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.
A major side-effect of this change is that stage-2 translation contexts
are now affected by all invalidations by VMID. VMIDs are all shared and
the only ways to prevent over-invalidation, since the stage-2 page tables
are not shared between CPU and SMMU, are to either disable BTM or allocate
different VMIDs. This patch does not address the problem.
Signed-off-by: Jean-Philippe Brucker <jean-philippe@xxxxxxxxxx>
---
v4->v5: bump feature bit
---
drivers/iommu/arm-smmu-v3.c | 19 +++++++++++++++++--
1 file changed, 17 insertions(+), 2 deletions(-)
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 21d458d817fc2..e7de8a7459fa4 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -56,6 +56,7 @@
#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 GENMASK(3, 2)
#define IDR0_TTF_AARCH64 2
@@ -655,6 +656,7 @@ struct arm_smmu_device {
#define ARM_SMMU_FEAT_VAX (1 << 14)
#define ARM_SMMU_FEAT_RANGE_INV (1 << 15)
#define ARM_SMMU_FEAT_E2H (1 << 16)
+#define ARM_SMMU_FEAT_BTM (1 << 17)
u32 features;
#define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0)
@@ -3814,11 +3816,14 @@ 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 */
@@ -3929,6 +3934,7 @@ 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);
@@ -3978,10 +3984,19 @@ 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.
--
2.26.0
