summaryrefslogtreecommitdiffstats
path: root/drivers/idle
diff options
context:
space:
mode:
authorThomas Renninger <trenn@suse.de>2012-01-19 18:18:42 +0100
committerLen Brown <len.brown@intel.com>2012-01-19 21:24:34 -0500
commit54d5dcc45af7adbb907072d042bbece4c2b4de6e (patch)
treea76ad45025545902b48aa6b58da630d7c87681a4 /drivers/idle
parentdcd6c92267155e70a94b3927bce681ce74b80d1f (diff)
downloadop-kernel-dev-54d5dcc45af7adbb907072d042bbece4c2b4de6e.zip
op-kernel-dev-54d5dcc45af7adbb907072d042bbece4c2b4de6e.tar.gz
ACPI processor hotplug: Split up acpi_processor_add
No functional change. This is needed because: When a CPU gets hotplugged, it's totally uninitialized and offline. cpuinfo_x86 struct (cpu_data(cpu)) is mostly zero (CPU feature flags, model, family,..). When a CPU gets hotplugged, struct processor is alloc'd, some sysfs files are set up but acpi_processor_add() must not try to access a MSR on this CPU or try to read out CPU feature,family, etc. This must be done in acpi_processor_start(). The next patch will delay the call of acpi_processor_start() for physically hotpluggedcores, to the time when they are onlined the first time. There it is safe then to access cpu_data(cpu) cpuinfo_x86 struct or access MSRs which is needed to set up cpuidle, throttling and other features. Tested and Signed-off-by: Thomas Renninger <trenn@suse.de> Signed-off-by: Len Brown <len.brown@intel.com>
Diffstat (limited to 'drivers/idle')
0 files changed, 0 insertions, 0 deletions
OpenPOWER on IntegriCloud