Merge tag 'kvm-ppc-next-4.21-2' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc into kvm-next

Second PPC KVM update for 4.21

This has 5 commits that fix page dirty tracking when running nested
HV KVM guests, from Suraj Jitindar Singh.

4 files changed, 93 insertions, 12 deletions

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 82a0a9f3c39c..38f1b879f569 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -203,6 +203,8 @@ extern int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr,
 			int table_index, u64 *pte_ret_p);
 extern int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 			struct kvmppc_pte *gpte, bool data, bool iswrite);
+extern void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
+				    unsigned int pshift, unsigned int lpid);
 extern void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa,
 			unsigned int shift,
 			const struct kvm_memory_slot *memslot,
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 34968fd2de24..21b1ed5df888 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -637,6 +637,9 @@ extern int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 			     unsigned long *rmapp, struct rmap_nested **n_rmap);
 extern void kvmhv_insert_nest_rmap(struct kvm *kvm, unsigned long *rmapp,
 				   struct rmap_nested **n_rmap);
+extern void kvmhv_update_nest_rmap_rc_list(struct kvm *kvm, unsigned long *rmapp,
+					   unsigned long clr, unsigned long set,
+					   unsigned long hpa, unsigned long nbytes);
 extern void kvmhv_remove_nest_rmap_range(struct kvm *kvm,
 				const struct kvm_memory_slot *memslot,
 				unsigned long gpa, unsigned long hpa,
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 870ef9d5eee6..fb88167a402a 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -294,8 +294,8 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	return 0;
 }
 
-static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
-				    unsigned int pshift, unsigned int lpid)
+void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
+			     unsigned int pshift, unsigned int lpid)
 {
 	unsigned long psize = PAGE_SIZE;
 	int psi;
@@ -982,12 +982,18 @@ int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	unsigned long gpa = gfn << PAGE_SHIFT;
 	unsigned int shift;
 	int ref = 0;
+	unsigned long old, *rmapp;
 
 	ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
 	if (ptep && pte_present(*ptep) && pte_young(*ptep)) {
-		kvmppc_radix_update_pte(kvm, ptep, _PAGE_ACCESSED, 0,
-					gpa, shift);
+		old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_ACCESSED, 0,
+					      gpa, shift);
 		/* XXX need to flush tlb here? */
+		/* Also clear bit in ptes in shadow pgtable for nested guests */
+		rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn];
+		kvmhv_update_nest_rmap_rc_list(kvm, rmapp, _PAGE_ACCESSED, 0,
+					       old & PTE_RPN_MASK,
+					       1UL << shift);
 		ref = 1;
 	}
 	return ref;
@@ -1017,15 +1023,23 @@ static int kvm_radix_test_clear_dirty(struct kvm *kvm,
 	pte_t *ptep;
 	unsigned int shift;
 	int ret = 0;
+	unsigned long old, *rmapp;
 
 	ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
 	if (ptep && pte_present(*ptep) && pte_dirty(*ptep)) {
 		ret = 1;
 		if (shift)
 			ret = 1 << (shift - PAGE_SHIFT);
-		kvmppc_radix_update_pte(kvm, ptep, _PAGE_DIRTY, 0,
-					gpa, shift);
+		spin_lock(&kvm->mmu_lock);
+		old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_DIRTY, 0,
+					      gpa, shift);
 		kvmppc_radix_tlbie_page(kvm, gpa, shift, kvm->arch.lpid);
+		/* Also clear bit in ptes in shadow pgtable for nested guests */
+		rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn];
+		kvmhv_update_nest_rmap_rc_list(kvm, rmapp, _PAGE_DIRTY, 0,
+					       old & PTE_RPN_MASK,
+					       1UL << shift);
+		spin_unlock(&kvm->mmu_lock);
 	}
 	return ret;
 }
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 9dce4b9c1d9c..735e0ac6f5b2 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -788,6 +788,57 @@ void kvmhv_insert_nest_rmap(struct kvm *kvm, unsigned long *rmapp,
 	*n_rmap = NULL;
 }
 
+static void kvmhv_update_nest_rmap_rc(struct kvm *kvm, u64 n_rmap,
+				      unsigned long clr, unsigned long set,
+				      unsigned long hpa, unsigned long mask)
+{
+	struct kvm_nested_guest *gp;
+	unsigned long gpa;
+	unsigned int shift, lpid;
+	pte_t *ptep;
+
+	gpa = n_rmap & RMAP_NESTED_GPA_MASK;
+	lpid = (n_rmap & RMAP_NESTED_LPID_MASK) >> RMAP_NESTED_LPID_SHIFT;
+	gp = kvmhv_find_nested(kvm, lpid);
+	if (!gp)
+		return;
+
+	/* Find the pte */
+	ptep = __find_linux_pte(gp->shadow_pgtable, gpa, NULL, &shift);
+	/*
+	 * If the pte is present and the pfn is still the same, update the pte.
+	 * If the pfn has changed then this is a stale rmap entry, the nested
+	 * gpa actually points somewhere else now, and there is nothing to do.
+	 * XXX A future optimisation would be to remove the rmap entry here.
+	 */
+	if (ptep && pte_present(*ptep) && ((pte_val(*ptep) & mask) == hpa)) {
+		__radix_pte_update(ptep, clr, set);
+		kvmppc_radix_tlbie_page(kvm, gpa, shift, lpid);
+	}
+}
+
+/*
+ * For a given list of rmap entries, update the rc bits in all ptes in shadow
+ * page tables for nested guests which are referenced by the rmap list.
+ */
+void kvmhv_update_nest_rmap_rc_list(struct kvm *kvm, unsigned long *rmapp,
+				    unsigned long clr, unsigned long set,
+				    unsigned long hpa, unsigned long nbytes)
+{
+	struct llist_node *entry = ((struct llist_head *) rmapp)->first;
+	struct rmap_nested *cursor;
+	unsigned long rmap, mask;
+
+	if ((clr | set) & ~(_PAGE_DIRTY | _PAGE_ACCESSED))
+		return;
+
+	mask = PTE_RPN_MASK & ~(nbytes - 1);
+	hpa &= mask;
+
+	for_each_nest_rmap_safe(cursor, entry, &rmap)
+		kvmhv_update_nest_rmap_rc(kvm, rmap, clr, set, hpa, mask);
+}
+
 static void kvmhv_remove_nest_rmap(struct kvm *kvm, u64 n_rmap,
 				   unsigned long hpa, unsigned long mask)
 {
@@ -1150,7 +1201,7 @@ static long kvmhv_handle_nested_set_rc(struct kvm_vcpu *vcpu,
 	struct kvm *kvm = vcpu->kvm;
 	bool writing = !!(dsisr & DSISR_ISSTORE);
 	u64 pgflags;
-	bool ret;
+	long ret;
 
 	/* Are the rc bits set in the L1 partition scoped pte? */
 	pgflags = _PAGE_ACCESSED;
@@ -1163,16 +1214,22 @@ static long kvmhv_handle_nested_set_rc(struct kvm_vcpu *vcpu,
 	/* Set the rc bit in the pte of our (L0) pgtable for the L1 guest */
 	ret = kvmppc_hv_handle_set_rc(kvm, kvm->arch.pgtable, writing,
 				     gpte.raddr, kvm->arch.lpid);
-	spin_unlock(&kvm->mmu_lock);
-	if (!ret)
-		return -EINVAL;
+	if (!ret) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
 
 	/* Set the rc bit in the pte of the shadow_pgtable for the nest guest */
 	ret = kvmppc_hv_handle_set_rc(kvm, gp->shadow_pgtable, writing, n_gpa,
 				      gp->shadow_lpid);
 	if (!ret)
-		return -EINVAL;
-	return 0;
+		ret = -EINVAL;
+	else
+		ret = 0;
+
+out_unlock:
+	spin_unlock(&kvm->mmu_lock);
+	return ret;
 }
 
 static inline int kvmppc_radix_level_to_shift(int level)
@@ -1322,6 +1379,8 @@ static long int __kvmhv_nested_page_fault(struct kvm_run *run,
 			return ret;
 		shift = kvmppc_radix_level_to_shift(level);
 	}
+	/* Align gfn to the start of the page */
+	gfn = (gpa & ~((1UL << shift) - 1)) >> PAGE_SHIFT;
 
 	/* 3. Compute the pte we need to insert for nest_gpa -> host r_addr */
 
@@ -1329,6 +1388,9 @@ static long int __kvmhv_nested_page_fault(struct kvm_run *run,
 	perm |= gpte.may_read ? 0UL : _PAGE_READ;
 	perm |= gpte.may_write ? 0UL : _PAGE_WRITE;
 	perm |= gpte.may_execute ? 0UL : _PAGE_EXEC;
+	/* Only set accessed/dirty (rc) bits if set in host and l1 guest ptes */
+	perm |= (gpte.rc & _PAGE_ACCESSED) ? 0UL : _PAGE_ACCESSED;
+	perm |= ((gpte.rc & _PAGE_DIRTY) && writing) ? 0UL : _PAGE_DIRTY;
 	pte = __pte(pte_val(pte) & ~perm);
 
 	/* What size pte can we insert? */