diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 4664c2a96c67..3dc1bcb0d01d 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -23,8 +23,7 @@ config IOMMU_IO_PGTABLE config IOMMU_IO_PGTABLE_LPAE bool "ARMv7/v8 Long Descriptor Format" select IOMMU_IO_PGTABLE - # SWIOTLB guarantees a dma_to_phys() implementation - depends on ARM || ARM64 || (COMPILE_TEST && SWIOTLB) + depends on HAS_DMA && (ARM || ARM64 || COMPILE_TEST) help Enable support for the ARM long descriptor pagetable format. This allocator supports 4K/2M/1G, 16K/32M and 64K/512M page diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index dafaf59dc3b8..286e890e7d64 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -56,6 +56,7 @@ #define IDR0_TTF_SHIFT 2 #define IDR0_TTF_MASK 0x3 #define IDR0_TTF_AARCH64 (2 << IDR0_TTF_SHIFT) +#define IDR0_TTF_AARCH32_64 (3 << IDR0_TTF_SHIFT) #define IDR0_S1P (1 << 1) #define IDR0_S2P (1 << 0) @@ -342,7 +343,8 @@ #define CMDQ_TLBI_0_VMID_SHIFT 32 #define CMDQ_TLBI_0_ASID_SHIFT 48 #define CMDQ_TLBI_1_LEAF (1UL << 0) -#define CMDQ_TLBI_1_ADDR_MASK ~0xfffUL +#define CMDQ_TLBI_1_VA_MASK ~0xfffUL +#define CMDQ_TLBI_1_IPA_MASK 0xfffffffff000UL #define CMDQ_PRI_0_SSID_SHIFT 12 #define CMDQ_PRI_0_SSID_MASK 0xfffffUL @@ -770,11 +772,13 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent) break; case CMDQ_OP_TLBI_NH_VA: cmd[0] |= (u64)ent->tlbi.asid << CMDQ_TLBI_0_ASID_SHIFT; - /* Fallthrough */ + cmd[1] |= ent->tlbi.leaf ? CMDQ_TLBI_1_LEAF : 0; + cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_VA_MASK; + break; case CMDQ_OP_TLBI_S2_IPA: cmd[0] |= (u64)ent->tlbi.vmid << CMDQ_TLBI_0_VMID_SHIFT; cmd[1] |= ent->tlbi.leaf ? CMDQ_TLBI_1_LEAF : 0; - cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_ADDR_MASK; + cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_IPA_MASK; break; case CMDQ_OP_TLBI_NH_ASID: cmd[0] |= (u64)ent->tlbi.asid << CMDQ_TLBI_0_ASID_SHIFT; @@ -2460,7 +2464,13 @@ static int arm_smmu_device_probe(struct arm_smmu_device *smmu) } /* We only support the AArch64 table format at present */ - if ((reg & IDR0_TTF_MASK << IDR0_TTF_SHIFT) < IDR0_TTF_AARCH64) { + switch (reg & IDR0_TTF_MASK << IDR0_TTF_SHIFT) { + case IDR0_TTF_AARCH32_64: + smmu->ias = 40; + /* Fallthrough */ + case IDR0_TTF_AARCH64: + break; + default: dev_err(smmu->dev, "AArch64 table format not supported!\n"); return -ENXIO; } @@ -2541,8 +2551,7 @@ static int arm_smmu_device_probe(struct arm_smmu_device *smmu) dev_warn(smmu->dev, "failed to set DMA mask for table walker\n"); - if (!smmu->ias) - smmu->ias = smmu->oas; + smmu->ias = max(smmu->ias, smmu->oas); dev_info(smmu->dev, "ias %lu-bit, oas %lu-bit (features 0x%08x)\n", smmu->ias, smmu->oas, smmu->features); diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 73c07482f487..7df97777662d 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -202,9 +202,9 @@ typedef u64 arm_lpae_iopte; static bool selftest_running = false; -static dma_addr_t __arm_lpae_dma_addr(struct device *dev, void *pages) +static dma_addr_t __arm_lpae_dma_addr(void *pages) { - return phys_to_dma(dev, virt_to_phys(pages)); + return (dma_addr_t)virt_to_phys(pages); } static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp, @@ -223,10 +223,10 @@ static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp, goto out_free; /* * We depend on the IOMMU being able to work with any physical - * address directly, so if the DMA layer suggests it can't by - * giving us back some translation, that bodes very badly... + * address directly, so if the DMA layer suggests otherwise by + * translating or truncating them, that bodes very badly... */ - if (dma != __arm_lpae_dma_addr(dev, pages)) + if (dma != virt_to_phys(pages)) goto out_unmap; } @@ -243,10 +243,8 @@ out_free: static void __arm_lpae_free_pages(void *pages, size_t size, struct io_pgtable_cfg *cfg) { - struct device *dev = cfg->iommu_dev; - if (!selftest_running) - dma_unmap_single(dev, __arm_lpae_dma_addr(dev, pages), + dma_unmap_single(cfg->iommu_dev, __arm_lpae_dma_addr(pages), size, DMA_TO_DEVICE); free_pages_exact(pages, size); } @@ -254,12 +252,11 @@ static void __arm_lpae_free_pages(void *pages, size_t size, static void __arm_lpae_set_pte(arm_lpae_iopte *ptep, arm_lpae_iopte pte, struct io_pgtable_cfg *cfg) { - struct device *dev = cfg->iommu_dev; - *ptep = pte; if (!selftest_running) - dma_sync_single_for_device(dev, __arm_lpae_dma_addr(dev, ptep), + dma_sync_single_for_device(cfg->iommu_dev, + __arm_lpae_dma_addr(ptep), sizeof(pte), DMA_TO_DEVICE); } @@ -629,6 +626,11 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg) if (cfg->oas > ARM_LPAE_MAX_ADDR_BITS) return NULL; + if (!selftest_running && cfg->iommu_dev->dma_pfn_offset) { + dev_err(cfg->iommu_dev, "Cannot accommodate DMA offset for IOMMU page tables\n"); + return NULL; + } + data = kmalloc(sizeof(*data), GFP_KERNEL); if (!data) return NULL;