diff options
Diffstat (limited to 'drivers/iommu')
-rw-r--r-- | drivers/iommu/Kconfig | 5 | ||||
-rw-r--r-- | drivers/iommu/amd_iommu.c | 13 | ||||
-rw-r--r-- | drivers/iommu/amd_iommu_init.c | 3 | ||||
-rw-r--r-- | drivers/iommu/amd_iommu_types.h | 1 | ||||
-rw-r--r-- | drivers/iommu/amd_iommu_v2.c | 7 | ||||
-rw-r--r-- | drivers/iommu/arm-smmu-v3.c | 21 | ||||
-rw-r--r-- | drivers/iommu/intel-iommu.c | 21 | ||||
-rw-r--r-- | drivers/iommu/io-pgtable-arm.c | 24 | ||||
-rw-r--r-- | drivers/iommu/iova.c | 120 |
9 files changed, 135 insertions, 80 deletions
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 4664c2a..cbe6a89 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 @@ -43,7 +42,7 @@ config IOMMU_IO_PGTABLE_LPAE_SELFTEST endmenu config IOMMU_IOVA - bool + tristate config OF_IOMMU def_bool y diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index f82060e7..532e2a2 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -1974,8 +1974,8 @@ static void set_dte_entry(u16 devid, struct protection_domain *domain, bool ats) static void clear_dte_entry(u16 devid) { /* remove entry from the device table seen by the hardware */ - amd_iommu_dev_table[devid].data[0] = IOMMU_PTE_P | IOMMU_PTE_TV; - amd_iommu_dev_table[devid].data[1] = 0; + amd_iommu_dev_table[devid].data[0] = IOMMU_PTE_P | IOMMU_PTE_TV; + amd_iommu_dev_table[devid].data[1] &= DTE_FLAG_MASK; amd_iommu_apply_erratum_63(devid); } @@ -2006,6 +2006,15 @@ static void do_detach(struct iommu_dev_data *dev_data) { struct amd_iommu *iommu; + /* + * First check if the device is still attached. It might already + * be detached from its domain because the generic + * iommu_detach_group code detached it and we try again here in + * our alias handling. + */ + if (!dev_data->domain) + return; + iommu = amd_iommu_rlookup_table[dev_data->devid]; /* decrease reference counters */ diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 5ef347a..1b066e7 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -1256,6 +1256,9 @@ static int iommu_init_pci(struct amd_iommu *iommu) if (!iommu->dev) return -ENODEV; + /* Prevent binding other PCI device drivers to IOMMU devices */ + iommu->dev->match_driver = false; + pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET, &iommu->cap); pci_read_config_dword(iommu->dev, cap_ptr + MMIO_RANGE_OFFSET, diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index f659088..c9b6472 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -295,6 +295,7 @@ #define IOMMU_PTE_IR (1ULL << 61) #define IOMMU_PTE_IW (1ULL << 62) +#define DTE_FLAG_MASK (0x3ffULL << 32) #define DTE_FLAG_IOTLB (0x01UL << 32) #define DTE_FLAG_GV (0x01ULL << 55) #define DTE_GLX_SHIFT (56) diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c index 1131664..d21d4ed 100644 --- a/drivers/iommu/amd_iommu_v2.c +++ b/drivers/iommu/amd_iommu_v2.c @@ -516,6 +516,13 @@ static void do_fault(struct work_struct *work) goto out; } + if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))) { + /* handle_mm_fault would BUG_ON() */ + up_read(&mm->mmap_sem); + handle_fault_error(fault); + goto out; + } + ret = handle_mm_fault(mm, vma, address, write); if (ret & VM_FAULT_ERROR) { /* failed to service fault */ diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index dafaf59..286e890 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/intel-iommu.c b/drivers/iommu/intel-iommu.c index 2d7349a..d65cf42 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -2115,15 +2115,19 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, return -ENOMEM; /* It is large page*/ if (largepage_lvl > 1) { + unsigned long nr_superpages, end_pfn; + pteval |= DMA_PTE_LARGE_PAGE; lvl_pages = lvl_to_nr_pages(largepage_lvl); + + nr_superpages = sg_res / lvl_pages; + end_pfn = iov_pfn + nr_superpages * lvl_pages - 1; + /* * Ensure that old small page tables are - * removed to make room for superpage, - * if they exist. + * removed to make room for superpage(s). */ - dma_pte_free_pagetable(domain, iov_pfn, - iov_pfn + lvl_pages - 1); + dma_pte_free_pagetable(domain, iov_pfn, end_pfn); } else { pteval &= ~(uint64_t)DMA_PTE_LARGE_PAGE; } @@ -2301,6 +2305,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, if (ret) { spin_unlock_irqrestore(&device_domain_lock, flags); + free_devinfo_mem(info); return NULL; } @@ -3215,6 +3220,8 @@ static struct iova *intel_alloc_iova(struct device *dev, /* Restrict dma_mask to the width that the iommu can handle */ dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw), dma_mask); + /* Ensure we reserve the whole size-aligned region */ + nrpages = __roundup_pow_of_two(nrpages); if (!dmar_forcedac && dma_mask > DMA_BIT_MASK(32)) { /* @@ -3711,7 +3718,7 @@ static inline int iommu_devinfo_cache_init(void) static int __init iommu_init_mempool(void) { int ret; - ret = iommu_iova_cache_init(); + ret = iova_cache_get(); if (ret) return ret; @@ -3725,7 +3732,7 @@ static int __init iommu_init_mempool(void) kmem_cache_destroy(iommu_domain_cache); domain_error: - iommu_iova_cache_destroy(); + iova_cache_put(); return -ENOMEM; } @@ -3734,7 +3741,7 @@ static void __init iommu_exit_mempool(void) { kmem_cache_destroy(iommu_devinfo_cache); kmem_cache_destroy(iommu_domain_cache); - iommu_iova_cache_destroy(); + iova_cache_put(); } static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev) diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 73c0748..7df9777 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; diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index b7c3d92..fa0adef 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -18,42 +18,9 @@ */ #include <linux/iova.h> +#include <linux/module.h> #include <linux/slab.h> -static struct kmem_cache *iommu_iova_cache; - -int iommu_iova_cache_init(void) -{ - int ret = 0; - - iommu_iova_cache = kmem_cache_create("iommu_iova", - sizeof(struct iova), - 0, - SLAB_HWCACHE_ALIGN, - NULL); - if (!iommu_iova_cache) { - pr_err("Couldn't create iova cache\n"); - ret = -ENOMEM; - } - - return ret; -} - -void iommu_iova_cache_destroy(void) -{ - kmem_cache_destroy(iommu_iova_cache); -} - -struct iova *alloc_iova_mem(void) -{ - return kmem_cache_alloc(iommu_iova_cache, GFP_ATOMIC); -} - -void free_iova_mem(struct iova *iova) -{ - kmem_cache_free(iommu_iova_cache, iova); -} - void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn, unsigned long pfn_32bit) @@ -72,6 +39,7 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule, iovad->start_pfn = start_pfn; iovad->dma_32bit_pfn = pfn_32bit; } +EXPORT_SYMBOL_GPL(init_iova_domain); static struct rb_node * __get_cached_rbnode(struct iova_domain *iovad, unsigned long *limit_pfn) @@ -120,19 +88,14 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free) } } -/* Computes the padding size required, to make the - * the start address naturally aligned on its size +/* + * Computes the padding size required, to make the start address + * naturally aligned on the power-of-two order of its size */ -static int -iova_get_pad_size(int size, unsigned int limit_pfn) +static unsigned int +iova_get_pad_size(unsigned int size, unsigned int limit_pfn) { - unsigned int pad_size = 0; - unsigned int order = ilog2(size); - - if (order) - pad_size = (limit_pfn + 1) % (1 << order); - - return pad_size; + return (limit_pfn + 1 - size) & (__roundup_pow_of_two(size) - 1); } static int __alloc_and_insert_iova_range(struct iova_domain *iovad, @@ -242,6 +205,57 @@ iova_insert_rbtree(struct rb_root *root, struct iova *iova) rb_insert_color(&iova->node, root); } +static struct kmem_cache *iova_cache; +static unsigned int iova_cache_users; +static DEFINE_MUTEX(iova_cache_mutex); + +struct iova *alloc_iova_mem(void) +{ + return kmem_cache_alloc(iova_cache, GFP_ATOMIC); +} +EXPORT_SYMBOL(alloc_iova_mem); + +void free_iova_mem(struct iova *iova) +{ + kmem_cache_free(iova_cache, iova); +} +EXPORT_SYMBOL(free_iova_mem); + +int iova_cache_get(void) +{ + mutex_lock(&iova_cache_mutex); + if (!iova_cache_users) { + iova_cache = kmem_cache_create( + "iommu_iova", sizeof(struct iova), 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!iova_cache) { + mutex_unlock(&iova_cache_mutex); + printk(KERN_ERR "Couldn't create iova cache\n"); + return -ENOMEM; + } + } + + iova_cache_users++; + mutex_unlock(&iova_cache_mutex); + + return 0; +} +EXPORT_SYMBOL_GPL(iova_cache_get); + +void iova_cache_put(void) +{ + mutex_lock(&iova_cache_mutex); + if (WARN_ON(!iova_cache_users)) { + mutex_unlock(&iova_cache_mutex); + return; + } + iova_cache_users--; + if (!iova_cache_users) + kmem_cache_destroy(iova_cache); + mutex_unlock(&iova_cache_mutex); +} +EXPORT_SYMBOL_GPL(iova_cache_put); + /** * alloc_iova - allocates an iova * @iovad: - iova domain in question @@ -265,12 +279,6 @@ alloc_iova(struct iova_domain *iovad, unsigned long size, if (!new_iova) return NULL; - /* If size aligned is set then round the size to - * to next power of two. - */ - if (size_aligned) - size = __roundup_pow_of_two(size); - ret = __alloc_and_insert_iova_range(iovad, size, limit_pfn, new_iova, size_aligned); @@ -281,6 +289,7 @@ alloc_iova(struct iova_domain *iovad, unsigned long size, return new_iova; } +EXPORT_SYMBOL_GPL(alloc_iova); /** * find_iova - find's an iova for a given pfn @@ -321,6 +330,7 @@ struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn) spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags); return NULL; } +EXPORT_SYMBOL_GPL(find_iova); /** * __free_iova - frees the given iova @@ -339,6 +349,7 @@ __free_iova(struct iova_domain *iovad, struct iova *iova) spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags); free_iova_mem(iova); } +EXPORT_SYMBOL_GPL(__free_iova); /** * free_iova - finds and frees the iova for a given pfn @@ -356,6 +367,7 @@ free_iova(struct iova_domain *iovad, unsigned long pfn) __free_iova(iovad, iova); } +EXPORT_SYMBOL_GPL(free_iova); /** * put_iova_domain - destroys the iova doamin @@ -378,6 +390,7 @@ void put_iova_domain(struct iova_domain *iovad) } spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags); } +EXPORT_SYMBOL_GPL(put_iova_domain); static int __is_range_overlap(struct rb_node *node, @@ -467,6 +480,7 @@ finish: spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags); return iova; } +EXPORT_SYMBOL_GPL(reserve_iova); /** * copy_reserved_iova - copies the reserved between domains @@ -493,6 +507,7 @@ copy_reserved_iova(struct iova_domain *from, struct iova_domain *to) } spin_unlock_irqrestore(&from->iova_rbtree_lock, flags); } +EXPORT_SYMBOL_GPL(copy_reserved_iova); struct iova * split_and_remove_iova(struct iova_domain *iovad, struct iova *iova, @@ -534,3 +549,6 @@ error: free_iova_mem(prev); return NULL; } + +MODULE_AUTHOR("Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>"); +MODULE_LICENSE("GPL"); |