diff options
Diffstat (limited to 'drivers/iommu/arm/arm-smmu')
| -rw-r--r-- | drivers/iommu/arm/arm-smmu/arm-smmu-impl.c | 5 | ||||
| -rw-r--r-- | drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c | 2 | ||||
| -rw-r--r-- | drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 121 | ||||
| -rw-r--r-- | drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h | 3 | ||||
| -rw-r--r-- | drivers/iommu/arm/arm-smmu/arm-smmu.c | 43 | ||||
| -rw-r--r-- | drivers/iommu/arm/arm-smmu/arm-smmu.h | 2 |
6 files changed, 143 insertions, 33 deletions
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c index 99030e6b16e7..db9b9a8e139c 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c @@ -110,7 +110,6 @@ static struct arm_smmu_device *cavium_smmu_impl_init(struct arm_smmu_device *smm int arm_mmu500_reset(struct arm_smmu_device *smmu) { u32 reg, major; - int i; /* * On MMU-500 r2p0 onwards we need to clear ACR.CACHE_LOCK before * writes to the context bank ACTLRs will stick. And we just hope that @@ -128,11 +127,12 @@ int arm_mmu500_reset(struct arm_smmu_device *smmu) reg |= ARM_MMU500_ACR_SMTNMB_TLBEN | ARM_MMU500_ACR_S2CRB_TLBEN; arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sACR, reg); +#ifdef CONFIG_ARM_SMMU_MMU_500_CPRE_ERRATA /* * Disable MMU-500's not-particularly-beneficial next-page * prefetcher for the sake of at least 5 known errata. */ - for (i = 0; i < smmu->num_context_banks; ++i) { + for (int i = 0; i < smmu->num_context_banks; ++i) { reg = arm_smmu_cb_read(smmu, i, ARM_SMMU_CB_ACTLR); reg &= ~ARM_MMU500_ACTLR_CPRE; arm_smmu_cb_write(smmu, i, ARM_SMMU_CB_ACTLR, reg); @@ -140,6 +140,7 @@ int arm_mmu500_reset(struct arm_smmu_device *smmu) if (reg & ARM_MMU500_ACTLR_CPRE) dev_warn_once(smmu->dev, "Failed to disable prefetcher for errata workarounds, check SACR.CACHE_LOCK\n"); } +#endif return 0; } diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c index 548783f3f8e8..d03b2239baad 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c @@ -73,7 +73,7 @@ void qcom_smmu_tlb_sync_debug(struct arm_smmu_device *smmu) if (__ratelimit(&rs)) { dev_err(smmu->dev, "TLB sync timed out -- SMMU may be deadlocked\n"); - cfg = qsmmu->cfg; + cfg = qsmmu->data->cfg; if (!cfg) return; diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c index 6372f3e25c4b..59d02687280e 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c @@ -16,6 +16,40 @@ #define QCOM_DUMMY_VAL -1 +/* + * SMMU-500 TRM defines BIT(0) as CMTLB (Enable context caching in the + * macro TLB) and BIT(1) as CPRE (Enable context caching in the prefetch + * buffer). The remaining bits are implementation defined and vary across + * SoCs. + */ + +#define CPRE (1 << 1) +#define CMTLB (1 << 0) +#define PREFETCH_SHIFT 8 +#define PREFETCH_DEFAULT 0 +#define PREFETCH_SHALLOW (1 << PREFETCH_SHIFT) +#define PREFETCH_MODERATE (2 << PREFETCH_SHIFT) +#define PREFETCH_DEEP (3 << PREFETCH_SHIFT) +#define GFX_ACTLR_PRR (1 << 5) + +static const struct of_device_id qcom_smmu_actlr_client_of_match[] = { + { .compatible = "qcom,adreno", + .data = (const void *) (PREFETCH_DEEP | CPRE | CMTLB) }, + { .compatible = "qcom,adreno-gmu", + .data = (const void *) (PREFETCH_DEEP | CPRE | CMTLB) }, + { .compatible = "qcom,adreno-smmu", + .data = (const void *) (PREFETCH_DEEP | CPRE | CMTLB) }, + { .compatible = "qcom,fastrpc", + .data = (const void *) (PREFETCH_DEEP | CPRE | CMTLB) }, + { .compatible = "qcom,sc7280-mdss", + .data = (const void *) (PREFETCH_SHALLOW | CPRE | CMTLB) }, + { .compatible = "qcom,sc7280-venus", + .data = (const void *) (PREFETCH_SHALLOW | CPRE | CMTLB) }, + { .compatible = "qcom,sm8550-mdss", + .data = (const void *) (PREFETCH_DEFAULT | CMTLB) }, + { } +}; + static struct qcom_smmu *to_qcom_smmu(struct arm_smmu_device *smmu) { return container_of(smmu, struct qcom_smmu, smmu); @@ -99,6 +133,47 @@ static void qcom_adreno_smmu_resume_translation(const void *cookie, bool termina arm_smmu_cb_write(smmu, cfg->cbndx, ARM_SMMU_CB_RESUME, reg); } +static void qcom_adreno_smmu_set_prr_bit(const void *cookie, bool set) +{ + struct arm_smmu_domain *smmu_domain = (void *)cookie; + struct arm_smmu_device *smmu = smmu_domain->smmu; + struct arm_smmu_cfg *cfg = &smmu_domain->cfg; + u32 reg = 0; + int ret; + + ret = pm_runtime_resume_and_get(smmu->dev); + if (ret < 0) { + dev_err(smmu->dev, "failed to get runtime PM: %d\n", ret); + return; + } + + reg = arm_smmu_cb_read(smmu, cfg->cbndx, ARM_SMMU_CB_ACTLR); + reg &= ~GFX_ACTLR_PRR; + if (set) + reg |= FIELD_PREP(GFX_ACTLR_PRR, 1); + arm_smmu_cb_write(smmu, cfg->cbndx, ARM_SMMU_CB_ACTLR, reg); + pm_runtime_put_autosuspend(smmu->dev); +} + +static void qcom_adreno_smmu_set_prr_addr(const void *cookie, phys_addr_t page_addr) +{ + struct arm_smmu_domain *smmu_domain = (void *)cookie; + struct arm_smmu_device *smmu = smmu_domain->smmu; + int ret; + + ret = pm_runtime_resume_and_get(smmu->dev); + if (ret < 0) { + dev_err(smmu->dev, "failed to get runtime PM: %d\n", ret); + return; + } + + writel_relaxed(lower_32_bits(page_addr), + smmu->base + ARM_SMMU_GFX_PRR_CFG_LADDR); + writel_relaxed(upper_32_bits(page_addr), + smmu->base + ARM_SMMU_GFX_PRR_CFG_UADDR); + pm_runtime_put_autosuspend(smmu->dev); +} + #define QCOM_ADRENO_SMMU_GPU_SID 0 static bool qcom_adreno_smmu_is_gpu_device(struct device *dev) @@ -207,13 +282,37 @@ static bool qcom_adreno_can_do_ttbr1(struct arm_smmu_device *smmu) return true; } +static void qcom_smmu_set_actlr_dev(struct device *dev, struct arm_smmu_device *smmu, int cbndx, + const struct of_device_id *client_match) +{ + const struct of_device_id *match = + of_match_device(client_match, dev); + + if (!match) { + dev_dbg(dev, "no ACTLR settings present\n"); + return; + } + + arm_smmu_cb_write(smmu, cbndx, ARM_SMMU_CB_ACTLR, (unsigned long)match->data); +} + static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain, struct io_pgtable_cfg *pgtbl_cfg, struct device *dev) { + const struct device_node *np = smmu_domain->smmu->dev->of_node; + struct arm_smmu_device *smmu = smmu_domain->smmu; + struct qcom_smmu *qsmmu = to_qcom_smmu(smmu); + const struct of_device_id *client_match; + int cbndx = smmu_domain->cfg.cbndx; struct adreno_smmu_priv *priv; smmu_domain->cfg.flush_walk_prefer_tlbiasid = true; + client_match = qsmmu->data->client_match; + + if (client_match) + qcom_smmu_set_actlr_dev(dev, smmu, cbndx, client_match); + /* Only enable split pagetables for the GPU device (SID 0) */ if (!qcom_adreno_smmu_is_gpu_device(dev)) return 0; @@ -239,6 +338,14 @@ static int qcom_adreno_smmu_init_context(struct arm_smmu_domain *smmu_domain, priv->get_fault_info = qcom_adreno_smmu_get_fault_info; priv->set_stall = qcom_adreno_smmu_set_stall; priv->resume_translation = qcom_adreno_smmu_resume_translation; + priv->set_prr_bit = NULL; + priv->set_prr_addr = NULL; + + if (of_device_is_compatible(np, "qcom,smmu-500") && + of_device_is_compatible(np, "qcom,adreno-smmu")) { + priv->set_prr_bit = qcom_adreno_smmu_set_prr_bit; + priv->set_prr_addr = qcom_adreno_smmu_set_prr_addr; + } return 0; } @@ -269,8 +376,18 @@ static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = { static int qcom_smmu_init_context(struct arm_smmu_domain *smmu_domain, struct io_pgtable_cfg *pgtbl_cfg, struct device *dev) { + struct arm_smmu_device *smmu = smmu_domain->smmu; + struct qcom_smmu *qsmmu = to_qcom_smmu(smmu); + const struct of_device_id *client_match; + int cbndx = smmu_domain->cfg.cbndx; + smmu_domain->cfg.flush_walk_prefer_tlbiasid = true; + client_match = qsmmu->data->client_match; + + if (client_match) + qcom_smmu_set_actlr_dev(dev, smmu, cbndx, client_match); + return 0; } @@ -507,7 +624,7 @@ static struct arm_smmu_device *qcom_smmu_create(struct arm_smmu_device *smmu, return ERR_PTR(-ENOMEM); qsmmu->smmu.impl = impl; - qsmmu->cfg = data->cfg; + qsmmu->data = data; return &qsmmu->smmu; } @@ -550,6 +667,7 @@ static const struct qcom_smmu_match_data qcom_smmu_500_impl0_data = { .impl = &qcom_smmu_500_impl, .adreno_impl = &qcom_adreno_smmu_500_impl, .cfg = &qcom_smmu_impl0_cfg, + .client_match = qcom_smmu_actlr_client_of_match, }; /* @@ -567,6 +685,7 @@ static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = { { .compatible = "qcom,sc8180x-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,sc8280xp-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,sdm630-smmu-v2", .data = &qcom_smmu_v2_data }, + { .compatible = "qcom,sdm670-smmu-v2", .data = &qcom_smmu_v2_data }, { .compatible = "qcom,sdm845-smmu-v2", .data = &qcom_smmu_v2_data }, { .compatible = "qcom,sdm845-smmu-500", .data = &sdm845_smmu_500_data }, { .compatible = "qcom,sm6115-smmu-500", .data = &qcom_smmu_500_impl0_data}, diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h index 3c134d1a6277..8addd453f5f1 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h @@ -8,7 +8,7 @@ struct qcom_smmu { struct arm_smmu_device smmu; - const struct qcom_smmu_config *cfg; + const struct qcom_smmu_match_data *data; bool bypass_quirk; u8 bypass_cbndx; u32 stall_enabled; @@ -28,6 +28,7 @@ struct qcom_smmu_match_data { const struct qcom_smmu_config *cfg; const struct arm_smmu_impl *impl; const struct arm_smmu_impl *adreno_impl; + const struct of_device_id * const client_match; }; irqreturn_t qcom_smmu_context_fault(int irq, void *dev); diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index 650664e0f6e3..de205a34ffc6 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -34,6 +34,7 @@ #include <linux/pm_runtime.h> #include <linux/ratelimit.h> #include <linux/slab.h> +#include <linux/string_choices.h> #include <linux/fsl/mc.h> @@ -1411,8 +1412,8 @@ static bool arm_smmu_capable(struct device *dev, enum iommu_cap cap) static struct arm_smmu_device *arm_smmu_get_by_fwnode(struct fwnode_handle *fwnode) { - struct device *dev = driver_find_device_by_fwnode(&arm_smmu_driver.driver, - fwnode); + struct device *dev = bus_find_device_by_fwnode(&platform_bus_type, fwnode); + put_device(dev); return dev ? dev_get_drvdata(dev) : NULL; } @@ -1437,17 +1438,6 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev) goto out_free; } else { smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode); - - /* - * Defer probe if the relevant SMMU instance hasn't finished - * probing yet. This is a fragile hack and we'd ideally - * avoid this race in the core code. Until that's ironed - * out, however, this is the most pragmatic option on the - * table. - */ - if (!smmu) - return ERR_PTR(dev_err_probe(dev, -EPROBE_DEFER, - "smmu dev has not bound yet\n")); } ret = -EINVAL; @@ -2117,7 +2107,7 @@ static void arm_smmu_rmr_install_bypass_smr(struct arm_smmu_device *smmu) } dev_notice(smmu->dev, "\tpreserved %d boot mapping%s\n", cnt, - cnt == 1 ? "" : "s"); + str_plural(cnt)); iort_put_rmr_sids(dev_fwnode(smmu->dev), &rmr_list); } @@ -2227,29 +2217,26 @@ static int arm_smmu_device_probe(struct platform_device *pdev) i, irq); } + platform_set_drvdata(pdev, smmu); + + /* Check for RMRs and install bypass SMRs if any */ + arm_smmu_rmr_install_bypass_smr(smmu); + + arm_smmu_device_reset(smmu); + arm_smmu_test_smr_masks(smmu); + err = iommu_device_sysfs_add(&smmu->iommu, smmu->dev, NULL, "smmu.%pa", &smmu->ioaddr); - if (err) { - dev_err(dev, "Failed to register iommu in sysfs\n"); - return err; - } + if (err) + return dev_err_probe(dev, err, "Failed to register iommu in sysfs\n"); err = iommu_device_register(&smmu->iommu, &arm_smmu_ops, using_legacy_binding ? NULL : dev); if (err) { - dev_err(dev, "Failed to register iommu\n"); iommu_device_sysfs_remove(&smmu->iommu); - return err; + return dev_err_probe(dev, err, "Failed to register iommu\n"); } - platform_set_drvdata(pdev, smmu); - - /* Check for RMRs and install bypass SMRs if any */ - arm_smmu_rmr_install_bypass_smr(smmu); - - arm_smmu_device_reset(smmu); - arm_smmu_test_smr_masks(smmu); - /* * We want to avoid touching dev->power.lock in fastpaths unless * it's really going to do something useful - pm_runtime_enabled() diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h index e2aeb511ae90..2dbf3243b5ad 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.h +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h @@ -154,6 +154,8 @@ enum arm_smmu_cbar_type { #define ARM_SMMU_SCTLR_M BIT(0) #define ARM_SMMU_CB_ACTLR 0x4 +#define ARM_SMMU_GFX_PRR_CFG_LADDR 0x6008 +#define ARM_SMMU_GFX_PRR_CFG_UADDR 0x600C #define ARM_SMMU_CB_RESUME 0x8 #define ARM_SMMU_RESUME_TERMINATE BIT(0) |