KVM: PPC: Book3S HV: Make HPT reading code notice R/C bit changes

At present, the code that determines whether a HPT entry has changed,
and thus needs to be sent to userspace when it is copying the HPT,
doesn't consider a hardware update to the reference and change bits
(R and C) in the HPT entries to constitute a change that needs to
be sent to userspace.  This adds code to check for changes in R and C
when we are scanning the HPT to find changed entries, and adds code
to set the changed flag for the HPTE when we update the R and C bits
in the guest view of the HPTE.

Since we now need to set the HPTE changed flag in book3s_64_mmu_hv.c
as well as book3s_hv_rm_mmu.c, we move the note_hpte_modification()
function into kvm_book3s_64.h.

Current Linux guest kernels don't use the hardware updates of R and C
in the HPT, so this change won't affect them.  Linux (or other) kernels
might in future want to use the R and C bits and have them correctly
transferred across when a guest is migrated, so it is better to correct
this deficiency.

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

1 files changed, 50 insertions, 9 deletions

diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 8cc18abd6dde..d641a6634b02 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -893,7 +893,10 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
 			/* Harvest R and C */
 			rcbits = hptep[1] & (HPTE_R_R | HPTE_R_C);
 			*rmapp |= rcbits << KVMPPC_RMAP_RC_SHIFT;
-			rev[i].guest_rpte = ptel | rcbits;
+			if (rcbits & ~rev[i].guest_rpte) {
+				rev[i].guest_rpte = ptel | rcbits;
+				note_hpte_modification(kvm, &rev[i]);
+			}
 		}
 		unlock_rmap(rmapp);
 		hptep[0] &= ~HPTE_V_HVLOCK;
@@ -976,7 +979,10 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 		/* Now check and modify the HPTE */
 		if ((hptep[0] & HPTE_V_VALID) && (hptep[1] & HPTE_R_R)) {
 			kvmppc_clear_ref_hpte(kvm, hptep, i);
-			rev[i].guest_rpte |= HPTE_R_R;
+			if (!(rev[i].guest_rpte & HPTE_R_R)) {
+				rev[i].guest_rpte |= HPTE_R_R;
+				note_hpte_modification(kvm, &rev[i]);
+			}
 			ret = 1;
 		}
 		hptep[0] &= ~HPTE_V_HVLOCK;
@@ -1080,7 +1086,10 @@ static int kvm_test_clear_dirty(struct kvm *kvm, unsigned long *rmapp)
 			hptep[1] &= ~HPTE_R_C;
 			eieio();
 			hptep[0] = (hptep[0] & ~HPTE_V_ABSENT) | HPTE_V_VALID;
-			rev[i].guest_rpte |= HPTE_R_C;
+			if (!(rev[i].guest_rpte & HPTE_R_C)) {
+				rev[i].guest_rpte |= HPTE_R_C;
+				note_hpte_modification(kvm, &rev[i]);
+			}
 			ret = 1;
 		}
 		hptep[0] &= ~HPTE_V_HVLOCK;
@@ -1193,16 +1202,36 @@ struct kvm_htab_ctx {
 
 #define HPTE_SIZE	(2 * sizeof(unsigned long))
 
+/*
+ * Returns 1 if this HPT entry has been modified or has pending
+ * R/C bit changes.
+ */
+static int hpte_dirty(struct revmap_entry *revp, unsigned long *hptp)
+{
+	unsigned long rcbits_unset;
+
+	if (revp->guest_rpte & HPTE_GR_MODIFIED)
+		return 1;
+
+	/* Also need to consider changes in reference and changed bits */
+	rcbits_unset = ~revp->guest_rpte & (HPTE_R_R | HPTE_R_C);
+	if ((hptp[0] & HPTE_V_VALID) && (hptp[1] & rcbits_unset))
+		return 1;
+
+	return 0;
+}
+
 static long record_hpte(unsigned long flags, unsigned long *hptp,
 			unsigned long *hpte, struct revmap_entry *revp,
 			int want_valid, int first_pass)
 {
 	unsigned long v, r;
+	unsigned long rcbits_unset;
 	int ok = 1;
 	int valid, dirty;
 
 	/* Unmodified entries are uninteresting except on the first pass */
-	dirty = !!(revp->guest_rpte & HPTE_GR_MODIFIED);
+	dirty = hpte_dirty(revp, hptp);
 	if (!first_pass && !dirty)
 		return 0;
 
@@ -1223,16 +1252,28 @@ static long record_hpte(unsigned long flags, unsigned long *hptp,
 		while (!try_lock_hpte(hptp, HPTE_V_HVLOCK))
 			cpu_relax();
 		v = hptp[0];
+
+		/* re-evaluate valid and dirty from synchronized HPTE value */
+		valid = !!(v & HPTE_V_VALID);
+		dirty = !!(revp->guest_rpte & HPTE_GR_MODIFIED);
+
+		/* Harvest R and C into guest view if necessary */
+		rcbits_unset = ~revp->guest_rpte & (HPTE_R_R | HPTE_R_C);
+		if (valid && (rcbits_unset & hptp[1])) {
+			revp->guest_rpte |= (hptp[1] & (HPTE_R_R | HPTE_R_C)) |
+				HPTE_GR_MODIFIED;
+			dirty = 1;
+		}
+
 		if (v & HPTE_V_ABSENT) {
 			v &= ~HPTE_V_ABSENT;
 			v |= HPTE_V_VALID;
+			valid = 1;
 		}
-		/* re-evaluate valid and dirty from synchronized HPTE value */
-		valid = !!(v & HPTE_V_VALID);
 		if ((flags & KVM_GET_HTAB_BOLTED_ONLY) && !(v & HPTE_V_BOLTED))
 			valid = 0;
-		r = revp->guest_rpte | (hptp[1] & (HPTE_R_R | HPTE_R_C));
-		dirty = !!(revp->guest_rpte & HPTE_GR_MODIFIED);
+
+		r = revp->guest_rpte;
 		/* only clear modified if this is the right sort of entry */
 		if (valid == want_valid && dirty) {
 			r &= ~HPTE_GR_MODIFIED;
@@ -1288,7 +1329,7 @@ static ssize_t kvm_htab_read(struct file *file, char __user *buf,
 		/* Skip uninteresting entries, i.e. clean on not-first pass */
 		if (!first_pass) {
 			while (i < kvm->arch.hpt_npte &&
-			       !(revp->guest_rpte & HPTE_GR_MODIFIED)) {
+			       !hpte_dirty(revp, hptp)) {
 				++i;
 				hptp += 2;
 				++revp;