[RFC PATCH v3 5/5] iommu/arm-smmu-v3: Enable broadcast TLB maintenance

[Shameer Kolothum]

From: Jean-Philippe Brucker <jean-philippe at linaro.org>

The SMMUv3 can handle invalidation targeted at TLB entries with shared
ASIDs. If the implementation supports broadcast TLB maintenance, enable it
and keep track of it in a feature bit. The SMMU will then be affected by
inner-shareable TLB invalidations from other agents.

In order to avoid over invalidation with stage-2 translation contexts,
enable BTM only when SMMUv3 supports eiher S1 or both S1 & S2 transaltion
contexts. In this way the default domain will use stage-1 and stage-2 will
be only used for NESTED Domain setup.

Signed-off-by: Jean-Philippe Brucker <jean-philippe at linaro.org>
[Shameer: Enable BTM only if S1 is supported]
Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi at huawei.com>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 24 +++++++++++++++++++--
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h |  1 +
 2 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index addc6308742b..06a13d78286a 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -4119,11 +4119,14 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu)
 	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 */
@@ -4289,6 +4292,7 @@ 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);
@@ -4341,7 +4345,7 @@ 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;
 	}
 
@@ -4368,6 +4372,22 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 
 	if (reg & IDR0_S2P)
 		smmu->features |= ARM_SMMU_FEAT_TRANS_S2;
+	/*
+	 * If S1 is supported, verify that BTM can be enabled.  If S2 is available
+	 * and BTM is enabled, S2 will be used exclusively for nested domains,
+	 * ensuring a KVM VMID is obtained.
+	 * BTM is beneficial when the CPU shares page tables with SMMUv3 (e.g., vSVA).
+	 */
+	if (reg & IDR0_S1P) {
+		/*
+		 * 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;
+	}
 
 	if (!(reg & (IDR0_S1P | IDR0_S2P))) {
 		dev_err(smmu->dev, "no translation support!\n");
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index 5890c233f73b..f554b6aa52c9 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -39,6 +39,7 @@ struct arm_smmu_device;
 #define IDR0_HTTU			GENMASK(7, 6)
 #define IDR0_HTTU_ACCESS		1
 #define IDR0_HTTU_ACCESS_DIRTY		2
+#define IDR0_BTM			(1 << 5)
 #define IDR0_COHACC			(1 << 4)
 #define IDR0_TTF			GENMASK(3, 2)
 #define IDR0_TTF_AARCH64		2
-- 
2.47.0