As documented by commit b488f021 "ACPI: restore comment justifying
'extra' P_LVLx access", Linux does an extra IO read after entering idle
because on (some) chipsets STPCLK# doesn't get asserted in time
to prevent further instruction processing.
This can never be the case on KVM, and a timer read causes an expensive
VM exit in turn causing useless load on host system. Detect KVM and skip
the read. TODO: whitelist more hypervisors?
Note: very lightly tested. Pls don't apply this yet, I am working on a
_CST implementation for KVM and will repost this without the RFC tag
when it's been tested properly.
Posting now for early flames/feedback.
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Radim Krčmář <rkrcmar@xxxxxxxxxx>
Cc: kvm@xxxxxxxxxxxxxxx
Signed-off-by: Michael S. Tsirkin <mst@xxxxxxxxxx>
---
drivers/acpi/processor_idle.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index abb559c..8ae28dc 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -33,6 +33,7 @@
#include <linux/cpuidle.h>
#include <linux/cpu.h>
#include <acpi/processor.h>
+#include <linux/kvm_para.h>
/*
* Include the apic definitions for x86 to have the APIC timer related defines
@@ -665,7 +666,8 @@ static void __cpuidle acpi_idle_do_entry(struct acpi_processor_cx *cx)
/* Dummy wait op - must do something useless after P_LVL2 read
because chipsets cannot guarantee that STPCLK# signal
gets asserted in time to freeze execution properly. */
- inl(acpi_gbl_FADT.xpm_timer_block.address);
+ if (!kvm_para_available())
+ inl(acpi_gbl_FADT.xpm_timer_block.address);
}
}
@@ -687,7 +689,8 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
else if (cx->entry_method == ACPI_CSTATE_SYSTEMIO) {
inb(cx->address);
/* See comment in acpi_idle_do_entry() */
- inl(acpi_gbl_FADT.xpm_timer_block.address);
+ if (!kvm_para_available())
+ inl(acpi_gbl_FADT.xpm_timer_block.address);
} else
return -ENODEV;
}
--
MST
