KVM: PPC: Book3s HV: Implement get_dirty_log using hardware changed bit

This changes the implementation of kvm_vm_ioctl_get_dirty_log() for
Book3s HV guests to use the hardware C (changed) bits in the guest
hashed page table.  Since this makes the implementation quite different
from the Book3s PR case, this moves the existing implementation from
book3s.c to book3s_pr.c and creates a new implementation in book3s_hv.c.
That implementation calls kvmppc_hv_get_dirty_log() to do the actual
work by calling kvm_test_clear_dirty on each page.  It iterates over
the HPTEs, clearing the C bit if set, and returns 1 if any C bit was
set (including the saved C bit in the rmap entry).

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>

1 files changed, 39 insertions, 0 deletions

diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 2da670405727..c193625d5289 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1056,6 +1056,45 @@ out:
 	return ret;
 }
 
+/*
+ * Get (and clear) the dirty memory log for a memory slot.
+ */
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
+				      struct kvm_dirty_log *log)
+{
+	struct kvm_memory_slot *memslot;
+	struct kvm_vcpu *vcpu;
+	ulong ga, ga_end;
+	int is_dirty = 0;
+	int r;
+	unsigned long n;
+
+	mutex_lock(&kvm->slots_lock);
+
+	r = kvm_get_dirty_log(kvm, log, &is_dirty);
+	if (r)
+		goto out;
+
+	/* If nothing is dirty, don't bother messing with page tables. */
+	if (is_dirty) {
+		memslot = id_to_memslot(kvm->memslots, log->slot);
+
+		ga = memslot->base_gfn << PAGE_SHIFT;
+		ga_end = ga + (memslot->npages << PAGE_SHIFT);
+
+		kvm_for_each_vcpu(n, vcpu, kvm)
+			kvmppc_mmu_pte_pflush(vcpu, ga, ga_end);
+
+		n = kvm_dirty_bitmap_bytes(memslot);
+		memset(memslot->dirty_bitmap, 0, n);
+	}
+
+	r = 0;
+out:
+	mutex_unlock(&kvm->slots_lock);
+	return r;
+}
+
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				      struct kvm_userspace_memory_region *mem)
 {