Stephan Diestelhorst c6e8256a7b x86, cpufreq: fix Speedfreq-SMI call that clobbers ECX ... I have found that using SMI to change the cpu's frequency on my DELL Latitude L400 clobbers the ECX register in speedstep_set_state, causing unneccessary retries because the "state" variable has changed silently (GCC assumes it is still present in ECX). play safe and avoid gcc caching any register across IO port accesses that trigger SMIs. Signed-off by: <Stephan.Diestelhorst@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>		2008-03-26 22:23:40 +01:00
..
acpi-cpufreq.c	x86: change NR_CPUS arrays in acpi-cpufreq	2008-01-30 13:33:12 +01:00
cpufreq-nforce2.c
e_powersaver.c	[CPUFREQ] Remove debugging message from e_powersaver	2008-03-05 14:45:31 -05:00
elanfreq.c
gx-suspmod.c	[CPUFREQ] gx-suspmod.c: use boot_cpu_data instead of current_cpu_data	2008-02-06 22:57:58 -05:00
Kconfig	[CPUFREQ] Remove pointless Kconfig dependancy	2008-02-06 22:57:57 -05:00
longhaul.c	x86: remove unneded casts	2008-01-30 13:33:23 +01:00
longhaul.h
longrun.c
Makefile
p4-clockmod.c
powernow-k6.c
powernow-k7.c	[CPUFREQ] arch/x86: Add missing "space"	2008-02-06 22:57:57 -05:00
powernow-k7.h
powernow-k8.c	[CPUFREQ] Fix sparse warning in powernow-k8	2008-02-06 22:57:59 -05:00
powernow-k8.h	[CPUFREQ] Powernow-k8: Update to support the latest Turion processors	2008-02-06 22:57:58 -05:00
sc520_freq.c
speedstep-centrino.c
speedstep-ich.c
speedstep-lib.c	Revert "speedstep-lib.c: fix frequency multiplier for Pentium4 models 0&1"	2007-11-20 14:20:21 -05:00
speedstep-lib.h
speedstep-smi.c	x86, cpufreq: fix Speedfreq-SMI call that clobbers ECX	2008-03-26 22:23:40 +01:00