KVM: arm64: nv: Handle FEAT_TTL hinted TLB operations

Support guest-provided information information to size the range of
required invalidation. This helps with reducing over-invalidation,
provided that the guest actually provides accurate information.
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20240614144552.2773592-12-maz@kernel.orgSigned-off-by: Oliver Upton <oliver.upton@linux.dev>

arch/arm64/include/asm/kvm_nested.h

@@ -124,6 +124,8 @@ extern void kvm_nested_s2_wp(struct kvm *kvm);
 extern void kvm_nested_s2_unmap(struct kvm *kvm);
 extern void kvm_nested_s2_flush(struct kvm *kvm);
 
+unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val);
+
 static inline bool kvm_supported_tlbi_s1e1_op(struct kvm_vcpu *vpcu, u32 instr)
 {
 	struct kvm *kvm = vpcu->kvm;

arch/arm64/kvm/nested.c

@@ -364,6 +364,95 @@ int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
 	return ret;
 }
 
+static unsigned int ttl_to_size(u8 ttl)
+{
+	int level = ttl & 3;
+	int gran = (ttl >> 2) & 3;
+	unsigned int max_size = 0;
+
+	switch (gran) {
+	case TLBI_TTL_TG_4K:
+		switch (level) {
+		case 0:
+			break;
+		case 1:
+			max_size = SZ_1G;
+			break;
+		case 2:
+			max_size = SZ_2M;
+			break;
+		case 3:
+			max_size = SZ_4K;
+			break;
+		}
+		break;
+	case TLBI_TTL_TG_16K:
+		switch (level) {
+		case 0:
+		case 1:
+			break;
+		case 2:
+			max_size = SZ_32M;
+			break;
+		case 3:
+			max_size = SZ_16K;
+			break;
+		}
+		break;
+	case TLBI_TTL_TG_64K:
+		switch (level) {
+		case 0:
+		case 1:
+			/* No 52bit IPA support */
+			break;
+		case 2:
+			max_size = SZ_512M;
+			break;
+		case 3:
+			max_size = SZ_64K;
+			break;
+		}
+		break;
+	default:			/* No size information */
+		break;
+	}
+
+	return max_size;
+}
+
+unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val)
+{
+	unsigned long max_size;
+	u8 ttl;
+
+	ttl = FIELD_GET(GENMASK_ULL(47, 44), val);
+
+	max_size = ttl_to_size(ttl);
+
+	if (!max_size) {
+		/* Compute the maximum extent of the invalidation */
+		switch (mmu->tlb_vtcr & VTCR_EL2_TG0_MASK) {
+		case VTCR_EL2_TG0_4K:
+			max_size = SZ_1G;
+			break;
+		case VTCR_EL2_TG0_16K:
+			max_size = SZ_32M;
+			break;
+		case VTCR_EL2_TG0_64K:
+		default:    /* IMPDEF: treat any other value as 64k */
+			/*
+			 * No, we do not support 52bit IPA in nested yet. Once
+			 * we do, this should be 4TB.
+			 */
+			max_size = SZ_512M;
+			break;
+		}
+	}
+
+	WARN_ON(!max_size);
+	return max_size;
+}
+
 /*
  * We can have multiple *different* MMU contexts with the same VMID:
  *

arch/arm64/kvm/sys_regs.c

@@ -2865,34 +2865,12 @@ static void s2_mmu_unmap_ipa(struct kvm_s2_mmu *mmu,
 	 *
 	 * - NS bit: we're non-secure only.
 	 *
-	 * - TTL field: We already have the granule size from the
-	 *   VTCR_EL2.TG0 field, and the level is only relevant to the
-	 *   guest's S2PT.
-	 *
 	 * - IPA[51:48]: We don't support 52bit IPA just yet...
 	 *
 	 * And of course, adjust the IPA to be on an actual address.
 	 */
 	base_addr = (info->ipa.addr & GENMASK_ULL(35, 0)) << 12;
-
-	/* Compute the maximum extent of the invalidation */
-	switch (mmu->tlb_vtcr & VTCR_EL2_TG0_MASK) {
-	case VTCR_EL2_TG0_4K:
-		max_size = SZ_1G;
-		break;
-	case VTCR_EL2_TG0_16K:
-		max_size = SZ_32M;
-		break;
-	case VTCR_EL2_TG0_64K:
-	default:	    /* IMPDEF: treat any other value as 64k */
-		/*
-		 * No, we do not support 52bit IPA in nested yet. Once
-		 * we do, this should be 4TB.
-		 */
-		max_size = SZ_512M;
-		break;
-	}
-
+	max_size = compute_tlb_inval_range(mmu, info->ipa.addr);
 	base_addr &= ~(max_size - 1);
 
 	kvm_stage2_unmap_range(mmu, base_addr, max_size);