haiku/headers
Pawel Dziepak a5b070f1fa x86: Store pointer to the current thread in gs:0
Apparently, reading from dr3 is slower than reading from memory
with cache hit.

Also, depending on hypervisor configuration, accessing dr3 may cause
a VM exit (and, at least on kvm, it does), what makes it much slower
than a memory access even when there is a cache miss.
2013-12-17 04:08:51 +01:00
..
build kernel: atomic_*() functions rework 2013-11-05 22:32:59 +01:00
compatibility Drop "protected"-define from bsd-compatibility header 2012-11-05 09:37:55 +01:00
config Merge branch 'master' into x86_64 2012-08-16 21:11:15 +01:00
cpp Remove remaining unnecessary 'volatile' qualifiers 2013-11-06 00:03:07 +01:00
glibc Make public glibc header printf.h usable. 2013-07-17 18:07:56 +02:00
libs Merge remote-tracking branch 'haiku/master' into package-management 2013-07-08 14:01:00 +02:00
os kernel, libroot: Add more memory info in system_info 2013-12-16 04:53:46 +01:00
posix libroot: Remove _SC_NPROCESSORS_MAX and _SC_CPUID_MAX 2013-12-06 21:54:07 +01:00
private x86: Store pointer to the current thread in gs:0 2013-12-17 04:08:51 +01:00
tools * Moved everything into the SymbolPatcher namespace. 2009-11-05 17:16:17 +00:00