x86: KVM guest: hypercall batching

Batch pte updates and tlb flushes in lazy MMU mode.

[avi:
 - adjust to mmu_op
 - helper for getting para_state without debug warnings]

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>

1 files changed, 60 insertions, 2 deletions

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index cbadc730496a..8b7a3cf37d2b 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -26,6 +26,22 @@
 #include <linux/cpu.h>
 #include <linux/mm.h>
 #include <linux/highmem.h>
+#include <linux/hardirq.h>
+
+#define MMU_QUEUE_SIZE 1024
+
+struct kvm_para_state {
+        u8 mmu_queue[MMU_QUEUE_SIZE];
+        int mmu_queue_len;
+        enum paravirt_lazy_mode mode;
+};
+
+static DEFINE_PER_CPU(struct kvm_para_state, para_state);
+
+static struct kvm_para_state *kvm_para_state(void)
+{
+        return &per_cpu(para_state, raw_smp_processor_id());
+}
 
 /*
  * No need for any "IO delay" on KVM
@@ -48,6 +64,28 @@ static void kvm_mmu_op(void *buffer, unsigned len)
         } while (len);
 }
 
+static void mmu_queue_flush(struct kvm_para_state *state)
+{
+        if (state->mmu_queue_len) {
+                kvm_mmu_op(state->mmu_queue, state->mmu_queue_len);
+                state->mmu_queue_len = 0;
+        }
+}
+
+static void kvm_deferred_mmu_op(void *buffer, int len)
+{
+        struct kvm_para_state *state = kvm_para_state();
+
+        if (state->mode != PARAVIRT_LAZY_MMU) {
+                kvm_mmu_op(buffer, len);
+                return;
+        }
+        if (state->mmu_queue_len + len > sizeof state->mmu_queue)
+                mmu_queue_flush(state);
+        memcpy(state->mmu_queue + state->mmu_queue_len, buffer, len);
+        state->mmu_queue_len += len;
+}
+
 static void kvm_mmu_write(void *dest, u64 val)
 {
         __u64 pte_phys;
@@ -68,7 +106,7 @@ static void kvm_mmu_write(void *dest, u64 val)
         wpte.pte_val = val;
         wpte.pte_phys = pte_phys;
 
-        kvm_mmu_op(&wpte, sizeof wpte);
+        kvm_deferred_mmu_op(&wpte, sizeof wpte);
 }
 
 /*
@@ -137,7 +175,7 @@ static void kvm_flush_tlb(void)
                 .header.op = KVM_MMU_OP_FLUSH_TLB,
         };
 
-        kvm_mmu_op(&ftlb, sizeof ftlb);
+        kvm_deferred_mmu_op(&ftlb, sizeof ftlb);
 }
 
 static void kvm_release_pt(u32 pfn)
@@ -150,6 +188,23 @@ static void kvm_release_pt(u32 pfn)
         kvm_mmu_op(&rpt, sizeof rpt);
 }
 
+static void kvm_enter_lazy_mmu(void)
+{
+        struct kvm_para_state *state = kvm_para_state();
+
+        paravirt_enter_lazy_mmu();
+        state->mode = paravirt_get_lazy_mode();
+}
+
+static void kvm_leave_lazy_mmu(void)
+{
+        struct kvm_para_state *state = kvm_para_state();
+
+        mmu_queue_flush(state);
+        paravirt_leave_lazy(paravirt_get_lazy_mode());
+        state->mode = paravirt_get_lazy_mode();
+}
+
 static void paravirt_ops_setup(void)
 {
         pv_info.name = "KVM";
@@ -178,6 +233,9 @@ static void paravirt_ops_setup(void)
                 pv_mmu_ops.release_pte = kvm_release_pt;
                 pv_mmu_ops.release_pmd = kvm_release_pt;
                 pv_mmu_ops.release_pud = kvm_release_pt;
+
+                pv_mmu_ops.lazy_mode.enter = kvm_enter_lazy_mmu;
+                pv_mmu_ops.lazy_mode.leave = kvm_leave_lazy_mmu;
         }
 }