Merge remote-tracking branches 'regulator/fix/anatop', 'regulator/fix/gpio', 'regulat...

[firefly-linux-kernel-4.4.55.git] / virt / kvm / kvm_main.c

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 4662a8877f6c7a06b81803d417e52120a009a15b..04146a2e1d8191e3e152954824594555884f5f6d 100644 (file)
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -397,6 +397,36 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
        return young;
 }
 
+static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn,
+                                       struct mm_struct *mm,
+                                       unsigned long start,
+                                       unsigned long end)
+{
+       struct kvm *kvm = mmu_notifier_to_kvm(mn);
+       int young, idx;
+
+       idx = srcu_read_lock(&kvm->srcu);
+       spin_lock(&kvm->mmu_lock);
+       /*
+        * Even though we do not flush TLB, this will still adversely
+        * affect performance on pre-Haswell Intel EPT, where there is
+        * no EPT Access Bit to clear so that we have to tear down EPT
+        * tables instead. If we find this unacceptable, we can always
+        * add a parameter to kvm_age_hva so that it effectively doesn't
+        * do anything on clear_young.
+        *
+        * Also note that currently we never issue secondary TLB flushes
+        * from clear_young, leaving this job up to the regular system
+        * cadence. If we find this inaccurate, we might come up with a
+        * more sophisticated heuristic later.
+        */
+       young = kvm_age_hva(kvm, start, end);
+       spin_unlock(&kvm->mmu_lock);
+       srcu_read_unlock(&kvm->srcu, idx);
+
+       return young;
+}
+
 static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn,
                                       struct mm_struct *mm,
                                       unsigned long address)
@@ -429,6 +459,7 @@ static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
        .invalidate_range_start = kvm_mmu_notifier_invalidate_range_start,
        .invalidate_range_end   = kvm_mmu_notifier_invalidate_range_end,
        .clear_flush_young      = kvm_mmu_notifier_clear_flush_young,
+       .clear_young            = kvm_mmu_notifier_clear_young,
        .test_young             = kvm_mmu_notifier_test_young,
        .change_pte             = kvm_mmu_notifier_change_pte,
        .release                = kvm_mmu_notifier_release,
@@ -1973,6 +2004,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
        if (vcpu->halt_poll_ns) {
                ktime_t stop = ktime_add_ns(ktime_get(), vcpu->halt_poll_ns);
 
+               ++vcpu->stat.halt_attempted_poll;
                do {
                        /*
                         * This sets KVM_REQ_UNHALT if an interrupt
@@ -2012,7 +2044,8 @@ out:
                else if (vcpu->halt_poll_ns < halt_poll_ns &&
                        block_ns < halt_poll_ns)
                        grow_halt_poll_ns(vcpu);
-       }
+       } else
+               vcpu->halt_poll_ns = 0;
 
        trace_kvm_vcpu_wakeup(block_ns, waited);
 }
@@ -3125,10 +3158,25 @@ static void kvm_io_bus_destroy(struct kvm_io_bus *bus)
 static inline int kvm_io_bus_cmp(const struct kvm_io_range *r1,
                                 const struct kvm_io_range *r2)
 {
-       if (r1->addr < r2->addr)
+       gpa_t addr1 = r1->addr;
+       gpa_t addr2 = r2->addr;
+
+       if (addr1 < addr2)
                return -1;
-       if (r1->addr + r1->len > r2->addr + r2->len)
+
+       /* If r2->len == 0, match the exact address.  If r2->len != 0,
+        * accept any overlapping write.  Any order is acceptable for
+        * overlapping ranges, because kvm_io_bus_get_first_dev ensures
+        * we process all of them.
+        */
+       if (r2->len) {
+               addr1 += r1->len;
+               addr2 += r2->len;
+       }
+
+       if (addr1 > addr2)
                return 1;
+
        return 0;
 }