[PATCH v3 53/66] KVM: arm64: nv: Add handling of ARMv8.4-TTL TLB invalidation

[Marc Zyngier]

Support guest-provided information information to find out about
the range of required invalidation.

Signed-off-by: Marc Zyngier <maz at kernel.org>
---
 arch/arm64/include/asm/kvm_nested.h |  1 +
 arch/arm64/kvm/nested.c             | 57 +++++++++++++++++++++
 arch/arm64/kvm/sys_regs.c           | 79 +++++++++++++++++++----------
 3 files changed, 109 insertions(+), 28 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 5fa3c634c8e1..7c47ad655e2e 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -123,6 +123,7 @@ extern bool __forward_traps(struct kvm_vcpu *vcpu, unsigned int reg,
 			    u64 control_bit);
 extern bool forward_traps(struct kvm_vcpu *vcpu, u64 control_bit);
 extern bool forward_nv_traps(struct kvm_vcpu *vcpu);
+unsigned int ttl_to_size(u8 ttl);
 
 struct sys_reg_params;
 struct sys_reg_desc;
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 9574fde823e6..05b711e730b6 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -351,6 +351,63 @@ int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa,
 	return ret;
 }
 
+
+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;
+}
+
 /* Must be called with kvm->lock held */
 struct kvm_s2_mmu *lookup_s2_mmu(struct kvm *kvm, u64 vttbr, u64 hcr)
 {
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 60d2fb6edc93..61094f5e955e 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -9,6 +9,7 @@
  *          Christoffer Dall <c.dall at virtualopensystems.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/bsearch.h>
 #include <linux/kvm_host.h>
 #include <linux/mm.h>
@@ -2578,59 +2579,81 @@ static bool handle_vmalls12e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	return true;
 }
 
+static unsigned long compute_tlb_inval_range(struct kvm_vcpu *vcpu,
+					     struct kvm_s2_mmu *mmu,
+					     u64 val)
+{
+	unsigned long max_size;
+	u8 ttl = 0;
+
+	if (cpus_have_const_cap(ARM64_HAS_ARMv8_4_TTL)) {
+		ttl = FIELD_GET(GENMASK_ULL(47, 44), val);
+	}
+
+	max_size = ttl_to_size(ttl);
+
+	if (!max_size) {
+		u64 vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
+
+		/* Compute the maximum extent of the invalidation */
+		switch ((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:
+			/*
+			 * No, we do not support 52bit IPA in nested yet. Once
+			 * we do, this should be 4TB.
+			 */
+			/* FIXME: remove the 52bit PA support from the IDregs */
+			max_size = SZ_512M;
+			break;
+		default:
+			BUG();
+		}
+	}
+
+	WARN_ON(!max_size);
+	return max_size;
+}
+
 static bool handle_ipas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 			     const struct sys_reg_desc *r)
 {
 	u64 vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
-	u64 vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2);
 	struct kvm_s2_mmu *mmu;
 	u64 base_addr;
-	int max_size;
+	unsigned long max_size;
 
 	/*
 	 * We drop a number of things from the supplied value:
 	 *
 	 * - 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 = (p->regval & GENMASK_ULL(35, 0)) << 12;
 
-	/* Compute the maximum extent of the invalidation */
-	switch ((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:
-		/*
-		 * No, we do not support 52bit IPA in nested yet. Once
-		 * we do, this should be 4TB.
-		 */
-		/* FIXME: remove the 52bit PA support from the IDregs */
-		max_size = SZ_512M;
-		break;
-	default:
-		BUG();
-	}
-
 	spin_lock(&vcpu->kvm->mmu_lock);
 
 	mmu = lookup_s2_mmu(vcpu->kvm, vttbr, HCR_VM);
-	if (mmu)
+	if (mmu) {
+		max_size = compute_tlb_inval_range(vcpu, mmu, p->regval);
+		base_addr &= ~(max_size - 1);
 		kvm_unmap_stage2_range(mmu, base_addr, max_size);
+	}
 
 	mmu = lookup_s2_mmu(vcpu->kvm, vttbr, 0);
-	if (mmu)
+	if (mmu) {
+		max_size = compute_tlb_inval_range(vcpu, mmu, p->regval);
+		base_addr &= ~(max_size - 1);
 		kvm_unmap_stage2_range(mmu, base_addr, max_size);
+	}
 
 	spin_unlock(&vcpu->kvm->mmu_lock);
 
-- 
2.29.2