Messages in this thread Patch in this message |  | | | Date | Tue, 19 May 2009 16:09:42 +0800 | | From | Shaohua Li <> | | Subject | [PATCH 1/2]cpuidle: makes AMD C1E works in acpi_idle |
| |
When AMD C1E is enabled, local APIC timer will stop even in C1. This patch uses broadcast ipi to replace local APIC timer in C1.
http://bugzilla.kernel.org/show_bug.cgi?id=13233
[ impact: avoid boot hang in AMD CPU with C1E enabled ]
Tested-by: Dmitry Lyzhyn <thisistempbox@yahoo.com> Signed-off-by: Shaohua Li <shaohua.li@intel.com> --- drivers/acpi/processor_idle.c | 6 ++++++ 1 file changed, 6 insertions(+) Index: linux/drivers/acpi/processor_idle.c =================================================================== --- linux.orig/drivers/acpi/processor_idle.c 2009-05-19 09:45:23.000000000 +0800 +++ linux/drivers/acpi/processor_idle.c 2009-05-19 09:56:59.000000000 +0800 @@ -148,6 +148,9 @@ static void acpi_timer_check_state(int s if (cpu_has(&cpu_data(pr->id), X86_FEATURE_ARAT)) return; + if (boot_cpu_has(X86_FEATURE_AMDC1E)) + type = ACPI_STATE_C1; + /* * Check, if one of the previous states already marked the lapic * unstable @@ -611,6 +614,7 @@ static int acpi_processor_power_verify(s switch (cx->type) { case ACPI_STATE_C1: cx->valid = 1; + acpi_timer_check_state(i, pr, cx); break; case ACPI_STATE_C2: @@ -835,6 +839,7 @@ static int acpi_idle_enter_c1(struct cpu return 0; } + acpi_state_timer_broadcast(pr, cx, 1); kt1 = ktime_get_real(); acpi_idle_do_entry(cx); kt2 = ktime_get_real(); @@ -842,6 +847,7 @@ static int acpi_idle_enter_c1(struct cpu local_irq_enable(); cx->usage++; + acpi_state_timer_broadcast(pr, cx, 0); return idle_time; }
|  |