summaryrefslogtreecommitdiffstats
path: root/sys/amd64/include
Commit message (Expand)AuthorAgeFilesLines
* Undo part of the tangle of having sys/lock.h and sys/mutex.h included inmarkm2001-05-011-10/+10
* Overhaul of the SMP code. Several portions of the SMP kernel support havejhb2001-04-274-576/+75
* Make the ap_boot_mtx mutex static.jhb2001-04-201-1/+1
* Back out 1.103. It wasn't approved by the owner of the file andimp2001-04-181-45/+45
* Blow away the panic mutex in favor of using a single atomic_cmpset() on ajhb2001-04-171-4/+0
* Rename the IPI API from smp_ipi_* to ipi_* since the smp_ prefix is justjhb2001-04-111-14/+14
* Remove constants defining the bitmasks of the old giant kernel lock.jhb2001-04-101-5/+0
* Remove the BETTER_CLOCK #ifdef's. The code is on by default and is herejhb2001-04-102-16/+4
* Add an MI API for sending IPI's. I used the same API present on the alphajhb2001-04-101-12/+55
* Axe the per-cpu variable witness_spin_check as it was replaced by thejhb2001-04-061-1/+0
* De __P() while I'm here. Done as a separate commit since it is justimp2001-04-031-45/+45
* Make this file C++ safe. It defines many useful functions (inb, outb)imp2001-04-031-0/+4
* Rework the witness code to work with sx locks as well as mutexes.jhb2001-03-282-0/+2
* - Switch from using save/disable/restore_intr to using critical_enter/exitjhb2001-03-281-5/+5
* - Add the new critical_t type used to save state inside of criticaljhb2001-03-281-15/+18
* Kill the 4MB kernel limit dead. [I hope :-)].peter2001-03-151-3/+9
* Fix mtx_legal2block. The only time that it is bad to block on a mutex isjhb2001-03-091-1/+0
* version 1.7 made some changes to correct problems identifed by compilingmdodd2001-03-023-3/+0
* Always use the ELF naming after the demise of asnames.h.peter2001-02-251-5/+0
* Remove the leading underscore from all symbols defined in x86 asmjake2001-02-252-3/+2
* Activate USER_LDT by default. The new thread libraries are going topeter2001-02-234-10/+1
* GC unused and now obsolete assertion macros.jhb2001-02-221-8/+0
* - Don't call clear_resched() in userret(), instead, clear the resched flagjhb2001-02-201-1/+0
* Removed all traces of T_ASTFLT (except for gaps where it was). It becamebde2001-02-191-1/+0
* Changed the aston() family to operate on a specified process instead ofbde2001-02-191-1/+1
* Fixed style bugs in clock.c rev.1.164 and cpu.h rev.1.52-1.53 -- declarebde2001-02-191-4/+1
* RIP <machine/lock.h>.markm2001-02-112-4/+33
* - Make astpending and need_resched process attributes rather than CPUjhb2001-02-102-38/+7
* Add a macro mtx_intr_enable() to alter a spin lock such that interruptsjhb2001-02-101-0/+1
* Woops, remove an obsolete reference to gd_cpu_lockid.jhb2001-02-091-1/+0
* Axe gd_cpu_lockid as it is no longer used.jhb2001-02-091-1/+0
* Change and clean the mutex lock interface.bmilekic2001-02-094-37/+80
* Remove some leftovers from the CMAP* stuff in globaldata and thepeter2001-01-302-14/+4
* Move the setting of curproc to idleproc up earlier in ap_init(). Thebmilekic2001-01-281-6/+6
* Defer assignment of low level interrupt handlers for PCI interruptstegge2001-01-282-37/+49
* Convert all simplelocks to mutexes and remove the simplelock implementations.jasone2001-01-242-32/+34
* - Proc locking.jhb2001-01-241-4/+7
* - Relocate portions of this file to get it into an order closer to that ofjhb2001-01-241-171/+153
* Move most of sys/mutex.h into kern/kern_mutex.c, thereby making the mutexjasone2001-01-211-0/+6
* Make intr_nesting_level per-process, rather than per-cpu. Setupjake2001-01-213-4/+4
* Remove APIC_INTR_DIAGNOSTIC - this has been disabled for some time now.peter2001-01-211-25/+0
* Remove the per-cpu pages used for copy and zero-ing pages of memoryjake2001-01-212-19/+0
* Simplify the i386 asm MTX_{ENTER,EXIT} macros to just call thejake2001-01-201-102/+16
* apic_itrace_splz[] is unusedpeter2001-01-191-1/+0
* Protect p_stat and p_oncpu with sched_lock in forward_signal().jhb2001-01-181-2/+9
* - Sort of lie and say that %eax is an output only and not an input for thejhb2001-01-171-2/+2
* Argh, disable the micro-ops again. I didn't test these adequately andjhb2001-01-161-1/+2
* - Use "+a" instead of "=&a" for several constraints. This should fixjhb2001-01-161-25/+19
* - Fix atomic_load_* and atomic_store_* to generate functions for atomic.cjhb2001-01-161-168/+123
* Revert the previous revision now that atomic_store_rel_ptr() actuallyjhb2001-01-141-4/+0
OpenPOWER on IntegriCloud