Use vector-hashing to deliver lowest-priority interrupts, As an
example, modern Intel CPUs in server platform use this method to
handle lowest-priority interrupts.
Signed-off-by: Feng Wu <feng.wu@xxxxxxxxx>
---
arch/x86/kvm/irq_comm.c | 27 ++++++++++++++++++-----
arch/x86/kvm/lapic.c | 57 ++++++++++++++++++++++++++++++++++++++++---------
arch/x86/kvm/lapic.h | 2 ++
arch/x86/kvm/x86.c | 9 ++++++++
arch/x86/kvm/x86.h | 1 +
5 files changed, 81 insertions(+), 15 deletions(-)
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 84b96d3..c8c5f61 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -32,6 +32,7 @@
#include "ioapic.h"
#include "lapic.h"
+#include "x86.h"
static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
struct kvm *kvm, int irq_source_id, int level,
@@ -53,8 +54,10 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
struct kvm_lapic_irq *irq, unsigned long *dest_map)
{
- int i, r = -1;
+ int i, r = -1, idx = 0;
struct kvm_vcpu *vcpu, *lowest = NULL;
+ unsigned long dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)];
+ unsigned int dest_vcpus = 0;
if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
kvm_lowest_prio_delivery(irq)) {
@@ -65,6 +68,8 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map))
return r;
+ memset(dest_vcpu_bitmap, 0, sizeof(dest_vcpu_bitmap));
+
kvm_for_each_vcpu(i, vcpu, kvm) {
if (!kvm_apic_present(vcpu))
continue;
@@ -78,13 +83,25 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
r = 0;
r += kvm_apic_set_irq(vcpu, irq, dest_map);
} else if (kvm_lapic_enabled(vcpu)) {
- if (!lowest)
- lowest = vcpu;
- else if (kvm_apic_compare_prio(vcpu, lowest) < 0)
- lowest = vcpu;
+ if (!kvm_vector_hashing_enabled()) {
+ if (!lowest)
+ lowest = vcpu;
+ else if (kvm_apic_compare_prio(vcpu, lowest) < 0)
+ lowest = vcpu;
+ } else {
+ __set_bit(vcpu->vcpu_id, dest_vcpu_bitmap);
+ dest_vcpus++;
+ }
}
}
+ if (dest_vcpus != 0) {
+ idx = kvm_vector_2_index(irq->vector, dest_vcpus,
+ dest_vcpu_bitmap, KVM_MAX_VCPUS);
+
+ lowest = kvm_get_vcpu(kvm, idx - 1);
+ }
+
if (lowest)
r = kvm_apic_set_irq(lowest, irq, dest_map);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index ecd4ea1..e29001f 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -678,6 +678,22 @@ bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
}
}
+int kvm_vector_2_index(u32 vector, u32 dest_vcpus,
+ const unsigned long *bitmap, u32 bitmap_size)
+{
+ u32 mod;
+ int i, idx = 0;
+
+ mod = vector % dest_vcpus;
+
+ for (i = 0; i <= mod; i++) {
+ idx = find_next_bit(bitmap, bitmap_size, idx) + 1;
+ BUG_ON(idx > bitmap_size);
+ }
+
+ return idx;
+}
+
bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
struct kvm_lapic_irq *irq, int *r, unsigned long *dest_map)
{
@@ -731,17 +747,38 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
dst = map->logical_map[cid];
if (kvm_lowest_prio_delivery(irq)) {
- int l = -1;
- for_each_set_bit(i, &bitmap, 16) {
- if (!dst[i])
- continue;
- if (l < 0)
- l = i;
- else if (kvm_apic_compare_prio(dst[i]->vcpu, dst[l]->vcpu) < 0)
- l = i;
+ if (!kvm_vector_hashing_enabled()) {
+ int l = -1;
+ for_each_set_bit(i, &bitmap, 16) {
+ if (!dst[i])
+ continue;
+ if (l < 0)
+ l = i;
+ else if (kvm_apic_compare_prio(dst[i]->vcpu, dst[l]->vcpu) < 0)
+ l = i;
+ }
+ bitmap = (l >= 0) ? 1 << l : 0;
+ } else {
+ int idx = 0;
+ unsigned int dest_vcpus = 0;
+
+ for_each_set_bit(i, &bitmap, 16) {
+ if (!dst[i] && !kvm_lapic_enabled(dst[i]->vcpu)) {
+ __clear_bit(i, &bitmap);
+ continue;
+ }
+ }
+
+ dest_vcpus = hweight16(bitmap);
+
+ if (dest_vcpus != 0) {
+ idx = kvm_vector_2_index(irq->vector,
+ dest_vcpus, &bitmap, 16);
+
+ bitmap = 0;
+ __set_bit(idx-1, &bitmap);
+ }
}
-
- bitmap = (l >= 0) ? 1 << l : 0;
}
}
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index fde8e35d..6890ef0 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -170,4 +170,6 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu);
bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
struct kvm_vcpu **dest_vcpu);
+int kvm_vector_2_index(u32 vector, u32 dest_vcpus,
+ const unsigned long *bitmap, u32 bitmap_size);
#endif
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4a6eff1..fb47730 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -118,6 +118,9 @@ module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
unsigned int lapic_timer_advance_ns = 0;
module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
+bool __read_mostly enable_vector_hashing = 1;
+module_param(enable_vector_hashing, bool, S_IRUGO);
+
static bool backwards_tsc_observed = false;
#define KVM_NR_SHARED_MSRS 16
@@ -8165,6 +8168,12 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
return kvm_x86_ops->update_pi_irte(kvm, host_irq, guest_irq, set);
}
+bool kvm_vector_hashing_enabled(void)
+{
+ return enable_vector_hashing;
+}
+EXPORT_SYMBOL_GPL(kvm_vector_hashing_enabled);
+
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index f2afa5f..04bd0f9 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -179,6 +179,7 @@ int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data);
int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
int page_num);
+bool kvm_vector_hashing_enabled(void);
#define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \
| XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \
--
2.1.0
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
