@@ -64,6 +64,7 @@
 #define IDR0_ASID16			(1 << 12)
 #define IDR0_ATS			(1 << 10)
 #define IDR0_HYP			(1 << 9)
+#define IDR0_BTM			(1 << 5)
 #define IDR0_COHACC			(1 << 4)
 #define IDR0_TTF_SHIFT			2
 #define IDR0_TTF_MASK			0x3

@@ -659,6 +660,7 @@ struct arm_smmu_device {
 #define ARM_SMMU_FEAT_HYP		(1 << 12)
 #define ARM_SMMU_FEAT_STALL_FORCE	(1 << 13)
 #define ARM_SMMU_FEAT_E2H		(1 << 14)
+#define ARM_SMMU_FEAT_BTM		(1 << 15)
 	u32				features;
 
 #define ARM_SMMU_OPT_SKIP_PREFETCH	(1 << 0)

@@ -2730,11 +2732,14 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
 	writel_relaxed(reg, smmu->base + ARM_SMMU_CR1);
 
 	/* CR2 (random crap) */
-	reg = CR2_PTM | CR2_RECINVSID;
+	reg = CR2_RECINVSID;
 
 	if (smmu->features & ARM_SMMU_FEAT_E2H)
 		reg |= CR2_E2H;
 
+	if (!(smmu->features & ARM_SMMU_FEAT_BTM))
+		reg |= CR2_PTM;
+
 	writel_relaxed(reg, smmu->base + ARM_SMMU_CR2);
 
 	/* Stream table */

@@ -2837,6 +2842,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 {
 	u32 reg;
 	bool coherent = smmu->features & ARM_SMMU_FEAT_COHERENCY;
+	bool vhe = cpus_have_cap(ARM64_HAS_VIRT_HOST_EXTN);
 
 	/* IDR0 */
 	reg = readl_relaxed(smmu->base + ARM_SMMU_IDR0);

@@ -2886,11 +2892,20 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 
 	if (reg & IDR0_HYP) {
 		smmu->features |= ARM_SMMU_FEAT_HYP;
-		if (cpus_have_cap(ARM64_HAS_VIRT_HOST_EXTN))
+		if (vhe)
 			smmu->features |= ARM_SMMU_FEAT_E2H;
 	}
 
 	/*
+	 * If the CPU is using VHE, but the SMMU doesn't support it, the SMMU
+	 * will create TLB entries for NH-EL1 world and will miss the
+	 * broadcasted TLB invalidations that target EL2-E2H world. Don't enable
+	 * BTM in that case.
+	 */
+	if (reg & IDR0_BTM && (!vhe || reg & IDR0_HYP))
+		smmu->features |= ARM_SMMU_FEAT_BTM;
+
+	/*
 	 * The coherency feature as set by FW is used in preference to the ID
 	 * register, but warn on mismatch.
 	 */