Force Write Back (FWB) changes how the S2 IOPTE's MemAttr field works. When S2FWB is supported and enabled the IOPTE will force cachable access to IOMMU_CACHE memory and deny cachable access otherwise. This is not especially meaningful for simple S2 domains, it apparently doesn't even force PCI no-snoop access to be coherent. However, when used with a nested S1, FWB has the effect of preventing the guest from choosing a MemAttr that would cause ordinary DMA to bypass the cache. Consistent with KVM we wish to deny the guest the ability to become incoherent with cached memory the hypervisor believes is cachable so we don't have to flush it. Turn on S2FWB whenever the SMMU supports it and use it for all S2 mappings. Signed-off-by: Jason Gunthorpe <jgg@xxxxxxxxxx> --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 6 ++++++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 3 +++ drivers/iommu/io-pgtable-arm.c | 24 +++++++++++++++++---- include/linux/io-pgtable.h | 2 ++ 4 files changed, 31 insertions(+), 4 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 531125f231b662..7fe1e27d11586c 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -1612,6 +1612,8 @@ void arm_smmu_make_s2_domain_ste(struct arm_smmu_ste *target, FIELD_PREP(STRTAB_STE_1_EATS, ats_enabled ? STRTAB_STE_1_EATS_TRANS : 0)); + if (smmu->features & ARM_SMMU_FEAT_S2FWB) + target->data[1] |= cpu_to_le64(STRTAB_STE_1_S2FWB); if (smmu->features & ARM_SMMU_FEAT_ATTR_TYPES_OVR) target->data[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG, STRTAB_STE_1_SHCFG_INCOMING)); @@ -2400,6 +2402,8 @@ static int arm_smmu_domain_finalise(struct arm_smmu_domain *smmu_domain, pgtbl_cfg.oas = smmu->oas; fmt = ARM_64_LPAE_S2; finalise_stage_fn = arm_smmu_domain_finalise_s2; + if (smmu->features & ARM_SMMU_FEAT_S2FWB) + pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_ARM_S2FWB; break; default: return -EINVAL; @@ -4189,6 +4193,8 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) /* IDR3 */ reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3); + if (FIELD_GET(IDR3_FWB, reg)) + smmu->features |= ARM_SMMU_FEAT_S2FWB; if (FIELD_GET(IDR3_RIL, reg)) smmu->features |= ARM_SMMU_FEAT_RANGE_INV; 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 8851a7abb5f0f3..7e8d2f36faebf3 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -55,6 +55,7 @@ #define IDR1_SIDSIZE GENMASK(5, 0) #define ARM_SMMU_IDR3 0xc +#define IDR3_FWB (1 << 8) #define IDR3_RIL (1 << 10) #define ARM_SMMU_IDR5 0x14 @@ -258,6 +259,7 @@ static inline u32 arm_smmu_strtab_l2_idx(u32 sid) #define STRTAB_STE_1_S1CSH GENMASK_ULL(7, 6) #define STRTAB_STE_1_S1STALLD (1UL << 27) +#define STRTAB_STE_1_S2FWB (1UL << 25) #define STRTAB_STE_1_EATS GENMASK_ULL(29, 28) #define STRTAB_STE_1_EATS_ABT 0UL @@ -700,6 +702,7 @@ struct arm_smmu_device { #define ARM_SMMU_FEAT_ATTR_TYPES_OVR (1 << 20) #define ARM_SMMU_FEAT_HA (1 << 21) #define ARM_SMMU_FEAT_HD (1 << 22) +#define ARM_SMMU_FEAT_S2FWB (1 << 23) u32 features; #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index f5d9fd1f45bf49..62bbb6037e1686 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -106,6 +106,18 @@ #define ARM_LPAE_PTE_HAP_FAULT (((arm_lpae_iopte)0) << 6) #define ARM_LPAE_PTE_HAP_READ (((arm_lpae_iopte)1) << 6) #define ARM_LPAE_PTE_HAP_WRITE (((arm_lpae_iopte)2) << 6) +/* + * For !FWB these code to: + * 1111 = Normal outer write back cachable / Inner Write Back Cachable + * Permit S1 to override + * 0101 = Normal Non-cachable / Inner Non-cachable + * 0001 = Device / Device-nGnRE + * For S2FWB these code: + * 0110 Force Normal Write Back + * 0101 Normal* is forced Normal-NC, Device unchanged + * 0001 Force Device-nGnRE + */ +#define ARM_LPAE_PTE_MEMATTR_FWB_WB (((arm_lpae_iopte)0x6) << 2) #define ARM_LPAE_PTE_MEMATTR_OIWB (((arm_lpae_iopte)0xf) << 2) #define ARM_LPAE_PTE_MEMATTR_NC (((arm_lpae_iopte)0x5) << 2) #define ARM_LPAE_PTE_MEMATTR_DEV (((arm_lpae_iopte)0x1) << 2) @@ -458,12 +470,16 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data, */ if (data->iop.fmt == ARM_64_LPAE_S2 || data->iop.fmt == ARM_32_LPAE_S2) { - if (prot & IOMMU_MMIO) + if (prot & IOMMU_MMIO) { pte |= ARM_LPAE_PTE_MEMATTR_DEV; - else if (prot & IOMMU_CACHE) - pte |= ARM_LPAE_PTE_MEMATTR_OIWB; - else + } else if (prot & IOMMU_CACHE) { + if (data->iop.cfg.quirks & IO_PGTABLE_QUIRK_ARM_S2FWB) + pte |= ARM_LPAE_PTE_MEMATTR_FWB_WB; + else + pte |= ARM_LPAE_PTE_MEMATTR_OIWB; + } else { pte |= ARM_LPAE_PTE_MEMATTR_NC; + } } else { if (prot & IOMMU_MMIO) pte |= (ARM_LPAE_MAIR_ATTR_IDX_DEV diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index f9a81761bfceda..aff9b020b6dcc7 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -87,6 +87,7 @@ struct io_pgtable_cfg { * attributes set in the TCR for a non-coherent page-table walker. * * IO_PGTABLE_QUIRK_ARM_HD: Enables dirty tracking in stage 1 pagetable. + * IO_PGTABLE_QUIRK_ARM_S2FWB: Use the FWB format for the MemAttrs bits */ #define IO_PGTABLE_QUIRK_ARM_NS BIT(0) #define IO_PGTABLE_QUIRK_NO_PERMS BIT(1) @@ -95,6 +96,7 @@ struct io_pgtable_cfg { #define IO_PGTABLE_QUIRK_ARM_TTBR1 BIT(5) #define IO_PGTABLE_QUIRK_ARM_OUTER_WBWA BIT(6) #define IO_PGTABLE_QUIRK_ARM_HD BIT(7) + #define IO_PGTABLE_QUIRK_ARM_S2FWB BIT(8) unsigned long quirks; unsigned long pgsize_bitmap; unsigned int ias; -- 2.46.0