid cache coherency issues with read-merge-write style operations. NFS also optimizes the write-covers-entire-buffer case by avoiding the read-before-write. There is quite a bit of room for further optimization in these areas. The VM system marks pages fully-valid (AKA vm_page_t->valid = VM_PAGE_BITS_ALL) in several places, most noteably in vm_fault. This is not correct operation. The vm_pager_get_pages() code is now responsible for marking VM pages all-valid. A number of VM helper routines have been added to aid in zeroing-out the invalid portions of a VM page prior to the page being marked all-valid. This operation is necessary to properly support mmap(). The zeroing occurs most often when dealing with file-EOF situations. Several bugs have been fixed in the NFS subsystem, including bits handling file and directory EOF situations and buf->b_flags consistancy issues relating to clearing B_ERROR & B_INVAL, and handling B_DONE. getblk() and allocbuf() have been rewritten. B_CACHE operation is now formally defined in comments and more straightforward in implementation. B_CACHE for VMIO buffers is based on the validity of the backing store. B_CACHE for non-VMIO buffers is based simply on whether the buffer is B_INVAL or not (B_CACHE set if B_INVAL clear, and vise-versa). biodone() is now responsible for setting B_CACHE when a successful read completes. B_CACHE is also set when a bdwrite() is initiated and when a bwrite() is initiated. VFS VOP_BWRITE routines (there are only two - nfs_bwrite() and bwrite()) are now expected to set B_CACHE. This means that bowrite() and bawrite() also set B_CACHE indirectly. There are a number of places in the code which were previously using buf->b_bufsize (which is DEV_BSIZE aligned) when they should have been using buf->b_bcount. These have been fixed. getblk() now clears B_DONE on return because the rest of the system is so bad about dealing with B_DONE. Major fixes to NFS/TCP have been made. A server-side bug could cause requests to be lost by the server due to nfs_realign() overwriting other rpc's in the same TCP mbuf chain. The server's kernel must be recompiled to get the benefit of the fixes. Submitted by: Matthew Dillon <dillon@apollo.backplane.com>
1999-05-02 23:57:16 +00:00
int r;
VM_OBJECT_ASSERT_WLOCKED(object);
The VFS/BIO subsystem contained a number of hacks in order to optimize piecemeal, middle-of-file writes for NFS. These hacks have caused no end of trouble, especially when combined with mmap(). I've removed them. Instead, NFS will issue a read-before-write to fully instantiate the struct buf containing the write. NFS does, however, optimize piecemeal appends to files. For most common file operations, you will not notice the difference. The sole remaining fragment in the VFS/BIO system is b_dirtyoff/end, which NFS uses to avoid cache coherency issues with read-merge-write style operations. NFS also optimizes the write-covers-entire-buffer case by avoiding the read-before-write. There is quite a bit of room for further optimization in these areas. The VM system marks pages fully-valid (AKA vm_page_t->valid = VM_PAGE_BITS_ALL) in several places, most noteably in vm_fault. This is not correct operation. The vm_pager_get_pages() code is now responsible for marking VM pages all-valid. A number of VM helper routines have been added to aid in zeroing-out the invalid portions of a VM page prior to the page being marked all-valid. This operation is necessary to properly support mmap(). The zeroing occurs most often when dealing with file-EOF situations. Several bugs have been fixed in the NFS subsystem, including bits handling file and directory EOF situations and buf->b_flags consistancy issues relating to clearing B_ERROR & B_INVAL, and handling B_DONE. getblk() and allocbuf() have been rewritten. B_CACHE operation is now formally defined in comments and more straightforward in implementation. B_CACHE for VMIO buffers is based on the validity of the backing store. B_CACHE for non-VMIO buffers is based simply on whether the buffer is B_INVAL or not (B_CACHE set if B_INVAL clear, and vise-versa). biodone() is now responsible for setting B_CACHE when a successful read completes. B_CACHE is also set when a bdwrite() is initiated and when a bwrite() is initiated. VFS VOP_BWRITE routines (there are only two - nfs_bwrite() and bwrite()) are now expected to set B_CACHE. This means that bowrite() and bawrite() also set B_CACHE indirectly. There are a number of places in the code which were previously using buf->b_bufsize (which is DEV_BSIZE aligned) when they should have been using buf->b_bcount. These have been fixed. getblk() now clears B_DONE on return because the rest of the system is so bad about dealing with B_DONE. Major fixes to NFS/TCP have been made. A server-side bug could cause requests to be lost by the server due to nfs_realign() overwriting other rpc's in the same TCP mbuf chain. The server's kernel must be recompiled to get the benefit of the fixes. Submitted by: Matthew Dillon <dillon@apollo.backplane.com>
1999-05-02 23:57:16 +00:00
r = (*pagertab[object->type]->pgo_getpages)(object, m, count, reqpage);
if (r == VM_PAGER_OK && m[reqpage]->valid != VM_PAGE_BITS_ALL) {
vm_page_zero_invalid(m[reqpage], TRUE);
}
return (r);
}
static inline int
vm_pager_get_pages_async(vm_object_t object, vm_page_t *m, int count,
int reqpage, pgo_getpages_iodone_t iodone, void *arg)
{
VM_OBJECT_ASSERT_WLOCKED(object);
return ((*pagertab[object->type]->pgo_getpages_async)(object, m,
count, reqpage, iodone, arg));
}
static __inline void
vm_pager_put_pages(
vm_object_t object,
vm_page_t *m,
int count,
int flags,
int *rtvals
) {
VM_OBJECT_ASSERT_WLOCKED(object);
(*pagertab[object->type]->pgo_putpages)
(object, m, count, flags, rtvals);
}
/*
* vm_pager_haspage
*
* Check to see if an object's pager has the requested page. The
* object's pager will also set before and after to give the caller
* some idea of the number of pages before and after the requested
* page can be I/O'd efficiently.
*
* The object must be locked.
*/
static __inline boolean_t
vm_pager_has_page(
vm_object_t object,
vm_pindex_t offset,
int *before,
int *after
) {
boolean_t ret;
VM_OBJECT_ASSERT_WLOCKED(object);
ret = (*pagertab[object->type]->pgo_haspage)
(object, offset, before, after);
return (ret);
}
/*
* vm_pager_page_unswapped
*
* Destroy swap associated with the page.
*
* The object containing the page must be locked.
* This function may not block.
*
* XXX: A much better name would be "vm_pager_page_dirtied()"
* XXX: It is not obvious if this could be profitably used by any
* XXX: pagers besides the swap_pager or if it should even be a
* XXX: generic pager_op in the first place.
*/
static __inline void
vm_pager_page_unswapped(vm_page_t m)
{
VM_OBJECT_ASSERT_LOCKED(m->object);
if (pagertab[m->object->type]->pgo_pageunswapped)
(*pagertab[m->object->type]->pgo_pageunswapped)(m);
}
struct cdev_pager_ops {
int (*cdev_pg_fault)(vm_object_t vm_obj, vm_ooffset_t offset,
int prot, vm_page_t *mres);
int (*cdev_pg_ctor)(void *handle, vm_ooffset_t size, vm_prot_t prot,
vm_ooffset_t foff, struct ucred *cred, u_short *color);
void (*cdev_pg_dtor)(void *handle);
};
vm_object_t cdev_pager_allocate(void *handle, enum obj_type tp,
struct cdev_pager_ops *ops, vm_ooffset_t size, vm_prot_t prot,
vm_ooffset_t foff, struct ucred *cred);
vm_object_t cdev_pager_lookup(void *handle);
void cdev_pager_free_page(vm_object_t object, vm_page_t m);
#endif /* _KERNEL */
These changes embody the support of the fully coherent merged VM buffer cache, much higher filesystem I/O performance, and much better paging performance. It represents the culmination of over 6 months of R&D. The majority of the merged VM/cache work is by John Dyson. The following highlights the most significant changes. Additionally, there are (mostly minor) changes to the various filesystem modules (nfs, msdosfs, etc) to support the new VM/buffer scheme. vfs_bio.c: Significant rewrite of most of vfs_bio to support the merged VM buffer cache scheme. The scheme is almost fully compatible with the old filesystem interface. Significant improvement in the number of opportunities for write clustering. vfs_cluster.c, vfs_subr.c Upgrade and performance enhancements in vfs layer code to support merged VM/buffer cache. Fixup of vfs_cluster to eliminate the bogus pagemove stuff. vm_object.c: Yet more improvements in the collapse code. Elimination of some windows that can cause list corruption. vm_pageout.c: Fixed it, it really works better now. Somehow in 2.0, some "enhancements" broke the code. This code has been reworked from the ground-up. vm_fault.c, vm_page.c, pmap.c, vm_object.c Support for small-block filesystems with merged VM/buffer cache scheme. pmap.c vm_map.c Dynamic kernel VM size, now we dont have to pre-allocate excessive numbers of kernel PTs. vm_glue.c Much simpler and more effective swapping code. No more gratuitous swapping. proc.h Fixed the problem that the p_lock flag was not being cleared on a fork. swap_pager.c, vnode_pager.c Removal of old vfs_bio cruft to support the past pseudo-coherency. Now the code doesn't need it anymore. machdep.c Changes to better support the parameter values for the merged VM/buffer cache scheme. machdep.c, kern_exec.c, vm_glue.c Implemented a seperate submap for temporary exec string space and another one to contain process upages. This eliminates all map fragmentation problems that previously existed. ffs_inode.c, ufs_inode.c, ufs_readwrite.c Changes for merged VM/buffer cache. Add "bypass" support for sneaking in on busy buffers. Submitted by: John Dyson and David Greenman
1995-01-09 16:06:02 +00:00
#endif /* _VM_PAGER_ */