KVM: PPC: Book3S HV: Implement H_CLEAR_REF and H_CLEAR_MOD

This adds implementations for the H_CLEAR_REF (test and clear reference
bit) and H_CLEAR_MOD (test and clear changed bit) hypercalls.

When clearing the reference or change bit in the guest view of the HPTE,
we also have to clear it in the real HPTE so that we can detect future
references or changes.  When we do so, we transfer the R or C bit value
to the rmap entry for the underlying host page so that kvm_age_hva_hv(),
kvm_test_age_hva_hv() and kvmppc_hv_get_dirty_log() know that the page
has been referenced and/or changed.

These hypercalls are not used by Linux guests.  These implementations
have been tested using a FreeBSD guest.

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

1 files changed, 119 insertions, 7 deletions

diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index c7a3ab2652d0..c1df9bb1e413 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -112,25 +112,38 @@ void kvmppc_update_rmap_change(unsigned long *rmap, unsigned long psize)
 }
 EXPORT_SYMBOL_GPL(kvmppc_update_rmap_change);
 
+/* Returns a pointer to the revmap entry for the page mapped by a HPTE */
+static unsigned long *revmap_for_hpte(struct kvm *kvm, unsigned long hpte_v,
+				      unsigned long hpte_gr)
+{
+	struct kvm_memory_slot *memslot;
+	unsigned long *rmap;
+	unsigned long gfn;
+
+	gfn = hpte_rpn(hpte_gr, hpte_page_size(hpte_v, hpte_gr));
+	memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn);
+	if (!memslot)
+		return NULL;
+
+	rmap = real_vmalloc_addr(&memslot->arch.rmap[gfn - memslot->base_gfn]);
+	return rmap;
+}
+
 /* Remove this HPTE from the chain for a real page */
 static void remove_revmap_chain(struct kvm *kvm, long pte_index,
 				struct revmap_entry *rev,
 				unsigned long hpte_v, unsigned long hpte_r)
 {
 	struct revmap_entry *next, *prev;
-	unsigned long gfn, ptel, head;
-	struct kvm_memory_slot *memslot;
+	unsigned long ptel, head;
 	unsigned long *rmap;
 	unsigned long rcbits;
 
 	rcbits = hpte_r & (HPTE_R_R | HPTE_R_C);
 	ptel = rev->guest_rpte |= rcbits;
-	gfn = hpte_rpn(ptel, hpte_page_size(hpte_v, ptel));
-	memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn);
-	if (!memslot)
+	rmap = revmap_for_hpte(kvm, hpte_v, ptel);
+	if (!rmap)
 		return;
-
-	rmap = real_vmalloc_addr(&memslot->arch.rmap[gfn - memslot->base_gfn]);
 	lock_rmap(rmap);
 
 	head = *rmap & KVMPPC_RMAP_INDEX;
@@ -678,6 +691,105 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
 	return H_SUCCESS;
 }
 
+long kvmppc_h_clear_ref(struct kvm_vcpu *vcpu, unsigned long flags,
+			unsigned long pte_index)
+{
+	struct kvm *kvm = vcpu->kvm;
+	__be64 *hpte;
+	unsigned long v, r, gr;
+	struct revmap_entry *rev;
+	unsigned long *rmap;
+	long ret = H_NOT_FOUND;
+
+	if (pte_index >= kvm->arch.hpt_npte)
+		return H_PARAMETER;
+
+	rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
+	hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4));
+	while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
+		cpu_relax();
+	v = be64_to_cpu(hpte[0]);
+	r = be64_to_cpu(hpte[1]);
+	if (!(v & (HPTE_V_VALID | HPTE_V_ABSENT)))
+		goto out;
+
+	gr = rev->guest_rpte;
+	if (rev->guest_rpte & HPTE_R_R) {
+		rev->guest_rpte &= ~HPTE_R_R;
+		note_hpte_modification(kvm, rev);
+	}
+	if (v & HPTE_V_VALID) {
+		gr |= r & (HPTE_R_R | HPTE_R_C);
+		if (r & HPTE_R_R) {
+			kvmppc_clear_ref_hpte(kvm, hpte, pte_index);
+			rmap = revmap_for_hpte(kvm, v, gr);
+			if (rmap) {
+				lock_rmap(rmap);
+				*rmap |= KVMPPC_RMAP_REFERENCED;
+				unlock_rmap(rmap);
+			}
+		}
+	}
+	vcpu->arch.gpr[4] = gr;
+	ret = H_SUCCESS;
+ out:
+	unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);
+	return ret;
+}
+
+long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags,
+			unsigned long pte_index)
+{
+	struct kvm *kvm = vcpu->kvm;
+	__be64 *hpte;
+	unsigned long v, r, gr;
+	struct revmap_entry *rev;
+	unsigned long *rmap;
+	long ret = H_NOT_FOUND;
+
+	if (pte_index >= kvm->arch.hpt_npte)
+		return H_PARAMETER;
+
+	rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
+	hpte = (__be64 *)(kvm->arch.hpt_virt + (pte_index << 4));
+	while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
+		cpu_relax();
+	v = be64_to_cpu(hpte[0]);
+	r = be64_to_cpu(hpte[1]);
+	if (!(v & (HPTE_V_VALID | HPTE_V_ABSENT)))
+		goto out;
+
+	gr = rev->guest_rpte;
+	if (gr & HPTE_R_C) {
+		rev->guest_rpte &= ~HPTE_R_C;
+		note_hpte_modification(kvm, rev);
+	}
+	if (v & HPTE_V_VALID) {
+		/* need to make it temporarily absent so C is stable */
+		hpte[0] |= cpu_to_be64(HPTE_V_ABSENT);
+		kvmppc_invalidate_hpte(kvm, hpte, pte_index);
+		r = be64_to_cpu(hpte[1]);
+		gr |= r & (HPTE_R_R | HPTE_R_C);
+		if (r & HPTE_R_C) {
+			unsigned long psize = hpte_page_size(v, r);
+			hpte[1] = cpu_to_be64(r & ~HPTE_R_C);
+			eieio();
+			rmap = revmap_for_hpte(kvm, v, gr);
+			if (rmap) {
+				lock_rmap(rmap);
+				*rmap |= KVMPPC_RMAP_CHANGED;
+				kvmppc_update_rmap_change(rmap, psize);
+				unlock_rmap(rmap);
+			}
+		}
+	}
+	vcpu->arch.gpr[4] = gr;
+	ret = H_SUCCESS;
+ out:
+	unlock_hpte(hpte, v & ~HPTE_V_HVLOCK);
+	return ret;
+}
+
 void kvmppc_invalidate_hpte(struct kvm *kvm, __be64 *hptep,
 			unsigned long pte_index)
 {