From: Jordan Crouse jcrouse@codeaurora.org
Add a new implementation hook to allow the implementation specific code to tweek the context bank configuration just before it gets written. The first user will be the Adreno GPU implementation to turn on SCTLR.HUPCF to ensure that a page fault doesn't terminating pending transactions. Doing so could hang the GPU if one of the terminated transactions is a CP read.
This depends on the arm-smmu adreno SMMU implementation [1].
[1] https://lore.kernel.org/patchwork/patch/1264452/
Signed-off-by: Jordan Crouse jcrouse@codeaurora.org Signed-off-by: Sai Prakash Ranjan saiprakash.ranjan@codeaurora.org --- drivers/iommu/arm-smmu-qcom.c | 13 +++++++++++++ drivers/iommu/arm-smmu.c | 29 +++++++++++++---------------- drivers/iommu/arm-smmu.h | 12 ++++++++++++ 3 files changed, 38 insertions(+), 16 deletions(-)
diff --git a/drivers/iommu/arm-smmu-qcom.c b/drivers/iommu/arm-smmu-qcom.c index cb2acb6b19dd..6462fb00f493 100644 --- a/drivers/iommu/arm-smmu-qcom.c +++ b/drivers/iommu/arm-smmu-qcom.c @@ -17,6 +17,18 @@ static bool qcom_adreno_smmu_is_gpu_device(struct arm_smmu_domain *smmu_domain) return of_device_is_compatible(smmu_domain->dev->of_node, "qcom,adreno"); }
+static void qcom_adreno_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain, + struct arm_smmu_cb *cb) +{ + /* + * On the GPU device we want to process subsequent transactions after a + * fault to keep the GPU from hanging + */ + + if (qcom_adreno_smmu_is_gpu_device(smmu_domain)) + cb->sctlr |= ARM_SMMU_SCTLR_HUPCF; +} + static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain, struct io_pgtable_cfg *pgtbl_cfg) { @@ -92,6 +104,7 @@ static const struct arm_smmu_impl qcom_adreno_smmu_impl = { .init_context = qcom_adreno_smmu_init_context, .def_domain_type = qcom_smmu_def_domain_type, .reset = qcom_smmu500_reset, + .init_context_bank = qcom_adreno_smmu_init_context_bank, };
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 4bd247dfd703..b2564f93d685 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -86,14 +86,6 @@ struct arm_smmu_smr { bool valid; };
-struct arm_smmu_cb { - u64 ttbr[2]; - u32 tcr[2]; - u32 mair[2]; - struct arm_smmu_cfg *cfg; - atomic_t aux; -}; - struct arm_smmu_master_cfg { struct arm_smmu_device *smmu; s16 smendx[]; @@ -580,6 +572,18 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain, cb->mair[1] = pgtbl_cfg->arm_lpae_s1_cfg.mair >> 32; } } + + cb->sctlr = ARM_SMMU_SCTLR_CFIE | ARM_SMMU_SCTLR_CFRE | ARM_SMMU_SCTLR_AFE | + ARM_SMMU_SCTLR_TRE | ARM_SMMU_SCTLR_M; + + if (stage1) + cb->sctlr |= ARM_SMMU_SCTLR_S1_ASIDPNE; + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) + cb->sctlr |= ARM_SMMU_SCTLR_E; + + /* Give the implementation a chance to adjust the configuration */ + if (smmu_domain->smmu->impl && smmu_domain->smmu->impl->init_context_bank) + smmu_domain->smmu->impl->init_context_bank(smmu_domain, cb); }
static void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx) @@ -658,14 +662,7 @@ static void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx) }
/* SCTLR */ - reg = ARM_SMMU_SCTLR_CFIE | ARM_SMMU_SCTLR_CFRE | ARM_SMMU_SCTLR_AFE | - ARM_SMMU_SCTLR_TRE | ARM_SMMU_SCTLR_M; - if (stage1) - reg |= ARM_SMMU_SCTLR_S1_ASIDPNE; - if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) - reg |= ARM_SMMU_SCTLR_E; - - arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_SCTLR, reg); + arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_SCTLR, cb->sctlr); }
/* diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h index 79d441024043..4a335ef3d97a 100644 --- a/drivers/iommu/arm-smmu.h +++ b/drivers/iommu/arm-smmu.h @@ -142,6 +142,7 @@ enum arm_smmu_cbar_type {
#define ARM_SMMU_CB_SCTLR 0x0 #define ARM_SMMU_SCTLR_S1_ASIDPNE BIT(12) +#define ARM_SMMU_SCTLR_HUPCF BIT(8) #define ARM_SMMU_SCTLR_CFCFG BIT(7) #define ARM_SMMU_SCTLR_CFIE BIT(6) #define ARM_SMMU_SCTLR_CFRE BIT(5) @@ -349,6 +350,15 @@ struct arm_smmu_domain { bool aux; };
+struct arm_smmu_cb { + u64 ttbr[2]; + u32 tcr[2]; + u32 mair[2]; + u32 sctlr; + struct arm_smmu_cfg *cfg; + atomic_t aux; +}; + static inline u32 arm_smmu_lpae_tcr(struct io_pgtable_cfg *cfg) { u32 tcr = FIELD_PREP(ARM_SMMU_TCR_TG0, cfg->arm_lpae_s1_cfg.tcr.tg) | @@ -403,6 +413,8 @@ struct arm_smmu_impl { void (*tlb_sync)(struct arm_smmu_device *smmu, int page, int sync, int status); int (*def_domain_type)(struct device *dev); + void (*init_context_bank)(struct arm_smmu_domain *smmu_domain, + struct arm_smmu_cb *cb); };
static inline void __iomem *arm_smmu_page(struct arm_smmu_device *smmu, int n)