diff options
| -rw-r--r-- | Documentation/admin-guide/kernel-parameters.txt | 12 | ||||
| -rw-r--r-- | drivers/iommu/Kconfig | 41 | ||||
| -rw-r--r-- | drivers/iommu/amd/amd_iommu_types.h | 6 | ||||
| -rw-r--r-- | drivers/iommu/amd/init.c | 7 | ||||
| -rw-r--r-- | drivers/iommu/amd/io_pgtable.c | 3 | ||||
| -rw-r--r-- | drivers/iommu/amd/iommu.c | 6 | ||||
| -rw-r--r-- | drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 3 | ||||
| -rw-r--r-- | drivers/iommu/arm/arm-smmu/arm-smmu.c | 21 | ||||
| -rw-r--r-- | drivers/iommu/intel/iommu.c | 139 | ||||
| -rw-r--r-- | drivers/iommu/io-pgtable-arm-v7s.c | 50 | ||||
| -rw-r--r-- | drivers/iommu/io-pgtable-arm.c | 223 | ||||
| -rw-r--r-- | drivers/iommu/iommu.c | 146 | ||||
| -rw-r--r-- | include/linux/io-pgtable.h | 8 | ||||
| -rw-r--r-- | include/linux/iommu.h | 11 |
14 files changed, 437 insertions, 239 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index bdb22006f713..90b525cf0ec2 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -290,10 +290,7 @@ amd_iommu= [HW,X86-64] Pass parameters to the AMD IOMMU driver in the system. Possible values are: - fullflush - enable flushing of IO/TLB entries when - they are unmapped. Otherwise they are - flushed before they will be reused, which - is a lot of faster + fullflush - Deprecated, equivalent to iommu.strict=1 off - do not initialize any AMD IOMMU found in the system force_isolation - Force device isolation for all @@ -1944,9 +1941,7 @@ this case, gfx device will use physical address for DMA. strict [Default Off] - With this option on every unmap_single operation will - result in a hardware IOTLB flush operation as opposed - to batching them for performance. + Deprecated, equivalent to iommu.strict=1. sp_off [Default Off] By default, super page will be supported if Intel IOMMU has the capability. With this option, super page will @@ -2047,9 +2042,10 @@ throughput at the cost of reduced device isolation. Will fall back to strict mode if not supported by the relevant IOMMU driver. - 1 - Strict mode (default). + 1 - Strict mode. DMA unmap operations invalidate IOMMU hardware TLBs synchronously. + unset - Use value of CONFIG_IOMMU_DEFAULT_{LAZY,STRICT}. Note: on x86, the default behaviour depends on the equivalent driver-specific parameters, but a strict mode explicitly specified by either method takes diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 07b7c25cbed8..c84da8205be7 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -90,6 +90,47 @@ config IOMMU_DEFAULT_PASSTHROUGH If unsure, say N here. +choice + prompt "IOMMU default DMA IOTLB invalidation mode" + depends on IOMMU_DMA + + default IOMMU_DEFAULT_LAZY if (AMD_IOMMU || INTEL_IOMMU) + default IOMMU_DEFAULT_STRICT + help + This option allows an IOMMU DMA IOTLB invalidation mode to be + chosen at build time, to override the default mode of each ARCH, + removing the need to pass in kernel parameters through command line. + It is still possible to provide common boot params to override this + config. + + If unsure, keep the default. + +config IOMMU_DEFAULT_STRICT + bool "strict" + help + For every IOMMU DMA unmap operation, the flush operation of IOTLB and + the free operation of IOVA are guaranteed to be done in the unmap + function. + +config IOMMU_DEFAULT_LAZY + bool "lazy" + help + Support lazy mode, where for every IOMMU DMA unmap operation, the + flush operation of IOTLB and the free operation of IOVA are deferred. + They are only guaranteed to be done before the related IOVA will be + reused. + + The isolation provided in this mode is not as secure as STRICT mode, + such that a vulnerable time window may be created between the DMA + unmap and the mappings cached in the IOMMU IOTLB or device TLB + finally being invalidated, where the device could still access the + memory which has already been unmapped by the device driver. + However this mode may provide better performance in high throughput + scenarios, and is still considerably more secure than passthrough + mode or no IOMMU. + +endchoice + config OF_IOMMU def_bool y depends on OF && IOMMU_API diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 94c1a7a9876d..8dbe61e2b3c1 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -779,12 +779,6 @@ extern u16 amd_iommu_last_bdf; /* allocation bitmap for domain ids */ extern unsigned long *amd_iommu_pd_alloc_bitmap; -/* - * If true, the addresses will be flushed on unmap time, not when - * they are reused - */ -extern bool amd_iommu_unmap_flush; - /* Smallest max PASID supported by any IOMMU in the system */ extern u32 amd_iommu_max_pasid; diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 1c7ae7d3c55d..239556c1f698 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -161,7 +161,6 @@ u16 amd_iommu_last_bdf; /* largest PCI device id we have to handle */ LIST_HEAD(amd_iommu_unity_map); /* a list of required unity mappings we find in ACPI */ -bool amd_iommu_unmap_flush; /* if true, flush on every unmap */ LIST_HEAD(amd_iommu_list); /* list of all AMD IOMMUs in the system */ @@ -3103,8 +3102,10 @@ static int __init parse_amd_iommu_intr(char *str) static int __init parse_amd_iommu_options(char *str) { for (; *str; ++str) { - if (strncmp(str, "fullflush", 9) == 0) - amd_iommu_unmap_flush = true; + if (strncmp(str, "fullflush", 9) == 0) { + pr_warn("amd_iommu=fullflush deprecated; use iommu.strict=1 instead\n"); + iommu_set_dma_strict(); + } if (strncmp(str, "force_enable", 12) == 0) amd_iommu_force_enable = true; if (strncmp(str, "off", 3) == 0) diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c index bb0ee5c9fde7..182c93a43efd 100644 --- a/drivers/iommu/amd/io_pgtable.c +++ b/drivers/iommu/amd/io_pgtable.c @@ -493,9 +493,6 @@ static phys_addr_t iommu_v1_iova_to_phys(struct io_pgtable_ops *ops, unsigned lo unsigned long offset_mask, pte_pgsize; u64 *pte, __pte; - if (pgtable->mode == PAGE_MODE_NONE) - return iova; - pte = fetch_pte(pgtable, iova, &pte_pgsize); if (!pte || !IOMMU_PTE_PRESENT(*pte)) diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index fb5c40715d10..7dedbea9c67f 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -1818,12 +1818,6 @@ void amd_iommu_domain_update(struct protection_domain *domain) static void __init amd_iommu_init_dma_ops(void) { swiotlb = (iommu_default_passthrough() || sme_me_mask) ? 1 : 0; - - if (amd_iommu_unmap_flush) - pr_info("IO/TLB flush on unmap enabled\n"); - else - pr_info("Lazy IO/TLB flushing enabled\n"); - iommu_set_dma_strict(amd_iommu_unmap_flush); } int __init amd_iommu_init_api(void) 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 235f9bdaeaf2..6346f21726f4 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -2488,9 +2488,6 @@ arm_smmu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops; - if (domain->type == IOMMU_DOMAIN_IDENTITY) - return iova; - if (!ops) return 0; diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index f22dbeb1e510..ac21170fa208 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -1198,8 +1198,9 @@ rpm_put: return ret; } -static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot, gfp_t gfp) +static int arm_smmu_map_pages(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t pgsize, size_t pgcount, + int prot, gfp_t gfp, size_t *mapped) { struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops; struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu; @@ -1209,14 +1210,15 @@ static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova, return -ENODEV; arm_smmu_rpm_get(smmu); - ret = ops->map(ops, iova, paddr, size, prot, gfp); + ret = ops->map_pages(ops, iova, paddr, pgsize, pgcount, prot, gfp, mapped); arm_smmu_rpm_put(smmu); return ret; } -static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, - size_t size, struct iommu_iotlb_gather *gather) +static size_t arm_smmu_unmap_pages(struct iommu_domain *domain, unsigned long iova, + size_t pgsize, size_t pgcount, + struct iommu_iotlb_gather *iotlb_gather) { struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops; struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu; @@ -1226,7 +1228,7 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, return 0; arm_smmu_rpm_get(smmu); - ret = ops->unmap(ops, iova, size, gather); + ret = ops->unmap_pages(ops, iova, pgsize, pgcount, iotlb_gather); arm_smmu_rpm_put(smmu); return ret; @@ -1320,9 +1322,6 @@ static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain, struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops; - if (domain->type == IOMMU_DOMAIN_IDENTITY) - return iova; - if (!ops) return 0; @@ -1582,8 +1581,8 @@ static struct iommu_ops arm_smmu_ops = { .domain_alloc = arm_smmu_domain_alloc, .domain_free = arm_smmu_domain_free, .attach_dev = arm_smmu_attach_dev, - .map = arm_smmu_map, - .unmap = arm_smmu_unmap, + .map_pages = arm_smmu_map_pages, + .unmap_pages = arm_smmu_unmap_pages, .flush_iotlb_all = arm_smmu_flush_iotlb_all, .iotlb_sync = arm_smmu_iotlb_sync, .iova_to_phys = arm_smmu_iova_to_phys, diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index dd22fc7d5176..c12cc955389a 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -85,24 +85,6 @@ #define LEVEL_STRIDE (9) #define LEVEL_MASK (((u64)1 << LEVEL_STRIDE) - 1) -/* - * This bitmap is used to advertise the page sizes our hardware support - * to the IOMMU core, which will then use this information to split - * physically contiguous memory regions it is mapping into page sizes - * that we support. - * - * Traditionally the IOMMU core just handed us the mappings directly, - * after making sure the size is an order of a 4KiB page and that the - * mapping has natural alignment. - * - * To retain this behavior, we currently advertise that we support - * all page sizes that are an order of 4KiB. - * - * If at some point we'd like to utilize the IOMMU core's new behavior, - * we could change this to advertise the real page sizes we support. - */ -#define INTEL_IOMMU_PGSIZES (~0xFFFUL) - static inline int agaw_to_level(int agaw) { return agaw + 2; @@ -361,7 +343,6 @@ int intel_iommu_enabled = 0; EXPORT_SYMBOL_GPL(intel_iommu_enabled); static int dmar_map_gfx = 1; -static int intel_iommu_strict; static int intel_iommu_superpage = 1; static int iommu_identity_mapping; static int iommu_skip_te_disable; @@ -454,8 +435,8 @@ static int __init intel_iommu_setup(char *str) pr_warn("intel_iommu=forcedac deprecated; use iommu.forcedac instead\n"); iommu_dma_forcedac = true; } else if (!strncmp(str, "strict", 6)) { - pr_info("Disable batched IOTLB flush\n"); - intel_iommu_strict = 1; + pr_warn("intel_iommu=strict deprecated; use iommu.strict=1 instead\n"); + iommu_set_dma_strict(); } else if (!strncmp(str, "sp_off", 6)) { pr_info("Disable supported super page\n"); intel_iommu_superpage = 0; @@ -736,6 +717,23 @@ static int domain_update_device_node(struct dmar_domain *domain) static void domain_update_iotlb(struct dmar_domain *domain); +/* Return the super pagesize bitmap if supported. */ +static unsigned long domain_super_pgsize_bitmap(struct dmar_domain *domain) +{ + unsigned long bitmap = 0; + + /* + * 1-level super page supports page size of 2MiB, 2-level super page + * supports page size of both 2MiB and 1GiB. + */ + if (domain->iommu_superpage == 1) + bitmap |= SZ_2M; + else if (domain->iommu_superpage == 2) + bitmap |= SZ_2M | SZ_1G; + + return bitmap; +} + /* Some capabilities may be different across iommus */ static void domain_update_iommu_cap(struct dmar_domain *domain) { @@ -762,6 +760,7 @@ static void domain_update_iommu_cap(struct dmar_domain *domain) else domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw); + domain->domain.pgsize_bitmap |= domain_super_pgsize_bitmap(domain); domain_update_iotlb(domain); } @@ -2334,9 +2333,9 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, unsigned long phys_pfn, unsigned long nr_pages, int prot) { + struct dma_pte *first_pte = NULL, *pte = NULL; unsigned int largepage_lvl = 0; unsigned long lvl_pages = 0; - struct dma_pte *pte = NULL; phys_addr_t pteval; u64 attr; @@ -2369,6 +2368,8 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, pte = pfn_to_dma_pte(domain, iov_pfn, &largepage_lvl); if (!pte) return -ENOMEM; + first_pte = pte; + /* It is large page*/ if (largepage_lvl > 1) { unsigned long end_pfn; @@ -2416,14 +2417,14 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, * recalculate 'pte' and switch back to smaller pages for the * end of the mapping, if the trailing size is not enough to * use another superpage (i.e. nr_pages < lvl_pages). - * - * We leave clflush for the leaf pte changes to iotlb_sync_map() - * callback. */ pte++; if (!nr_pages || first_pte_in_page(pte) || - (largepage_lvl > 1 && nr_pages < lvl_pages)) + (largepage_lvl > 1 && nr_pages < lvl_pages)) { + domain_flush_cache(domain, first_pte, + (void *)pte - (void *)first_pte); pte = NULL; + } } return 0; @@ -4393,9 +4394,9 @@ int __init intel_iommu_init(void) * is likely to be much lower than the overhead of synchronizing * the virtual and physical IOMMU page-tables. */ - if (!intel_iommu_strict && cap_caching_mode(iommu->cap)) { - pr_warn("IOMMU batching is disabled due to virtualization"); - intel_iommu_strict = 1; + if (cap_caching_mode(iommu->cap)) { + pr_info_once("IOMMU batching disallowed due to virtualization\n"); + iommu_set_dma_strict(); } iommu_device_sysfs_add(&iommu->iommu, NULL, intel_iommu_groups, @@ -4404,7 +4405,6 @@ int __init intel_iommu_init(void) } up_read(&dmar_global_lock); - iommu_set_dma_strict(intel_iommu_strict); bus_set_iommu(&pci_bus_type, &intel_iommu_ops); if (si_domain && !hw_pass_through) register_memory_notifier(&intel_iommu_memory_nb); @@ -5067,6 +5067,28 @@ static int intel_iommu_map(struct iommu_domain *domain, hpa >> VTD_PAGE_SHIFT, size, prot); } +static int intel_iommu_map_pages(struct iommu_domain *domain, + unsigned long iova, phys_addr_t paddr, + size_t pgsize, size_t pgcount, + int prot, gfp_t gfp, size_t *mapped) +{ + unsigned long pgshift = __ffs(pgsize); + size_t size = pgcount << pgshift; + int ret; + + if (pgsize != SZ_4K && pgsize != SZ_2M && pgsize != SZ_1G) + return -EINVAL; + + if (!IS_ALIGNED(iova | paddr, pgsize)) + return -EINVAL; + + ret = intel_iommu_map(domain, iova, paddr, size, prot, gfp); + if (!ret && mapped) + *mapped = size; + + return ret; +} + static size_t intel_iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *gather) @@ -5096,6 +5118,17 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain, return size; } +static size_t intel_iommu_unmap_pages(struct iommu_domain *domain, + unsigned long iova, + size_t pgsize, size_t pgcount, + struct iommu_iotlb_gather *gather) +{ + unsigned long pgshift = __ffs(pgsize); + size_t size = pgcount << pgshift; + + return intel_iommu_unmap(domain, iova, size, gather); +} + static void intel_iommu_tlb_sync(struct iommu_domain *domain, struct iommu_iotlb_gather *gather) { @@ -5532,39 +5565,6 @@ static bool risky_device(struct pci_dev *pdev) return false; } -static void clflush_sync_map(struct dmar_domain *domain, unsigned long clf_pfn, - unsigned long clf_pages) -{ - struct dma_pte *first_pte = NULL, *pte = NULL; - unsigned long lvl_pages = 0; - int level = 0; - - while (clf_pages > 0) { - if (!pte) { - level = 0; - pte = pfn_to_dma_pte(domain, clf_pfn, &level); - if (WARN_ON(!pte)) - return; - first_pte = pte; - lvl_pages = lvl_to_nr_pages(level); - } - - if (WARN_ON(!lvl_pages || clf_pages < lvl_pages)) - return; - - clf_pages -= lvl_pages; - clf_pfn += lvl_pages; - pte++; - - if (!clf_pages || first_pte_in_page(pte) || - (level > 1 && clf_pages < lvl_pages)) { - domain_flush_cache(domain, first_pte, - (void *)pte - (void *)first_pte); - pte = NULL; - } - } -} - static void intel_iommu_iotlb_sync_map(struct iommu_domain *domain, unsigned long iova, size_t size) { @@ -5574,9 +5574,6 @@ static void intel_iommu_iotlb_sync_map(struct iommu_domain *domain, struct intel_iommu *iommu; int iommu_id; - if (!dmar_domain->iommu_coherency) - clflush_sync_map(dmar_domain, pfn, pages); - for_each_domain_iommu(iommu_id, dmar_domain) { iommu = g_iommus[iommu_id]; __mapping_notify_one(iommu, dmar_domain, pfn, pages); @@ -5593,9 +5590,9 @@ const struct iommu_ops intel_iommu_ops = { .aux_attach_dev = intel_iommu_aux_attach_device, .aux_detach_dev = intel_iommu_aux_detach_device, .aux_get_pasid = intel_iommu_aux_get_pasid, - .map = intel_iommu_map, + .map_pages = intel_iommu_map_pages, + .unmap_pages = intel_iommu_unmap_pages, .iotlb_sync_map = intel_iommu_iotlb_sync_map, - .unmap = intel_iommu_unmap, .flush_iotlb_all = intel_flush_iotlb_all, .iotlb_sync = intel_iommu_tlb_sync, .iova_to_phys = intel_iommu_iova_to_phys, @@ -5611,7 +5608,7 @@ const struct iommu_ops intel_iommu_ops = { .dev_disable_feat = intel_iommu_dev_disable_feat, .is_attach_deferred = intel_iommu_is_attach_deferred, .def_domain_type = device_def_domain_type, - .pgsize_bitmap = INTEL_IOMMU_PGSIZES, + .pgsize_bitmap = SZ_4K, #ifdef CONFIG_INTEL_IOMMU_SVM .cache_invalidate = intel_iommu_sva_invalidate, .sva_bind_gpasid = intel_svm_bind_gpasid, @@ -5714,8 +5711,8 @@ static void quirk_calpella_no_shadow_gtt(struct pci_dev *dev) } else if (dmar_map_gfx) { /* we have to ensure the gfx device is idle before we flush */ pci_info(dev, "Disabling batched IOTLB flush on Ironlake\n"); - intel_iommu_strict = 1; - } + iommu_set_dma_strict(); + } } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0040, quirk_calpella_no_shadow_gtt); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_calpella_no_shadow_gtt); diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index d4004bcf333a..5db90d7ce2ec 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -519,11 +519,12 @@ static int __arm_v7s_map(struct arm_v7s_io_pgtable *data, unsigned long iova, return __arm_v7s_map(data, iova, paddr, size, prot, lvl + 1, cptep, gfp); } -static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova, - phys_addr_t paddr, size_t size, int prot, gfp_t gfp) +static int arm_v7s_map_pages(struct io_pgtable_ops *ops, unsigned long iova, + phys_addr_t paddr, size_t pgsize, size_t pgcount, + int prot, gfp_t gfp, size_t *mapped) { struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops); - int ret; + int ret = -EINVAL; if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias) || paddr >= (1ULL << data->iop.cfg.oas))) @@ -533,7 +534,17 @@ static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova, if (!(prot & (IOMMU_READ | IOMMU_WRITE))) return 0; - ret = __arm_v7s_map(data, iova, paddr, size, prot, 1, data->pgd, gfp); + while (pgcount--) { + ret = __arm_v7s_map(data, iova, paddr, pgsize, prot, 1, data->pgd, + gfp); + if (ret) + break; + + iova += pgsize; + paddr += pgsize; + if (mapped) + *mapped += pgsize; + } /* * Synchronise all PTE updates for the new mapping before there's * a chance for anything to kick off a table walk for the new iova. @@ -543,6 +554,12 @@ static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova, return ret; } +static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova, + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) +{ + return arm_v7s_map_pages(ops, iova, paddr, size, 1, prot, gfp, NULL); +} + static void arm_v7s_free_pgtable(struct io_pgtable *iop) { struct arm_v7s_io_pgtable *data = io_pgtable_to_data(iop); @@ -710,15 +727,32 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data, return __arm_v7s_unmap(data, gather, iova, size, lvl + 1, ptep); } -static size_t arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova, - size_t size, struct iommu_iotlb_gather *gather) +static size_t arm_v7s_unmap_pages(struct io_pgtable_ops *ops, unsigned long iova, + size_t pgsize, size_t pgcount, + struct iommu_iotlb_gather *gather) { struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops); + size_t unmapped = 0, ret; if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias))) return 0; - return __arm_v7s_unmap(data, gather, iova, size, 1, data->pgd); + while (pgcount--) { + ret = __arm_v7s_unmap(data, gather, iova, pgsize, 1, data->pgd); + if (!ret) + break; + + unmapped += pgsize; + iova += pgsize; + } + + return unmapped; +} + +static size_t arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova, + size_t size, struct iommu_iotlb_gather *gather) +{ + return arm_v7s_unmap_pages(ops, iova, size, 1, gather); } static phys_addr_t arm_v7s_iova_to_phys(struct io_pgtable_ops *ops, @@ -780,7 +814,9 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg, data->iop.ops = (struct io_pgtable_ops) { .map = arm_v7s_map, + .map_pages = arm_v7s_map_pages, .unmap = arm_v7s_unmap, + .unmap_pages = arm_v7s_unmap_pages, .iova_to_phys = arm_v7s_iova_to_phys, }; diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 87def58e79b5..053df4048a29 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -46,6 +46,9 @@ #define ARM_LPAE_PGD_SIZE(d) \ (sizeof(arm_lpae_iopte) << (d)->pgd_bits) +#define ARM_LPAE_PTES_PER_TABLE(d) \ + (ARM_LPAE_GRANULE(d) >> ilog2(sizeof(arm_lpae_iopte))) + /* * Calculate the index at level l used to map virtual address a using the * pagetable in d. @@ -232,70 +235,77 @@ static void __arm_lpae_free_pages(void *pages, size_t size, free_pages((unsigned long)pages, get_order(size)); } -static void __arm_lpae_sync_pte(arm_lpae_iopte *ptep, +static void __arm_lpae_sync_pte(arm_lpae_iopte *ptep, int num_entries, struct io_pgtable_cfg *cfg) { dma_sync_single_for_device(cfg->iommu_dev, __arm_lpae_dma_addr(ptep), - sizeof(*ptep), DMA_TO_DEVICE); + sizeof(*ptep) * num_entries, DMA_TO_DEVICE); } -static void __arm_lpae_set_pte(arm_lpae_iopte *ptep, arm_lpae_iopte pte, - struct io_pgtable_cfg *cfg) +static void __arm_lpae_clear_pte(arm_lpae_iopte *ptep, struct io_pgtable_cfg *cfg) { - *ptep = pte; + + *ptep = 0; if (!cfg->coherent_walk) - __arm_lpae_sync_pte(ptep, cfg); + __arm_lpae_sync_pte(ptep, 1, cfg); } static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, struct iommu_iotlb_gather *gather, - unsigned long iova, size_t size, int lvl, - arm_lpae_iopte *ptep); + unsigned long iova, size_t size, size_t pgcount, + int lvl, arm_lpae_iopte *ptep); static void __arm_lpae_init_pte(struct arm_lpae_io_pgtable *data, phys_addr_t paddr, arm_lpae_iopte prot, - int lvl, arm_lpae_iopte *ptep) + int lvl, int num_entries, arm_lpae_iopte *ptep) { arm_lpae_iopte pte = prot; + struct io_pgtable_cfg *cfg = &data->iop.cfg; + size_t sz = ARM_LPAE_BLOCK_SIZE(lvl, data); + int i; if (data->iop.fmt != ARM_MALI_LPAE && lvl == ARM_LPAE_MAX_LEVELS - 1) pte |= ARM_LPAE_PTE_TYPE_PAGE; else pte |= ARM_LPAE_PTE_TYPE_BLOCK; - pte |= paddr_to_iopte(paddr, data); + for (i = 0; i < num_entries; i++) + ptep[i] = pte | paddr_to_iopte(paddr + i * sz, data); - __arm_lpae_set_pte(ptep, pte, &data->iop.cfg); + if (!cfg->coherent_walk) + __arm_lpae_sync_pte(ptep, num_entries, cfg); } static int arm_lpae_init_pte(struct arm_lpae_io_pgtable *data, unsigned long iova, phys_addr_t paddr, - arm_lpae_iopte prot, int lvl, + arm_lpae_iopte prot, int lvl, int num_entries, arm_lpae_iopte *ptep) { - arm_lpae_iopte pte = *ptep; - - if (iopte_leaf(pte, lvl, data->iop.fmt)) { - /* We require an unmap first */ - WARN_ON(!selftest_running); - return -EEXIST; - } else if (iopte_type(pte) == ARM_LPAE_PTE_TYPE_TABLE) { - /* - * We need to unmap and free the old table before - * overwriting it with a block entry. - */ - arm_lpae_iopte *tblp; - size_t sz = ARM_LPAE_BLOCK_SIZE(lvl, data); - - tblp = ptep - ARM_LPAE_LVL_IDX(iova, lvl, data); - if (__arm_lpae_unmap(data, NULL, iova, sz, lvl, tblp) != sz) { - WARN_ON(1); - return -EINVAL; + int i; + + for (i = 0; i < num_entries; i++) + if (iopte_leaf(ptep[i], lvl, data->iop.fmt)) { + /* We require an unmap first */ + WARN_ON(!selftest_running); + return -EEXIST; + } else if (iopte_type(ptep[i]) == ARM_LPAE_PTE_TYPE_TABLE) { + /* + * We need to unmap and free the old table before + * overwriting it with a block entry. + */ + arm_lpae_iopte *tblp; + size_t sz = ARM_LPAE_BLOCK_SIZE(lvl, data); + + tblp = ptep - ARM_LPAE_LVL_IDX(iova, lvl, data); + if (__arm_lpae_unmap(data, NULL, iova + i * sz, sz, 1, + lvl, tblp) != sz) { + WARN_ON(1); + return -EINVAL; + } } - } - __arm_lpae_init_pte(data, paddr, prot, lvl, ptep); + __arm_lpae_init_pte(data, paddr, prot, lvl, num_entries, ptep); return 0; } @@ -323,7 +333,7 @@ static arm_lpae_iopte arm_lpae_install_table(arm_lpae_iopte *table, return old; /* Even if it's not ours, there's no point waiting; just kick it */ - __arm_lpae_sync_pte(ptep, cfg); + __arm_lpae_sync_pte(ptep, 1, cfg); if (old == curr) WRITE_ONCE(*ptep, new | ARM_LPAE_PTE_SW_SYNC); @@ -331,20 +341,30 @@ static arm_lpae_iopte arm_lpae_install_table(arm_lpae_iopte *table, } static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova, - phys_addr_t paddr, size_t size, arm_lpae_iopte prot, - int lvl, arm_lpae_iopte *ptep, gfp_t gfp) + phys_addr_t paddr, size_t size, size_t pgcount, + arm_lpae_iopte prot, int lvl, arm_lpae_iopte *ptep, + gfp_t gfp, size_t *mapped) { arm_lpae_iopte *cptep, pte; size_t block_size = ARM_LPAE_BLOCK_SIZE(lvl, data); size_t tblsz = ARM_LPAE_GRANULE(data); struct io_pgtable_cfg *cfg = &data->iop.cfg; + int ret = 0, num_entries, max_entries, map_idx_start; /* Find our entry at the current level */ - ptep += ARM_LPAE_LVL_IDX(iova, lvl, data); + map_idx_start = ARM_LPAE_LVL_IDX(iova, lvl, data); + ptep += map_idx_start; /* If we can install a leaf entry at this level, then do so */ - if (size == block_size) - return arm_lpae_init_pte(data, iova, paddr, prot, lvl, ptep); + if (size == block_size) { + max_entries = ARM_LPAE_PTES_PER_TABLE(data) - map_idx_start; + num_entries = min_t(int, pgcount, max_entries); + ret = arm_lpae_init_pte(data, iova, paddr, prot, lvl, num_entries, ptep); + if (!ret && mapped) + *mapped += num_entries * size; + + return ret; + } /* We can't allocate tables at the final level */ if (WARN_ON(lvl >= ARM_LPAE_MAX_LEVELS - 1)) @@ -361,7 +381,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova, if (pte) __arm_lpae_free_pages(cptep, tblsz, cfg); } else if (!cfg->coherent_walk && !(pte & ARM_LPAE_PTE_SW_SYNC)) { - __arm_lpae_sync_pte(ptep, cfg); + __arm_lpae_sync_pte(ptep, 1, cfg); } if (pte && !iopte_leaf(pte, lvl, data->iop.fmt)) { @@ -373,7 +393,8 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova, } /* Rinse, repeat */ - return __arm_lpae_map(data, iova, paddr, size, prot, lvl + 1, cptep, gfp); + return __arm_lpae_map(data, iova, paddr, size, pgcount, prot, lvl + 1, + cptep, gfp, mapped); } static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data, @@ -440,8 +461,9 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data, return pte; } -static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova, - phys_addr_t paddr, size_t size, int iommu_prot, gfp_t gfp) +static int arm_lpae_map_pages(struct io_pgtable_ops *ops, unsigned long iova, + phys_addr_t paddr, size_t pgsize, size_t pgcount, + int iommu_prot, gfp_t gfp, size_t *mapped) { struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops); struct io_pgtable_cfg *cfg = &data->iop.cfg; @@ -450,7 +472,7 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova, arm_lpae_iopte prot; long iaext = (s64)iova >> cfg->ias; - if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size)) + if (WARN_ON(!pgsize || (pgsize & cfg->pgsize_bitmap) != pgsize)) return -EINVAL; if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1) @@ -463,7 +485,8 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova, return 0; prot = arm_lpae_prot_to_pte(data, iommu_prot); - ret = __arm_lpae_map(data, iova, paddr, size, prot, lvl, ptep, gfp); + ret = __arm_lpae_map(data, iova, paddr, pgsize, pgcount, prot, lvl, + ptep, gfp, mapped); /* * Synchronise all PTE updates for the new mapping before there's * a chance for anything to kick off a table walk for the new iova. @@ -473,6 +496,13 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova, return ret; } +static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova, + phys_addr_t paddr, size_t size, int iommu_prot, gfp_t gfp) +{ + return arm_lpae_map_pages(ops, iova, paddr, size, 1, iommu_prot, gfp, + NULL); +} + static void __arm_lpae_free_pgtable(struct arm_lpae_io_pgtable *data, int lvl, arm_lpae_iopte *ptep) { @@ -516,14 +546,15 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, struct iommu_iotlb_gather *gather, unsigned long iova, size_t size, arm_lpae_iopte blk_pte, int lvl, - arm_lpae_iopte *ptep) + arm_lpae_iopte *ptep, size_t pgcount) { struct io_pgtable_cfg *cfg = &data->iop.cfg; arm_lpae_iopte pte, *tablep; phys_addr_t blk_paddr; size_t tablesz = ARM_LPAE_GRANULE(data); size_t split_sz = ARM_LPAE_BLOCK_SIZE(lvl, data); - int i, unmap_idx = -1; + int ptes_per_table = ARM_LPAE_PTES_PER_TABLE(data); + int i, unmap_idx_start = -1, num_entries = 0, max_entries; if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS)) return 0; @@ -532,18 +563,21 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, if (!tablep) return 0; /* Bytes unmapped */ - if (size == split_sz) - unmap_idx = ARM_LPAE_LVL_IDX(iova, lvl, data); + if (size == split_sz) { + unmap_idx_start = ARM_LPAE_LVL_IDX(iova, lvl, data); + max_entries = ptes_per_table - unmap_idx_start; + num_entries = min_t(int, pgcount, max_entries); + } blk_paddr = iopte_to_paddr(blk_pte, data); pte = iopte_prot(blk_pte); - for (i = 0; i < tablesz / sizeof(pte); i++, blk_paddr += split_sz) { + for (i = 0; i < ptes_per_table; i++, blk_paddr += split_sz) { /* Unmap! */ - if (i == unmap_idx) + if (i >= unmap_idx_start && i < (unmap_idx_start + num_entries)) continue; - __arm_lpae_init_pte(data, blk_paddr, pte, lvl, &tablep[i]); + __arm_lpae_init_pte(data, blk_paddr, pte, lvl, 1, &tablep[i]); } pte = arm_lpae_install_table(tablep, ptep, blk_pte, cfg); @@ -558,76 +592,92 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, return 0; tablep = iopte_deref(pte, data); - } else if (unmap_idx >= 0) { - io_pgtable_tlb_add_page(&data->iop, gather, iova, size); - return size; + } else if (unmap_idx_start >= 0) { + for (i = 0; i < num_entries; i++) + io_pgtable_tlb_add_page(&data->iop, gather, iova + i * size, size); + + return num_entries * size; } - return __arm_lpae_unmap(data, gather, iova, size, lvl, tablep); + return __arm_lpae_unmap(data, gather, iova, size, pgcount, lvl, tablep); } static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, struct iommu_iotlb_gather *gather, - unsigned long iova, size_t size, int lvl, - arm_lpae_iopte *ptep) + unsigned long iova, size_t size, size_t pgcount, + int lvl, arm_lpae_iopte *ptep) { arm_lpae_iopte pte; struct io_pgtable *iop = &data->iop; + int i = 0, num_entries, max_entries, unmap_idx_start; /* Something went horribly wrong and we ran out of page table */ if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS)) return 0; - ptep += ARM_LPAE_LVL_IDX(iova, lvl, data); + unmap_idx_start = ARM_LPAE_LVL_IDX(iova, lvl, data); + ptep += unmap_idx_start; pte = READ_ONCE(*ptep); if (WARN_ON(!pte)) return 0; /* If the size matches this level, we're in the right place */ if (size == ARM_LPAE_BLOCK_SIZE(lvl, data)) { - __arm_lpae_set_pte(ptep, 0, &iop->cfg); - - if (!iopte_leaf(pte, lvl, iop->fmt)) { - /* Also flush any partial walks */ - io_pgtable_tlb_flush_walk(iop, iova, size, - ARM_LPAE_GRANULE(data)); - ptep = iopte_deref(pte, data); - __arm_lpae_free_pgtable(data, lvl + 1, ptep); - } else if (iop->cfg.quirks & IO_PGTABLE_QUIRK_NON_STRICT) { - /* - * Order the PTE update against queueing the IOVA, to - * guarantee that a flush callback from a different CPU - * has observed it before the TLBIALL can be issued. - */ - smp_wmb(); - } else { - io_pgtable_tlb_add_page(iop, gather, iova, size); + max_entries = ARM_LPAE_PTES_PER_TABLE(data) - unmap_idx_start; + num_entries = min_t(int, pgcount, max_entries); + + while (i < num_entries) { + pte = READ_ONCE(*ptep); + if (WARN_ON(!pte)) + break; + + __arm_lpae_clear_pte(ptep, &iop->cfg); + + if (!iopte_leaf(pte, lvl, iop->fmt)) { + /* Also flush any partial walks */ + io_pgtable_tlb_flush_walk(iop, iova + i * size, size, + ARM_LPAE_GRANULE(data)); + __arm_lpae_free_pgtable(data, lvl + 1, iopte_deref(pte, data)); + } else if (iop->cfg.quirks & IO_PGTABLE_QUIRK_NON_STRICT) { + /* + * Order the PTE update against queueing the IOVA, to + * guarantee that a flush callback from a different CPU + * has observed it before the TLBIALL can be issued. + */ + smp_wmb(); + } else { + io_pgtable_tlb_add_page(iop, gather, iova + i * size, size); + } + + ptep++; + i++; } - return size; + return i * size; } else if (iopte_leaf(pte, lvl, iop->fmt)) { /* * Insert a table at the next level to map the old region, * minus the part we want to unmap */ return arm_lpae_split_blk_unmap(data, gather, iova, size, pte, - lvl + 1, ptep); + lvl + 1, ptep, pgcount); } /* Keep on walkin' */ ptep = iopte_deref(pte, data); - return __arm_lpae_unmap(data, gather, iova, size, lvl + 1, ptep); + return __arm_lpae_unmap(data, gather, iova, size, pgcount, lvl + 1, ptep); } -static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova, - size_t size, struct iommu_iotlb_gather *gather) +static size_t arm_lpae_unmap_pages(struct io_pgtable_ops *ops, unsigned long iova, + size_t pgsize, size_t pgcount, + struct iommu_iotlb_gather *gather) { struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops); struct io_pgtable_cfg *cfg = &data->iop.cfg; arm_lpae_iopte *ptep = data->pgd; long iaext = (s64)iova >> cfg->ias; - if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size)) + if (WARN_ON(!pgsize || (pgsize & cfg->pgsize_bitmap) != pgsize || !pgcount)) return 0; if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1) @@ -635,7 +685,14 @@ static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova, if (WARN_ON(iaext)) return 0; - return __arm_lpae_unmap(data, gather, iova, size, data->start_level, ptep); + return __arm_lpae_unmap(data, gather, iova, pgsize, pgcount, + data->start_level, ptep); +} + +static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova, + size_t size, struct iommu_iotlb_gather *gather) +{ + return arm_lpae_unmap_pages(ops, iova, size, 1, gather); } static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops, @@ -750,7 +807,9 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg) data->iop.ops = (struct io_pgtable_ops) { .map = arm_lpae_map, + .map_pages = arm_lpae_map_pages, .unmap = arm_lpae_unmap, + .unmap_pages = arm_lpae_unmap_pages, .iova_to_phys = arm_lpae_iova_to_phys, }; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 5419c4b9f27a..f2cda9950bd5 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -8,6 +8,7 @@ #include <linux/device.h> #include <linux/kernel.h> +#include <linux/bits.h> #include <linux/bug.h> #include <linux/types.h> #include <linux/init.h> @@ -29,7 +30,7 @@ static struct kset *iommu_group_kset; static DEFINE_IDA(iommu_group_ida); static unsigned int iommu_def_domain_type __read_mostly; -static bool iommu_dma_strict __read_mostly = true; +static bool iommu_dma_strict __read_mostly = IS_ENABLED(CONFIG_IOMMU_DEFAULT_STRICT); static u32 iommu_cmd_line __read_mostly; struct iommu_group { @@ -138,6 +139,11 @@ static int __init iommu_subsys_init(void) (iommu_cmd_line & IOMMU_CMD_LINE_DMA_API) ? "(set via kernel command line)" : ""); + pr_info("DMA domain TLB invalidation policy: %s mode %s\n", + iommu_dma_strict ? "strict" : "lazy", + (iommu_cmd_line & IOMMU_CMD_LINE_STRICT) ? + "(set via kernel command line)" : ""); + return 0; } subsys_initcall(iommu_subsys_init); @@ -344,10 +350,9 @@ static int __init iommu_dma_setup(char *str) } early_param("iommu.strict", iommu_dma_setup); -void iommu_set_dma_strict(bool strict) +void iommu_set_dma_strict(void) { - if (strict || !(iommu_cmd_line & IOMMU_CMD_LINE_STRICT)) - iommu_dma_strict = strict; + iommu_dma_strict = true; } bool iommu_get_dma_strict(struct iommu_domain *domain) @@ -2367,45 +2372,94 @@ EXPORT_SYMBOL_GPL(iommu_detach_group); phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { - if (unlikely(domain->ops->iova_to_phys == NULL)) + if (domain->type == IOMMU_DOMAIN_IDENTITY) + return iova; + + if (domain->type == IOMMU_DOMAIN_BLOCKED) return 0; return domain->ops->iova_to_phys(domain, iova); } EXPORT_SYMBOL_GPL(iommu_iova_to_phys); -static size_t iommu_pgsize(struct iommu_domain *domain, - unsigned long addr_merge, size_t size) +static size_t iommu_pgsize(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, size_t *count) { - unsigned int pgsize_idx; - size_t pgsize; + unsigned int pgsize_idx, pgsize_idx_next; + unsigned long pgsizes; + size_t offset, pgsize, pgsize_next; + unsigned long addr_merge = paddr | iova; - /* Max page size that still fits into 'size' */ - pgsize_idx = __fls(size); + /* Page sizes supported by the hardware and small enough for @size */ + pgsizes = domain->pgsize_bitmap & GENMASK(__fls(size), 0); - /* need to consider alignment requirements ? */ - if (likely(addr_merge)) { - /* Max page size allowed by address */ - unsigned int align_pgsize_idx = __ffs(addr_merge); - pgsize_idx = min(pgsize_idx, align_pgsize_idx); - } + /* Constrain the page sizes further based on the maximum alignment */ + if (likely(addr_merge)) + pgsizes &= GENMASK(__ffs(addr_merge), 0); - /* build a mask of acceptable page sizes */ - pgsize = (1UL << (pgsize_idx + 1)) - 1; + /* Make sure we have at least one suitable page size */ + BUG_ON(!pgsizes); - /* throw away page sizes not supported by the hardware */ - pgsize &= domain->pgsize_bitmap; + /* Pick the biggest page size remaining */ + pgsize_idx = __fls(pgsizes); + pgsize = BIT(pgsize_idx); + if (!count) + return pgsize; + + /* Find the next biggest support page size, if it exists */ + pgsizes = domain->pgsize_bitmap & ~GENMASK(pgsize_idx, 0); + if (!pgsizes) + goto out_set_count; + + pgsize_idx_next = __ffs(pgsizes); + pgsize_next = BIT(pgsize_idx_next); + + /* + * There's no point trying a bigger page size unless the virtual + * and physical addresses are similarly offset within the larger page. + */ + if ((iova ^ paddr) & (pgsize_next - 1)) + goto out_set_count; - /* make sure we're still sane */ - BUG_ON(!pgsize); + /* Calculate the offset to the next page size alignment boundary */ + offset = pgsize_next - (addr_merge & (pgsize_next - 1)); - /* pick the biggest page */ - pgsize_idx = __fls(pgsize); - pgsize = 1UL << pgsize_idx; + /* + * If size is big enough to accommodate the larger page, reduce + * the number of smaller pages. + */ + if (offset + pgsize_next <= size) + size = offset; +out_set_count: + *count = size >> pgsize_idx; return pgsize; } +static int __iommu_map_pages(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot, + gfp_t gfp, size_t *mapped) +{ + const struct iommu_ops *ops = domain->ops; + size_t pgsize, count; + int ret; + + pgsize = iommu_pgsize(domain, iova, paddr, size, &count); + + pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx count %zu\n", + iova, &paddr, pgsize, count); + + if (ops->map_pages) { + ret = ops->map_pages(domain, iova, paddr, pgsize, count, prot, + gfp, mapped); + } else { + ret = ops->map(domain, iova, paddr, pgsize, prot, gfp); + *mapped = ret ? 0 : pgsize; + } + + return ret; +} + static int __iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { @@ -2416,7 +2470,7 @@ static int __iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t orig_paddr = paddr; int ret = 0; - if (unlikely(ops->map == NULL || + if (unlikely(!(ops->map || ops->map_pages) || domain->pgsize_bitmap == 0UL)) return -ENODEV; @@ -2440,18 +2494,21 @@ static int __iommu_map(struct iommu_domain *domain, unsigned long iova, pr_debug("map: iova 0x%lx pa %pa size 0x%zx\n", iova, &paddr, size); while (size) { - size_t pgsize = iommu_pgsize(domain, iova | paddr, size); + size_t mapped = 0; - pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx\n", - iova, &paddr, pgsize); - ret = ops->map(domain, iova, paddr, pgsize, prot, gfp); + ret = __iommu_map_pages(domain, iova, paddr, size, prot, gfp, + &mapped); + /* + * Some pages may have been mapped, even if an error occurred, + * so we should account for those so they can be unmapped. + */ + size -= mapped; if (ret) break; - iova += pgsize; - paddr += pgsize; - size -= pgsize; + iova += mapped; + paddr += mapped; } /* unroll mapping in case something went wrong */ @@ -2491,6 +2548,19 @@ int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova, } EXPORT_SYMBOL_GPL(iommu_map_atomic); +static size_t __iommu_unmap_pages(struct iommu_domain *domain, + unsigned long iova, size_t size, + struct iommu_iotlb_gather *iotlb_gather) +{ + const struct iommu_ops *ops = domain->ops; + size_t pgsize, count; + + pgsize = iommu_pgsize(domain, iova, iova, size, &count); + return ops->unmap_pages ? + ops->unmap_pages(domain, iova, pgsize, count, iotlb_gather) : + ops->unmap(domain, iova, pgsize, iotlb_gather); +} + static size_t __iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *iotlb_gather) @@ -2500,7 +2570,7 @@ static size_t __iommu_unmap(struct iommu_domain *domain, unsigned long orig_iova = iova; unsigned int min_pagesz; - if (unlikely(ops->unmap == NULL || + if (unlikely(!(ops->unmap || ops->unmap_pages) || domain->pgsize_bitmap == 0UL)) return 0; @@ -2528,9 +2598,9 @@ static size_t __iommu_unmap(struct iommu_domain *domain, * or we hit an area that isn't mapped. */ while (unmapped < size) { - size_t pgsize = iommu_pgsize(domain, iova, size - unmapped); - - unmapped_page = ops->unmap(domain, iova, pgsize, iotlb_gather); + unmapped_page = __iommu_unmap_pages(domain, iova, + size - unmapped, + iotlb_gather); if (!unmapped_page) break; diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 4d40dfa75b55..c43f3b899d2a 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -143,7 +143,9 @@ struct io_pgtable_cfg { * struct io_pgtable_ops - Page table manipulation API for IOMMU drivers. * * @map: Map a physically contiguous memory region. + * @map_pages: Map a physically contiguous range of pages of the same size. * @unmap: Unmap a physically contiguous memory region. + * @unmap_pages: Unmap a range of virtually contiguous pages of the same size. * @iova_to_phys: Translate iova to physical address. * * These functions map directly onto the iommu_ops member functions with @@ -152,8 +154,14 @@ struct io_pgtable_cfg { struct io_pgtable_ops { int (*map)(struct io_pgtable_ops *ops, unsigned long iova, phys_addr_t paddr, size_t size, int prot, gfp_t gfp); + int (*map_pages)(struct io_pgtable_ops *ops, unsigned long iova, + phys_addr_t paddr, size_t pgsize, size_t pgcount, + int prot, gfp_t gfp, size_t *mapped); size_t (*unmap)(struct io_pgtable_ops *ops, unsigned long iova, size_t size, struct iommu_iotlb_gather *gather); + size_t (*unmap_pages)(struct io_pgtable_ops *ops, unsigned long iova, + size_t pgsize, size_t pgcount, + struct iommu_iotlb_gather *gather); phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops, unsigned long iova); }; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 979a5ceeea55..e552ecfefcf7 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -180,7 +180,10 @@ struct iommu_iotlb_gather { * @attach_dev: attach device to an iommu domain * @detach_dev: detach device from an iommu domain * @map: map a physically contiguous memory region to an iommu domain + * @map_pages: map a physically contiguous set of pages of the same size to + * an iommu domain. * @unmap: unmap a physically contiguous memory region from an iommu domain + * @unmap_pages: unmap a number of pages of the same size from an iommu domain * @flush_iotlb_all: Synchronously flush all hardware TLBs for this domain * @iotlb_sync_map: Sync mappings created recently using @map to the hardware * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush @@ -229,8 +232,14 @@ struct iommu_ops { void (*detach_dev)(struct iommu_domain *domain, struct device *dev); int (*map)(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot, gfp_t gfp); + int (*map_pages)(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t pgsize, size_t pgcount, + int prot, gfp_t gfp, size_t *mapped); size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *iotlb_gather); + size_t (*unmap_pages)(struct iommu_domain *domain, unsigned long iova, + size_t pgsize, size_t pgcount, + struct iommu_iotlb_gather *iotlb_gather); void (*flush_iotlb_all)(struct iommu_domain *domain); void (*iotlb_sync_map)(struct iommu_domain *domain, unsigned long iova, size_t size); @@ -476,7 +485,7 @@ int iommu_enable_nesting(struct iommu_domain *domain); int iommu_set_pgtable_quirks(struct iommu_domain *domain, unsigned long quirks); -void iommu_set_dma_strict(bool val); +void iommu_set_dma_strict(void); bool iommu_get_dma_strict(struct iommu_domain *domain); extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev, |