| Commit message (Expand) | Author | Age | Files | Lines |
* | - Proc locking. | jhb | 2001-01-24 | 1 | -4/+7 |
* | - Relocate portions of this file to get it into an order closer to that of | jhb | 2001-01-24 | 1 | -171/+153 |
* | Move most of sys/mutex.h into kern/kern_mutex.c, thereby making the mutex | jasone | 2001-01-21 | 1 | -0/+6 |
* | Make intr_nesting_level per-process, rather than per-cpu. Setup | jake | 2001-01-21 | 3 | -4/+4 |
* | Remove APIC_INTR_DIAGNOSTIC - this has been disabled for some time now. | peter | 2001-01-21 | 1 | -25/+0 |
* | Remove the per-cpu pages used for copy and zero-ing pages of memory | jake | 2001-01-21 | 2 | -19/+0 |
* | Simplify the i386 asm MTX_{ENTER,EXIT} macros to just call the | jake | 2001-01-20 | 1 | -102/+16 |
* | apic_itrace_splz[] is unused | peter | 2001-01-19 | 1 | -1/+0 |
* | Protect p_stat and p_oncpu with sched_lock in forward_signal(). | jhb | 2001-01-18 | 1 | -2/+9 |
* | - Sort of lie and say that %eax is an output only and not an input for the | jhb | 2001-01-17 | 1 | -2/+2 |
* | Argh, disable the micro-ops again. I didn't test these adequately and | jhb | 2001-01-16 | 1 | -1/+2 |
* | - Use "+a" instead of "=&a" for several constraints. This should fix | jhb | 2001-01-16 | 1 | -25/+19 |
* | - Fix atomic_load_* and atomic_store_* to generate functions for atomic.c | jhb | 2001-01-16 | 1 | -168/+123 |
* | Revert the previous revision now that atomic_store_rel_ptr() actually | jhb | 2001-01-14 | 1 | -4/+0 |
* | Fix the atomic_load_acq() and atomic_store_rel() functions to properly | jhb | 2001-01-14 | 1 | -5/+43 |
* | Work around the broken atomic_store_rel_ptr() on the i386 arch by just | jhb | 2001-01-14 | 1 | -0/+4 |
* | Change return ??? to return -1 in some #if 0'ed code. | jake | 2001-01-12 | 1 | -2/+2 |
* | Remove unused per-cpu variables inside_intr and ss_eflags. | jake | 2001-01-12 | 1 | -2/+0 |
* | Use PCPU_GET, PCPU_PTR and PCPU_SET to access all per-cpu variables | jake | 2001-01-10 | 2 | -22/+22 |
* | Fix a warning. The type of globaldata.gd_prvspace has changed. | jake | 2001-01-08 | 1 | -1/+2 |
* | Implement accessors for per-cpu variables which don't depend on the | jake | 2001-01-06 | 1 | -3/+2 |
* | Use %fs to access per-cpu variables in uni-processor kernels the same | jake | 2001-01-06 | 2 | -6/+4 |
* | Introduce a new potientially cleaner interface for accessing per-cpu | jake | 2000-12-13 | 1 | -0/+6 |
* | Fix the assembly mutex macros to call the appropriate witness functions if | jhb | 2000-12-12 | 1 | -3/+38 |
* | Fix a jump to the wrong label, <sigh>. Put a period at the end of a | jake | 2000-12-08 | 1 | -2/+2 |
* | Argh, revert the clobber changes. Since %ecx and %edx aren't call safe, | jhb | 2000-12-08 | 1 | -9/+9 |
* | Change the calling conventions of the MTX_ENTER macro to match | jake | 2000-12-08 | 1 | -11/+13 |
* | Well, the previous commit wasn't entirely correct either. For now, just | jhb | 2000-12-08 | 1 | -1/+2 |
* | Move extern tsc_present outside function to quelch a warning. | phk | 2000-12-07 | 1 | -1/+4 |
* | Fix broken register restraints that needlessly clobbered registers %ecx | jhb | 2000-12-07 | 1 | -13/+13 |
* | This is kind of a nasty hack, but it appears to solve the Compaq DL360 | peter | 2000-12-06 | 1 | -2/+13 |
* | Move io_apic_{read,write} from apic_ipl.s (where they do not belong) into | peter | 2000-12-06 | 1 | -4/+3 |
* | GC unused assembler function apic_eoi() | peter | 2000-12-06 | 1 | -1/+0 |
* | Remove the last of the MD netisr code. It is now all MI. Remove | jake | 2000-12-05 | 1 | -1/+0 |
* | Cleanup some leftover lint from the old interrupt system. | peter | 2000-12-04 | 2 | -7/+2 |
* | (1) Allow a stray lock prefix to be compiled out with the | jake | 2000-12-04 | 1 | -16/+24 |
* | Namespace cleanup. Remove some #includes in favour of an explicit | markm | 2000-12-02 | 1 | -3/+2 |
* | Don't use p->p_sigstk.ss_flags to keep state of whether the | marcel | 2000-11-30 | 1 | -1/+2 |
* | Increase NKPT from 17 to 30. This fixes the 4GB ram boot panic on both | peter | 2000-11-30 | 1 | -1/+1 |
* | Don't wait forever for CPUs to stop or restart. Instead, give up after a | jhb | 2000-11-28 | 1 | -2/+19 |
* | Assembler fixes. | markm | 2000-11-21 | 1 | -4/+4 |
* | Add a consistent API to a feature that most modern CPUs have; a fast | markm | 2000-11-21 | 1 | -0/+21 |
* | Fix a bug with handling of the saved interrupt state for spin mutexes in | jhb | 2000-11-13 | 1 | -2/+2 |
* | Make MINSIGSTKSZ machine dependent, and have the sigaltstack | marcel | 2000-11-09 | 1 | -0/+6 |
* | The x86 atomic operations are already locked, so they do not need an | jhb | 2000-10-28 | 1 | -2/+0 |
* | Declare or #define per-cpu globals in <machine/globals.h> in all cases. | bde | 2000-10-27 | 6 | -31/+0 |
* | - Add atomic_cmpset_{acq_,rel_,}_long | jhb | 2000-10-25 | 1 | -0/+52 |
* | - Overhaul the software interrupt code to use interrupt threads for each | jhb | 2000-10-25 | 1 | -2/+1 |
* | Define the mtx_legal2block() macro used in the witness code that managed | jhb | 2000-10-20 | 1 | -0/+2 |
* | Catch up to moving headers: | jhb | 2000-10-20 | 1 | -1/+1 |