d/freebsd-nq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
3905c09afb
freebsd-nq/sys/i386/include/smp.h

174 lines
4.7 KiB
C
Raw Normal View History

Man the liferafts! Here comes the long awaited SMP -> -current merge! There are various options documented in i386/conf/LINT, there is more to come over the next few days. The kernel should run pretty much "as before" without the options to activate SMP mode. There are a handful of known "loose ends" that need to be fixed, but have been put off since the SMP kernel is in a moderately good condition at the moment. This commit is the result of the tinkering and testing over the last 14 months by many people. A special thanks to Steve Passe for implementing the APIC code!
1997-04-26 11:46:25 +00:00
/*
* ----------------------------------------------------------------------------
* "THE BEER-WARE LICENSE" (Revision 42):
* <phk@FreeBSD.org> wrote this file. As long as you retain this notice you
* can do whatever you want with this stuff. If we meet some day, and you think
* this stuff is worth it, you can buy me a beer in return. Poul-Henning Kamp
* ----------------------------------------------------------------------------
*
Fixed imen declaration. Submitted by: Bruce Evans <bde@zeta.org.au>
1997-07-31 17:28:20 +00:00
* $Id: smp.h,v 1.23 1997/07/31 05:39:48 fsmp Exp $
Man the liferafts! Here comes the long awaited SMP -> -current merge! There are various options documented in i386/conf/LINT, there is more to come over the next few days. The kernel should run pretty much "as before" without the options to activate SMP mode. There are a handful of known "loose ends" that need to be fixed, but have been put off since the SMP kernel is in a moderately good condition at the moment. This commit is the result of the tinkering and testing over the last 14 months by many people. A special thanks to Steve Passe for implementing the APIC code!
1997-04-26 11:46:25 +00:00
*
*/
#ifndef _MACHINE_SMP_H_
#define _MACHINE_SMP_H_
#ifdef KERNEL
Force user to config SMP kernel with "options APIC_IO". Reviewed by: Peter Wemm <peter@spinner.DIALix.COM>
1997-05-06 21:29:57 +00:00
#if defined(SMP) && !defined(APIC_IO)
# error APIC_IO required for SMP, add "options APIC_IO" to your config file.
Preliminaries for stop_cpus()/restart_cpus(). Both are turned off by default. Added macro for displaying POST codes from kernel.
1997-06-27 23:12:31 +00:00
#endif /* SMP && !APIC_IO */
Force user to config SMP kernel with "options APIC_IO". Reviewed by: Peter Wemm <peter@spinner.DIALix.COM>
1997-05-06 21:29:57 +00:00
Modified the PEND_INTS algorithm to fix the ISA INT loss problem. Noticed by: dave adkins <adkin003@gold.tc.umn.edu> and others.
1997-07-28 03:59:54 +00:00
/* Number of CPUs. */
Man the liferafts! Here comes the long awaited SMP -> -current merge! There are various options documented in i386/conf/LINT, there is more to come over the next few days. The kernel should run pretty much "as before" without the options to activate SMP mode. There are a handful of known "loose ends" that need to be fixed, but have been put off since the SMP kernel is in a moderately good condition at the moment. This commit is the result of the tinkering and testing over the last 14 months by many people. A special thanks to Steve Passe for implementing the APIC code!
1997-04-26 11:46:25 +00:00
#if defined(SMP) && !defined(NCPU)
# define NCPU 2
#endif /* SMP && NCPU */
Modified the PEND_INTS algorithm to fix the ISA INT loss problem. Noticed by: dave adkins <adkin003@gold.tc.umn.edu> and others.
1997-07-28 03:59:54 +00:00
/* Number of IO APICs. */
#if defined(APIC_IO) && !defined(NAPIC)
# define NAPIC 1
#endif /* SMP && NAPIC */
Man the liferafts! Here comes the long awaited SMP -> -current merge! There are various options documented in i386/conf/LINT, there is more to come over the next few days. The kernel should run pretty much "as before" without the options to activate SMP mode. There are a handful of known "loose ends" that need to be fixed, but have been put off since the SMP kernel is in a moderately good condition at the moment. This commit is the result of the tinkering and testing over the last 14 months by many people. A special thanks to Steve Passe for implementing the APIC code!
1997-04-26 11:46:25 +00:00
#if defined(SMP) || defined(APIC_IO)
Modified the PEND_INTS algorithm to fix the ISA INT loss problem. Noticed by: dave adkins <adkin003@gold.tc.umn.edu> and others.
1997-07-28 03:59:54 +00:00
#ifndef LOCORE
Preliminaries for stop_cpus()/restart_cpus(). Both are turned off by default. Added macro for displaying POST codes from kernel.
1997-06-27 23:12:31 +00:00
/*
* For sending values to POST displays.
Additional debugging functions and macros. "spurious INTerrupt" support.
1997-07-06 23:40:15 +00:00
* XXX FIXME: where does this really belong, isa.h/isa.c perhaps?
Preliminaries for stop_cpus()/restart_cpus(). Both are turned off by default. Added macro for displaying POST codes from kernel.
1997-06-27 23:12:31 +00:00
*/
Additional debugging functions and macros. "spurious INTerrupt" support.
1997-07-06 23:40:15 +00:00
extern int current_postcode; /** XXX currently in mp_machdep.c */
#define POSTCODE(X) current_postcode = (X), \
outb(0x80, current_postcode)
#define POSTCODE_LO(X) current_postcode &= 0xf0, \
current_postcode |= ((X) & 0x0f), \
outb(0x80, current_postcode)
#define POSTCODE_HI(X) current_postcode &= 0x0f, \
current_postcode |= (((X) << 4) & 0xf0), \
outb(0x80, current_postcode)
Preliminaries for stop_cpus()/restart_cpus(). Both are turned off by default. Added macro for displaying POST codes from kernel.
1997-06-27 23:12:31 +00:00
apic.h now has structure definitions for both the local APIC and io APIC. apic.h has defines like: #define lapic__id lapic->id Once private pages and "known virtual addr" mapping of the APICs is ready all 'lapic__XXX' will be changed to 'lapic.XXX', and the defines will be removed. Changes to smp.h for lapic_t lapic && ioapic_t ioapic pointers, currently equal to apic_base && io_apic_base, will stand alone with the private page mapping.
1997-05-29 05:57:43 +00:00
#include <machine/apic.h>
Man the liferafts! Here comes the long awaited SMP -> -current merge! There are various options documented in i386/conf/LINT, there is more to come over the next few days. The kernel should run pretty much "as before" without the options to activate SMP mode. There are a handful of known "loose ends" that need to be fixed, but have been put off since the SMP kernel is in a moderately good condition at the moment. This commit is the result of the tinkering and testing over the last 14 months by many people. A special thanks to Steve Passe for implementing the APIC code!
1997-04-26 11:46:25 +00:00
/* global data in mpboot.s */
extern int bootMP_size;
/* functions in mpboot.s */
void bootMP __P((void));
/* global data in mplock.s */
extern u_int mp_lock;
/* functions in mplock.s */
void get_mplock __P((void));
void rel_mplock __P((void));
changed expect_lock() to try_lock(), the real name used in mplock.s
1997-04-30 19:04:26 +00:00
void try_mplock __P((void));
Man the liferafts! Here comes the long awaited SMP -> -current merge! There are various options documented in i386/conf/LINT, there is more to come over the next few days. The kernel should run pretty much "as before" without the options to activate SMP mode. There are a handful of known "loose ends" that need to be fixed, but have been put off since the SMP kernel is in a moderately good condition at the moment. This commit is the result of the tinkering and testing over the last 14 months by many people. A special thanks to Steve Passe for implementing the APIC code!
1997-04-26 11:46:25 +00:00
Preliminaries for stop_cpus()/restart_cpus(). Both are turned off by default. Added macro for displaying POST codes from kernel.
1997-06-27 23:12:31 +00:00
/* global data in apic_vector.s */
Last commit didn't take, operator error???
1997-07-22 20:12:32 +00:00
extern u_int ivectors[];
Preliminaries for stop_cpus()/restart_cpus(). Both are turned off by default. Added macro for displaying POST codes from kernel.
1997-06-27 23:12:31 +00:00
extern volatile u_int stopped_cpus;
extern volatile u_int started_cpus;
Last commit didn't take, operator error???
1997-07-22 20:12:32 +00:00
/* global data in apic_ipl.s */
extern u_int vec[];
extern u_int Xintr8254;
extern u_int mask8254;
Fixed imen declaration. Submitted by: Bruce Evans <bde@zeta.org.au>
1997-07-31 17:28:20 +00:00
extern volatile struct simplelock imen_lock;
Last commit didn't take, operator error???
1997-07-22 20:12:32 +00:00
/* functions in apic_ipl.s */
void vec8254 __P((void));
void INTREN __P((u_int));
void INTRDIS __P((u_int));
void apic_eoi __P((void));
u_int io_apic_read __P((int, int));
void io_apic_write __P((int, int, u_int));
param.h: Macros to convert the Lite2 lock manager primitives to the names used in the kernel proper. This allows us to hide them from the lock manager till they can be turned on. smp.h: declarations for the new simplelock functions.
1997-07-24 23:48:53 +00:00
/* functions in simplelock.s */
Coded simple_lock and friends in asm.
1997-07-23 05:49:19 +00:00
#include <machine/param.h>
void s_lock_init __P((struct simplelock *));
void s_lock __P((__volatile struct simplelock *));
int s_lock_try __P((__volatile struct simplelock *));
void s_unlock __P((__volatile struct simplelock *));
Man the liferafts! Here comes the long awaited SMP -> -current merge! There are various options documented in i386/conf/LINT, there is more to come over the next few days. The kernel should run pretty much "as before" without the options to activate SMP mode. There are a handful of known "loose ends" that need to be fixed, but have been put off since the SMP kernel is in a moderately good condition at the moment. This commit is the result of the tinkering and testing over the last 14 months by many people. A special thanks to Steve Passe for implementing the APIC code!
1997-04-26 11:46:25 +00:00
/* global data in mp_machdep.c */
extern int mp_ncpus;
extern int mp_naps;
extern int mp_nbusses;
extern int mp_napics;
extern int mp_picmode;
extern int boot_cpu_id;
extern vm_offset_t cpu_apic_address;
extern vm_offset_t io_apic_address[];
extern u_int32_t cpu_apic_versions[];
extern u_int32_t io_apic_versions[];
extern int cpu_num_to_apic_id[];
extern int io_num_to_apic_id[];
extern int apic_id_to_logical[];
Preliminaries for stop_cpus()/restart_cpus(). Both are turned off by default. Added macro for displaying POST codes from kernel.
1997-06-27 23:12:31 +00:00
extern u_int all_cpus;
Preliminary support for per-cpu data pages. This eliminates a lot of #ifdef SMP type code. Things like _curproc reside in a data page that is unique on each cpu, eliminating the expensive macros like: #define curproc (SMPcurproc[cpunumber()]) There are some unresolved bootstrap and address space sharing issues at present, but Steve is waiting on this for other work. There is still some strictly temporary code present that isn't exactly pretty. This is part of a larger change that has run into some bumps, this part is standalone so it should be safe. The temporary code goes away when the full idle cpu support is finished. Reviewed by: fsmp, dyson
1997-06-22 16:04:22 +00:00
extern u_int SMP_prvpt[];
extern u_char SMP_ioapic[];
Man the liferafts! Here comes the long awaited SMP -> -current merge! There are various options documented in i386/conf/LINT, there is more to come over the next few days. The kernel should run pretty much "as before" without the options to activate SMP mode. There are a handful of known "loose ends" that need to be fixed, but have been put off since the SMP kernel is in a moderately good condition at the moment. This commit is the result of the tinkering and testing over the last 14 months by many people. A special thanks to Steve Passe for implementing the APIC code!
1997-04-26 11:46:25 +00:00
/* functions in mp_machdep.c */
u_int mp_bootaddress __P((u_int));
Add declaration of mp_probe(). This is now called directly from machdep.c.
1997-05-28 18:44:11 +00:00
int mp_probe __P((void));
Man the liferafts! Here comes the long awaited SMP -> -current merge! There are various options documented in i386/conf/LINT, there is more to come over the next few days. The kernel should run pretty much "as before" without the options to activate SMP mode. There are a handful of known "loose ends" that need to be fixed, but have been put off since the SMP kernel is in a moderately good condition at the moment. This commit is the result of the tinkering and testing over the last 14 months by many people. A special thanks to Steve Passe for implementing the APIC code!
1997-04-26 11:46:25 +00:00
void mp_start __P((void));
void mp_announce __P((void));
Modified to declare merged/renamed functions: - get_isa_apic_mask() -> isa_apic_mask() - get_isa_apic_irq() && get_eisa_apic_irq() -> isa_apic_pin() - get_pci_apic_irq() -> pci_apic_pin()
1997-06-25 20:59:15 +00:00
u_int isa_apic_mask __P((u_int));
int isa_apic_pin __P((int));
int pci_apic_pin __P((int, int, int));
Code to handle SMP/APIC_IO mapping of ISA INTs to APIC pins above IRQ15. - doesn't break my system. - NOT yet verified on the affected motherboard. Submitted by: "John S. Dyson" <toor@dyson.iquest.net>
1997-05-05 22:56:37 +00:00
int undirect_isa_irq __P((int));
Man the liferafts! Here comes the long awaited SMP -> -current merge! There are various options documented in i386/conf/LINT, there is more to come over the next few days. The kernel should run pretty much "as before" without the options to activate SMP mode. There are a handful of known "loose ends" that need to be fixed, but have been put off since the SMP kernel is in a moderately good condition at the moment. This commit is the result of the tinkering and testing over the last 14 months by many people. A special thanks to Steve Passe for implementing the APIC code!
1997-04-26 11:46:25 +00:00
int undirect_pci_irq __P((int));
int apic_bus_type __P((int));
int apic_src_bus_id __P((int, int));
int apic_src_bus_irq __P((int, int));
int apic_int_type __P((int, int));
int apic_trigger __P((int, int));
int apic_polarity __P((int, int));
General cleanup of APIC code. stop_cpus/restart_cpus STILL not working!
1997-07-08 23:32:58 +00:00
void bsp_apic_configure __P((void));
Man the liferafts! Here comes the long awaited SMP -> -current merge! There are various options documented in i386/conf/LINT, there is more to come over the next few days. The kernel should run pretty much "as before" without the options to activate SMP mode. There are a handful of known "loose ends" that need to be fixed, but have been put off since the SMP kernel is in a moderately good condition at the moment. This commit is the result of the tinkering and testing over the last 14 months by many people. A special thanks to Steve Passe for implementing the APIC code!
1997-04-26 11:46:25 +00:00
void init_secondary __P((void));
void smp_invltlb __P((void));
Preliminaries for stop_cpus()/restart_cpus(). Both are turned off by default. Added macro for displaying POST codes from kernel.
1997-06-27 23:12:31 +00:00
int stop_cpus __P((u_int));
int restart_cpus __P((u_int));
Man the liferafts! Here comes the long awaited SMP -> -current merge! There are various options documented in i386/conf/LINT, there is more to come over the next few days. The kernel should run pretty much "as before" without the options to activate SMP mode. There are a handful of known "loose ends" that need to be fixed, but have been put off since the SMP kernel is in a moderately good condition at the moment. This commit is the result of the tinkering and testing over the last 14 months by many people. A special thanks to Steve Passe for implementing the APIC code!
1997-04-26 11:46:25 +00:00
/* global data in mpapic.c */
Preliminary support for per-cpu data pages. This eliminates a lot of #ifdef SMP type code. Things like _curproc reside in a data page that is unique on each cpu, eliminating the expensive macros like: #define curproc (SMPcurproc[cpunumber()]) There are some unresolved bootstrap and address space sharing issues at present, but Steve is waiting on this for other work. There is still some strictly temporary code present that isn't exactly pretty. This is part of a larger change that has run into some bumps, this part is standalone so it should be safe. The temporary code goes away when the full idle cpu support is finished. Reviewed by: fsmp, dyson
1997-06-22 16:04:22 +00:00
extern volatile lapic_t lapic;
Man the liferafts! Here comes the long awaited SMP -> -current merge! There are various options documented in i386/conf/LINT, there is more to come over the next few days. The kernel should run pretty much "as before" without the options to activate SMP mode. There are a handful of known "loose ends" that need to be fixed, but have been put off since the SMP kernel is in a moderately good condition at the moment. This commit is the result of the tinkering and testing over the last 14 months by many people. A special thanks to Steve Passe for implementing the APIC code!
1997-04-26 11:46:25 +00:00
#if defined(MULTIPLE_IOAPICS)
#error MULTIPLE_IOAPICSXXX
#else
Preliminary support for per-cpu data pages. This eliminates a lot of #ifdef SMP type code. Things like _curproc reside in a data page that is unique on each cpu, eliminating the expensive macros like: #define curproc (SMPcurproc[cpunumber()]) There are some unresolved bootstrap and address space sharing issues at present, but Steve is waiting on this for other work. There is still some strictly temporary code present that isn't exactly pretty. This is part of a larger change that has run into some bumps, this part is standalone so it should be safe. The temporary code goes away when the full idle cpu support is finished. Reviewed by: fsmp, dyson
1997-06-22 16:04:22 +00:00
extern volatile ioapic_t *ioapic[];
Man the liferafts! Here comes the long awaited SMP -> -current merge! There are various options documented in i386/conf/LINT, there is more to come over the next few days. The kernel should run pretty much "as before" without the options to activate SMP mode. There are a handful of known "loose ends" that need to be fixed, but have been put off since the SMP kernel is in a moderately good condition at the moment. This commit is the result of the tinkering and testing over the last 14 months by many people. A special thanks to Steve Passe for implementing the APIC code!
1997-04-26 11:46:25 +00:00
#endif /* MULTIPLE_IOAPICS */
/* functions in mpapic.c */
Pass string arg to apic_dump.
1997-07-20 18:02:19 +00:00
void apic_dump __P((char*));
General cleanup of APIC code. stop_cpus/restart_cpus STILL not working!
1997-07-08 23:32:58 +00:00
void apic_initialize __P((void));
Last commit didn't take, operator error???
1997-07-22 20:12:32 +00:00
void imen_dump __P((void));
cleaned up FAST_IPI code. - one-liners all become inline. - multi-liners become functions. - FAST_IPI defines go away. re-worked APICIPI_BANDAID code. - now refered to as DETECT_DEADLOCK. - on by default.
1997-05-01 19:33:12 +00:00
int apic_ipi __P((int, int, int));
Man the liferafts! Here comes the long awaited SMP -> -current merge! There are various options documented in i386/conf/LINT, there is more to come over the next few days. The kernel should run pretty much "as before" without the options to activate SMP mode. There are a handful of known "loose ends" that need to be fixed, but have been put off since the SMP kernel is in a moderately good condition at the moment. This commit is the result of the tinkering and testing over the last 14 months by many people. A special thanks to Steve Passe for implementing the APIC code!
1997-04-26 11:46:25 +00:00
int selected_apic_ipi __P((u_int, int, int));
int io_apic_setup __P((int));
int ext_int_setup __P((int, int));
#if defined(READY)
void clr_io_apic_mask24 __P((int, u_int32_t));
void set_io_apic_mask24 __P((int, u_int32_t));
#endif /* READY */
void set_apic_timer __P((int));
int read_apic_timer __P((void));
void u_sleep __P((int));
/* global data in init_smp.c */
extern int smp_active;
remove all the SMP_INVLTLB defines, making the code default for APIC_IO. Reviewed by: informal discussion with Peter Wemm <peter@spinner.DIALix.COM>
1997-04-28 00:25:00 +00:00
extern int invltlb_ok;
Man the liferafts! Here comes the long awaited SMP -> -current merge! There are various options documented in i386/conf/LINT, there is more to come over the next few days. The kernel should run pretty much "as before" without the options to activate SMP mode. There are a handful of known "loose ends" that need to be fixed, but have been put off since the SMP kernel is in a moderately good condition at the moment. This commit is the result of the tinkering and testing over the last 14 months by many people. A special thanks to Steve Passe for implementing the APIC code!
1997-04-26 11:46:25 +00:00
Preliminaries for stop_cpus()/restart_cpus(). Both are turned off by default. Added macro for displaying POST codes from kernel.
1997-06-27 23:12:31 +00:00
/* 'private' global data in locore.s */
Preliminary support for per-cpu data pages. This eliminates a lot of #ifdef SMP type code. Things like _curproc reside in a data page that is unique on each cpu, eliminating the expensive macros like: #define curproc (SMPcurproc[cpunumber()]) There are some unresolved bootstrap and address space sharing issues at present, but Steve is waiting on this for other work. There is still some strictly temporary code present that isn't exactly pretty. This is part of a larger change that has run into some bumps, this part is standalone so it should be safe. The temporary code goes away when the full idle cpu support is finished. Reviewed by: fsmp, dyson
1997-06-22 16:04:22 +00:00
extern volatile u_int cpuid;
extern volatile u_int cpu_lockid;
Preliminaries for stop_cpus()/restart_cpus(). Both are turned off by default. Added macro for displaying POST codes from kernel.
1997-06-27 23:12:31 +00:00
extern volatile u_int other_cpus;
Man the liferafts! Here comes the long awaited SMP -> -current merge! There are various options documented in i386/conf/LINT, there is more to come over the next few days. The kernel should run pretty much "as before" without the options to activate SMP mode. There are a handful of known "loose ends" that need to be fixed, but have been put off since the SMP kernel is in a moderately good condition at the moment. This commit is the result of the tinkering and testing over the last 14 months by many people. A special thanks to Steve Passe for implementing the APIC code!
1997-04-26 11:46:25 +00:00
Modified the PEND_INTS algorithm to fix the ISA INT loss problem. Noticed by: dave adkins <adkin003@gold.tc.umn.edu> and others.
1997-07-28 03:59:54 +00:00
#endif /* !LOCORE */
Man the liferafts! Here comes the long awaited SMP -> -current merge! There are various options documented in i386/conf/LINT, there is more to come over the next few days. The kernel should run pretty much "as before" without the options to activate SMP mode. There are a handful of known "loose ends" that need to be fixed, but have been put off since the SMP kernel is in a moderately good condition at the moment. This commit is the result of the tinkering and testing over the last 14 months by many people. A special thanks to Steve Passe for implementing the APIC code!
1997-04-26 11:46:25 +00:00
#endif /* SMP || APIC_IO */
#endif /* KERNEL */
#endif /* _MACHINE_SMP_H_ */
Reference in New Issue Copy Permalink