[PATCH RFC 4/5] x86: eoi micro-optimization

["Michael S. Tsirkin" <mst@redhat.com>]

We know both register and value for eoi beforehand,
so there's no need to check it and no need to do math
to calculate the msr. Saves instructions/branches
on each EOI when using x2apic.

I checked the generated code to verify that it
actually is shorter, but haven't done any
performance testing. What's appropriate here
and what kind of test makes the most sense?

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 arch/x86/include/asm/apic.h           |    5 +++++
 arch/x86/kernel/apic/x2apic_cluster.c |    2 +-
 arch/x86/kernel/apic/x2apic_phys.c    |    2 +-
 arch/x86/kernel/apic/x2apic_uv_x.c    |    2 +-
 4 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 74efb8d..5eb6d56 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -138,6 +138,11 @@ static inline void native_apic_msr_write(u32 reg, u32 v)
 	wrmsr(APIC_BASE_MSR + (reg >> 4), v, 0);
 }
 
+static inline void native_apic_msr_eoi_write(u32 reg, u32 v)
+{
+	wrmsr(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0);
+}
+
 static inline u32 native_apic_msr_read(u32 reg)
 {
 	u64 msr;
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index a5baa78..ff35cff 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -260,7 +260,7 @@ static struct apic apic_x2apic_cluster = {
 
 	.read				= native_apic_msr_read,
 	.write				= native_apic_msr_write,
-	.eoi_write			= native_apic_msr_write,
+	.eoi_write			= native_apic_msr_eoi_write,
 	.icr_read			= native_x2apic_icr_read,
 	.icr_write			= native_x2apic_icr_write,
 	.wait_icr_idle			= native_x2apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index aac165b..06a0812 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -166,7 +166,7 @@ static struct apic apic_x2apic_phys = {
 
 	.read				= native_apic_msr_read,
 	.write				= native_apic_msr_write,
-	.eoi_write			= native_apic_msr_write,
+	.eoi_write			= native_apic_msr_eoi_write,
 	.icr_read			= native_x2apic_icr_read,
 	.icr_write			= native_x2apic_icr_write,
 	.wait_icr_idle			= native_x2apic_wait_icr_idle,
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 5b0e3d0..c6d03f7 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -404,7 +404,7 @@ static struct apic __refdata apic_x2apic_uv_x = {
 
 	.read				= native_apic_msr_read,
 	.write				= native_apic_msr_write,
-	.eoi_write			= native_apic_msr_write,
+	.eoi_write			= native_apic_msr_eoi_write,
 	.icr_read			= native_x2apic_icr_read,
 	.icr_write			= native_x2apic_icr_write,
 	.wait_icr_idle			= native_x2apic_wait_icr_idle,
-- 
1.7.9.111.gf3fb0