KVM: PPC: Book3S HV: Handle memory slot deletion and modification correctly

This adds an implementation of kvm_arch_flush_shadow_memslot for
Book3S HV, and arranges for kvmppc_core_commit_memory_region to
flush the dirty log when modifying an existing slot.  With this,
we can handle deletion and modification of memory slots.

kvm_arch_flush_shadow_memslot calls kvmppc_core_flush_memslot, which
on Book3S HV now traverses the reverse map chains to remove any HPT
(hashed page table) entries referring to pages in the memslot.  This
gets called by generic code whenever deleting a memslot or changing
the guest physical address for a memslot.

We flush the dirty log in kvmppc_core_commit_memory_region for
consistency with what x86 does.  We only need to flush when an
existing memslot is being modified, because for a new memslot the
rmap array (which stores the dirty bits) is all zero, meaning that
every page is considered clean already, and when deleting a memslot
we obviously don't care about the dirty bits any more.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

1 files changed, 28 insertions, 5 deletions

diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index a389cc62b16c..f598366e51c6 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -851,7 +851,8 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
 		psize = hpte_page_size(hptep[0], ptel);
 		if ((hptep[0] & HPTE_V_VALID) &&
 		    hpte_rpn(ptel, psize) == gfn) {
-			hptep[0] |= HPTE_V_ABSENT;
+			if (kvm->arch.using_mmu_notifiers)
+				hptep[0] |= HPTE_V_ABSENT;
 			kvmppc_invalidate_hpte(kvm, hptep, i);
 			/* Harvest R and C */
 			rcbits = hptep[1] & (HPTE_R_R | HPTE_R_C);
@@ -878,6 +879,28 @@ int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
 	return 0;
 }
 
+void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
+{
+	unsigned long *rmapp;
+	unsigned long gfn;
+	unsigned long n;
+
+	rmapp = memslot->arch.rmap;
+	gfn = memslot->base_gfn;
+	for (n = memslot->npages; n; --n) {
+		/*
+		 * Testing the present bit without locking is OK because
+		 * the memslot has been marked invalid already, and hence
+		 * no new HPTEs referencing this page can be created,
+		 * thus the present bit can't go from 0 to 1.
+		 */
+		if (*rmapp & KVMPPC_RMAP_PRESENT)
+			kvm_unmap_rmapp(kvm, rmapp, gfn);
+		++rmapp;
+		++gfn;
+	}
+}
+
 static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 			 unsigned long gfn)
 {
@@ -1031,16 +1054,16 @@ static int kvm_test_clear_dirty(struct kvm *kvm, unsigned long *rmapp)
 	return ret;
 }
 
-long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
+long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot,
+			     unsigned long *map)
 {
 	unsigned long i;
-	unsigned long *rmapp, *map;
+	unsigned long *rmapp;
 
 	preempt_disable();
 	rmapp = memslot->arch.rmap;
-	map = memslot->dirty_bitmap;
 	for (i = 0; i < memslot->npages; ++i) {
-		if (kvm_test_clear_dirty(kvm, rmapp))
+		if (kvm_test_clear_dirty(kvm, rmapp) && map)
 			__set_bit_le(i, map);
 		++rmapp;
 	}