KVM: PPC: Book3S HV: Add a mechanism for recording modified HPTEs

This uses a bit in our record of the guest view of the HPTE to record
when the HPTE gets modified.  We use a reserved bit for this, and ensure
that this bit is always cleared in HPTE values returned to the guest.

The recording of modified HPTEs is only done if other code indicates
its interest by setting kvm->arch.hpte_mod_interest to a non-zero value.
The reason for this is that when later commits add facilities for
userspace to read the HPT, the first pass of reading the HPT will be
quicker if there are no (or very few) HPTEs marked as modified,
rather than having most HPTEs marked as modified.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

arch/powerpc/include/asm/kvm_book3s_64.h

@@ -50,6 +50,15 @@ extern int kvm_hpt_order;		/* order of preallocated HPTs */
 #define HPTE_V_HVLOCK	0x40UL
 #define HPTE_V_ABSENT	0x20UL
 
+/*
+ * We use this bit in the guest_rpte field of the revmap entry
+ * to indicate a modified HPTE.
+ */
+#define HPTE_GR_MODIFIED	(1ul << 62)
+
+/* These bits are reserved in the guest view of the HPTE */
+#define HPTE_GR_RESERVED	HPTE_GR_MODIFIED
+
 static inline long try_lock_hpte(unsigned long *hpte, unsigned long bits)
 {
 	unsigned long tmp, old;

arch/powerpc/include/asm/kvm_host.h

@@ -248,6 +248,7 @@ struct kvm_arch {
 	atomic_t vcpus_running;
 	unsigned long hpt_npte;
 	unsigned long hpt_mask;
+	atomic_t hpte_mod_interest;
 	spinlock_t slot_phys_lock;
 	unsigned short last_vcpu[NR_CPUS];
 	struct kvmppc_vcore *vcores[KVM_MAX_VCORES];

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -66,6 +66,17 @@ void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev,
 }
 EXPORT_SYMBOL_GPL(kvmppc_add_revmap_chain);
 
+/*
+ * Note modification of an HPTE; set the HPTE modified bit
+ * if anyone is interested.
+ */
+static inline void note_hpte_modification(struct kvm *kvm,
+					  struct revmap_entry *rev)
+{
+	if (atomic_read(&kvm->arch.hpte_mod_interest))
+		rev->guest_rpte |= HPTE_GR_MODIFIED;
+}
+
 /* 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,
@@ -138,7 +149,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 	unsigned long slot_fn, hva;
 	unsigned long *hpte;
 	struct revmap_entry *rev;
-	unsigned long g_ptel = ptel;
+	unsigned long g_ptel;
 	struct kvm_memory_slot *memslot;
 	unsigned long *physp, pte_size;
 	unsigned long is_io;
@@ -153,6 +164,8 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 		return H_PARAMETER;
 	writing = hpte_is_writable(ptel);
 	pteh &= ~(HPTE_V_HVLOCK | HPTE_V_ABSENT | HPTE_V_VALID);
+	ptel &= ~HPTE_GR_RESERVED;
+	g_ptel = ptel;
 
 	/* used later to detect if we might have been invalidated */
 	mmu_seq = kvm->mmu_notifier_seq;
@@ -287,8 +300,10 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 	rev = &kvm->arch.revmap[pte_index];
 	if (realmode)
 		rev = real_vmalloc_addr(rev);
-	if (rev)
+	if (rev) {
 		rev->guest_rpte = g_ptel;
+		note_hpte_modification(kvm, rev);
+	}
 
 	/* Link HPTE into reverse-map chain */
 	if (pteh & HPTE_V_VALID) {
@@ -392,7 +407,8 @@ long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
 		/* Read PTE low word after tlbie to get final R/C values */
 		remove_revmap_chain(kvm, pte_index, rev, v, hpte[1]);
 	}
-	r = rev->guest_rpte;
+	r = rev->guest_rpte & ~HPTE_GR_RESERVED;
+	note_hpte_modification(kvm, rev);
 	unlock_hpte(hpte, 0);
 
 	vcpu->arch.gpr[4] = v;
@@ -466,6 +482,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 
 			args[j] = ((0x80 | flags) << 56) + pte_index;
 			rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
+			note_hpte_modification(kvm, rev);
 
 			if (!(hp[0] & HPTE_V_VALID)) {
 				/* insert R and C bits from PTE */
@@ -555,6 +572,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 	if (rev) {
 		r = (rev->guest_rpte & ~mask) | bits;
 		rev->guest_rpte = r;
+		note_hpte_modification(kvm, rev);
 	}
 	r = (hpte[1] & ~mask) | bits;
 
@@ -606,8 +624,10 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
 			v &= ~HPTE_V_ABSENT;
 			v |= HPTE_V_VALID;
 		}
-		if (v & HPTE_V_VALID)
+		if (v & HPTE_V_VALID) {
 			r = rev[i].guest_rpte | (r & (HPTE_R_R | HPTE_R_C));
+			r &= ~HPTE_GR_RESERVED;
+		}
 		vcpu->arch.gpr[4 + i * 2] = v;
 		vcpu->arch.gpr[5 + i * 2] = r;
 	}