KVM: optimize ISR lookups
We perform ISR lookups twice: during interrupt
injection and on EOI. Typical workloads only have
a single bit set there. So we can avoid ISR scans by
1. counting bits as we set/clear them in ISR
2. on set, caching the injected vector number
3. on clear, invalidating the cache
The real purpose of this is enabling PV EOI
which needs to quickly validate the vector.
But non PV guests also benefit: with this patch,
and without interrupt nesting, apic_find_highest_isr
will always return immediately without scanning ISR.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 93c1574..805d887 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -107,6 +107,16 @@
clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
}
+static inline int __apic_test_and_set_vector(int vec, void *bitmap)
+{
+ return __test_and_set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
+}
+
+static inline int __apic_test_and_clear_vector(int vec, void *bitmap)
+{
+ return __test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
+}
+
static inline int apic_hw_enabled(struct kvm_lapic *apic)
{
return (apic)->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE;
@@ -210,6 +220,16 @@
return fls(word[word_offset << 2]) - 1 + (word_offset << 5);
}
+static u8 count_vectors(void *bitmap)
+{
+ u32 *word = bitmap;
+ int word_offset;
+ u8 count = 0;
+ for (word_offset = 0; word_offset < MAX_APIC_VECTOR >> 5; ++word_offset)
+ count += hweight32(word[word_offset << 2]);
+ return count;
+}
+
static inline int apic_test_and_set_irr(int vec, struct kvm_lapic *apic)
{
apic->irr_pending = true;
@@ -242,6 +262,27 @@
apic->irr_pending = true;
}
+static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
+{
+ if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
+ ++apic->isr_count;
+ BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
+ /*
+ * ISR (in service register) bit is set when injecting an interrupt.
+ * The highest vector is injected. Thus the latest bit set matches
+ * the highest bit in ISR.
+ */
+ apic->highest_isr_cache = vec;
+}
+
+static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
+{
+ if (__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
+ --apic->isr_count;
+ BUG_ON(apic->isr_count < 0);
+ apic->highest_isr_cache = -1;
+}
+
int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic = vcpu->arch.apic;
@@ -273,6 +314,10 @@
static inline int apic_find_highest_isr(struct kvm_lapic *apic)
{
int result;
+ if (!apic->isr_count)
+ return -1;
+ if (likely(apic->highest_isr_cache != -1))
+ return apic->highest_isr_cache;
result = find_highest_vector(apic->regs + APIC_ISR);
ASSERT(result == -1 || result >= 16);
@@ -492,7 +537,7 @@
if (vector == -1)
return;
- apic_clear_vector(vector, apic->regs + APIC_ISR);
+ apic_clear_isr(vector, apic);
apic_update_ppr(apic);
if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) &&
@@ -1081,6 +1126,8 @@
apic_set_reg(apic, APIC_TMR + 0x10 * i, 0);
}
apic->irr_pending = false;
+ apic->isr_count = 0;
+ apic->highest_isr_cache = -1;
update_divide_count(apic);
atomic_set(&apic->lapic_timer.pending, 0);
if (kvm_vcpu_is_bsp(vcpu))
@@ -1248,7 +1295,7 @@
if (vector == -1)
return -1;
- apic_set_vector(vector, apic->regs + APIC_ISR);
+ apic_set_isr(vector, apic);
apic_update_ppr(apic);
apic_clear_irr(vector, apic);
return vector;
@@ -1267,6 +1314,8 @@
update_divide_count(apic);
start_apic_timer(apic);
apic->irr_pending = true;
+ apic->isr_count = count_vectors(apic->regs + APIC_ISR);
+ apic->highest_isr_cache = -1;
kvm_make_request(KVM_REQ_EVENT, vcpu);
}