KVM: PPC: Book3S HV: Report VPA and DTL modifications in dirty map
At present, the KVM_GET_DIRTY_LOG ioctl doesn't report modifications
done by the host to the virtual processor areas (VPAs) and dispatch
trace logs (DTLs) registered by the guest. This is because those
modifications are done either in real mode or in the host kernel
context, and in neither case does the access go through the guest's
HPT, and thus no change (C) bit gets set in the guest's HPT.
However, the changes done by the host do need to be tracked so that
the modified pages get transferred when doing live migration. In
order to track these modifications, this adds a dirty flag to the
struct representing the VPA/DTL areas, and arranges to set the flag
when the VPA/DTL gets modified by the host. Then, when we are
collecting the dirty log, we also check the dirty flags for the
VPA and DTL for each vcpu and set the relevant bit in the dirty log
if necessary. Doing this also means we now need to keep track of
the guest physical address of the VPA/DTL areas.
So as not to lose track of modifications to a VPA/DTL area when it gets
unregistered, or when a new area gets registered in its place, we need
to transfer the dirty state to the rmap chain. This adds code to
kvmppc_unpin_guest_page() to do that if the area was dirty. To simplify
that code, we now require that all VPA, DTL and SLB shadow buffer areas
fit within a single host page. Guests already comply with this
requirement because pHyp requires that these areas not cross a 4k
boundary.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 1e521ba..5af0f29 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -259,7 +259,7 @@
len = ((struct reg_vpa *)va)->length.hword;
else
len = ((struct reg_vpa *)va)->length.word;
- kvmppc_unpin_guest_page(kvm, va);
+ kvmppc_unpin_guest_page(kvm, va, vpa, false);
/* Check length */
if (len > nb || len < sizeof(struct reg_vpa))
@@ -359,13 +359,13 @@
va = NULL;
nb = 0;
if (gpa)
- va = kvmppc_pin_guest_page(kvm, vpap->next_gpa, &nb);
+ va = kvmppc_pin_guest_page(kvm, gpa, &nb);
spin_lock(&vcpu->arch.vpa_update_lock);
if (gpa == vpap->next_gpa)
break;
/* sigh... unpin that one and try again */
if (va)
- kvmppc_unpin_guest_page(kvm, va);
+ kvmppc_unpin_guest_page(kvm, va, gpa, false);
}
vpap->update_pending = 0;
@@ -375,12 +375,15 @@
* has changed the mappings underlying guest memory,
* so unregister the region.
*/
- kvmppc_unpin_guest_page(kvm, va);
+ kvmppc_unpin_guest_page(kvm, va, gpa, false);
va = NULL;
}
if (vpap->pinned_addr)
- kvmppc_unpin_guest_page(kvm, vpap->pinned_addr);
+ kvmppc_unpin_guest_page(kvm, vpap->pinned_addr, vpap->gpa,
+ vpap->dirty);
+ vpap->gpa = gpa;
vpap->pinned_addr = va;
+ vpap->dirty = false;
if (va)
vpap->pinned_end = va + vpap->len;
}
@@ -472,6 +475,7 @@
/* order writing *dt vs. writing vpa->dtl_idx */
smp_wmb();
vpa->dtl_idx = ++vcpu->arch.dtl_index;
+ vcpu->arch.dtl.dirty = true;
}
int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
@@ -913,15 +917,19 @@
return ERR_PTR(err);
}
+static void unpin_vpa(struct kvm *kvm, struct kvmppc_vpa *vpa)
+{
+ if (vpa->pinned_addr)
+ kvmppc_unpin_guest_page(kvm, vpa->pinned_addr, vpa->gpa,
+ vpa->dirty);
+}
+
void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
{
spin_lock(&vcpu->arch.vpa_update_lock);
- if (vcpu->arch.dtl.pinned_addr)
- kvmppc_unpin_guest_page(vcpu->kvm, vcpu->arch.dtl.pinned_addr);
- if (vcpu->arch.slb_shadow.pinned_addr)
- kvmppc_unpin_guest_page(vcpu->kvm, vcpu->arch.slb_shadow.pinned_addr);
- if (vcpu->arch.vpa.pinned_addr)
- kvmppc_unpin_guest_page(vcpu->kvm, vcpu->arch.vpa.pinned_addr);
+ unpin_vpa(vcpu->kvm, &vcpu->arch.dtl);
+ unpin_vpa(vcpu->kvm, &vcpu->arch.slb_shadow);
+ unpin_vpa(vcpu->kvm, &vcpu->arch.vpa);
spin_unlock(&vcpu->arch.vpa_update_lock);
kvm_vcpu_uninit(vcpu);
kmem_cache_free(kvm_vcpu_cache, vcpu);