freebsd-dev/sys/kern/kern_subr.c

433 lines
9.8 KiB
C
Raw Normal View History

1994-05-24 10:09:53 +00:00
/*
* Copyright (c) 1982, 1986, 1991, 1993
* The Regents of the University of California. All rights reserved.
* (c) UNIX System Laboratories, Inc.
* All or some portions of this file are derived from material licensed
* to the University of California by American Telephone and Telegraph
* Co. or Unix System Laboratories, Inc. and are reproduced herein with
* the permission of UNIX System Laboratories, Inc.
*
* 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.
* 3. All advertising materials mentioning features or use of this software
* must display the following acknowledgement:
* This product includes software developed by the University of
* California, Berkeley and its contributors.
* 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.
*
* @(#)kern_subr.c 8.3 (Berkeley) 1/21/94
1999-08-28 01:08:13 +00:00
* $FreeBSD$
1994-05-24 10:09:53 +00:00
*/
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/ktr.h>
#include <sys/lock.h>
#include <sys/mutex.h>
1994-05-24 10:09:53 +00:00
#include <sys/proc.h>
#include <sys/malloc.h>
#include <sys/resourcevar.h>
#include <sys/sysctl.h>
VM level code cleanups. 1) Start using TSM. Struct procs continue to point to upages structure, after being freed. Struct vmspace continues to point to pte object and kva space for kstack. u_map is now superfluous. 2) vm_map's don't need to be reference counted. They always exist either in the kernel or in a vmspace. The vmspaces are managed by reference counts. 3) Remove the "wired" vm_map nonsense. 4) No need to keep a cache of kernel stack kva's. 5) Get rid of strange looking ++var, and change to var++. 6) Change more data structures to use our "zone" allocator. Added struct proc, struct vmspace and struct vnode. This saves a significant amount of kva space and physical memory. Additionally, this enables TSM for the zone managed memory. 7) Keep ioopt disabled for now. 8) Remove the now bogus "single use" map concept. 9) Use generation counts or id's for data structures residing in TSM, where it allows us to avoid unneeded restart overhead during traversals, where blocking might occur. 10) Account better for memory deficits, so the pageout daemon will be able to make enough memory available (experimental.) 11) Fix some vnode locking problems. (From Tor, I think.) 12) Add a check in ufs_lookup, to avoid lots of unneeded calls to bcmp. (experimental.) 13) Significantly shrink, cleanup, and make slightly faster the vm_fault.c code. Use generation counts, get rid of unneded collpase operations, and clean up the cluster code. 14) Make vm_zone more suitable for TSM. This commit is partially as a result of discussions and contributions from other people, including DG, Tor Egge, PHK, and probably others that I have forgotten to attribute (so let me know, if I forgot.) This is not the infamous, final cleanup of the vnode stuff, but a necessary step. Vnode mgmt should be correct, but things might still change, and there is still some missing stuff (like ioopt, and physical backing of non-merged cache files, debugging of layering concepts.)
1998-01-22 17:30:44 +00:00
#include <sys/vnode.h>
#include <vm/vm.h>
#include <vm/vm_page.h>
#include <vm/vm_map.h>
1994-05-24 10:09:53 +00:00
SYSCTL_INT(_kern, KERN_IOV_MAX, iov_max, CTLFLAG_RD, NULL, UIO_MAXIOV,
"Maximum number of elements in an I/O vector; sysconf(_SC_IOV_MAX)");
int
1994-05-24 10:09:53 +00:00
uiomove(cp, n, uio)
register caddr_t cp;
register int n;
register struct uio *uio;
{
struct thread *td = curthread;
1994-05-24 10:09:53 +00:00
register struct iovec *iov;
u_int cnt;
int error = 0;
int save = 0;
1994-05-24 10:09:53 +00:00
KASSERT(uio->uio_rw == UIO_READ || uio->uio_rw == UIO_WRITE,
1999-01-10 01:58:29 +00:00
("uiomove: mode"));
KASSERT(uio->uio_segflg != UIO_USERSPACE || uio->uio_td == curthread,
1999-01-10 01:58:29 +00:00
("uiomove proc"));
if (td) {
mtx_lock_spin(&sched_lock);
save = td->td_flags & TDF_DEADLKTREAT;
td->td_flags |= TDF_DEADLKTREAT;
mtx_unlock_spin(&sched_lock);
}
1994-05-24 10:09:53 +00:00
while (n > 0 && uio->uio_resid) {
iov = uio->uio_iov;
cnt = iov->iov_len;
if (cnt == 0) {
uio->uio_iov++;
uio->uio_iovcnt--;
continue;
}
if (cnt > n)
cnt = n;
1995-02-12 09:11:47 +00:00
1994-05-24 10:09:53 +00:00
switch (uio->uio_segflg) {
case UIO_USERSPACE:
case UIO_USERISPACE:
if (ticks - PCPU_GET(switchticks) >= hogticks)
uio_yield();
1994-05-24 10:09:53 +00:00
if (uio->uio_rw == UIO_READ)
error = copyout(cp, iov->iov_base, cnt);
else
error = copyin(iov->iov_base, cp, cnt);
if (error)
break;
1994-05-24 10:09:53 +00:00
break;
case UIO_SYSSPACE:
if (uio->uio_rw == UIO_READ)
bcopy((caddr_t)cp, iov->iov_base, cnt);
else
bcopy(iov->iov_base, (caddr_t)cp, cnt);
break;
case UIO_NOCOPY:
break;
}
iov->iov_base += cnt;
iov->iov_len -= cnt;
uio->uio_resid -= cnt;
uio->uio_offset += cnt;
cp += cnt;
n -= cnt;
}
if (td != curthread) printf("uiomove: IT CHANGED!");
td = curthread; /* Might things have changed in copyin/copyout? */
if (td) {
mtx_lock_spin(&sched_lock);
td->td_flags = (td->td_flags & ~TDF_DEADLKTREAT) | save;
mtx_unlock_spin(&sched_lock);
}
return (error);
}
int
uiomoveco(cp, n, uio, obj)
caddr_t cp;
int n;
struct uio *uio;
struct vm_object *obj;
{
struct iovec *iov;
u_int cnt;
int error;
KASSERT(uio->uio_rw == UIO_READ || uio->uio_rw == UIO_WRITE,
1999-01-10 01:58:29 +00:00
("uiomoveco: mode"));
KASSERT(uio->uio_segflg != UIO_USERSPACE || uio->uio_td == curthread,
1999-01-10 01:58:29 +00:00
("uiomoveco proc"));
while (n > 0 && uio->uio_resid) {
iov = uio->uio_iov;
cnt = iov->iov_len;
if (cnt == 0) {
uio->uio_iov++;
uio->uio_iovcnt--;
continue;
}
if (cnt > n)
cnt = n;
switch (uio->uio_segflg) {
case UIO_USERSPACE:
case UIO_USERISPACE:
if (ticks - PCPU_GET(switchticks) >= hogticks)
uio_yield();
if (uio->uio_rw == UIO_READ) {
These changes appear to give us benefits with both small (32MB) and large (1G) memory machine configurations. I was able to run 'dbench 32' on a 32MB system without bring the machine to a grinding halt. * buffer cache hash table now dynamically allocated. This will have no effect on memory consumption for smaller systems and will help scale the buffer cache for larger systems. * minor enhancement to pmap_clearbit(). I noticed that all the calls to it used constant arguments. Making it an inline allows the constants to propogate to deeper inlines and should produce better code. * removal of inherent vfs_ioopt support through the emplacement of appropriate #ifdef's, with John's permission. If we do not find a use for it by the end of the year we will remove it entirely. * removal of getnewbufloops* counters & sysctl's - no longer necessary for debugging, getnewbuf() is now optimal. * buffer hash table functions removed from sys/buf.h and localized to vfs_bio.c * VFS_BIO_NEED_DIRTYFLUSH flag and support code added ( bwillwrite() ), allowing processes to block when too many dirty buffers are present in the system. * removal of a softdep test in bdwrite() that is no longer necessary now that bdwrite() no longer attempts to flush dirty buffers. * slight optimization added to bqrelse() - there is no reason to test for available buffer space on B_DELWRI buffers. * addition of reverse-scanning code to vfs_bio_awrite(). vfs_bio_awrite() will attempt to locate clusterable areas in both the forward and reverse direction relative to the offset of the buffer passed to it. This will probably not make much of a difference now, but I believe we will start to rely on it heavily in the future if we decide to shift some of the burden of the clustering closer to the actual I/O initiation. * Removal of the newbufcnt and lastnewbuf counters that Kirk added. They do not fix any race conditions that haven't already been fixed by the gbincore() test done after the only call to getnewbuf(). getnewbuf() is a static, so there is no chance of it being misused by other modules. ( Unless Kirk can think of a specific thing that this code fixes. I went through it very carefully and didn't see anything ). * removal of VOP_ISLOCKED() check in flushbufqueues(). I do not think this check is necessary, the buffer should flush properly whether the vnode is locked or not. ( yes? ). * removal of extra arguments passed to getnewbuf() that are not necessary. * missed cluster_wbuild() that had to be a cluster_wbuild_wb() in vfs_cluster.c * vn_write() now calls bwillwrite() *PRIOR* to locking the vnode, which should greatly aid flushing operations in heavy load situations - both the pageout and update daemons will be able to operate more efficiently. * removal of b_usecount. We may add it back in later but for now it is useless. Prior implementations of the buffer cache never had enough buffers for it to be useful, and current implementations which make more buffers available might not benefit relative to the amount of sophistication required to implement a b_usecount. Straight LRU should work just as well, especially when most things are VMIO backed. I expect that (even though John will not like this assumption) directories will become VMIO backed some point soon. Submitted by: Matthew Dillon <dillon@backplane.com> Reviewed by: Kirk McKusick <mckusick@mckusick.com>
1999-07-08 06:06:00 +00:00
#ifdef ENABLE_VFS_IOOPT
VM level code cleanups. 1) Start using TSM. Struct procs continue to point to upages structure, after being freed. Struct vmspace continues to point to pte object and kva space for kstack. u_map is now superfluous. 2) vm_map's don't need to be reference counted. They always exist either in the kernel or in a vmspace. The vmspaces are managed by reference counts. 3) Remove the "wired" vm_map nonsense. 4) No need to keep a cache of kernel stack kva's. 5) Get rid of strange looking ++var, and change to var++. 6) Change more data structures to use our "zone" allocator. Added struct proc, struct vmspace and struct vnode. This saves a significant amount of kva space and physical memory. Additionally, this enables TSM for the zone managed memory. 7) Keep ioopt disabled for now. 8) Remove the now bogus "single use" map concept. 9) Use generation counts or id's for data structures residing in TSM, where it allows us to avoid unneeded restart overhead during traversals, where blocking might occur. 10) Account better for memory deficits, so the pageout daemon will be able to make enough memory available (experimental.) 11) Fix some vnode locking problems. (From Tor, I think.) 12) Add a check in ufs_lookup, to avoid lots of unneeded calls to bcmp. (experimental.) 13) Significantly shrink, cleanup, and make slightly faster the vm_fault.c code. Use generation counts, get rid of unneded collpase operations, and clean up the cluster code. 14) Make vm_zone more suitable for TSM. This commit is partially as a result of discussions and contributions from other people, including DG, Tor Egge, PHK, and probably others that I have forgotten to attribute (so let me know, if I forgot.) This is not the infamous, final cleanup of the vnode stuff, but a necessary step. Vnode mgmt should be correct, but things might still change, and there is still some missing stuff (like ioopt, and physical backing of non-merged cache files, debugging of layering concepts.)
1998-01-22 17:30:44 +00:00
if (vfs_ioopt && ((cnt & PAGE_MASK) == 0) &&
((((intptr_t) iov->iov_base) & PAGE_MASK) == 0) &&
((uio->uio_offset & PAGE_MASK) == 0) &&
((((intptr_t) cp) & PAGE_MASK) == 0)) {
error = vm_uiomove(&curproc->p_vmspace->vm_map, obj,
uio->uio_offset, cnt,
(vm_offset_t) iov->iov_base, NULL);
These changes appear to give us benefits with both small (32MB) and large (1G) memory machine configurations. I was able to run 'dbench 32' on a 32MB system without bring the machine to a grinding halt. * buffer cache hash table now dynamically allocated. This will have no effect on memory consumption for smaller systems and will help scale the buffer cache for larger systems. * minor enhancement to pmap_clearbit(). I noticed that all the calls to it used constant arguments. Making it an inline allows the constants to propogate to deeper inlines and should produce better code. * removal of inherent vfs_ioopt support through the emplacement of appropriate #ifdef's, with John's permission. If we do not find a use for it by the end of the year we will remove it entirely. * removal of getnewbufloops* counters & sysctl's - no longer necessary for debugging, getnewbuf() is now optimal. * buffer hash table functions removed from sys/buf.h and localized to vfs_bio.c * VFS_BIO_NEED_DIRTYFLUSH flag and support code added ( bwillwrite() ), allowing processes to block when too many dirty buffers are present in the system. * removal of a softdep test in bdwrite() that is no longer necessary now that bdwrite() no longer attempts to flush dirty buffers. * slight optimization added to bqrelse() - there is no reason to test for available buffer space on B_DELWRI buffers. * addition of reverse-scanning code to vfs_bio_awrite(). vfs_bio_awrite() will attempt to locate clusterable areas in both the forward and reverse direction relative to the offset of the buffer passed to it. This will probably not make much of a difference now, but I believe we will start to rely on it heavily in the future if we decide to shift some of the burden of the clustering closer to the actual I/O initiation. * Removal of the newbufcnt and lastnewbuf counters that Kirk added. They do not fix any race conditions that haven't already been fixed by the gbincore() test done after the only call to getnewbuf(). getnewbuf() is a static, so there is no chance of it being misused by other modules. ( Unless Kirk can think of a specific thing that this code fixes. I went through it very carefully and didn't see anything ). * removal of VOP_ISLOCKED() check in flushbufqueues(). I do not think this check is necessary, the buffer should flush properly whether the vnode is locked or not. ( yes? ). * removal of extra arguments passed to getnewbuf() that are not necessary. * missed cluster_wbuild() that had to be a cluster_wbuild_wb() in vfs_cluster.c * vn_write() now calls bwillwrite() *PRIOR* to locking the vnode, which should greatly aid flushing operations in heavy load situations - both the pageout and update daemons will be able to operate more efficiently. * removal of b_usecount. We may add it back in later but for now it is useless. Prior implementations of the buffer cache never had enough buffers for it to be useful, and current implementations which make more buffers available might not benefit relative to the amount of sophistication required to implement a b_usecount. Straight LRU should work just as well, especially when most things are VMIO backed. I expect that (even though John will not like this assumption) directories will become VMIO backed some point soon. Submitted by: Matthew Dillon <dillon@backplane.com> Reviewed by: Kirk McKusick <mckusick@mckusick.com>
1999-07-08 06:06:00 +00:00
} else
#endif
{
error = copyout(cp, iov->iov_base, cnt);
}
} else {
error = copyin(iov->iov_base, cp, cnt);
}
if (error)
return (error);
break;
case UIO_SYSSPACE:
if (uio->uio_rw == UIO_READ)
bcopy((caddr_t)cp, iov->iov_base, cnt);
else
bcopy(iov->iov_base, (caddr_t)cp, cnt);
1994-05-24 10:09:53 +00:00
break;
case UIO_NOCOPY:
break;
1994-05-24 10:09:53 +00:00
}
iov->iov_base += cnt;
iov->iov_len -= cnt;
uio->uio_resid -= cnt;
uio->uio_offset += cnt;
cp += cnt;
n -= cnt;
}
1995-02-12 09:11:47 +00:00
return (0);
1994-05-24 10:09:53 +00:00
}
These changes appear to give us benefits with both small (32MB) and large (1G) memory machine configurations. I was able to run 'dbench 32' on a 32MB system without bring the machine to a grinding halt. * buffer cache hash table now dynamically allocated. This will have no effect on memory consumption for smaller systems and will help scale the buffer cache for larger systems. * minor enhancement to pmap_clearbit(). I noticed that all the calls to it used constant arguments. Making it an inline allows the constants to propogate to deeper inlines and should produce better code. * removal of inherent vfs_ioopt support through the emplacement of appropriate #ifdef's, with John's permission. If we do not find a use for it by the end of the year we will remove it entirely. * removal of getnewbufloops* counters & sysctl's - no longer necessary for debugging, getnewbuf() is now optimal. * buffer hash table functions removed from sys/buf.h and localized to vfs_bio.c * VFS_BIO_NEED_DIRTYFLUSH flag and support code added ( bwillwrite() ), allowing processes to block when too many dirty buffers are present in the system. * removal of a softdep test in bdwrite() that is no longer necessary now that bdwrite() no longer attempts to flush dirty buffers. * slight optimization added to bqrelse() - there is no reason to test for available buffer space on B_DELWRI buffers. * addition of reverse-scanning code to vfs_bio_awrite(). vfs_bio_awrite() will attempt to locate clusterable areas in both the forward and reverse direction relative to the offset of the buffer passed to it. This will probably not make much of a difference now, but I believe we will start to rely on it heavily in the future if we decide to shift some of the burden of the clustering closer to the actual I/O initiation. * Removal of the newbufcnt and lastnewbuf counters that Kirk added. They do not fix any race conditions that haven't already been fixed by the gbincore() test done after the only call to getnewbuf(). getnewbuf() is a static, so there is no chance of it being misused by other modules. ( Unless Kirk can think of a specific thing that this code fixes. I went through it very carefully and didn't see anything ). * removal of VOP_ISLOCKED() check in flushbufqueues(). I do not think this check is necessary, the buffer should flush properly whether the vnode is locked or not. ( yes? ). * removal of extra arguments passed to getnewbuf() that are not necessary. * missed cluster_wbuild() that had to be a cluster_wbuild_wb() in vfs_cluster.c * vn_write() now calls bwillwrite() *PRIOR* to locking the vnode, which should greatly aid flushing operations in heavy load situations - both the pageout and update daemons will be able to operate more efficiently. * removal of b_usecount. We may add it back in later but for now it is useless. Prior implementations of the buffer cache never had enough buffers for it to be useful, and current implementations which make more buffers available might not benefit relative to the amount of sophistication required to implement a b_usecount. Straight LRU should work just as well, especially when most things are VMIO backed. I expect that (even though John will not like this assumption) directories will become VMIO backed some point soon. Submitted by: Matthew Dillon <dillon@backplane.com> Reviewed by: Kirk McKusick <mckusick@mckusick.com>
1999-07-08 06:06:00 +00:00
#ifdef ENABLE_VFS_IOOPT
int
uioread(n, uio, obj, nread)
int n;
struct uio *uio;
struct vm_object *obj;
int *nread;
{
int npagesmoved;
struct iovec *iov;
u_int cnt, tcnt;
int error;
*nread = 0;
if (vfs_ioopt < 2)
VM level code cleanups. 1) Start using TSM. Struct procs continue to point to upages structure, after being freed. Struct vmspace continues to point to pte object and kva space for kstack. u_map is now superfluous. 2) vm_map's don't need to be reference counted. They always exist either in the kernel or in a vmspace. The vmspaces are managed by reference counts. 3) Remove the "wired" vm_map nonsense. 4) No need to keep a cache of kernel stack kva's. 5) Get rid of strange looking ++var, and change to var++. 6) Change more data structures to use our "zone" allocator. Added struct proc, struct vmspace and struct vnode. This saves a significant amount of kva space and physical memory. Additionally, this enables TSM for the zone managed memory. 7) Keep ioopt disabled for now. 8) Remove the now bogus "single use" map concept. 9) Use generation counts or id's for data structures residing in TSM, where it allows us to avoid unneeded restart overhead during traversals, where blocking might occur. 10) Account better for memory deficits, so the pageout daemon will be able to make enough memory available (experimental.) 11) Fix some vnode locking problems. (From Tor, I think.) 12) Add a check in ufs_lookup, to avoid lots of unneeded calls to bcmp. (experimental.) 13) Significantly shrink, cleanup, and make slightly faster the vm_fault.c code. Use generation counts, get rid of unneded collpase operations, and clean up the cluster code. 14) Make vm_zone more suitable for TSM. This commit is partially as a result of discussions and contributions from other people, including DG, Tor Egge, PHK, and probably others that I have forgotten to attribute (so let me know, if I forgot.) This is not the infamous, final cleanup of the vnode stuff, but a necessary step. Vnode mgmt should be correct, but things might still change, and there is still some missing stuff (like ioopt, and physical backing of non-merged cache files, debugging of layering concepts.)
1998-01-22 17:30:44 +00:00
return 0;
error = 0;
while (n > 0 && uio->uio_resid) {
iov = uio->uio_iov;
cnt = iov->iov_len;
if (cnt == 0) {
uio->uio_iov++;
uio->uio_iovcnt--;
continue;
}
if (cnt > n)
cnt = n;
if ((uio->uio_segflg == UIO_USERSPACE) &&
((((intptr_t) iov->iov_base) & PAGE_MASK) == 0) &&
((uio->uio_offset & PAGE_MASK) == 0) ) {
if (cnt < PAGE_SIZE)
break;
cnt &= ~PAGE_MASK;
if (ticks - PCPU_GET(switchticks) >= hogticks)
uio_yield();
error = vm_uiomove(&curproc->p_vmspace->vm_map, obj,
uio->uio_offset, cnt,
(vm_offset_t) iov->iov_base, &npagesmoved);
if (npagesmoved == 0)
break;
tcnt = npagesmoved * PAGE_SIZE;
cnt = tcnt;
if (error)
break;
iov->iov_base += cnt;
iov->iov_len -= cnt;
uio->uio_resid -= cnt;
uio->uio_offset += cnt;
*nread += cnt;
n -= cnt;
} else {
break;
}
}
return error;
}
These changes appear to give us benefits with both small (32MB) and large (1G) memory machine configurations. I was able to run 'dbench 32' on a 32MB system without bring the machine to a grinding halt. * buffer cache hash table now dynamically allocated. This will have no effect on memory consumption for smaller systems and will help scale the buffer cache for larger systems. * minor enhancement to pmap_clearbit(). I noticed that all the calls to it used constant arguments. Making it an inline allows the constants to propogate to deeper inlines and should produce better code. * removal of inherent vfs_ioopt support through the emplacement of appropriate #ifdef's, with John's permission. If we do not find a use for it by the end of the year we will remove it entirely. * removal of getnewbufloops* counters & sysctl's - no longer necessary for debugging, getnewbuf() is now optimal. * buffer hash table functions removed from sys/buf.h and localized to vfs_bio.c * VFS_BIO_NEED_DIRTYFLUSH flag and support code added ( bwillwrite() ), allowing processes to block when too many dirty buffers are present in the system. * removal of a softdep test in bdwrite() that is no longer necessary now that bdwrite() no longer attempts to flush dirty buffers. * slight optimization added to bqrelse() - there is no reason to test for available buffer space on B_DELWRI buffers. * addition of reverse-scanning code to vfs_bio_awrite(). vfs_bio_awrite() will attempt to locate clusterable areas in both the forward and reverse direction relative to the offset of the buffer passed to it. This will probably not make much of a difference now, but I believe we will start to rely on it heavily in the future if we decide to shift some of the burden of the clustering closer to the actual I/O initiation. * Removal of the newbufcnt and lastnewbuf counters that Kirk added. They do not fix any race conditions that haven't already been fixed by the gbincore() test done after the only call to getnewbuf(). getnewbuf() is a static, so there is no chance of it being misused by other modules. ( Unless Kirk can think of a specific thing that this code fixes. I went through it very carefully and didn't see anything ). * removal of VOP_ISLOCKED() check in flushbufqueues(). I do not think this check is necessary, the buffer should flush properly whether the vnode is locked or not. ( yes? ). * removal of extra arguments passed to getnewbuf() that are not necessary. * missed cluster_wbuild() that had to be a cluster_wbuild_wb() in vfs_cluster.c * vn_write() now calls bwillwrite() *PRIOR* to locking the vnode, which should greatly aid flushing operations in heavy load situations - both the pageout and update daemons will be able to operate more efficiently. * removal of b_usecount. We may add it back in later but for now it is useless. Prior implementations of the buffer cache never had enough buffers for it to be useful, and current implementations which make more buffers available might not benefit relative to the amount of sophistication required to implement a b_usecount. Straight LRU should work just as well, especially when most things are VMIO backed. I expect that (even though John will not like this assumption) directories will become VMIO backed some point soon. Submitted by: Matthew Dillon <dillon@backplane.com> Reviewed by: Kirk McKusick <mckusick@mckusick.com>
1999-07-08 06:06:00 +00:00
#endif
1994-05-24 10:09:53 +00:00
/*
* Give next character to user as result of read.
*/
int
1994-05-24 10:09:53 +00:00
ureadc(c, uio)
register int c;
register struct uio *uio;
{
register struct iovec *iov;
again:
if (uio->uio_iovcnt == 0 || uio->uio_resid == 0)
panic("ureadc");
iov = uio->uio_iov;
if (iov->iov_len == 0) {
uio->uio_iovcnt--;
uio->uio_iov++;
goto again;
}
switch (uio->uio_segflg) {
case UIO_USERSPACE:
if (subyte(iov->iov_base, c) < 0)
return (EFAULT);
break;
case UIO_SYSSPACE:
*iov->iov_base = c;
break;
case UIO_USERISPACE:
if (suibyte(iov->iov_base, c) < 0)
return (EFAULT);
break;
case UIO_NOCOPY:
break;
1994-05-24 10:09:53 +00:00
}
iov->iov_base++;
iov->iov_len--;
uio->uio_resid--;
uio->uio_offset++;
return (0);
}
/*
* General routine to allocate a hash table.
*/
void *
hashinit(elements, type, hashmask)
int elements;
struct malloc_type *type;
1994-05-24 10:09:53 +00:00
u_long *hashmask;
{
long hashsize;
LIST_HEAD(generic, generic) *hashtbl;
1994-05-24 10:09:53 +00:00
int i;
if (elements <= 0)
1995-05-08 23:11:12 +00:00
panic("hashinit: bad elements");
1994-05-24 10:09:53 +00:00
for (hashsize = 1; hashsize <= elements; hashsize <<= 1)
continue;
hashsize >>= 1;
hashtbl = malloc((u_long)hashsize * sizeof(*hashtbl), type, M_WAITOK);
for (i = 0; i < hashsize; i++)
LIST_INIT(&hashtbl[i]);
*hashmask = hashsize - 1;
return (hashtbl);
}
static int primes[] = { 1, 13, 31, 61, 127, 251, 509, 761, 1021, 1531, 2039,
2557, 3067, 3583, 4093, 4603, 5119, 5623, 6143, 6653,
7159, 7673, 8191, 12281, 16381, 24571, 32749 };
#define NPRIMES (sizeof(primes) / sizeof(primes[0]))
/*
* General routine to allocate a prime number sized hash table.
*/
void *
phashinit(elements, type, nentries)
int elements;
struct malloc_type *type;
u_long *nentries;
{
long hashsize;
LIST_HEAD(generic, generic) *hashtbl;
int i;
if (elements <= 0)
1995-05-08 23:11:12 +00:00
panic("phashinit: bad elements");
for (i = 1, hashsize = primes[1]; hashsize <= elements;) {
i++;
if (i == NPRIMES)
break;
hashsize = primes[i];
}
hashsize = primes[i - 1];
hashtbl = malloc((u_long)hashsize * sizeof(*hashtbl), type, M_WAITOK);
for (i = 0; i < hashsize; i++)
LIST_INIT(&hashtbl[i]);
*nentries = hashsize;
return (hashtbl);
}
void
uio_yield()
{
struct thread *td;
td = curthread;
Change and clean the mutex lock interface. mtx_enter(lock, type) becomes: mtx_lock(lock) for sleep locks (MTX_DEF-initialized locks) mtx_lock_spin(lock) for spin locks (MTX_SPIN-initialized) similarily, for releasing a lock, we now have: mtx_unlock(lock) for MTX_DEF and mtx_unlock_spin(lock) for MTX_SPIN. We change the caller interface for the two different types of locks because the semantics are entirely different for each case, and this makes it explicitly clear and, at the same time, it rids us of the extra `type' argument. The enter->lock and exit->unlock change has been made with the idea that we're "locking data" and not "entering locked code" in mind. Further, remove all additional "flags" previously passed to the lock acquire/release routines with the exception of two: MTX_QUIET and MTX_NOSWITCH The functionality of these flags is preserved and they can be passed to the lock/unlock routines by calling the corresponding wrappers: mtx_{lock, unlock}_flags(lock, flag(s)) and mtx_{lock, unlock}_spin_flags(lock, flag(s)) for MTX_DEF and MTX_SPIN locks, respectively. Re-inline some lock acq/rel code; in the sleep lock case, we only inline the _obtain_lock()s in order to ensure that the inlined code fits into a cache line. In the spin lock case, we inline recursion and actually only perform a function call if we need to spin. This change has been made with the idea that we generally tend to avoid spin locks and that also the spin locks that we do have and are heavily used (i.e. sched_lock) do recurse, and therefore in an effort to reduce function call overhead for some architectures (such as alpha), we inline recursion for this case. Create a new malloc type for the witness code and retire from using the M_DEV type. The new type is called M_WITNESS and is only declared if WITNESS is enabled. Begin cleaning up some machdep/mutex.h code - specifically updated the "optimized" inlined code in alpha/mutex.h and wrote MTX_LOCK_SPIN and MTX_UNLOCK_SPIN asm macros for the i386/mutex.h as we presently need those. Finally, caught up to the interface changes in all sys code. Contributors: jake, jhb, jasone (in no particular order)
2001-02-09 06:11:45 +00:00
mtx_lock_spin(&sched_lock);
Change the preemption code for software interrupt thread schedules and mutex releases to not require flags for the cases when preemption is not allowed: The purpose of the MTX_NOSWITCH and SWI_NOSWITCH flags is to prevent switching to a higher priority thread on mutex releease and swi schedule, respectively when that switch is not safe. Now that the critical section API maintains a per-thread nesting count, the kernel can easily check whether or not it should switch without relying on flags from the programmer. This fixes a few bugs in that all current callers of swi_sched() used SWI_NOSWITCH, when in fact, only the ones called from fast interrupt handlers and the swi_sched of softclock needed this flag. Note that to ensure that swi_sched()'s in clock and fast interrupt handlers do not switch, these handlers have to be explicitly wrapped in critical_enter/exit pairs. Presently, just wrapping the handlers is sufficient, but in the future with the fully preemptive kernel, the interrupt must be EOI'd before critical_exit() is called. (critical_exit() can switch due to a deferred preemption in a fully preemptive kernel.) I've tested the changes to the interrupt code on i386 and alpha. I have not tested ia64, but the interrupt code is almost identical to the alpha code, so I expect it will work fine. PowerPC and ARM do not yet have interrupt code in the tree so they shouldn't be broken. Sparc64 is broken, but that's been ok'd by jake and tmm who will be fixing the interrupt code for sparc64 shortly. Reviewed by: peter Tested on: i386, alpha
2002-01-05 08:47:13 +00:00
DROP_GIANT();
td->td_ksegrp->kg_pri.pri_level = td->td_ksegrp->kg_pri.pri_user;
setrunqueue(td);
td->td_proc->p_stats->p_ru.ru_nivcsw++;
mi_switch();
Change and clean the mutex lock interface. mtx_enter(lock, type) becomes: mtx_lock(lock) for sleep locks (MTX_DEF-initialized locks) mtx_lock_spin(lock) for spin locks (MTX_SPIN-initialized) similarily, for releasing a lock, we now have: mtx_unlock(lock) for MTX_DEF and mtx_unlock_spin(lock) for MTX_SPIN. We change the caller interface for the two different types of locks because the semantics are entirely different for each case, and this makes it explicitly clear and, at the same time, it rids us of the extra `type' argument. The enter->lock and exit->unlock change has been made with the idea that we're "locking data" and not "entering locked code" in mind. Further, remove all additional "flags" previously passed to the lock acquire/release routines with the exception of two: MTX_QUIET and MTX_NOSWITCH The functionality of these flags is preserved and they can be passed to the lock/unlock routines by calling the corresponding wrappers: mtx_{lock, unlock}_flags(lock, flag(s)) and mtx_{lock, unlock}_spin_flags(lock, flag(s)) for MTX_DEF and MTX_SPIN locks, respectively. Re-inline some lock acq/rel code; in the sleep lock case, we only inline the _obtain_lock()s in order to ensure that the inlined code fits into a cache line. In the spin lock case, we inline recursion and actually only perform a function call if we need to spin. This change has been made with the idea that we generally tend to avoid spin locks and that also the spin locks that we do have and are heavily used (i.e. sched_lock) do recurse, and therefore in an effort to reduce function call overhead for some architectures (such as alpha), we inline recursion for this case. Create a new malloc type for the witness code and retire from using the M_DEV type. The new type is called M_WITNESS and is only declared if WITNESS is enabled. Begin cleaning up some machdep/mutex.h code - specifically updated the "optimized" inlined code in alpha/mutex.h and wrote MTX_LOCK_SPIN and MTX_UNLOCK_SPIN asm macros for the i386/mutex.h as we presently need those. Finally, caught up to the interface changes in all sys code. Contributors: jake, jhb, jasone (in no particular order)
2001-02-09 06:11:45 +00:00
mtx_unlock_spin(&sched_lock);
PICKUP_GIANT();
}
int
copyinfrom(const void *src, void *dst, size_t len, int seg)
{
int error = 0;
switch (seg) {
case UIO_USERSPACE:
error = copyin(src, dst, len);
break;
case UIO_SYSSPACE:
bcopy(src, dst, len);
break;
default:
panic("copyinfrom: bad seg %d\n", seg);
}
return (error);
}
int
copyinstrfrom(const void *src, void *dst, size_t len, size_t *copied, int seg)
{
int error = 0;
switch (seg) {
case UIO_USERSPACE:
error = copyinstr(src, dst, len, copied);
break;
case UIO_SYSSPACE:
error = copystr(src, dst, len, copied);
break;
default:
panic("copyinstrfrom: bad seg %d\n", seg);
}
return (error);
}