diff options
author | Thomas Renninger <trenn@suse.de> | 2012-01-19 21:18:42 +0400 |
---|---|---|
committer | Len Brown <len.brown@intel.com> | 2012-01-20 06:24:34 +0400 |
commit | 54d5dcc45af7adbb907072d042bbece4c2b4de6e (patch) | |
tree | a76ad45025545902b48aa6b58da630d7c87681a4 /drivers/idle | |
parent | dcd6c92267155e70a94b3927bce681ce74b80d1f (diff) | |
download | linux-54d5dcc45af7adbb907072d042bbece4c2b4de6e.tar.xz |
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