2005-01-06 22:18:23 +00:00
|
|
|
/*-
|
2003-10-23 06:41:59 +00:00
|
|
|
* Copyright (c) 2003 The FreeBSD Project
|
2000-09-29 13:46:07 +00:00
|
|
|
* All rights reserved.
|
|
|
|
|
*
|
2003-10-23 06:41:59 +00:00
|
|
|
* 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.
|
2000-09-29 13:46:07 +00:00
|
|
|
*
|
2003-10-23 06:41:59 +00:00
|
|
|
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``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 AUTHOR 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.
|
2000-09-29 13:46:07 +00:00
|
|
|
*
|
2003-10-23 06:41:59 +00:00
|
|
|
* $FreeBSD$
|
2000-09-29 13:46:07 +00:00
|
|
|
*/
|
|
|
|
|
|
2001-12-06 18:17:02 +00:00
|
|
|
#ifndef _MACHINE_PROC_H_
|
|
|
|
|
#define _MACHINE_PROC_H_
|
|
|
|
|
|
2001-09-12 08:38:13 +00:00
|
|
|
struct mdthread {
|
Improve SMP support:
o Allocate a VHPT per CPU. The VHPT is a hash table that the CPU
uses to look up translations it can't find in the TLB. As such,
the VHPT serves as a level 1 cache (the TLB being a level 0 cache)
and best results are obtained when it's not shared between CPUs.
The collision chain (i.e. the hash bucket) is shared between CPUs,
as all buckets together constitute our collection of PTEs. To
achieve this, the collision chain does not point to the first PTE
in the list anymore, but to a hash bucket head structure. The
head structure contains the pointer to the first PTE in the list,
as well as a mutex to lock the bucket. Thus, each bucket is locked
independently of each other. With at least 1024 buckets in the VHPT,
this provides for sufficiently finei-grained locking to make the
ssolution scalable to large SMP machines.
o Add synchronisation to the lazy FP context switching. We do this
with a seperate per-thread lock. On SMP machines the lazy high FP
context switching without synchronisation caused inconsistent
state, which resulted in a panic. Since the use of the high FP
registers is not common, it's possible that races exist. The ia64
package build has proven to be a good stress test, so this will
get plenty of exercise in the near future.
o Don't use the local ID of the processor we want to send the IPI to
as the argument to ipi_send(). use the struct pcpu pointer instead.
The reason for this is that IPI delivery is unreliable. It has been
observed that sending an IPI to a CPU causes it to receive a stray
external interrupt. As such, we need a way to make the delivery
reliable. The intended solution is to queue requests in the target
CPU's per-CPU structure and use a single IPI to inform the CPU that
there's a new entry in the queue. If that IPI gets lost, the CPU
can check it's queue at any convenient time (such as for each
clock interrupt). This also allows us to send requests to a CPU
without interrupting it, if such would be beneficial.
With these changes SMP is almost working. There are still some random
process crashes and the machine can hang due to having the IPI lost
that deals with the high FP context switch.
The overhead of introducing the hash bucket head structure results
in a performance degradation of about 1% for UP (extra pointer
indirection). This is surprisingly small and is offset by gaining
reasonably/good scalable SMP support.
2005-08-06 20:28:19 +00:00
|
|
|
struct mtx md_highfp_mtx;
|
Divorce critical sections from spinlocks. Critical sections as denoted by
critical_enter() and critical_exit() are now solely a mechanism for
deferring kernel preemptions. They no longer have any affect on
interrupts. This means that standalone critical sections are now very
cheap as they are simply unlocked integer increments and decrements for the
common case.
Spin mutexes now use a separate KPI implemented in MD code: spinlock_enter()
and spinlock_exit(). This KPI is responsible for providing whatever MD
guarantees are needed to ensure that a thread holding a spin lock won't
be preempted by any other code that will try to lock the same lock. For
now all archs continue to block interrupts in a "spinlock section" as they
did formerly in all critical sections. Note that I've also taken this
opportunity to push a few things into MD code rather than MI. For example,
critical_fork_exit() no longer exists. Instead, MD code ensures that new
threads have the correct state when they are created. Also, we no longer
try to fixup the idlethreads for APs in MI code. Instead, each arch sets
the initial curthread and adjusts the state of the idle thread it borrows
in order to perform the initial context switch.
This change is largely a big NOP, but the cleaner separation it provides
will allow for more efficient alternative locking schemes in other parts
of the kernel (bare critical sections rather than per-CPU spin mutexes
for per-CPU data for example).
Reviewed by: grehan, cognet, arch@, others
Tested on: i386, alpha, sparc64, powerpc, arm, possibly more
2005-04-04 21:53:56 +00:00
|
|
|
int md_spinlock_count; /* (k) */
|
Improve SMP support:
o Allocate a VHPT per CPU. The VHPT is a hash table that the CPU
uses to look up translations it can't find in the TLB. As such,
the VHPT serves as a level 1 cache (the TLB being a level 0 cache)
and best results are obtained when it's not shared between CPUs.
The collision chain (i.e. the hash bucket) is shared between CPUs,
as all buckets together constitute our collection of PTEs. To
achieve this, the collision chain does not point to the first PTE
in the list anymore, but to a hash bucket head structure. The
head structure contains the pointer to the first PTE in the list,
as well as a mutex to lock the bucket. Thus, each bucket is locked
independently of each other. With at least 1024 buckets in the VHPT,
this provides for sufficiently finei-grained locking to make the
ssolution scalable to large SMP machines.
o Add synchronisation to the lazy FP context switching. We do this
with a seperate per-thread lock. On SMP machines the lazy high FP
context switching without synchronisation caused inconsistent
state, which resulted in a panic. Since the use of the high FP
registers is not common, it's possible that races exist. The ia64
package build has proven to be a good stress test, so this will
get plenty of exercise in the near future.
o Don't use the local ID of the processor we want to send the IPI to
as the argument to ipi_send(). use the struct pcpu pointer instead.
The reason for this is that IPI delivery is unreliable. It has been
observed that sending an IPI to a CPU causes it to receive a stray
external interrupt. As such, we need a way to make the delivery
reliable. The intended solution is to queue requests in the target
CPU's per-CPU structure and use a single IPI to inform the CPU that
there's a new entry in the queue. If that IPI gets lost, the CPU
can check it's queue at any convenient time (such as for each
clock interrupt). This also allows us to send requests to a CPU
without interrupting it, if such would be beneficial.
With these changes SMP is almost working. There are still some random
process crashes and the machine can hang due to having the IPI lost
that deals with the high FP context switch.
The overhead of introducing the hash bucket head structure results
in a performance degradation of about 1% for UP (extra pointer
indirection). This is surprisingly small and is offset by gaining
reasonably/good scalable SMP support.
2005-08-06 20:28:19 +00:00
|
|
|
int md_saved_intr; /* (k) */
|
2000-09-29 13:46:07 +00:00
|
|
|
};
|
|
|
|
|
|
2001-09-12 08:38:13 +00:00
|
|
|
struct mdproc {
|
2003-05-16 21:26:42 +00:00
|
|
|
int __dummy; /* Avoid having an empty struct. */
|
2001-09-12 08:38:13 +00:00
|
|
|
};
|
2001-12-06 18:17:02 +00:00
|
|
|
|
|
|
|
|
#endif /* !_MACHINE_PROC_H_ */
|
