diff options
Diffstat (limited to 'drivers/iommu')
-rw-r--r-- | drivers/iommu/Kconfig | 3 | ||||
-rw-r--r-- | drivers/iommu/amd_iommu.c | 76 | ||||
-rw-r--r-- | drivers/iommu/amd_iommu_init.c | 25 | ||||
-rw-r--r-- | drivers/iommu/amd_iommu_types.h | 4 | ||||
-rw-r--r-- | drivers/iommu/amd_iommu_v2.c | 4 | ||||
-rw-r--r-- | drivers/iommu/arm-smmu-v3.c | 215 | ||||
-rw-r--r-- | drivers/iommu/arm-smmu.c | 326 | ||||
-rw-r--r-- | drivers/iommu/dma-iommu.c | 199 | ||||
-rw-r--r-- | drivers/iommu/dmar.c | 35 | ||||
-rw-r--r-- | drivers/iommu/exynos-iommu.c | 16 | ||||
-rw-r--r-- | drivers/iommu/intel-iommu.c | 209 | ||||
-rw-r--r-- | drivers/iommu/intel-svm.c | 28 | ||||
-rw-r--r-- | drivers/iommu/io-pgtable-arm-v7s.c | 11 | ||||
-rw-r--r-- | drivers/iommu/io-pgtable-arm.c | 12 | ||||
-rw-r--r-- | drivers/iommu/iommu-sysfs.c | 61 | ||||
-rw-r--r-- | drivers/iommu/iommu.c | 274 | ||||
-rw-r--r-- | drivers/iommu/iova.c | 25 | ||||
-rw-r--r-- | drivers/iommu/ipmmu-vmsa.c | 2 | ||||
-rw-r--r-- | drivers/iommu/msm_iommu.c | 73 | ||||
-rw-r--r-- | drivers/iommu/msm_iommu.h | 3 | ||||
-rw-r--r-- | drivers/iommu/mtk_iommu.c | 108 | ||||
-rw-r--r-- | drivers/iommu/mtk_iommu.h | 13 | ||||
-rw-r--r-- | drivers/iommu/mtk_iommu_v1.c | 105 | ||||
-rw-r--r-- | drivers/iommu/of_iommu.c | 43 | ||||
-rw-r--r-- | drivers/iommu/s390-iommu.c | 1 |
25 files changed, 1324 insertions, 547 deletions
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 8ee54d71c7eb..37e204f3d9be 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -352,9 +352,6 @@ config MTK_IOMMU_V1 select IOMMU_API select MEMORY select MTK_SMI - select COMMON_CLK_MT2701_MMSYS - select COMMON_CLK_MT2701_IMGSYS - select COMMON_CLK_MT2701_VDECSYS help Support for the M4U on certain Mediatek SoCs. M4U generation 1 HW is Multimedia Memory Managememt Unit. This option enables remapping of diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 754595ee11b6..1b5b8c5361c5 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -112,7 +112,7 @@ static struct timer_list queue_timer; * Domain for untranslated devices - only allocated * if iommu=pt passed on kernel cmd line. */ -static const struct iommu_ops amd_iommu_ops; +const struct iommu_ops amd_iommu_ops; static ATOMIC_NOTIFIER_HEAD(ppr_notifier); int amd_iommu_max_glx_val = -1; @@ -373,6 +373,8 @@ static struct iommu_group *acpihid_device_group(struct device *dev) if (!entry->group) entry->group = generic_device_group(dev); + else + iommu_group_ref_get(entry->group); return entry->group; } @@ -443,6 +445,7 @@ static void init_iommu_group(struct device *dev) static int iommu_init_device(struct device *dev) { struct iommu_dev_data *dev_data; + struct amd_iommu *iommu; int devid; if (dev->archdata.iommu) @@ -452,6 +455,8 @@ static int iommu_init_device(struct device *dev) if (devid < 0) return devid; + iommu = amd_iommu_rlookup_table[devid]; + dev_data = find_dev_data(devid); if (!dev_data) return -ENOMEM; @@ -467,8 +472,7 @@ static int iommu_init_device(struct device *dev) dev->archdata.iommu = dev_data; - iommu_device_link(amd_iommu_rlookup_table[dev_data->devid]->iommu_dev, - dev); + iommu_device_link(&iommu->iommu, dev); return 0; } @@ -493,13 +497,16 @@ static void iommu_ignore_device(struct device *dev) static void iommu_uninit_device(struct device *dev) { - int devid; struct iommu_dev_data *dev_data; + struct amd_iommu *iommu; + int devid; devid = get_device_id(dev); if (devid < 0) return; + iommu = amd_iommu_rlookup_table[devid]; + dev_data = search_dev_data(devid); if (!dev_data) return; @@ -507,8 +514,7 @@ static void iommu_uninit_device(struct device *dev) if (dev_data->domain) detach_device(dev); - iommu_device_unlink(amd_iommu_rlookup_table[dev_data->devid]->iommu_dev, - dev); + iommu_device_unlink(&iommu->iommu, dev); iommu_group_remove_device(dev); @@ -1021,7 +1027,7 @@ again: next_tail = (tail + sizeof(*cmd)) % CMD_BUFFER_SIZE; left = (head - next_tail) % CMD_BUFFER_SIZE; - if (left <= 2) { + if (left <= 0x20) { struct iommu_cmd sync_cmd; int ret; @@ -3159,9 +3165,10 @@ static bool amd_iommu_capable(enum iommu_cap cap) return false; } -static void amd_iommu_get_dm_regions(struct device *dev, - struct list_head *head) +static void amd_iommu_get_resv_regions(struct device *dev, + struct list_head *head) { + struct iommu_resv_region *region; struct unity_map_entry *entry; int devid; @@ -3170,41 +3177,56 @@ static void amd_iommu_get_dm_regions(struct device *dev, return; list_for_each_entry(entry, &amd_iommu_unity_map, list) { - struct iommu_dm_region *region; + size_t length; + int prot = 0; if (devid < entry->devid_start || devid > entry->devid_end) continue; - region = kzalloc(sizeof(*region), GFP_KERNEL); + length = entry->address_end - entry->address_start; + if (entry->prot & IOMMU_PROT_IR) + prot |= IOMMU_READ; + if (entry->prot & IOMMU_PROT_IW) + prot |= IOMMU_WRITE; + + region = iommu_alloc_resv_region(entry->address_start, + length, prot, + IOMMU_RESV_DIRECT); if (!region) { pr_err("Out of memory allocating dm-regions for %s\n", dev_name(dev)); return; } - - region->start = entry->address_start; - region->length = entry->address_end - entry->address_start; - if (entry->prot & IOMMU_PROT_IR) - region->prot |= IOMMU_READ; - if (entry->prot & IOMMU_PROT_IW) - region->prot |= IOMMU_WRITE; - list_add_tail(®ion->list, head); } + + region = iommu_alloc_resv_region(MSI_RANGE_START, + MSI_RANGE_END - MSI_RANGE_START + 1, + 0, IOMMU_RESV_RESERVED); + if (!region) + return; + list_add_tail(®ion->list, head); + + region = iommu_alloc_resv_region(HT_RANGE_START, + HT_RANGE_END - HT_RANGE_START + 1, + 0, IOMMU_RESV_RESERVED); + if (!region) + return; + list_add_tail(®ion->list, head); } -static void amd_iommu_put_dm_regions(struct device *dev, +static void amd_iommu_put_resv_regions(struct device *dev, struct list_head *head) { - struct iommu_dm_region *entry, *next; + struct iommu_resv_region *entry, *next; list_for_each_entry_safe(entry, next, head, list) kfree(entry); } -static void amd_iommu_apply_dm_region(struct device *dev, +static void amd_iommu_apply_resv_region(struct device *dev, struct iommu_domain *domain, - struct iommu_dm_region *region) + struct iommu_resv_region *region) { struct dma_ops_domain *dma_dom = to_dma_ops_domain(to_pdomain(domain)); unsigned long start, end; @@ -3215,7 +3237,7 @@ static void amd_iommu_apply_dm_region(struct device *dev, WARN_ON_ONCE(reserve_iova(&dma_dom->iovad, start, end) == NULL); } -static const struct iommu_ops amd_iommu_ops = { +const struct iommu_ops amd_iommu_ops = { .capable = amd_iommu_capable, .domain_alloc = amd_iommu_domain_alloc, .domain_free = amd_iommu_domain_free, @@ -3228,9 +3250,9 @@ static const struct iommu_ops amd_iommu_ops = { .add_device = amd_iommu_add_device, .remove_device = amd_iommu_remove_device, .device_group = amd_iommu_device_group, - .get_dm_regions = amd_iommu_get_dm_regions, - .put_dm_regions = amd_iommu_put_dm_regions, - .apply_dm_region = amd_iommu_apply_dm_region, + .get_resv_regions = amd_iommu_get_resv_regions, + .put_resv_regions = amd_iommu_put_resv_regions, + .apply_resv_region = amd_iommu_apply_resv_region, .pgsize_bitmap = AMD_IOMMU_PGSIZES, }; diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 157e93421fb8..04cdac7ab3e3 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -28,6 +28,7 @@ #include <linux/amd-iommu.h> #include <linux/export.h> #include <linux/iommu.h> +#include <linux/kmemleak.h> #include <asm/pci-direct.h> #include <asm/iommu.h> #include <asm/gart.h> @@ -93,6 +94,8 @@ * out of it. */ +extern const struct iommu_ops amd_iommu_ops; + /* * structure describing one IOMMU in the ACPI table. Typically followed by one * or more ivhd_entrys. @@ -1634,9 +1637,10 @@ static int iommu_init_pci(struct amd_iommu *iommu) amd_iommu_erratum_746_workaround(iommu); amd_iommu_ats_write_check_workaround(iommu); - iommu->iommu_dev = iommu_device_create(&iommu->dev->dev, iommu, - amd_iommu_groups, "ivhd%d", - iommu->index); + iommu_device_sysfs_add(&iommu->iommu, &iommu->dev->dev, + amd_iommu_groups, "ivhd%d", iommu->index); + iommu_device_set_ops(&iommu->iommu, &amd_iommu_ops); + iommu_device_register(&iommu->iommu); return pci_enable_device(iommu->dev); } @@ -2090,6 +2094,7 @@ static struct syscore_ops amd_iommu_syscore_ops = { static void __init free_on_init_error(void) { + kmemleak_free(irq_lookup_table); free_pages((unsigned long)irq_lookup_table, get_order(rlookup_table_size)); @@ -2207,14 +2212,13 @@ static void __init free_dma_resources(void) static int __init early_amd_iommu_init(void) { struct acpi_table_header *ivrs_base; - acpi_size ivrs_size; acpi_status status; int i, remap_cache_sz, ret = 0; if (!amd_iommu_detected) return -ENODEV; - status = acpi_get_table_with_size("IVRS", 0, &ivrs_base, &ivrs_size); + status = acpi_get_table("IVRS", 0, &ivrs_base); if (status == AE_NOT_FOUND) return -ENODEV; else if (ACPI_FAILURE(status)) { @@ -2229,7 +2233,7 @@ static int __init early_amd_iommu_init(void) */ ret = check_ivrs_checksum(ivrs_base); if (ret) - return ret; + goto out; amd_iommu_target_ivhd_type = get_highest_supported_ivhd_type(ivrs_base); DUMP_printk("Using IVHD type %#x\n", amd_iommu_target_ivhd_type); @@ -2321,6 +2325,8 @@ static int __init early_amd_iommu_init(void) irq_lookup_table = (void *)__get_free_pages( GFP_KERNEL | __GFP_ZERO, get_order(rlookup_table_size)); + kmemleak_alloc(irq_lookup_table, rlookup_table_size, + 1, GFP_KERNEL); if (!irq_lookup_table) goto out; } @@ -2334,7 +2340,7 @@ static int __init early_amd_iommu_init(void) out: /* Don't leak any ACPI memory */ - early_acpi_os_unmap_memory((char __iomem *)ivrs_base, ivrs_size); + acpi_put_table(ivrs_base); ivrs_base = NULL; return ret; @@ -2358,10 +2364,9 @@ out: static bool detect_ivrs(void) { struct acpi_table_header *ivrs_base; - acpi_size ivrs_size; acpi_status status; - status = acpi_get_table_with_size("IVRS", 0, &ivrs_base, &ivrs_size); + status = acpi_get_table("IVRS", 0, &ivrs_base); if (status == AE_NOT_FOUND) return false; else if (ACPI_FAILURE(status)) { @@ -2370,7 +2375,7 @@ static bool detect_ivrs(void) return false; } - early_acpi_os_unmap_memory((char __iomem *)ivrs_base, ivrs_size); + acpi_put_table(ivrs_base); /* Make sure ACS will be enabled during PCI probe */ pci_request_acs(); diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index 0d91785ebdc3..af00f381a7b1 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -535,8 +535,8 @@ struct amd_iommu { /* if one, we need to send a completion wait command */ bool need_sync; - /* IOMMU sysfs device */ - struct device *iommu_dev; + /* Handle for IOMMU core code */ + struct iommu_device iommu; /* * We can't rely on the BIOS to restore all values on reinit, so we diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c index 594849a3a9be..f8ed8c95b685 100644 --- a/drivers/iommu/amd_iommu_v2.c +++ b/drivers/iommu/amd_iommu_v2.c @@ -805,8 +805,10 @@ int amd_iommu_init_device(struct pci_dev *pdev, int pasids) goto out_free_domain; group = iommu_group_get(&pdev->dev); - if (!group) + if (!group) { + ret = -EINVAL; goto out_free_domain; + } ret = iommu_attach_group(dev_state->domain, group); if (ret != 0) diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 15c01c3cd540..5806a6acc94e 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -20,6 +20,8 @@ * This driver is powered by bad coffee and bombay mix. */ +#include <linux/acpi.h> +#include <linux/acpi_iort.h> #include <linux/delay.h> #include <linux/dma-iommu.h> #include <linux/err.h> @@ -267,9 +269,6 @@ #define STRTAB_STE_1_SHCFG_INCOMING 1UL #define STRTAB_STE_1_SHCFG_SHIFT 44 -#define STRTAB_STE_1_PRIVCFG_UNPRIV 2UL -#define STRTAB_STE_1_PRIVCFG_SHIFT 48 - #define STRTAB_STE_2_S2VMID_SHIFT 0 #define STRTAB_STE_2_S2VMID_MASK 0xffffUL #define STRTAB_STE_2_VTCR_SHIFT 32 @@ -410,6 +409,9 @@ /* High-level queue structures */ #define ARM_SMMU_POLL_TIMEOUT_US 100 +#define MSI_IOVA_BASE 0x8000000 +#define MSI_IOVA_LENGTH 0x100000 + static bool disable_bypass; module_param_named(disable_bypass, disable_bypass, bool, S_IRUGO); MODULE_PARM_DESC(disable_bypass, @@ -614,6 +616,9 @@ struct arm_smmu_device { unsigned int sid_bits; struct arm_smmu_strtab_cfg strtab_cfg; + + /* IOMMU core code handle */ + struct iommu_device iommu; }; /* SMMU private data for each master */ @@ -1040,13 +1045,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, } } - /* Nuke the existing Config, as we're going to rewrite it */ - val &= ~(STRTAB_STE_0_CFG_MASK << STRTAB_STE_0_CFG_SHIFT); - - if (ste->valid) - val |= STRTAB_STE_0_V; - else - val &= ~STRTAB_STE_0_V; + /* Nuke the existing STE_0 value, as we're going to rewrite it */ + val = ste->valid ? STRTAB_STE_0_V : 0; if (ste->bypass) { val |= disable_bypass ? STRTAB_STE_0_CFG_ABORT @@ -1071,9 +1071,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, #ifdef CONFIG_PCI_ATS STRTAB_STE_1_EATS_TRANS << STRTAB_STE_1_EATS_SHIFT | #endif - STRTAB_STE_1_STRW_NSEL1 << STRTAB_STE_1_STRW_SHIFT | - STRTAB_STE_1_PRIVCFG_UNPRIV << - STRTAB_STE_1_PRIVCFG_SHIFT); + STRTAB_STE_1_STRW_NSEL1 << STRTAB_STE_1_STRW_SHIFT); if (smmu->features & ARM_SMMU_FEAT_STALLS) dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD); @@ -1081,7 +1079,6 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, val |= (ste->s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK << STRTAB_STE_0_S1CTXPTR_SHIFT) | STRTAB_STE_0_CFG_S1_TRANS; - } if (ste->s2_cfg) { @@ -1358,7 +1355,7 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size, } while (size -= granule); } -static struct iommu_gather_ops arm_smmu_gather_ops = { +static const struct iommu_gather_ops arm_smmu_gather_ops = { .tlb_flush_all = arm_smmu_tlb_inv_context, .tlb_add_flush = arm_smmu_tlb_inv_range_nosync, .tlb_sync = arm_smmu_tlb_sync, @@ -1370,8 +1367,6 @@ static bool arm_smmu_capable(enum iommu_cap cap) switch (cap) { case IOMMU_CAP_CACHE_COHERENCY: return true; - case IOMMU_CAP_INTR_REMAP: - return true; /* MSIs are just memory writes */ case IOMMU_CAP_NOEXEC: return true; default: @@ -1723,13 +1718,14 @@ static struct platform_driver arm_smmu_driver; static int arm_smmu_match_node(struct device *dev, void *data) { - return dev->of_node == data; + return dev->fwnode == data; } -static struct arm_smmu_device *arm_smmu_get_by_node(struct device_node *np) +static +struct arm_smmu_device *arm_smmu_get_by_fwnode(struct fwnode_handle *fwnode) { struct device *dev = driver_find_device(&arm_smmu_driver.driver, NULL, - np, arm_smmu_match_node); + fwnode, arm_smmu_match_node); put_device(dev); return dev ? dev_get_drvdata(dev) : NULL; } @@ -1765,7 +1761,7 @@ static int arm_smmu_add_device(struct device *dev) master = fwspec->iommu_priv; smmu = master->smmu; } else { - smmu = arm_smmu_get_by_node(to_of_node(fwspec->iommu_fwnode)); + smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode); if (!smmu) return -ENODEV; master = kzalloc(sizeof(*master), GFP_KERNEL); @@ -1792,8 +1788,10 @@ static int arm_smmu_add_device(struct device *dev) } group = iommu_group_get_for_dev(dev); - if (!IS_ERR(group)) + if (!IS_ERR(group)) { iommu_group_put(group); + iommu_device_link(&smmu->iommu, dev); + } return PTR_ERR_OR_ZERO(group); } @@ -1802,14 +1800,17 @@ static void arm_smmu_remove_device(struct device *dev) { struct iommu_fwspec *fwspec = dev->iommu_fwspec; struct arm_smmu_master_data *master; + struct arm_smmu_device *smmu; if (!fwspec || fwspec->ops != &arm_smmu_ops) return; master = fwspec->iommu_priv; + smmu = master->smmu; if (master && master->ste.valid) arm_smmu_detach_dev(dev); iommu_group_remove_device(dev); + iommu_device_unlink(&smmu->iommu, dev); kfree(master); iommu_fwspec_free(dev); } @@ -1880,6 +1881,29 @@ static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args) return iommu_fwspec_add_ids(dev, args->args, 1); } +static void arm_smmu_get_resv_regions(struct device *dev, + struct list_head *head) +{ + struct iommu_resv_region *region; + int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO; + + region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH, + prot, IOMMU_RESV_MSI); + if (!region) + return; + + list_add_tail(®ion->list, head); +} + +static void arm_smmu_put_resv_regions(struct device *dev, + struct list_head *head) +{ + struct iommu_resv_region *entry, *next; + + list_for_each_entry_safe(entry, next, head, list) + kfree(entry); +} + static struct iommu_ops arm_smmu_ops = { .capable = arm_smmu_capable, .domain_alloc = arm_smmu_domain_alloc, @@ -1895,6 +1919,8 @@ static struct iommu_ops arm_smmu_ops = { .domain_get_attr = arm_smmu_domain_get_attr, .domain_set_attr = arm_smmu_domain_set_attr, .of_xlate = arm_smmu_of_xlate, + .get_resv_regions = arm_smmu_get_resv_regions, + .put_resv_regions = arm_smmu_put_resv_regions, .pgsize_bitmap = -1UL, /* Restricted during device attach */ }; @@ -1980,17 +2006,9 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu) u32 size, l1size; struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg; - /* - * If we can resolve everything with a single L2 table, then we - * just need a single L1 descriptor. Otherwise, calculate the L1 - * size, capped to the SIDSIZE. - */ - if (smmu->sid_bits < STRTAB_SPLIT) { - size = 0; - } else { - size = STRTAB_L1_SZ_SHIFT - (ilog2(STRTAB_L1_DESC_DWORDS) + 3); - size = min(size, smmu->sid_bits - STRTAB_SPLIT); - } + /* Calculate the L1 size, capped to the SIDSIZE. */ + size = STRTAB_L1_SZ_SHIFT - (ilog2(STRTAB_L1_DESC_DWORDS) + 3); + size = min(size, smmu->sid_bits - STRTAB_SPLIT); cfg->num_l1_ents = 1 << size; size += STRTAB_SPLIT; @@ -2380,10 +2398,10 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass) return 0; } -static int arm_smmu_device_probe(struct arm_smmu_device *smmu) +static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) { u32 reg; - bool coherent; + bool coherent = smmu->features & ARM_SMMU_FEAT_COHERENCY; /* IDR0 */ reg = readl_relaxed(smmu->base + ARM_SMMU_IDR0); @@ -2435,13 +2453,9 @@ static int arm_smmu_device_probe(struct arm_smmu_device *smmu) smmu->features |= ARM_SMMU_FEAT_HYP; /* - * The dma-coherent property is used in preference to the ID + * The coherency feature as set by FW is used in preference to the ID * register, but warn on mismatch. */ - coherent = of_dma_is_coherent(smmu->dev->of_node); - if (coherent) - smmu->features |= ARM_SMMU_FEAT_COHERENCY; - if (!!(reg & IDR0_COHACC) != coherent) dev_warn(smmu->dev, "IDR0.COHACC overridden by dma-coherent property (%s)\n", coherent ? "true" : "false"); @@ -2505,6 +2519,13 @@ static int arm_smmu_device_probe(struct arm_smmu_device *smmu) smmu->ssid_bits = reg >> IDR1_SSID_SHIFT & IDR1_SSID_MASK; smmu->sid_bits = reg >> IDR1_SID_SHIFT & IDR1_SID_MASK; + /* + * If the SMMU supports fewer bits than would fill a single L2 stream + * table, use a linear table instead. + */ + if (smmu->sid_bits <= STRTAB_SPLIT) + smmu->features &= ~ARM_SMMU_FEAT_2_LVL_STRTAB; + /* IDR5 */ reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5); @@ -2562,21 +2583,62 @@ static int arm_smmu_device_probe(struct arm_smmu_device *smmu) return 0; } -static int arm_smmu_device_dt_probe(struct platform_device *pdev) +#ifdef CONFIG_ACPI +static int arm_smmu_device_acpi_probe(struct platform_device *pdev, + struct arm_smmu_device *smmu) +{ + struct acpi_iort_smmu_v3 *iort_smmu; + struct device *dev = smmu->dev; + struct acpi_iort_node *node; + + node = *(struct acpi_iort_node **)dev_get_platdata(dev); + + /* Retrieve SMMUv3 specific data */ + iort_smmu = (struct acpi_iort_smmu_v3 *)node->node_data; + + if (iort_smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE) + smmu->features |= ARM_SMMU_FEAT_COHERENCY; + + return 0; +} +#else +static inline int arm_smmu_device_acpi_probe(struct platform_device *pdev, + struct arm_smmu_device *smmu) +{ + return -ENODEV; +} +#endif + +static int arm_smmu_device_dt_probe(struct platform_device *pdev, + struct arm_smmu_device *smmu) { - int irq, ret; - struct resource *res; - struct arm_smmu_device *smmu; struct device *dev = &pdev->dev; - bool bypass = true; u32 cells; + int ret = -EINVAL; if (of_property_read_u32(dev->of_node, "#iommu-cells", &cells)) dev_err(dev, "missing #iommu-cells property\n"); else if (cells != 1) dev_err(dev, "invalid #iommu-cells value (%d)\n", cells); else - bypass = false; + ret = 0; + + parse_driver_options(smmu); + + if (of_dma_is_coherent(dev->of_node)) + smmu->features |= ARM_SMMU_FEAT_COHERENCY; + + return ret; +} + +static int arm_smmu_device_probe(struct platform_device *pdev) +{ + int irq, ret; + struct resource *res; + resource_size_t ioaddr; + struct arm_smmu_device *smmu; + struct device *dev = &pdev->dev; + bool bypass; smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL); if (!smmu) { @@ -2591,6 +2653,7 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev) dev_err(dev, "MMIO region too small (%pr)\n", res); return -EINVAL; } + ioaddr = res->start; smmu->base = devm_ioremap_resource(dev, res); if (IS_ERR(smmu->base)) @@ -2613,10 +2676,19 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev) if (irq > 0) smmu->gerr_irq = irq; - parse_driver_options(smmu); + if (dev->of_node) { + ret = arm_smmu_device_dt_probe(pdev, smmu); + } else { + ret = arm_smmu_device_acpi_probe(pdev, smmu); + if (ret == -ENODEV) + return ret; + } + + /* Set bypass mode according to firmware probing result */ + bypass = !!ret; /* Probe the h/w */ - ret = arm_smmu_device_probe(smmu); + ret = arm_smmu_device_hw_probe(smmu); if (ret) return ret; @@ -2634,19 +2706,37 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev) return ret; /* And we're up. Go go go! */ - of_iommu_set_ops(dev->of_node, &arm_smmu_ops); -#ifdef CONFIG_PCI - pci_request_acs(); - ret = bus_set_iommu(&pci_bus_type, &arm_smmu_ops); + ret = iommu_device_sysfs_add(&smmu->iommu, dev, NULL, + "smmu3.%pa", &ioaddr); if (ret) return ret; + + iommu_device_set_ops(&smmu->iommu, &arm_smmu_ops); + iommu_device_set_fwnode(&smmu->iommu, dev->fwnode); + + ret = iommu_device_register(&smmu->iommu); + +#ifdef CONFIG_PCI + if (pci_bus_type.iommu_ops != &arm_smmu_ops) { + pci_request_acs(); + ret = bus_set_iommu(&pci_bus_type, &arm_smmu_ops); + if (ret) + return ret; + } #endif #ifdef CONFIG_ARM_AMBA - ret = bus_set_iommu(&amba_bustype, &arm_smmu_ops); - if (ret) - return ret; + if (amba_bustype.iommu_ops != &arm_smmu_ops) { + ret = bus_set_iommu(&amba_bustype, &arm_smmu_ops); + if (ret) + return ret; + } #endif - return bus_set_iommu(&platform_bus_type, &arm_smmu_ops); + if (platform_bus_type.iommu_ops != &arm_smmu_ops) { + ret = bus_set_iommu(&platform_bus_type, &arm_smmu_ops); + if (ret) + return ret; + } + return 0; } static int arm_smmu_device_remove(struct platform_device *pdev) @@ -2668,7 +2758,7 @@ static struct platform_driver arm_smmu_driver = { .name = "arm-smmu-v3", .of_match_table = of_match_ptr(arm_smmu_of_match), }, - .probe = arm_smmu_device_dt_probe, + .probe = arm_smmu_device_probe, .remove = arm_smmu_device_remove, }; @@ -2706,6 +2796,17 @@ static int __init arm_smmu_of_init(struct device_node *np) } IOMMU_OF_DECLARE(arm_smmuv3, "arm,smmu-v3", arm_smmu_of_init); +#ifdef CONFIG_ACPI +static int __init acpi_smmu_v3_init(struct acpi_table_header *table) +{ + if (iort_node_match(ACPI_IORT_NODE_SMMU_V3)) + return arm_smmu_init(); + + return 0; +} +IORT_ACPI_DECLARE(arm_smmu_v3, ACPI_SIG_IORT, acpi_smmu_v3_init); +#endif + MODULE_DESCRIPTION("IOMMU API for ARM architected SMMUv3 implementations"); MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index c841eb7a1a74..abf6496843a6 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -24,10 +24,13 @@ * - v7/v8 long-descriptor format * - Non-secure access to the SMMU * - Context fault reporting + * - Extended Stream ID (16 bit) */ #define pr_fmt(fmt) "arm-smmu: " fmt +#include <linux/acpi.h> +#include <linux/acpi_iort.h> #include <linux/atomic.h> #include <linux/delay.h> #include <linux/dma-iommu.h> @@ -85,6 +88,7 @@ #define sCR0_CLIENTPD (1 << 0) #define sCR0_GFRE (1 << 1) #define sCR0_GFIE (1 << 2) +#define sCR0_EXIDENABLE (1 << 3) #define sCR0_GCFGFRE (1 << 4) #define sCR0_GCFGFIE (1 << 5) #define sCR0_USFCFG (1 << 10) @@ -124,6 +128,7 @@ #define ID0_NUMIRPT_MASK 0xff #define ID0_NUMSIDB_SHIFT 9 #define ID0_NUMSIDB_MASK 0xf +#define ID0_EXIDS (1 << 8) #define ID0_NUMSMRG_SHIFT 0 #define ID0_NUMSMRG_MASK 0xff @@ -167,6 +172,7 @@ #define ARM_SMMU_GR0_S2CR(n) (0xc00 + ((n) << 2)) #define S2CR_CBNDX_SHIFT 0 #define S2CR_CBNDX_MASK 0xff +#define S2CR_EXIDVALID (1 << 10) #define S2CR_TYPE_SHIFT 16 #define S2CR_TYPE_MASK 0x3 enum arm_smmu_s2cr_type { @@ -247,6 +253,7 @@ enum arm_smmu_s2cr_privcfg { #define ARM_MMU500_ACTLR_CPRE (1 << 1) #define ARM_MMU500_ACR_CACHE_LOCK (1 << 26) +#define ARM_MMU500_ACR_SMTNMB_TLBEN (1 << 8) #define CB_PAR_F (1 << 0) @@ -257,6 +264,7 @@ enum arm_smmu_s2cr_privcfg { #define TTBCR2_SEP_SHIFT 15 #define TTBCR2_SEP_UPSTREAM (0x7 << TTBCR2_SEP_SHIFT) +#define TTBCR2_AS (1 << 4) #define TTBRn_ASID_SHIFT 48 @@ -278,6 +286,9 @@ enum arm_smmu_s2cr_privcfg { #define FSYNR0_WNR (1 << 4) +#define MSI_IOVA_BASE 0x8000000 +#define MSI_IOVA_LENGTH 0x100000 + static int force_stage; module_param(force_stage, int, S_IRUGO); MODULE_PARM_DESC(force_stage, @@ -324,8 +335,10 @@ struct arm_smmu_master_cfg { #define INVALID_SMENDX -1 #define __fwspec_cfg(fw) ((struct arm_smmu_master_cfg *)fw->iommu_priv) #define fwspec_smmu(fw) (__fwspec_cfg(fw)->smmu) +#define fwspec_smendx(fw, i) \ + (i >= fw->num_ids ? INVALID_SMENDX : __fwspec_cfg(fw)->smendx[i]) #define for_each_cfg_sme(fw, i, idx) \ - for (i = 0; idx = __fwspec_cfg(fw)->smendx[i], i < fw->num_ids; ++i) + for (i = 0; idx = fwspec_smendx(fw, i), i < fw->num_ids; ++i) struct arm_smmu_device { struct device *dev; @@ -346,6 +359,7 @@ struct arm_smmu_device { #define ARM_SMMU_FEAT_FMT_AARCH64_64K (1 << 9) #define ARM_SMMU_FEAT_FMT_AARCH32_L (1 << 10) #define ARM_SMMU_FEAT_FMT_AARCH32_S (1 << 11) +#define ARM_SMMU_FEAT_EXIDS (1 << 12) u32 features; #define ARM_SMMU_OPT_SECURE_CFG_ACCESS (1 << 0) @@ -375,6 +389,9 @@ struct arm_smmu_device { unsigned int *irqs; u32 cavium_id_base; /* Specific to Cavium */ + + /* IOMMU core code handle */ + struct iommu_device iommu; }; enum arm_smmu_context_fmt { @@ -640,7 +657,7 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size, } } -static struct iommu_gather_ops arm_smmu_gather_ops = { +static const struct iommu_gather_ops arm_smmu_gather_ops = { .tlb_flush_all = arm_smmu_tlb_inv_context, .tlb_add_flush = arm_smmu_tlb_inv_range_nosync, .tlb_sync = arm_smmu_tlb_sync, @@ -773,6 +790,8 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain, reg = pgtbl_cfg->arm_lpae_s1_cfg.tcr; reg2 = pgtbl_cfg->arm_lpae_s1_cfg.tcr >> 32; reg2 |= TTBCR2_SEP_UPSTREAM; + if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64) + reg2 |= TTBCR2_AS; } if (smmu->version > ARM_SMMU_V1) writel_relaxed(reg2, cb_base + ARM_SMMU_CB_TTBCR2); @@ -1043,7 +1062,7 @@ static void arm_smmu_write_smr(struct arm_smmu_device *smmu, int idx) struct arm_smmu_smr *smr = smmu->smrs + idx; u32 reg = smr->id << SMR_ID_SHIFT | smr->mask << SMR_MASK_SHIFT; - if (smr->valid) + if (!(smmu->features & ARM_SMMU_FEAT_EXIDS) && smr->valid) reg |= SMR_VALID; writel_relaxed(reg, ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_SMR(idx)); } @@ -1055,6 +1074,9 @@ static void arm_smmu_write_s2cr(struct arm_smmu_device *smmu, int idx) (s2cr->cbndx & S2CR_CBNDX_MASK) << S2CR_CBNDX_SHIFT | (s2cr->privcfg & S2CR_PRIVCFG_MASK) << S2CR_PRIVCFG_SHIFT; + if (smmu->features & ARM_SMMU_FEAT_EXIDS && smmu->smrs && + smmu->smrs[idx].valid) + reg |= S2CR_EXIDVALID; writel_relaxed(reg, ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_S2CR(idx)); } @@ -1065,6 +1087,34 @@ static void arm_smmu_write_sme(struct arm_smmu_device *smmu, int idx) arm_smmu_write_smr(smmu, idx); } +/* + * The width of SMR's mask field depends on sCR0_EXIDENABLE, so this function + * should be called after sCR0 is written. + */ +static void arm_smmu_test_smr_masks(struct arm_smmu_device *smmu) +{ + void __iomem *gr0_base = ARM_SMMU_GR0(smmu); + u32 smr; + + if (!smmu->smrs) + return; + + /* + * SMR.ID bits may not be preserved if the corresponding MASK + * bits are set, so check each one separately. We can reject + * masters later if they try to claim IDs outside these masks. + */ + smr = smmu->streamid_mask << SMR_ID_SHIFT; + writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0)); + smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0)); + smmu->streamid_mask = smr >> SMR_ID_SHIFT; + + smr = smmu->streamid_mask << SMR_MASK_SHIFT; + writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0)); + smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0)); + smmu->smr_mask_mask = smr >> SMR_MASK_SHIFT; +} + static int arm_smmu_find_sme(struct arm_smmu_device *smmu, u16 id, u16 mask) { struct arm_smmu_smr *smrs = smmu->smrs; @@ -1209,7 +1259,7 @@ static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain, continue; s2cr[idx].type = type; - s2cr[idx].privcfg = S2CR_PRIVCFG_UNPRIV; + s2cr[idx].privcfg = S2CR_PRIVCFG_DEFAULT; s2cr[idx].cbndx = cbndx; arm_smmu_write_s2cr(smmu, idx); } @@ -1228,6 +1278,16 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) return -ENXIO; } + /* + * FIXME: The arch/arm DMA API code tries to attach devices to its own + * domains between of_xlate() and add_device() - we have no way to cope + * with that, so until ARM gets converted to rely on groups and default + * domains, just say no (but more politely than by dereferencing NULL). + * This should be at least a WARN_ON once that's sorted. + */ + if (!fwspec->iommu_priv) + return -ENODEV; + smmu = fwspec_smmu(fwspec); /* Ensure that the domain is finalised */ ret = arm_smmu_init_domain_context(domain, smmu); @@ -1356,8 +1416,6 @@ static bool arm_smmu_capable(enum iommu_cap cap) * requests. */ return true; - case IOMMU_CAP_INTR_REMAP: - return true; /* MSIs are just memory writes */ case IOMMU_CAP_NOEXEC: return true; default: @@ -1367,13 +1425,14 @@ static bool arm_smmu_capable(enum iommu_cap cap) static int arm_smmu_match_node(struct device *dev, void *data) { - return dev->of_node == data; + return dev->fwnode == data; } -static struct arm_smmu_device *arm_smmu_get_by_node(struct device_node *np) +static +struct arm_smmu_device *arm_smmu_get_by_fwnode(struct fwnode_handle *fwnode) { struct device *dev = driver_find_device(&arm_smmu_driver.driver, NULL, - np, arm_smmu_match_node); + fwnode, arm_smmu_match_node); put_device(dev); return dev ? dev_get_drvdata(dev) : NULL; } @@ -1390,8 +1449,8 @@ static int arm_smmu_add_device(struct device *dev) fwspec = dev->iommu_fwspec; if (ret) goto out_free; - } else if (fwspec) { - smmu = arm_smmu_get_by_node(to_of_node(fwspec->iommu_fwnode)); + } else if (fwspec && fwspec->ops == &arm_smmu_ops) { + smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode); } else { return -ENODEV; } @@ -1428,6 +1487,8 @@ static int arm_smmu_add_device(struct device *dev) if (ret) goto out_free; + iommu_device_link(&smmu->iommu, dev); + return 0; out_free: @@ -1440,10 +1501,17 @@ out_free: static void arm_smmu_remove_device(struct device *dev) { struct iommu_fwspec *fwspec = dev->iommu_fwspec; + struct arm_smmu_master_cfg *cfg; + struct arm_smmu_device *smmu; + if (!fwspec || fwspec->ops != &arm_smmu_ops) return; + cfg = fwspec->iommu_priv; + smmu = cfg->smmu; + + iommu_device_unlink(&smmu->iommu, dev); arm_smmu_master_free_smes(fwspec); iommu_group_remove_device(dev); kfree(fwspec->iommu_priv); @@ -1466,7 +1534,7 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev) } if (group) - return group; + return iommu_group_ref_get(group); if (dev_is_pci(dev)) group = pci_device_group(dev); @@ -1533,6 +1601,29 @@ static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args) return iommu_fwspec_add_ids(dev, &fwid, 1); } +static void arm_smmu_get_resv_regions(struct device *dev, + struct list_head *head) +{ + struct iommu_resv_region *region; + int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO; + + region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH, + prot, IOMMU_RESV_MSI); + if (!region) + return; + + list_add_tail(®ion->list, head); +} + +static void arm_smmu_put_resv_regions(struct device *dev, + struct list_head *head) +{ + struct iommu_resv_region *entry, *next; + + list_for_each_entry_safe(entry, next, head, list) + kfree(entry); +} + static struct iommu_ops arm_smmu_ops = { .capable = arm_smmu_capable, .domain_alloc = arm_smmu_domain_alloc, @@ -1548,6 +1639,8 @@ static struct iommu_ops arm_smmu_ops = { .domain_get_attr = arm_smmu_domain_get_attr, .domain_set_attr = arm_smmu_domain_set_attr, .of_xlate = arm_smmu_of_xlate, + .get_resv_regions = arm_smmu_get_resv_regions, + .put_resv_regions = arm_smmu_put_resv_regions, .pgsize_bitmap = -1UL, /* Restricted during device attach */ }; @@ -1569,16 +1662,22 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu) for (i = 0; i < smmu->num_mapping_groups; ++i) arm_smmu_write_sme(smmu, i); - /* - * Before clearing ARM_MMU500_ACTLR_CPRE, need to - * clear CACHE_LOCK bit of ACR first. And, CACHE_LOCK - * bit is only present in MMU-500r2 onwards. - */ - reg = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID7); - major = (reg >> ID7_MAJOR_SHIFT) & ID7_MAJOR_MASK; - if ((smmu->model == ARM_MMU500) && (major >= 2)) { + if (smmu->model == ARM_MMU500) { + /* + * Before clearing ARM_MMU500_ACTLR_CPRE, need to + * clear CACHE_LOCK bit of ACR first. And, CACHE_LOCK + * bit is only present in MMU-500r2 onwards. + */ + reg = readl_relaxed(gr0_base + ARM_SMMU_GR0_ID7); + major = (reg >> ID7_MAJOR_SHIFT) & ID7_MAJOR_MASK; reg = readl_relaxed(gr0_base + ARM_SMMU_GR0_sACR); - reg &= ~ARM_MMU500_ACR_CACHE_LOCK; + if (major >= 2) + reg &= ~ARM_MMU500_ACR_CACHE_LOCK; + /* + * Allow unmatched Stream IDs to allocate bypass + * TLB entries for reduced latency. + */ + reg |= ARM_MMU500_ACR_SMTNMB_TLBEN; writel_relaxed(reg, gr0_base + ARM_SMMU_GR0_sACR); } @@ -1626,6 +1725,9 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu) if (smmu->features & ARM_SMMU_FEAT_VMID16) reg |= sCR0_VMID16EN; + if (smmu->features & ARM_SMMU_FEAT_EXIDS) + reg |= sCR0_EXIDENABLE; + /* Push the button */ __arm_smmu_tlb_sync(smmu); writel(reg, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0); @@ -1655,7 +1757,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu) unsigned long size; void __iomem *gr0_base = ARM_SMMU_GR0(smmu); u32 id; - bool cttw_dt, cttw_reg; + bool cttw_reg, cttw_fw = smmu->features & ARM_SMMU_FEAT_COHERENT_WALK; int i; dev_notice(smmu->dev, "probing hardware configuration...\n"); @@ -1700,27 +1802,27 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu) /* * In order for DMA API calls to work properly, we must defer to what - * the DT says about coherency, regardless of what the hardware claims. + * the FW says about coherency, regardless of what the hardware claims. * Fortunately, this also opens up a workaround for systems where the * ID register value has ended up configured incorrectly. */ - cttw_dt = of_dma_is_coherent(smmu->dev->of_node); cttw_reg = !!(id & ID0_CTTW); - if (cttw_dt) - smmu->features |= ARM_SMMU_FEAT_COHERENT_WALK; - if (cttw_dt || cttw_reg) + if (cttw_fw || cttw_reg) dev_notice(smmu->dev, "\t%scoherent table walk\n", - cttw_dt ? "" : "non-"); - if (cttw_dt != cttw_reg) + cttw_fw ? "" : "non-"); + if (cttw_fw != cttw_reg) dev_notice(smmu->dev, - "\t(IDR0.CTTW overridden by dma-coherent property)\n"); + "\t(IDR0.CTTW overridden by FW configuration)\n"); /* Max. number of entries we have for stream matching/indexing */ - size = 1 << ((id >> ID0_NUMSIDB_SHIFT) & ID0_NUMSIDB_MASK); + if (smmu->version == ARM_SMMU_V2 && id & ID0_EXIDS) { + smmu->features |= ARM_SMMU_FEAT_EXIDS; + size = 1 << 16; + } else { + size = 1 << ((id >> ID0_NUMSIDB_SHIFT) & ID0_NUMSIDB_MASK); + } smmu->streamid_mask = size - 1; if (id & ID0_SMS) { - u32 smr; - smmu->features |= ARM_SMMU_FEAT_STREAM_MATCH; size = (id >> ID0_NUMSMRG_SHIFT) & ID0_NUMSMRG_MASK; if (size == 0) { @@ -1729,21 +1831,6 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu) return -ENODEV; } - /* - * SMR.ID bits may not be preserved if the corresponding MASK - * bits are set, so check each one separately. We can reject - * masters later if they try to claim IDs outside these masks. - */ - smr = smmu->streamid_mask << SMR_ID_SHIFT; - writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0)); - smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0)); - smmu->streamid_mask = smr >> SMR_ID_SHIFT; - - smr = smmu->streamid_mask << SMR_MASK_SHIFT; - writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0)); - smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0)); - smmu->smr_mask_mask = smr >> SMR_MASK_SHIFT; - /* Zero-initialised to mark as invalid */ smmu->smrs = devm_kcalloc(smmu->dev, size, sizeof(*smmu->smrs), GFP_KERNEL); @@ -1751,8 +1838,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu) return -ENOMEM; dev_notice(smmu->dev, - "\tstream matching with %lu register groups, mask 0x%x", - size, smmu->smr_mask_mask); + "\tstream matching with %lu register groups", size); } /* s2cr->type == 0 means translation, so initialise explicitly */ smmu->s2crs = devm_kmalloc_array(smmu->dev, size, sizeof(*smmu->s2crs), @@ -1894,15 +1980,83 @@ static const struct of_device_id arm_smmu_of_match[] = { }; MODULE_DEVICE_TABLE(of, arm_smmu_of_match); -static int arm_smmu_device_dt_probe(struct platform_device *pdev) +#ifdef CONFIG_ACPI +static int acpi_smmu_get_data(u32 model, struct arm_smmu_device *smmu) +{ + int ret = 0; + + switch (model) { + case ACPI_IORT_SMMU_V1: + case ACPI_IORT_SMMU_CORELINK_MMU400: + smmu->version = ARM_SMMU_V1; + smmu->model = GENERIC_SMMU; + break; + case ACPI_IORT_SMMU_V2: + smmu->version = ARM_SMMU_V2; + smmu->model = GENERIC_SMMU; + break; + case ACPI_IORT_SMMU_CORELINK_MMU500: + smmu->version = ARM_SMMU_V2; + smmu->model = ARM_MMU500; + break; + default: + ret = -ENODEV; + } + + return ret; +} + +static int arm_smmu_device_acpi_probe(struct platform_device *pdev, + struct arm_smmu_device *smmu) +{ + struct device *dev = smmu->dev; + struct acpi_iort_node *node = + *(struct acpi_iort_node **)dev_get_platdata(dev); + struct acpi_iort_smmu *iort_smmu; + int ret; + + /* Retrieve SMMU1/2 specific data */ + iort_smmu = (struct acpi_iort_smmu *)node->node_data; + + ret = acpi_smmu_get_data(iort_smmu->model, smmu); + if (ret < 0) + return ret; + + /* Ignore the configuration access interrupt */ + smmu->num_global_irqs = 1; + + if (iort_smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK) + smmu->features |= ARM_SMMU_FEAT_COHERENT_WALK; + + return 0; +} +#else +static inline int arm_smmu_device_acpi_probe(struct platform_device *pdev, + struct arm_smmu_device *smmu) +{ + return -ENODEV; +} +#endif + +static int arm_smmu_device_dt_probe(struct platform_device *pdev, + struct arm_smmu_device *smmu) { const struct arm_smmu_match_data *data; - struct resource *res; - struct arm_smmu_device *smmu; struct device *dev = &pdev->dev; - int num_irqs, i, err; bool legacy_binding; + if (of_property_read_u32(dev->of_node, "#global-interrupts", + &smmu->num_global_irqs)) { + dev_err(dev, "missing #global-interrupts property\n"); + return -ENODEV; + } + + data = of_device_get_match_data(dev); + smmu->version = data->version; + smmu->model = data->model; + + parse_driver_options(smmu); + legacy_binding = of_find_property(dev->of_node, "mmu-masters", NULL); if (legacy_binding && !using_generic_binding) { if (!using_legacy_binding) @@ -1915,6 +2069,20 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev) return -ENODEV; } + if (of_dma_is_coherent(dev->of_node)) + smmu->features |= ARM_SMMU_FEAT_COHERENT_WALK; + + return 0; +} + +static int arm_smmu_device_probe(struct platform_device *pdev) +{ + struct resource *res; + resource_size_t ioaddr; + struct arm_smmu_device *smmu; + struct device *dev = &pdev->dev; + int num_irqs, i, err; + smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL); if (!smmu) { dev_err(dev, "failed to allocate arm_smmu_device\n"); @@ -1922,22 +2090,21 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev) } smmu->dev = dev; - data = of_device_get_match_data(dev); - smmu->version = data->version; - smmu->model = data->model; + if (dev->of_node) + err = arm_smmu_device_dt_probe(pdev, smmu); + else + err = arm_smmu_device_acpi_probe(pdev, smmu); + + if (err) + return err; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + ioaddr = res->start; smmu->base = devm_ioremap_resource(dev, res); if (IS_ERR(smmu->base)) return PTR_ERR(smmu->base); smmu->size = resource_size(res); - if (of_property_read_u32(dev->of_node, "#global-interrupts", - &smmu->num_global_irqs)) { - dev_err(dev, "missing #global-interrupts property\n"); - return -ENODEV; - } - num_irqs = 0; while ((res = platform_get_resource(pdev, IORESOURCE_IRQ, num_irqs))) { num_irqs++; @@ -1972,8 +2139,6 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev) if (err) return err; - parse_driver_options(smmu); - if (smmu->version == ARM_SMMU_V2 && smmu->num_context_banks != smmu->num_context_irqs) { dev_err(dev, @@ -1995,9 +2160,25 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev) } } - of_iommu_set_ops(dev->of_node, &arm_smmu_ops); + err = iommu_device_sysfs_add(&smmu->iommu, smmu->dev, NULL, + "smmu.%pa", &ioaddr); + if (err) { + dev_err(dev, "Failed to register iommu in sysfs\n"); + return err; + } + + iommu_device_set_ops(&smmu->iommu, &arm_smmu_ops); + iommu_device_set_fwnode(&smmu->iommu, dev->fwnode); + + err = iommu_device_register(&smmu->iommu); + if (err) { + dev_err(dev, "Failed to register iommu\n"); + return err; + } + platform_set_drvdata(pdev, smmu); arm_smmu_device_reset(smmu); + arm_smmu_test_smr_masks(smmu); /* Oh, for a proper bus abstraction */ if (!iommu_present(&platform_bus_type)) @@ -2035,7 +2216,7 @@ static struct platform_driver arm_smmu_driver = { .name = "arm-smmu", .of_match_table = of_match_ptr(arm_smmu_of_match), }, - .probe = arm_smmu_device_dt_probe, + .probe = arm_smmu_device_probe, .remove = arm_smmu_device_remove, }; @@ -2078,6 +2259,17 @@ IOMMU_OF_DECLARE(arm_mmu401, "arm,mmu-401", arm_smmu_of_init); IOMMU_OF_DECLARE(arm_mmu500, "arm,mmu-500", arm_smmu_of_init); IOMMU_OF_DECLARE(cavium_smmuv2, "cavium,smmu-v2", arm_smmu_of_init); +#ifdef CONFIG_ACPI +static int __init arm_smmu_acpi_init(struct acpi_table_header *table) +{ + if (iort_node_match(ACPI_IORT_NODE_SMMU)) + return arm_smmu_init(); + + return 0; +} +IORT_ACPI_DECLARE(arm_smmu, ACPI_SIG_IORT, arm_smmu_acpi_init); +#endif + MODULE_DESCRIPTION("IOMMU API for ARM architected SMMU implementations"); MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index c5ab8667e6f2..48d36ce59efb 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -37,15 +37,50 @@ struct iommu_dma_msi_page { phys_addr_t phys; }; +enum iommu_dma_cookie_type { + IOMMU_DMA_IOVA_COOKIE, + IOMMU_DMA_MSI_COOKIE, +}; + struct iommu_dma_cookie { - struct iova_domain iovad; - struct list_head msi_page_list; - spinlock_t msi_lock; + enum iommu_dma_cookie_type type; + union { + /* Full allocator for IOMMU_DMA_IOVA_COOKIE */ + struct iova_domain iovad; + /* Trivial linear page allocator for IOMMU_DMA_MSI_COOKIE */ + dma_addr_t msi_iova; + }; + struct list_head msi_page_list; + spinlock_t msi_lock; }; +static inline size_t cookie_msi_granule(struct iommu_dma_cookie *cookie) +{ + if (cookie->type == IOMMU_DMA_IOVA_COOKIE) + return cookie->iovad.granule; + return PAGE_SIZE; +} + static inline struct iova_domain *cookie_iovad(struct iommu_domain *domain) { - return &((struct iommu_dma_cookie *)domain->iova_cookie)->iovad; + struct iommu_dma_cookie *cookie = domain->iova_cookie; + + if (cookie->type == IOMMU_DMA_IOVA_COOKIE) + return &cookie->iovad; + return NULL; +} + +static struct iommu_dma_cookie *cookie_alloc(enum iommu_dma_cookie_type type) +{ + struct iommu_dma_cookie *cookie; + + cookie = kzalloc(sizeof(*cookie), GFP_KERNEL); + if (cookie) { + spin_lock_init(&cookie->msi_lock); + INIT_LIST_HEAD(&cookie->msi_page_list); + cookie->type = type; + } + return cookie; } int iommu_dma_init(void) @@ -62,25 +97,53 @@ int iommu_dma_init(void) */ int iommu_get_dma_cookie(struct iommu_domain *domain) { + if (domain->iova_cookie) + return -EEXIST; + + domain->iova_cookie = cookie_alloc(IOMMU_DMA_IOVA_COOKIE); + if (!domain->iova_cookie) + return -ENOMEM; + + return 0; +} +EXPORT_SYMBOL(iommu_get_dma_cookie); + +/** + * iommu_get_msi_cookie - Acquire just MSI remapping resources + * @domain: IOMMU domain to prepare + * @base: Start address of IOVA region for MSI mappings + * + * Users who manage their own IOVA allocation and do not want DMA API support, + * but would still like to take advantage of automatic MSI remapping, can use + * this to initialise their own domain appropriately. Users should reserve a + * contiguous IOVA region, starting at @base, large enough to accommodate the + * number of PAGE_SIZE mappings necessary to cover every MSI doorbell address + * used by the devices attached to @domain. + */ +int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base) +{ struct iommu_dma_cookie *cookie; + if (domain->type != IOMMU_DOMAIN_UNMANAGED) + return -EINVAL; + if (domain->iova_cookie) return -EEXIST; - cookie = kzalloc(sizeof(*cookie), GFP_KERNEL); + cookie = cookie_alloc(IOMMU_DMA_MSI_COOKIE); if (!cookie) return -ENOMEM; - spin_lock_init(&cookie->msi_lock); - INIT_LIST_HEAD(&cookie->msi_page_list); + cookie->msi_iova = base; domain->iova_cookie = cookie; return 0; } -EXPORT_SYMBOL(iommu_get_dma_cookie); +EXPORT_SYMBOL(iommu_get_msi_cookie); /** * iommu_put_dma_cookie - Release a domain's DMA mapping resources - * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie() + * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie() or + * iommu_get_msi_cookie() * * IOMMU drivers should normally call this from their domain_free callback. */ @@ -92,7 +155,7 @@ void iommu_put_dma_cookie(struct iommu_domain *domain) if (!cookie) return; - if (cookie->iovad.granule) + if (cookie->type == IOMMU_DMA_IOVA_COOKIE && cookie->iovad.granule) put_iova_domain(&cookie->iovad); list_for_each_entry_safe(msi, tmp, &cookie->msi_page_list, list) { @@ -137,11 +200,13 @@ static void iova_reserve_pci_windows(struct pci_dev *dev, int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, u64 size, struct device *dev) { - struct iova_domain *iovad = cookie_iovad(domain); + struct iommu_dma_cookie *cookie = domain->iova_cookie; + struct iova_domain *iovad = &cookie->iovad; unsigned long order, base_pfn, end_pfn; + bool pci = dev && dev_is_pci(dev); - if (!iovad) - return -ENODEV; + if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE) + return -EINVAL; /* Use the smallest supported page size for IOVA granularity */ order = __ffs(domain->pgsize_bitmap); @@ -161,19 +226,31 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, end_pfn = min_t(unsigned long, end_pfn, domain->geometry.aperture_end >> order); } + /* + * PCI devices may have larger DMA masks, but still prefer allocating + * within a 32-bit mask to avoid DAC addressing. Such limitations don't + * apply to the typical platform device, so for those we may as well + * leave the cache limit at the top of their range to save an rb_last() + * traversal on every allocation. + */ + if (pci) + end_pfn &= DMA_BIT_MASK(32) >> order; - /* All we can safely do with an existing domain is enlarge it */ + /* start_pfn is always nonzero for an already-initialised domain */ if (iovad->start_pfn) { if (1UL << order != iovad->granule || - base_pfn != iovad->start_pfn || - end_pfn < iovad->dma_32bit_pfn) { + base_pfn != iovad->start_pfn) { pr_warn("Incompatible range for DMA domain\n"); return -EFAULT; } - iovad->dma_32bit_pfn = end_pfn; + /* + * If we have devices with different DMA masks, move the free + * area cache limit down for the benefit of the smaller one. + */ + iovad->dma_32bit_pfn = min(end_pfn, iovad->dma_32bit_pfn); } else { init_iova_domain(iovad, 1UL << order, base_pfn, end_pfn); - if (dev && dev_is_pci(dev)) + if (pci) iova_reserve_pci_windows(to_pci_dev(dev), iovad); } return 0; @@ -181,16 +258,22 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, EXPORT_SYMBOL(iommu_dma_init_domain); /** - * dma_direction_to_prot - Translate DMA API directions to IOMMU API page flags + * dma_info_to_prot - Translate DMA API directions and attributes to IOMMU API + * page flags. * @dir: Direction of DMA transfer * @coherent: Is the DMA master cache-coherent? + * @attrs: DMA attributes for the mapping * * Return: corresponding IOMMU API page protection flags */ -int dma_direction_to_prot(enum dma_data_direction dir, bool coherent) +int dma_info_to_prot(enum dma_data_direction dir, bool coherent, + unsigned long attrs) { int prot = coherent ? IOMMU_CACHE : 0; + if (attrs & DMA_ATTR_PRIVILEGED) + prot |= IOMMU_PRIV; + switch (dir) { case DMA_BIDIRECTIONAL: return prot | IOMMU_READ | IOMMU_WRITE; @@ -204,19 +287,28 @@ int dma_direction_to_prot(enum dma_data_direction dir, bool coherent) } static struct iova *__alloc_iova(struct iommu_domain *domain, size_t size, - dma_addr_t dma_limit) + dma_addr_t dma_limit, struct device *dev) { struct iova_domain *iovad = cookie_iovad(domain); unsigned long shift = iova_shift(iovad); unsigned long length = iova_align(iovad, size) >> shift; + struct iova *iova = NULL; if (domain->geometry.force_aperture) dma_limit = min(dma_limit, domain->geometry.aperture_end); + + /* Try to get PCI devices a SAC address */ + if (dma_limit > DMA_BIT_MASK(32) && dev_is_pci(dev)) + iova = alloc_iova(iovad, length, DMA_BIT_MASK(32) >> shift, + true); /* * Enforce size-alignment to be safe - there could perhaps be an * attribute to control this per-device, or at least per-domain... */ - return alloc_iova(iovad, length, dma_limit >> shift, true); + if (!iova) + iova = alloc_iova(iovad, length, dma_limit >> shift, true); + + return iova; } /* The IOVA allocator knows what we mapped, so just unmap whatever that was */ @@ -369,7 +461,7 @@ struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp, if (!pages) return NULL; - iova = __alloc_iova(domain, size, dev->coherent_dma_mask); + iova = __alloc_iova(domain, size, dev->coherent_dma_mask, dev); if (!iova) goto out_free_pages; @@ -432,16 +524,15 @@ int iommu_dma_mmap(struct page **pages, size_t size, struct vm_area_struct *vma) return ret; } -dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, int prot) +static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys, + size_t size, int prot) { dma_addr_t dma_addr; struct iommu_domain *domain = iommu_get_domain_for_dev(dev); struct iova_domain *iovad = cookie_iovad(domain); - phys_addr_t phys = page_to_phys(page) + offset; size_t iova_off = iova_offset(iovad, phys); size_t len = iova_align(iovad, size + iova_off); - struct iova *iova = __alloc_iova(domain, len, dma_get_mask(dev)); + struct iova *iova = __alloc_iova(domain, len, dma_get_mask(dev), dev); if (!iova) return DMA_ERROR_CODE; @@ -454,6 +545,12 @@ dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, return dma_addr + iova_off; } +dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, int prot) +{ + return __iommu_dma_map(dev, page_to_phys(page) + offset, size, prot); +} + void iommu_dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir, unsigned long attrs) { @@ -593,7 +690,7 @@ int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, prev = s; } - iova = __alloc_iova(domain, iova_len, dma_get_mask(dev)); + iova = __alloc_iova(domain, iova_len, dma_get_mask(dev), dev); if (!iova) goto out_restore_sg; @@ -624,14 +721,17 @@ void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, __iommu_dma_unmap(iommu_get_domain_for_dev(dev), sg_dma_address(sg)); } -int iommu_dma_supported(struct device *dev, u64 mask) +dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys, + size_t size, enum dma_data_direction dir, unsigned long attrs) { - /* - * 'Special' IOMMUs which don't have the same addressing capability - * as the CPU will have to wait until we have some way to query that - * before they'll be able to use this framework. - */ - return 1; + return __iommu_dma_map(dev, phys, size, + dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO); +} + +void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ + __iommu_dma_unmap(iommu_get_domain_for_dev(dev), handle); } int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) @@ -644,11 +744,12 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev, { struct iommu_dma_cookie *cookie = domain->iova_cookie; struct iommu_dma_msi_page *msi_page; - struct iova_domain *iovad = &cookie->iovad; + struct iova_domain *iovad = cookie_iovad(domain); struct iova *iova; int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO; + size_t size = cookie_msi_granule(cookie); - msi_addr &= ~(phys_addr_t)iova_mask(iovad); + msi_addr &= ~(phys_addr_t)(size - 1); list_for_each_entry(msi_page, &cookie->msi_page_list, list) if (msi_page->phys == msi_addr) return msi_page; @@ -657,13 +758,18 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev, if (!msi_page) return NULL; - iova = __alloc_iova(domain, iovad->granule, dma_get_mask(dev)); - if (!iova) - goto out_free_page; - msi_page->phys = msi_addr; - msi_page->iova = iova_dma_addr(iovad, iova); - if (iommu_map(domain, msi_page->iova, msi_addr, iovad->granule, prot)) + if (iovad) { + iova = __alloc_iova(domain, size, dma_get_mask(dev), dev); + if (!iova) + goto out_free_page; + msi_page->iova = iova_dma_addr(iovad, iova); + } else { + msi_page->iova = cookie->msi_iova; + cookie->msi_iova += size; + } + + if (iommu_map(domain, msi_page->iova, msi_addr, size, prot)) goto out_free_iova; INIT_LIST_HEAD(&msi_page->list); @@ -671,7 +777,10 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev, return msi_page; out_free_iova: - __free_iova(iovad, iova); + if (iovad) + __free_iova(iovad, iova); + else + cookie->msi_iova -= size; out_free_page: kfree(msi_page); return NULL; @@ -712,7 +821,7 @@ void iommu_dma_map_msi_msg(int irq, struct msi_msg *msg) msg->data = ~0U; } else { msg->address_hi = upper_32_bits(msi_page->iova); - msg->address_lo &= iova_mask(&cookie->iovad); + msg->address_lo &= cookie_msi_granule(cookie) - 1; msg->address_lo += lower_32_bits(msi_page->iova); } } diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 58470f5ced04..d9c0decfc91a 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -68,13 +68,14 @@ DECLARE_RWSEM(dmar_global_lock); LIST_HEAD(dmar_drhd_units); struct acpi_table_header * __initdata dmar_tbl; -static acpi_size dmar_tbl_size; static int dmar_dev_scope_status = 1; static unsigned long dmar_seq_ids[BITS_TO_LONGS(DMAR_UNITS_SUPPORTED)]; static int alloc_iommu(struct dmar_drhd_unit *drhd); static void free_iommu(struct intel_iommu *iommu); +extern const struct iommu_ops intel_iommu_ops; + static void dmar_register_drhd_unit(struct dmar_drhd_unit *drhd) { /* @@ -338,7 +339,9 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb, struct pci_dev *pdev = to_pci_dev(data); struct dmar_pci_notify_info *info; - /* Only care about add/remove events for physical functions */ + /* Only care about add/remove events for physical functions. + * For VFs we actually do the lookup based on the corresponding + * PF in device_to_iommu() anyway. */ if (pdev->is_virtfn) return NOTIFY_DONE; if (action != BUS_NOTIFY_ADD_DEVICE && @@ -541,9 +544,7 @@ static int __init dmar_table_detect(void) acpi_status status = AE_OK; /* if we could find DMAR table, then there are DMAR devices */ - status = acpi_get_table_with_size(ACPI_SIG_DMAR, 0, - (struct acpi_table_header **)&dmar_tbl, - &dmar_tbl_size); + status = acpi_get_table(ACPI_SIG_DMAR, 0, &dmar_tbl); if (ACPI_SUCCESS(status) && !dmar_tbl) { pr_warn("Unable to map DMAR\n"); @@ -904,8 +905,10 @@ int __init detect_intel_iommu(void) x86_init.iommu.iommu_init = intel_iommu_init; #endif - early_acpi_os_unmap_memory((void __iomem *)dmar_tbl, dmar_tbl_size); - dmar_tbl = NULL; + if (dmar_tbl) { + acpi_put_table(dmar_tbl); + dmar_tbl = NULL; + } up_write(&dmar_global_lock); return ret ? 1 : -ENODEV; @@ -1077,14 +1080,17 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) raw_spin_lock_init(&iommu->register_lock); if (intel_iommu_enabled) { - iommu->iommu_dev = iommu_device_create(NULL, iommu, - intel_iommu_groups, - "%s", iommu->name); + err = iommu_device_sysfs_add(&iommu->iommu, NULL, + intel_iommu_groups, + "%s", iommu->name); + if (err) + goto err_unmap; - if (IS_ERR(iommu->iommu_dev)) { - err = PTR_ERR(iommu->iommu_dev); + iommu_device_set_ops(&iommu->iommu, &intel_iommu_ops); + + err = iommu_device_register(&iommu->iommu); + if (err) goto err_unmap; - } } drhd->iommu = iommu; @@ -1102,7 +1108,8 @@ error: static void free_iommu(struct intel_iommu *iommu) { - iommu_device_destroy(iommu->iommu_dev); + iommu_device_sysfs_remove(&iommu->iommu); + iommu_device_unregister(&iommu->iommu); if (iommu->irq) { if (iommu->pr_irq) { diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index fa529c2125f5..a7e0821c9967 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -276,6 +276,8 @@ struct sysmmu_drvdata { struct list_head owner_node; /* node for owner controllers list */ phys_addr_t pgtable; /* assigned page table structure */ unsigned int version; /* our version */ + + struct iommu_device iommu; /* IOMMU core handle */ }; static struct exynos_iommu_domain *to_exynos_domain(struct iommu_domain *dom) @@ -612,6 +614,18 @@ static int __init exynos_sysmmu_probe(struct platform_device *pdev) data->sysmmu = dev; spin_lock_init(&data->lock); + ret = iommu_device_sysfs_add(&data->iommu, &pdev->dev, NULL, + dev_name(data->sysmmu)); + if (ret) + return ret; + + iommu_device_set_ops(&data->iommu, &exynos_iommu_ops); + iommu_device_set_fwnode(&data->iommu, &dev->of_node->fwnode); + + ret = iommu_device_register(&data->iommu); + if (ret) + return ret; + platform_set_drvdata(pdev, data); __sysmmu_get_version(data); @@ -629,8 +643,6 @@ static int __init exynos_sysmmu_probe(struct platform_device *pdev) pm_runtime_enable(dev); - of_iommu_set_ops(dev->of_node, &exynos_iommu_ops); - return 0; } diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index a4407eabf0e6..f5e02f8e7371 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -440,6 +440,7 @@ struct dmar_rmrr_unit { u64 end_address; /* reserved end address */ struct dmar_dev_scope *devices; /* target devices */ int devices_cnt; /* target device count */ + struct iommu_resv_region *resv; /* reserved region handle */ }; struct dmar_atsr_unit { @@ -547,7 +548,7 @@ EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped); static DEFINE_SPINLOCK(device_domain_lock); static LIST_HEAD(device_domain_list); -static const struct iommu_ops intel_iommu_ops; +const struct iommu_ops intel_iommu_ops; static bool translation_pre_enabled(struct intel_iommu *iommu) { @@ -892,7 +893,13 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf return NULL; if (dev_is_pci(dev)) { + struct pci_dev *pf_pdev; + pdev = to_pci_dev(dev); + /* VFs aren't listed in scope tables; we need to look up + * the PF instead to find the IOMMU. */ + pf_pdev = pci_physfn(pdev); + dev = &pf_pdev->dev; segment = pci_domain_nr(pdev->bus); } else if (has_acpi_companion(dev)) dev = &ACPI_COMPANION(dev)->dev; @@ -905,6 +912,13 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf for_each_active_dev_scope(drhd->devices, drhd->devices_cnt, i, tmp) { if (tmp == dev) { + /* For a VF use its original BDF# not that of the PF + * which we used for the IOMMU lookup. Strictly speaking + * we could do this for all PCI devices; we only need to + * get the BDF# from the scope table for ACPI matches. */ + if (pdev->is_virtfn) + goto got_pdev; + *bus = drhd->devices[i].bus; *devfn = drhd->devices[i].devfn; goto out; @@ -1131,7 +1145,7 @@ static void dma_pte_free_level(struct dmar_domain *domain, int level, if (!dma_pte_present(pte) || dma_pte_superpage(pte)) goto next; - level_pfn = pfn & level_mask(level - 1); + level_pfn = pfn & level_mask(level); level_pte = phys_to_virt(dma_pte_addr(pte)); if (level > 2) @@ -1711,6 +1725,7 @@ static void disable_dmar_iommu(struct intel_iommu *iommu) if (!iommu->domains || !iommu->domain_ids) return; +again: spin_lock_irqsave(&device_domain_lock, flags); list_for_each_entry_safe(info, tmp, &device_domain_list, global) { struct dmar_domain *domain; @@ -1723,10 +1738,19 @@ static void disable_dmar_iommu(struct intel_iommu *iommu) domain = info->domain; - dmar_remove_one_dev_info(domain, info->dev); + __dmar_remove_one_dev_info(info); - if (!domain_type_is_vm_or_si(domain)) + if (!domain_type_is_vm_or_si(domain)) { + /* + * The domain_exit() function can't be called under + * device_domain_lock, as it takes this lock itself. + * So release the lock here and re-run the loop + * afterwards. + */ + spin_unlock_irqrestore(&device_domain_lock, flags); domain_exit(domain); + goto again; + } } spin_unlock_irqrestore(&device_domain_lock, flags); @@ -2014,6 +2038,25 @@ static int domain_context_mapping_one(struct dmar_domain *domain, if (context_present(context)) goto out_unlock; + /* + * For kdump cases, old valid entries may be cached due to the + * in-flight DMA and copied pgtable, but there is no unmapping + * behaviour for them, thus we need an explicit cache flush for + * the newly-mapped device. For kdump, at this point, the device + * is supposed to finish reset at its driver probe stage, so no + * in-flight DMA will exist, and we don't need to worry anymore + * hereafter. + */ + if (context_copied(context)) { + u16 did_old = context_domain_id(context); + + if (did_old >= 0 && did_old < cap_ndoms(iommu->cap)) + iommu->flush.flush_context(iommu, did_old, + (((u16)bus) << 8) | devfn, + DMA_CCMD_MASK_NOBIT, + DMA_CCMD_DEVICE_INVL); + } + pgd = domain->pgd; context_clear_entry(context); @@ -3283,13 +3326,14 @@ static int __init init_dmars(void) iommu_identity_mapping |= IDENTMAP_GFX; #endif + check_tylersburg_isoch(); + if (iommu_identity_mapping) { ret = si_domain_init(hw_pass_through); if (ret) goto free_iommu; } - check_tylersburg_isoch(); /* * If we copied translations from a previous kernel in the kdump @@ -4204,27 +4248,40 @@ static inline void init_iommu_pm_ops(void) {} int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg) { struct acpi_dmar_reserved_memory *rmrr; + int prot = DMA_PTE_READ|DMA_PTE_WRITE; struct dmar_rmrr_unit *rmrru; + size_t length; rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL); if (!rmrru) - return -ENOMEM; + goto out; rmrru->hdr = header; rmrr = (struct acpi_dmar_reserved_memory *)header; rmrru->base_address = rmrr->base_address; rmrru->end_address = rmrr->end_address; + + length = rmrr->end_address - rmrr->base_address + 1; + rmrru->resv = iommu_alloc_resv_region(rmrr->base_address, length, prot, + IOMMU_RESV_DIRECT); + if (!rmrru->resv) + goto free_rmrru; + rmrru->devices = dmar_alloc_dev_scope((void *)(rmrr + 1), ((void *)rmrr) + rmrr->header.length, &rmrru->devices_cnt); - if (rmrru->devices_cnt && rmrru->devices == NULL) { - kfree(rmrru); - return -ENOMEM; - } + if (rmrru->devices_cnt && rmrru->devices == NULL) + goto free_all; list_add(&rmrru->list, &dmar_rmrr_units); return 0; +free_all: + kfree(rmrru->resv); +free_rmrru: + kfree(rmrru); +out: + return -ENOMEM; } static struct dmar_atsr_unit *dmar_find_atsr(struct acpi_dmar_atsr *atsr) @@ -4438,6 +4495,7 @@ static void intel_iommu_free_dmars(void) list_for_each_entry_safe(rmrru, rmrr_n, &dmar_rmrr_units, list) { list_del(&rmrru->list); dmar_free_dev_scope(&rmrru->devices, &rmrru->devices_cnt); + kfree(rmrru->resv); kfree(rmrru); } @@ -4665,25 +4723,13 @@ static void free_all_cpu_cached_iovas(unsigned int cpu) } } -static int intel_iommu_cpu_notifier(struct notifier_block *nfb, - unsigned long action, void *v) +static int intel_iommu_cpu_dead(unsigned int cpu) { - unsigned int cpu = (unsigned long)v; - - switch (action) { - case CPU_DEAD: - case CPU_DEAD_FROZEN: - free_all_cpu_cached_iovas(cpu); - flush_unmaps_timeout(cpu); - break; - } - return NOTIFY_OK; + free_all_cpu_cached_iovas(cpu); + flush_unmaps_timeout(cpu); + return 0; } -static struct notifier_block intel_iommu_cpu_nb = { - .notifier_call = intel_iommu_cpu_notifier, -}; - static ssize_t intel_iommu_show_version(struct device *dev, struct device_attribute *attr, char *buf) @@ -4823,17 +4869,20 @@ int __init intel_iommu_init(void) init_iommu_pm_ops(); - for_each_active_iommu(iommu, drhd) - iommu->iommu_dev = iommu_device_create(NULL, iommu, - intel_iommu_groups, - "%s", iommu->name); + for_each_active_iommu(iommu, drhd) { + iommu_device_sysfs_add(&iommu->iommu, NULL, + intel_iommu_groups, + "%s", iommu->name); + iommu_device_set_ops(&iommu->iommu, &intel_iommu_ops); + iommu_device_register(&iommu->iommu); + } bus_set_iommu(&pci_bus_type, &intel_iommu_ops); bus_register_notifier(&pci_bus_type, &device_nb); if (si_domain && !hw_pass_through) register_memory_notifier(&intel_iommu_memory_nb); - register_hotcpu_notifier(&intel_iommu_cpu_nb); - + cpuhp_setup_state(CPUHP_IOMMU_INTEL_DEAD, "iommu/intel:dead", NULL, + intel_iommu_cpu_dead); intel_iommu_enabled = 1; return 0; @@ -5148,7 +5197,7 @@ static int intel_iommu_add_device(struct device *dev) if (!iommu) return -ENODEV; - iommu_device_link(iommu->iommu_dev, dev); + iommu_device_link(&iommu->iommu, dev); group = iommu_group_get_for_dev(dev); @@ -5170,10 +5219,68 @@ static void intel_iommu_remove_device(struct device *dev) iommu_group_remove_device(dev); - iommu_device_unlink(iommu->iommu_dev, dev); + iommu_device_unlink(&iommu->iommu, dev); +} + +static void intel_iommu_get_resv_regions(struct device *device, + struct list_head *head) +{ + struct iommu_resv_region *reg; + struct dmar_rmrr_unit *rmrr; + struct device *i_dev; + int i; + + rcu_read_lock(); + for_each_rmrr_units(rmrr) { + for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt, + i, i_dev) { + if (i_dev != device) + continue; + + list_add_tail(&rmrr->resv->list, head); + } + } + rcu_read_unlock(); + + reg = iommu_alloc_resv_region(IOAPIC_RANGE_START, + IOAPIC_RANGE_END - IOAPIC_RANGE_START + 1, + 0, IOMMU_RESV_RESERVED); + if (!reg) + return; + list_add_tail(®->list, head); +} + +static void intel_iommu_put_resv_regions(struct device *dev, + struct list_head *head) +{ + struct iommu_resv_region *entry, *next; + + list_for_each_entry_safe(entry, next, head, list) { + if (entry->type == IOMMU_RESV_RESERVED) + kfree(entry); + } } #ifdef CONFIG_INTEL_IOMMU_SVM +#define MAX_NR_PASID_BITS (20) +static inline unsigned long intel_iommu_get_pts(struct intel_iommu *iommu) +{ + /* + * Convert ecap_pss to extend context entry pts encoding, also + * respect the soft pasid_max value set by the iommu. + * - number of PASID bits = ecap_pss + 1 + * - number of PASID table entries = 2^(pts + 5) + * Therefore, pts = ecap_pss - 4 + * e.g. KBL ecap_pss = 0x13, PASID has 20 bits, pts = 15 + */ + if (ecap_pss(iommu->ecap) < 5) + return 0; + + /* pasid_max is encoded as actual number of entries not the bits */ + return find_first_bit((unsigned long *)&iommu->pasid_max, + MAX_NR_PASID_BITS) - 5; +} + int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sdev) { struct device_domain_info *info; @@ -5206,7 +5313,9 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sd if (!(ctx_lo & CONTEXT_PASIDE)) { context[1].hi = (u64)virt_to_phys(iommu->pasid_state_table); - context[1].lo = (u64)virt_to_phys(iommu->pasid_table) | ecap_pss(iommu->ecap); + context[1].lo = (u64)virt_to_phys(iommu->pasid_table) | + intel_iommu_get_pts(iommu); + wmb(); /* CONTEXT_TT_MULTI_LEVEL and CONTEXT_TT_DEV_IOTLB are both * extended to permit requests-with-PASID if the PASIDE bit @@ -5281,20 +5390,22 @@ struct intel_iommu *intel_svm_device_to_iommu(struct device *dev) } #endif /* CONFIG_INTEL_IOMMU_SVM */ -static const struct iommu_ops intel_iommu_ops = { - .capable = intel_iommu_capable, - .domain_alloc = intel_iommu_domain_alloc, - .domain_free = intel_iommu_domain_free, - .attach_dev = intel_iommu_attach_device, - .detach_dev = intel_iommu_detach_device, - .map = intel_iommu_map, - .unmap = intel_iommu_unmap, - .map_sg = default_iommu_map_sg, - .iova_to_phys = intel_iommu_iova_to_phys, - .add_device = intel_iommu_add_device, - .remove_device = intel_iommu_remove_device, - .device_group = pci_device_group, - .pgsize_bitmap = INTEL_IOMMU_PGSIZES, +const struct iommu_ops intel_iommu_ops = { + .capable = intel_iommu_capable, + .domain_alloc = intel_iommu_domain_alloc, + .domain_free = intel_iommu_domain_free, + .attach_dev = intel_iommu_attach_device, + .detach_dev = intel_iommu_detach_device, + .map = intel_iommu_map, + .unmap = intel_iommu_unmap, + .map_sg = default_iommu_map_sg, + .iova_to_phys = intel_iommu_iova_to_phys, + .add_device = intel_iommu_add_device, + .remove_device = intel_iommu_remove_device, + .get_resv_regions = intel_iommu_get_resv_regions, + .put_resv_regions = intel_iommu_put_resv_regions, + .device_group = pci_device_group, + .pgsize_bitmap = INTEL_IOMMU_PGSIZES, }; static void quirk_iommu_g4x_gfx(struct pci_dev *dev) diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index 8ebb3530afa7..cb72e0011310 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -39,10 +39,18 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu) struct page *pages; int order; - order = ecap_pss(iommu->ecap) + 7 - PAGE_SHIFT; - if (order < 0) - order = 0; - + /* Start at 2 because it's defined as 2^(1+PSS) */ + iommu->pasid_max = 2 << ecap_pss(iommu->ecap); + + /* Eventually I'm promised we will get a multi-level PASID table + * and it won't have to be physically contiguous. Until then, + * limit the size because 8MiB contiguous allocations can be hard + * to come by. The limit of 0x20000, which is 1MiB for each of + * the PASID and PASID-state tables, is somewhat arbitrary. */ + if (iommu->pasid_max > 0x20000) + iommu->pasid_max = 0x20000; + + order = get_order(sizeof(struct pasid_entry) * iommu->pasid_max); pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order); if (!pages) { pr_warn("IOMMU: %s: Failed to allocate PASID table\n", @@ -53,6 +61,8 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu) pr_info("%s: Allocated order %d PASID table.\n", iommu->name, order); if (ecap_dis(iommu->ecap)) { + /* Just making it explicit... */ + BUILD_BUG_ON(sizeof(struct pasid_entry) != sizeof(struct pasid_state_entry)); pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order); if (pages) iommu->pasid_state_table = page_address(pages); @@ -68,11 +78,7 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu) int intel_svm_free_pasid_tables(struct intel_iommu *iommu) { - int order; - - order = ecap_pss(iommu->ecap) + 7 - PAGE_SHIFT; - if (order < 0) - order = 0; + int order = get_order(sizeof(struct pasid_entry) * iommu->pasid_max); if (iommu->pasid_table) { free_pages((unsigned long)iommu->pasid_table, order); @@ -371,8 +377,8 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ } svm->iommu = iommu; - if (pasid_max > 2 << ecap_pss(iommu->ecap)) - pasid_max = 2 << ecap_pss(iommu->ecap); + if (pasid_max > iommu->pasid_max) + pasid_max = iommu->pasid_max; /* Do not use PASID 0 in caching mode (virtualised IOMMU) */ ret = idr_alloc(&iommu->pasid_idr, svm, diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index f50e51c1a9c8..1c049e2e12bf 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -265,7 +265,9 @@ static arm_v7s_iopte arm_v7s_prot_to_pte(int prot, int lvl, if (!(prot & IOMMU_MMIO)) pte |= ARM_V7S_ATTR_TEX(1); if (ap) { - pte |= ARM_V7S_PTE_AF | ARM_V7S_PTE_AP_UNPRIV; + pte |= ARM_V7S_PTE_AF; + if (!(prot & IOMMU_PRIV)) + pte |= ARM_V7S_PTE_AP_UNPRIV; if (!(prot & IOMMU_WRITE)) pte |= ARM_V7S_PTE_AP_RDONLY; } @@ -288,6 +290,8 @@ static int arm_v7s_pte_to_prot(arm_v7s_iopte pte, int lvl) if (!(attr & ARM_V7S_PTE_AP_RDONLY)) prot |= IOMMU_WRITE; + if (!(attr & ARM_V7S_PTE_AP_UNPRIV)) + prot |= IOMMU_PRIV; if ((attr & (ARM_V7S_TEX_MASK << ARM_V7S_TEX_SHIFT)) == 0) prot |= IOMMU_MMIO; else if (pte & ARM_V7S_ATTR_C) @@ -793,8 +797,7 @@ static int __init arm_v7s_do_selftests(void) * Distinct mappings of different granule sizes. */ iova = 0; - i = find_first_bit(&cfg.pgsize_bitmap, BITS_PER_LONG); - while (i != BITS_PER_LONG) { + for_each_set_bit(i, &cfg.pgsize_bitmap, BITS_PER_LONG) { size = 1UL << i; if (ops->map(ops, iova, iova, size, IOMMU_READ | IOMMU_WRITE | @@ -811,8 +814,6 @@ static int __init arm_v7s_do_selftests(void) return __FAIL(ops); iova += SZ_16M; - i++; - i = find_next_bit(&cfg.pgsize_bitmap, BITS_PER_LONG, i); loopnr++; } diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index f5c90e1366ce..feacc54bec68 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -350,11 +350,14 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data, if (data->iop.fmt == ARM_64_LPAE_S1 || data->iop.fmt == ARM_32_LPAE_S1) { - pte = ARM_LPAE_PTE_AP_UNPRIV | ARM_LPAE_PTE_nG; + pte = ARM_LPAE_PTE_nG; if (!(prot & IOMMU_WRITE) && (prot & IOMMU_READ)) pte |= ARM_LPAE_PTE_AP_RDONLY; + if (!(prot & IOMMU_PRIV)) + pte |= ARM_LPAE_PTE_AP_UNPRIV; + if (prot & IOMMU_MMIO) pte |= (ARM_LPAE_MAIR_ATTR_IDX_DEV << ARM_LPAE_PTE_ATTRINDX_SHIFT); @@ -916,7 +919,7 @@ static void dummy_tlb_sync(void *cookie) WARN_ON(cookie != cfg_cookie); } -static struct iommu_gather_ops dummy_tlb_ops __initdata = { +static const struct iommu_gather_ops dummy_tlb_ops __initconst = { .tlb_flush_all = dummy_tlb_flush_all, .tlb_add_flush = dummy_tlb_add_flush, .tlb_sync = dummy_tlb_sync, @@ -980,8 +983,7 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg) * Distinct mappings of different granule sizes. */ iova = 0; - j = find_first_bit(&cfg->pgsize_bitmap, BITS_PER_LONG); - while (j != BITS_PER_LONG) { + for_each_set_bit(j, &cfg->pgsize_bitmap, BITS_PER_LONG) { size = 1UL << j; if (ops->map(ops, iova, iova, size, IOMMU_READ | @@ -999,8 +1001,6 @@ static int __init arm_lpae_run_tests(struct io_pgtable_cfg *cfg) return __FAIL(ops, i); iova += SZ_1G; - j++; - j = find_next_bit(&cfg->pgsize_bitmap, BITS_PER_LONG, j); } /* Partial unmap */ diff --git a/drivers/iommu/iommu-sysfs.c b/drivers/iommu/iommu-sysfs.c index 39b2d9127dbf..c58351ed61c1 100644 --- a/drivers/iommu/iommu-sysfs.c +++ b/drivers/iommu/iommu-sysfs.c @@ -50,85 +50,76 @@ static int __init iommu_dev_init(void) postcore_initcall(iommu_dev_init); /* - * Create an IOMMU device and return a pointer to it. IOMMU specific - * attributes can be provided as an attribute group, allowing a unique - * namespace per IOMMU type. + * Init the struct device for the IOMMU. IOMMU specific attributes can + * be provided as an attribute group, allowing a unique namespace per + * IOMMU type. */ -struct device *iommu_device_create(struct device *parent, void *drvdata, - const struct attribute_group **groups, - const char *fmt, ...) +int iommu_device_sysfs_add(struct iommu_device *iommu, + struct device *parent, + const struct attribute_group **groups, + const char *fmt, ...) { - struct device *dev; va_list vargs; int ret; - dev = kzalloc(sizeof(*dev), GFP_KERNEL); - if (!dev) - return ERR_PTR(-ENOMEM); + device_initialize(&iommu->dev); - device_initialize(dev); - - dev->class = &iommu_class; - dev->parent = parent; - dev->groups = groups; - dev_set_drvdata(dev, drvdata); + iommu->dev.class = &iommu_class; + iommu->dev.parent = parent; + iommu->dev.groups = groups; va_start(vargs, fmt); - ret = kobject_set_name_vargs(&dev->kobj, fmt, vargs); + ret = kobject_set_name_vargs(&iommu->dev.kobj, fmt, vargs); va_end(vargs); if (ret) goto error; - ret = device_add(dev); + ret = device_add(&iommu->dev); if (ret) goto error; - return dev; + return 0; error: - put_device(dev); - return ERR_PTR(ret); + put_device(&iommu->dev); + return ret; } -void iommu_device_destroy(struct device *dev) +void iommu_device_sysfs_remove(struct iommu_device *iommu) { - if (!dev || IS_ERR(dev)) - return; - - device_unregister(dev); + device_unregister(&iommu->dev); } - /* * IOMMU drivers can indicate a device is managed by a given IOMMU using * this interface. A link to the device will be created in the "devices" * directory of the IOMMU device in sysfs and an "iommu" link will be * created under the linked device, pointing back at the IOMMU device. */ -int iommu_device_link(struct device *dev, struct device *link) +int iommu_device_link(struct iommu_device *iommu, struct device *link) { int ret; - if (!dev || IS_ERR(dev)) + if (!iommu || IS_ERR(iommu)) return -ENODEV; - ret = sysfs_add_link_to_group(&dev->kobj, "devices", + ret = sysfs_add_link_to_group(&iommu->dev.kobj, "devices", &link->kobj, dev_name(link)); if (ret) return ret; - ret = sysfs_create_link_nowarn(&link->kobj, &dev->kobj, "iommu"); + ret = sysfs_create_link_nowarn(&link->kobj, &iommu->dev.kobj, "iommu"); if (ret) - sysfs_remove_link_from_group(&dev->kobj, "devices", + sysfs_remove_link_from_group(&iommu->dev.kobj, "devices", dev_name(link)); return ret; } -void iommu_device_unlink(struct device *dev, struct device *link) +void iommu_device_unlink(struct iommu_device *iommu, struct device *link) { - if (!dev || IS_ERR(dev)) + if (!iommu || IS_ERR(iommu)) return; sysfs_remove_link(&link->kobj, "iommu"); - sysfs_remove_link_from_group(&dev->kobj, "devices", dev_name(link)); + sysfs_remove_link_from_group(&iommu->dev.kobj, "devices", dev_name(link)); } diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 9a2f1960873b..8ea14f41a979 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -55,7 +55,7 @@ struct iommu_group { struct iommu_domain *domain; }; -struct iommu_device { +struct group_device { struct list_head list; struct device *dev; char *name; @@ -68,6 +68,12 @@ struct iommu_group_attribute { const char *buf, size_t count); }; +static const char * const iommu_group_resv_type_string[] = { + [IOMMU_RESV_DIRECT] = "direct", + [IOMMU_RESV_RESERVED] = "reserved", + [IOMMU_RESV_MSI] = "msi", +}; + #define IOMMU_GROUP_ATTR(_name, _mode, _show, _store) \ struct iommu_group_attribute iommu_group_attr_##_name = \ __ATTR(_name, _mode, _show, _store) @@ -77,6 +83,25 @@ struct iommu_group_attribute iommu_group_attr_##_name = \ #define to_iommu_group(_kobj) \ container_of(_kobj, struct iommu_group, kobj) +static LIST_HEAD(iommu_device_list); +static DEFINE_SPINLOCK(iommu_device_lock); + +int iommu_device_register(struct iommu_device *iommu) +{ + spin_lock(&iommu_device_lock); + list_add_tail(&iommu->list, &iommu_device_list); + spin_unlock(&iommu_device_lock); + + return 0; +} + +void iommu_device_unregister(struct iommu_device *iommu) +{ + spin_lock(&iommu_device_lock); + list_del(&iommu->list); + spin_unlock(&iommu_device_lock); +} + static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus, unsigned type); static int __iommu_attach_device(struct iommu_domain *domain, @@ -133,8 +158,131 @@ static ssize_t iommu_group_show_name(struct iommu_group *group, char *buf) return sprintf(buf, "%s\n", group->name); } +/** + * iommu_insert_resv_region - Insert a new region in the + * list of reserved regions. + * @new: new region to insert + * @regions: list of regions + * + * The new element is sorted by address with respect to the other + * regions of the same type. In case it overlaps with another + * region of the same type, regions are merged. In case it + * overlaps with another region of different type, regions are + * not merged. + */ +static int iommu_insert_resv_region(struct iommu_resv_region *new, + struct list_head *regions) +{ + struct iommu_resv_region *region; + phys_addr_t start = new->start; + phys_addr_t end = new->start + new->length - 1; + struct list_head *pos = regions->next; + + while (pos != regions) { + struct iommu_resv_region *entry = + list_entry(pos, struct iommu_resv_region, list); + phys_addr_t a = entry->start; + phys_addr_t b = entry->start + entry->length - 1; + int type = entry->type; + + if (end < a) { + goto insert; + } else if (start > b) { + pos = pos->next; + } else if ((start >= a) && (end <= b)) { + if (new->type == type) + goto done; + else + pos = pos->next; + } else { + if (new->type == type) { + phys_addr_t new_start = min(a, start); + phys_addr_t new_end = max(b, end); + + list_del(&entry->list); + entry->start = new_start; + entry->length = new_end - new_start + 1; + iommu_insert_resv_region(entry, regions); + } else { + pos = pos->next; + } + } + } +insert: + region = iommu_alloc_resv_region(new->start, new->length, + new->prot, new->type); + if (!region) + return -ENOMEM; + + list_add_tail(®ion->list, pos); +done: + return 0; +} + +static int +iommu_insert_device_resv_regions(struct list_head *dev_resv_regions, + struct list_head *group_resv_regions) +{ + struct iommu_resv_region *entry; + int ret = 0; + + list_for_each_entry(entry, dev_resv_regions, list) { + ret = iommu_insert_resv_region(entry, group_resv_regions); + if (ret) + break; + } + return ret; +} + +int iommu_get_group_resv_regions(struct iommu_group *group, + struct list_head *head) +{ + struct group_device *device; + int ret = 0; + + mutex_lock(&group->mutex); + list_for_each_entry(device, &group->devices, list) { + struct list_head dev_resv_regions; + + INIT_LIST_HEAD(&dev_resv_regions); + iommu_get_resv_regions(device->dev, &dev_resv_regions); + ret = iommu_insert_device_resv_regions(&dev_resv_regions, head); + iommu_put_resv_regions(device->dev, &dev_resv_regions); + if (ret) + break; + } + mutex_unlock(&group->mutex); + return ret; +} +EXPORT_SYMBOL_GPL(iommu_get_group_resv_regions); + +static ssize_t iommu_group_show_resv_regions(struct iommu_group *group, + char *buf) +{ + struct iommu_resv_region *region, *next; + struct list_head group_resv_regions; + char *str = buf; + + INIT_LIST_HEAD(&group_resv_regions); + iommu_get_group_resv_regions(group, &group_resv_regions); + + list_for_each_entry_safe(region, next, &group_resv_regions, list) { + str += sprintf(str, "0x%016llx 0x%016llx %s\n", + (long long int)region->start, + (long long int)(region->start + + region->length - 1), + iommu_group_resv_type_string[region->type]); + kfree(region); + } + + return (str - buf); +} + static IOMMU_GROUP_ATTR(name, S_IRUGO, iommu_group_show_name, NULL); +static IOMMU_GROUP_ATTR(reserved_regions, 0444, + iommu_group_show_resv_regions, NULL); + static void iommu_group_release(struct kobject *kobj) { struct iommu_group *group = to_iommu_group(kobj); @@ -212,6 +360,11 @@ struct iommu_group *iommu_group_alloc(void) */ kobject_put(&group->kobj); + ret = iommu_group_create_file(group, + &iommu_group_attr_reserved_regions); + if (ret) + return ERR_PTR(ret); + pr_debug("Allocated group %d\n", group->id); return group; @@ -318,7 +471,7 @@ static int iommu_group_create_direct_mappings(struct iommu_group *group, struct device *dev) { struct iommu_domain *domain = group->default_domain; - struct iommu_dm_region *entry; + struct iommu_resv_region *entry; struct list_head mappings; unsigned long pg_size; int ret = 0; @@ -331,18 +484,21 @@ static int iommu_group_create_direct_mappings(struct iommu_group *group, pg_size = 1UL << __ffs(domain->pgsize_bitmap); INIT_LIST_HEAD(&mappings); - iommu_get_dm_regions(dev, &mappings); + iommu_get_resv_regions(dev, &mappings); /* We need to consider overlapping regions for different devices */ list_for_each_entry(entry, &mappings, list) { dma_addr_t start, end, addr; - if (domain->ops->apply_dm_region) - domain->ops->apply_dm_region(dev, domain, entry); + if (domain->ops->apply_resv_region) + domain->ops->apply_resv_region(dev, domain, entry); start = ALIGN(entry->start, pg_size); end = ALIGN(entry->start + entry->length, pg_size); + if (entry->type != IOMMU_RESV_DIRECT) + continue; + for (addr = start; addr < end; addr += pg_size) { phys_addr_t phys_addr; @@ -358,7 +514,7 @@ static int iommu_group_create_direct_mappings(struct iommu_group *group, } out: - iommu_put_dm_regions(dev, &mappings); + iommu_put_resv_regions(dev, &mappings); return ret; } @@ -374,7 +530,7 @@ out: int iommu_group_add_device(struct iommu_group *group, struct device *dev) { int ret, i = 0; - struct iommu_device *device; + struct group_device *device; device = kzalloc(sizeof(*device), GFP_KERNEL); if (!device) @@ -383,36 +539,30 @@ int iommu_group_add_device(struct iommu_group *group, struct device *dev) device->dev = dev; ret = sysfs_create_link(&dev->kobj, &group->kobj, "iommu_group"); - if (ret) { - kfree(device); - return ret; - } + if (ret) + goto err_free_device; device->name = kasprintf(GFP_KERNEL, "%s", kobject_name(&dev->kobj)); rename: if (!device->name) { - sysfs_remove_link(&dev->kobj, "iommu_group"); - kfree(device); - return -ENOMEM; + ret = -ENOMEM; + goto err_remove_link; } ret = sysfs_create_link_nowarn(group->devices_kobj, &dev->kobj, device->name); if (ret) { - kfree(device->name); if (ret == -EEXIST && i >= 0) { /* * Account for the slim chance of collision * and append an instance to the name. */ + kfree(device->name); device->name = kasprintf(GFP_KERNEL, "%s.%d", kobject_name(&dev->kobj), i++); goto rename; } - - sysfs_remove_link(&dev->kobj, "iommu_group"); - kfree(device); - return ret; + goto err_free_name; } kobject_get(group->devices_kobj); @@ -424,8 +574,10 @@ rename: mutex_lock(&group->mutex); list_add_tail(&device->list, &group->devices); if (group->domain) - __iommu_attach_device(group->domain, dev); + ret = __iommu_attach_device(group->domain, dev); mutex_unlock(&group->mutex); + if (ret) + goto err_put_group; /* Notify any listeners about change to group. */ blocking_notifier_call_chain(&group->notifier, @@ -436,6 +588,21 @@ rename: pr_info("Adding device %s to group %d\n", dev_name(dev), group->id); return 0; + +err_put_group: + mutex_lock(&group->mutex); + list_del(&device->list); + mutex_unlock(&group->mutex); + dev->iommu_group = NULL; + kobject_put(group->devices_kobj); +err_free_name: + kfree(device->name); +err_remove_link: + sysfs_remove_link(&dev->kobj, "iommu_group"); +err_free_device: + kfree(device); + pr_err("Failed to add device %s to group %d: %d\n", dev_name(dev), group->id, ret); + return ret; } EXPORT_SYMBOL_GPL(iommu_group_add_device); @@ -449,7 +616,7 @@ EXPORT_SYMBOL_GPL(iommu_group_add_device); void iommu_group_remove_device(struct device *dev) { struct iommu_group *group = dev->iommu_group; - struct iommu_device *tmp_device, *device = NULL; + struct group_device *tmp_device, *device = NULL; pr_info("Removing device %s from group %d\n", dev_name(dev), group->id); @@ -484,7 +651,7 @@ EXPORT_SYMBOL_GPL(iommu_group_remove_device); static int iommu_group_device_count(struct iommu_group *group) { - struct iommu_device *entry; + struct group_device *entry; int ret = 0; list_for_each_entry(entry, &group->devices, list) @@ -507,7 +674,7 @@ static int iommu_group_device_count(struct iommu_group *group) static int __iommu_group_for_each_dev(struct iommu_group *group, void *data, int (*fn)(struct device *, void *)) { - struct iommu_device *device; + struct group_device *device; int ret = 0; list_for_each_entry(device, &group->devices, list) { @@ -552,6 +719,19 @@ struct iommu_group *iommu_group_get(struct device *dev) EXPORT_SYMBOL_GPL(iommu_group_get); /** + * iommu_group_ref_get - Increment reference on a group + * @group: the group to use, must not be NULL + * + * This function is called by iommu drivers to take additional references on an + * existing group. Returns the given group for convenience. + */ +struct iommu_group *iommu_group_ref_get(struct iommu_group *group) +{ + kobject_get(group->devices_kobj); + return group; +} + +/** * iommu_group_put - Decrement group reference * @group: the group to use * @@ -1546,20 +1726,38 @@ int iommu_domain_set_attr(struct iommu_domain *domain, } EXPORT_SYMBOL_GPL(iommu_domain_set_attr); -void iommu_get_dm_regions(struct device *dev, struct list_head *list) +void iommu_get_resv_regions(struct device *dev, struct list_head *list) { const struct iommu_ops *ops = dev->bus->iommu_ops; - if (ops && ops->get_dm_regions) - ops->get_dm_regions(dev, list); + if (ops && ops->get_resv_regions) + ops->get_resv_regions(dev, list); } -void iommu_put_dm_regions(struct device *dev, struct list_head *list) +void iommu_put_resv_regions(struct device *dev, struct list_head *list) { const struct iommu_ops *ops = dev->bus->iommu_ops; - if (ops && ops->put_dm_regions) - ops->put_dm_regions(dev, list); + if (ops && ops->put_resv_regions) + ops->put_resv_regions(dev, list); +} + +struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start, + size_t length, + int prot, int type) +{ + struct iommu_resv_region *region; + + region = kzalloc(sizeof(*region), GFP_KERNEL); + if (!region) + return NULL; + + INIT_LIST_HEAD(®ion->list); + region->start = start; + region->length = length; + region->prot = prot; + region->type = type; + return region; } /* Request that a device is direct mapped by the IOMMU */ @@ -1615,6 +1813,21 @@ out: return ret; } +const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode) +{ + const struct iommu_ops *ops = NULL; + struct iommu_device *iommu; + + spin_lock(&iommu_device_lock); + list_for_each_entry(iommu, &iommu_device_list, list) + if (iommu->fwnode == fwnode) { + ops = iommu->ops; + break; + } + spin_unlock(&iommu_device_lock); + return ops; +} + int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode, const struct iommu_ops *ops) { @@ -1661,13 +1874,14 @@ int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids) fwspec = krealloc(dev->iommu_fwspec, size, GFP_KERNEL); if (!fwspec) return -ENOMEM; + + dev->iommu_fwspec = fwspec; } for (i = 0; i < num_ids; i++) fwspec->ids[fwspec->num_ids + i] = ids[i]; fwspec->num_ids += num_ids; - dev->iommu_fwspec = fwspec; return 0; } EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids); diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index e23001bfcfee..b7268a14184f 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -56,13 +56,13 @@ EXPORT_SYMBOL_GPL(init_iova_domain); static struct rb_node * __get_cached_rbnode(struct iova_domain *iovad, unsigned long *limit_pfn) { - if ((*limit_pfn != iovad->dma_32bit_pfn) || + if ((*limit_pfn > iovad->dma_32bit_pfn) || (iovad->cached32_node == NULL)) return rb_last(&iovad->rbroot); else { struct rb_node *prev_node = rb_prev(iovad->cached32_node); struct iova *curr_iova = - container_of(iovad->cached32_node, struct iova, node); + rb_entry(iovad->cached32_node, struct iova, node); *limit_pfn = curr_iova->pfn_lo - 1; return prev_node; } @@ -86,11 +86,11 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free) if (!iovad->cached32_node) return; curr = iovad->cached32_node; - cached_iova = container_of(curr, struct iova, node); + cached_iova = rb_entry(curr, struct iova, node); if (free->pfn_lo >= cached_iova->pfn_lo) { struct rb_node *node = rb_next(&free->node); - struct iova *iova = container_of(node, struct iova, node); + struct iova *iova = rb_entry(node, struct iova, node); /* only cache if it's below 32bit pfn */ if (node && iova->pfn_lo < iovad->dma_32bit_pfn) @@ -125,7 +125,7 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad, curr = __get_cached_rbnode(iovad, &limit_pfn); prev = curr; while (curr) { - struct iova *curr_iova = container_of(curr, struct iova, node); + struct iova *curr_iova = rb_entry(curr, struct iova, node); if (limit_pfn < curr_iova->pfn_lo) goto move_left; @@ -171,8 +171,7 @@ move_left: /* Figure out where to put new node */ while (*entry) { - struct iova *this = container_of(*entry, - struct iova, node); + struct iova *this = rb_entry(*entry, struct iova, node); parent = *entry; if (new->pfn_lo < this->pfn_lo) @@ -201,7 +200,7 @@ iova_insert_rbtree(struct rb_root *root, struct iova *iova) struct rb_node **new = &(root->rb_node), *parent = NULL; /* Figure out where to put new node */ while (*new) { - struct iova *this = container_of(*new, struct iova, node); + struct iova *this = rb_entry(*new, struct iova, node); parent = *new; @@ -311,7 +310,7 @@ private_find_iova(struct iova_domain *iovad, unsigned long pfn) assert_spin_locked(&iovad->iova_rbtree_lock); while (node) { - struct iova *iova = container_of(node, struct iova, node); + struct iova *iova = rb_entry(node, struct iova, node); /* If pfn falls within iova's range, return iova */ if ((pfn >= iova->pfn_lo) && (pfn <= iova->pfn_hi)) { @@ -463,7 +462,7 @@ void put_iova_domain(struct iova_domain *iovad) spin_lock_irqsave(&iovad->iova_rbtree_lock, flags); node = rb_first(&iovad->rbroot); while (node) { - struct iova *iova = container_of(node, struct iova, node); + struct iova *iova = rb_entry(node, struct iova, node); rb_erase(node, &iovad->rbroot); free_iova_mem(iova); @@ -477,7 +476,7 @@ static int __is_range_overlap(struct rb_node *node, unsigned long pfn_lo, unsigned long pfn_hi) { - struct iova *iova = container_of(node, struct iova, node); + struct iova *iova = rb_entry(node, struct iova, node); if ((pfn_lo <= iova->pfn_hi) && (pfn_hi >= iova->pfn_lo)) return 1; @@ -541,7 +540,7 @@ reserve_iova(struct iova_domain *iovad, spin_lock_irqsave(&iovad->iova_rbtree_lock, flags); for (node = rb_first(&iovad->rbroot); node; node = rb_next(node)) { if (__is_range_overlap(node, pfn_lo, pfn_hi)) { - iova = container_of(node, struct iova, node); + iova = rb_entry(node, struct iova, node); __adjust_overlap_range(iova, &pfn_lo, &pfn_hi); if ((pfn_lo >= iova->pfn_lo) && (pfn_hi <= iova->pfn_hi)) @@ -578,7 +577,7 @@ copy_reserved_iova(struct iova_domain *from, struct iova_domain *to) spin_lock_irqsave(&from->iova_rbtree_lock, flags); for (node = rb_first(&from->rbroot); node; node = rb_next(node)) { - struct iova *iova = container_of(node, struct iova, node); + struct iova *iova = rb_entry(node, struct iova, node); struct iova *new_iova; new_iova = reserve_iova(to, iova->pfn_lo, iova->pfn_hi); diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index ace331da6459..b7e14ee863f9 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -313,6 +313,8 @@ static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain) domain->cfg.ias = 32; domain->cfg.oas = 40; domain->cfg.tlb = &ipmmu_gather_ops; + domain->io_domain.geometry.aperture_end = DMA_BIT_MASK(32); + domain->io_domain.geometry.force_aperture = true; /* * TODO: Add support for coherent walk through CCI with DVM and remove * cache handling. For now, delegate it to the io-pgtable code. diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index b09692bb5b0a..d0448353d501 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -371,6 +371,58 @@ static int msm_iommu_domain_config(struct msm_priv *priv) return 0; } +/* Must be called under msm_iommu_lock */ +static struct msm_iommu_dev *find_iommu_for_dev(struct device *dev) +{ + struct msm_iommu_dev *iommu, *ret = NULL; + struct msm_iommu_ctx_dev *master; + + list_for_each_entry(iommu, &qcom_iommu_devices, dev_node) { + master = list_first_entry(&iommu->ctx_list, + struct msm_iommu_ctx_dev, + list); + if (master->of_node == dev->of_node) { + ret = iommu; + break; + } + } + + return ret; +} + +static int msm_iommu_add_device(struct device *dev) +{ + struct msm_iommu_dev *iommu; + unsigned long flags; + int ret = 0; + + spin_lock_irqsave(&msm_iommu_lock, flags); + + iommu = find_iommu_for_dev(dev); + if (iommu) + iommu_device_link(&iommu->iommu, dev); + else + ret = -ENODEV; + + spin_unlock_irqrestore(&msm_iommu_lock, flags); + + return ret; +} + +static void msm_iommu_remove_device(struct device *dev) +{ + struct msm_iommu_dev *iommu; + unsigned long flags; + + spin_lock_irqsave(&msm_iommu_lock, flags); + + iommu = find_iommu_for_dev(dev); + if (iommu) + iommu_device_unlink(&iommu->iommu, dev); + + spin_unlock_irqrestore(&msm_iommu_lock, flags); +} + static int msm_iommu_attach_dev(struct iommu_domain *domain, struct device *dev) { int ret = 0; @@ -646,6 +698,8 @@ static struct iommu_ops msm_iommu_ops = { .unmap = msm_iommu_unmap, .map_sg = default_iommu_map_sg, .iova_to_phys = msm_iommu_iova_to_phys, + .add_device = msm_iommu_add_device, + .remove_device = msm_iommu_remove_device, .pgsize_bitmap = MSM_IOMMU_PGSIZES, .of_xlate = qcom_iommu_of_xlate, }; @@ -653,6 +707,7 @@ static struct iommu_ops msm_iommu_ops = { static int msm_iommu_probe(struct platform_device *pdev) { struct resource *r; + resource_size_t ioaddr; struct msm_iommu_dev *iommu; int ret, par, val; @@ -696,6 +751,7 @@ static int msm_iommu_probe(struct platform_device *pdev) ret = PTR_ERR(iommu->base); goto fail; } + ioaddr = r->start; iommu->irq = platform_get_irq(pdev, 0); if (iommu->irq < 0) { @@ -737,7 +793,22 @@ static int msm_iommu_probe(struct platform_device *pdev) } list_add(&iommu->dev_node, &qcom_iommu_devices); - of_iommu_set_ops(pdev->dev.of_node, &msm_iommu_ops); + + ret = iommu_device_sysfs_add(&iommu->iommu, iommu->dev, NULL, + "msm-smmu.%pa", &ioaddr); + if (ret) { + pr_err("Could not add msm-smmu at %pa to sysfs\n", &ioaddr); + goto fail; + } + + iommu_device_set_ops(&iommu->iommu, &msm_iommu_ops); + iommu_device_set_fwnode(&iommu->iommu, &pdev->dev.of_node->fwnode); + + ret = iommu_device_register(&iommu->iommu); + if (ret) { + pr_err("Could not register msm-smmu at %pa\n", &ioaddr); + goto fail; + } pr_info("device mapped at %p, irq %d with %d ctx banks\n", iommu->base, iommu->irq, iommu->ncb); diff --git a/drivers/iommu/msm_iommu.h b/drivers/iommu/msm_iommu.h index 4ca25d50d679..ae92d2779c42 100644 --- a/drivers/iommu/msm_iommu.h +++ b/drivers/iommu/msm_iommu.h @@ -19,6 +19,7 @@ #define MSM_IOMMU_H #include <linux/interrupt.h> +#include <linux/iommu.h> #include <linux/clk.h> /* Sharability attributes of MSM IOMMU mappings */ @@ -68,6 +69,8 @@ struct msm_iommu_dev { struct list_head dom_node; struct list_head ctx_list; DECLARE_BITMAP(context_map, IOMMU_MAX_CBS); + + struct iommu_device iommu; }; /** diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index b12c12d74c33..5d14cd15198d 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -195,14 +195,14 @@ static irqreturn_t mtk_iommu_isr(int irq, void *dev_id) static void mtk_iommu_config(struct mtk_iommu_data *data, struct device *dev, bool enable) { - struct mtk_iommu_client_priv *head, *cur, *next; struct mtk_smi_larb_iommu *larb_mmu; unsigned int larbid, portid; + struct iommu_fwspec *fwspec = dev->iommu_fwspec; + int i; - head = dev->archdata.iommu; - list_for_each_entry_safe(cur, next, &head->client, client) { - larbid = MTK_M4U_TO_LARB(cur->mtk_m4u_id); - portid = MTK_M4U_TO_PORT(cur->mtk_m4u_id); + for (i = 0; i < fwspec->num_ids; ++i) { + larbid = MTK_M4U_TO_LARB(fwspec->ids[i]); + portid = MTK_M4U_TO_PORT(fwspec->ids[i]); larb_mmu = &data->smi_imu.larb_imu[larbid]; dev_dbg(dev, "%s iommu port: %d\n", @@ -282,14 +282,12 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain, struct device *dev) { struct mtk_iommu_domain *dom = to_mtk_domain(domain); - struct mtk_iommu_client_priv *priv = dev->archdata.iommu; - struct mtk_iommu_data *data; + struct mtk_iommu_data *data = dev->iommu_fwspec->iommu_priv; int ret; - if (!priv) + if (!data) return -ENODEV; - data = dev_get_drvdata(priv->m4udev); if (!data->m4u_dom) { data->m4u_dom = dom; ret = mtk_iommu_domain_finalise(data); @@ -310,13 +308,11 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain, static void mtk_iommu_detach_device(struct iommu_domain *domain, struct device *dev) { - struct mtk_iommu_client_priv *priv = dev->archdata.iommu; - struct mtk_iommu_data *data; + struct mtk_iommu_data *data = dev->iommu_fwspec->iommu_priv; - if (!priv) + if (!data) return; - data = dev_get_drvdata(priv->m4udev); mtk_iommu_config(data, dev, false); } @@ -364,10 +360,14 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain, static int mtk_iommu_add_device(struct device *dev) { + struct mtk_iommu_data *data; struct iommu_group *group; - if (!dev->archdata.iommu) /* Not a iommu client device */ - return -ENODEV; + if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops) + return -ENODEV; /* Not a iommu client device */ + + data = dev->iommu_fwspec->iommu_priv; + iommu_device_link(&data->iommu, dev); group = iommu_group_get_for_dev(dev); if (IS_ERR(group)) @@ -379,44 +379,38 @@ static int mtk_iommu_add_device(struct device *dev) static void mtk_iommu_remove_device(struct device *dev) { - struct mtk_iommu_client_priv *head, *cur, *next; + struct mtk_iommu_data *data; - head = dev->archdata.iommu; - if (!head) + if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops) return; - list_for_each_entry_safe(cur, next, &head->client, client) { - list_del(&cur->client); - kfree(cur); - } - kfree(head); - dev->archdata.iommu = NULL; + data = dev->iommu_fwspec->iommu_priv; + iommu_device_unlink(&data->iommu, dev); iommu_group_remove_device(dev); + iommu_fwspec_free(dev); } static struct iommu_group *mtk_iommu_device_group(struct device *dev) { - struct mtk_iommu_data *data; - struct mtk_iommu_client_priv *priv; + struct mtk_iommu_data *data = dev->iommu_fwspec->iommu_priv; - priv = dev->archdata.iommu; - if (!priv) + if (!data) return ERR_PTR(-ENODEV); /* All the client devices are in the same m4u iommu-group */ - data = dev_get_drvdata(priv->m4udev); if (!data->m4u_group) { data->m4u_group = iommu_group_alloc(); if (IS_ERR(data->m4u_group)) dev_err(dev, "Failed to allocate M4U IOMMU group\n"); + } else { + iommu_group_ref_get(data->m4u_group); } return data->m4u_group; } static int mtk_iommu_of_xlate(struct device *dev, struct of_phandle_args *args) { - struct mtk_iommu_client_priv *head, *priv, *next; struct platform_device *m4updev; if (args->args_count != 1) { @@ -425,38 +419,16 @@ static int mtk_iommu_of_xlate(struct device *dev, struct of_phandle_args *args) return -EINVAL; } - if (!dev->archdata.iommu) { + if (!dev->iommu_fwspec->iommu_priv) { /* Get the m4u device */ m4updev = of_find_device_by_node(args->np); if (WARN_ON(!m4updev)) return -EINVAL; - head = kzalloc(sizeof(*head), GFP_KERNEL); - if (!head) - return -ENOMEM; - - dev->archdata.iommu = head; - INIT_LIST_HEAD(&head->client); - head->m4udev = &m4updev->dev; - } else { - head = dev->archdata.iommu; + dev->iommu_fwspec->iommu_priv = platform_get_drvdata(m4updev); } - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) - goto err_free_mem; - - priv->mtk_m4u_id = args->args[0]; - list_add_tail(&priv->client, &head->client); - - return 0; - -err_free_mem: - list_for_each_entry_safe(priv, next, &head->client, client) - kfree(priv); - kfree(head); - dev->archdata.iommu = NULL; - return -ENOMEM; + return iommu_fwspec_add_ids(dev, args->args, 1); } static struct iommu_ops mtk_iommu_ops = { @@ -534,6 +506,7 @@ static int mtk_iommu_probe(struct platform_device *pdev) struct mtk_iommu_data *data; struct device *dev = &pdev->dev; struct resource *res; + resource_size_t ioaddr; struct component_match *match = NULL; void *protect; int i, larb_nr, ret; @@ -556,6 +529,7 @@ static int mtk_iommu_probe(struct platform_device *pdev) data->base = devm_ioremap_resource(dev, res); if (IS_ERR(data->base)) return PTR_ERR(data->base); + ioaddr = res->start; data->irq = platform_get_irq(pdev, 0); if (data->irq < 0) @@ -583,17 +557,19 @@ static int mtk_iommu_probe(struct platform_device *pdev) continue; plarbdev = of_find_device_by_node(larbnode); - of_node_put(larbnode); if (!plarbdev) { plarbdev = of_platform_device_create( larbnode, NULL, platform_bus_type.dev_root); - if (!plarbdev) + if (!plarbdev) { + of_node_put(larbnode); return -EPROBE_DEFER; + } } data->smi_imu.larb_imu[i].dev = &plarbdev->dev; - component_match_add(dev, &match, compare_of, larbnode); + component_match_add_release(dev, &match, release_of, + compare_of, larbnode); } platform_set_drvdata(pdev, data); @@ -602,6 +578,18 @@ static int mtk_iommu_probe(struct platform_device *pdev) if (ret) return ret; + ret = iommu_device_sysfs_add(&data->iommu, dev, NULL, + "mtk-iommu.%pa", &ioaddr); + if (ret) + return ret; + + iommu_device_set_ops(&data->iommu, &mtk_iommu_ops); + iommu_device_set_fwnode(&data->iommu, &pdev->dev.of_node->fwnode); + + ret = iommu_device_register(&data->iommu); + if (ret) + return ret; + if (!iommu_present(&platform_bus_type)) bus_set_iommu(&platform_bus_type, &mtk_iommu_ops); @@ -612,6 +600,9 @@ static int mtk_iommu_remove(struct platform_device *pdev) { struct mtk_iommu_data *data = platform_get_drvdata(pdev); + iommu_device_sysfs_remove(&data->iommu); + iommu_device_unregister(&data->iommu); + if (iommu_present(&platform_bus_type)) bus_set_iommu(&platform_bus_type, NULL); @@ -690,7 +681,6 @@ static int mtk_iommu_init_fn(struct device_node *np) return ret; } - of_iommu_set_ops(np, &mtk_iommu_ops); return 0; } diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h index 3dab13b4a211..2a28eadeea0e 100644 --- a/drivers/iommu/mtk_iommu.h +++ b/drivers/iommu/mtk_iommu.h @@ -34,12 +34,6 @@ struct mtk_iommu_suspend_reg { u32 int_main_control; }; -struct mtk_iommu_client_priv { - struct list_head client; - unsigned int mtk_m4u_id; - struct device *m4udev; -}; - struct mtk_iommu_domain; struct mtk_iommu_data { @@ -53,6 +47,8 @@ struct mtk_iommu_data { struct iommu_group *m4u_group; struct mtk_smi_iommu smi_imu; /* SMI larb iommu info */ bool enable_4GB; + + struct iommu_device iommu; }; static inline int compare_of(struct device *dev, void *data) @@ -60,6 +56,11 @@ static inline int compare_of(struct device *dev, void *data) return dev->of_node == data; } +static inline void release_of(struct device *dev, void *data) +{ + of_node_put(data); +} + static inline int mtk_iommu_bind(struct device *dev) { struct mtk_iommu_data *data = dev_get_drvdata(dev); diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index b8aeb0768483..19e010083408 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -204,14 +204,14 @@ static irqreturn_t mtk_iommu_isr(int irq, void *dev_id) static void mtk_iommu_config(struct mtk_iommu_data *data, struct device *dev, bool enable) { - struct mtk_iommu_client_priv *head, *cur, *next; struct mtk_smi_larb_iommu *larb_mmu; unsigned int larbid, portid; + struct iommu_fwspec *fwspec = dev->iommu_fwspec; + int i; - head = dev->archdata.iommu; - list_for_each_entry_safe(cur, next, &head->client, client) { - larbid = mt2701_m4u_to_larb(cur->mtk_m4u_id); - portid = mt2701_m4u_to_port(cur->mtk_m4u_id); + for (i = 0; i < fwspec->num_ids; ++i) { + larbid = mt2701_m4u_to_larb(fwspec->ids[i]); + portid = mt2701_m4u_to_port(fwspec->ids[i]); larb_mmu = &data->smi_imu.larb_imu[larbid]; dev_dbg(dev, "%s iommu port: %d\n", @@ -271,14 +271,12 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain, struct device *dev) { struct mtk_iommu_domain *dom = to_mtk_domain(domain); - struct mtk_iommu_client_priv *priv = dev->archdata.iommu; - struct mtk_iommu_data *data; + struct mtk_iommu_data *data = dev->iommu_fwspec->iommu_priv; int ret; - if (!priv) + if (!data) return -ENODEV; - data = dev_get_drvdata(priv->m4udev); if (!data->m4u_dom) { data->m4u_dom = dom; ret = mtk_iommu_domain_finalise(data); @@ -295,13 +293,11 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain, static void mtk_iommu_detach_device(struct iommu_domain *domain, struct device *dev) { - struct mtk_iommu_client_priv *priv = dev->archdata.iommu; - struct mtk_iommu_data *data; + struct mtk_iommu_data *data = dev->iommu_fwspec->iommu_priv; - if (!priv) + if (!data) return; - data = dev_get_drvdata(priv->m4udev); mtk_iommu_config(data, dev, false); } @@ -366,6 +362,8 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain, return pa; } +static struct iommu_ops mtk_iommu_ops; + /* * MTK generation one iommu HW only support one iommu domain, and all the client * sharing the same iova address space. @@ -373,7 +371,7 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain, static int mtk_iommu_create_mapping(struct device *dev, struct of_phandle_args *args) { - struct mtk_iommu_client_priv *head, *priv, *next; + struct mtk_iommu_data *data; struct platform_device *m4updev; struct dma_iommu_mapping *mtk_mapping; struct device *m4udev; @@ -385,41 +383,37 @@ static int mtk_iommu_create_mapping(struct device *dev, return -EINVAL; } - if (!dev->archdata.iommu) { + if (!dev->iommu_fwspec) { + ret = iommu_fwspec_init(dev, &args->np->fwnode, &mtk_iommu_ops); + if (ret) + return ret; + } else if (dev->iommu_fwspec->ops != &mtk_iommu_ops) { + return -EINVAL; + } + + if (!dev->iommu_fwspec->iommu_priv) { /* Get the m4u device */ m4updev = of_find_device_by_node(args->np); if (WARN_ON(!m4updev)) return -EINVAL; - head = kzalloc(sizeof(*head), GFP_KERNEL); - if (!head) - return -ENOMEM; - - dev->archdata.iommu = head; - INIT_LIST_HEAD(&head->client); - head->m4udev = &m4updev->dev; - } else { - head = dev->archdata.iommu; + dev->iommu_fwspec->iommu_priv = platform_get_drvdata(m4updev); } - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) { - ret = -ENOMEM; - goto err_free_mem; - } - priv->mtk_m4u_id = args->args[0]; - list_add_tail(&priv->client, &head->client); + ret = iommu_fwspec_add_ids(dev, args->args, 1); + if (ret) + return ret; - m4udev = head->m4udev; + data = dev->iommu_fwspec->iommu_priv; + m4udev = data->dev; mtk_mapping = m4udev->archdata.iommu; if (!mtk_mapping) { /* MTK iommu support 4GB iova address space. */ mtk_mapping = arm_iommu_create_mapping(&platform_bus_type, 0, 1ULL << 32); - if (IS_ERR(mtk_mapping)) { - ret = PTR_ERR(mtk_mapping); - goto err_free_mem; - } + if (IS_ERR(mtk_mapping)) + return PTR_ERR(mtk_mapping); + m4udev->archdata.iommu = mtk_mapping; } @@ -432,11 +426,6 @@ static int mtk_iommu_create_mapping(struct device *dev, err_release_mapping: arm_iommu_release_mapping(mtk_mapping); m4udev->archdata.iommu = NULL; -err_free_mem: - list_for_each_entry_safe(priv, next, &head->client, client) - kfree(priv); - kfree(head); - dev->archdata.iommu = NULL; return ret; } @@ -458,8 +447,8 @@ static int mtk_iommu_add_device(struct device *dev) of_node_put(iommu_spec.np); } - if (!dev->archdata.iommu) /* Not a iommu client device */ - return -ENODEV; + if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops) + return -ENODEV; /* Not a iommu client device */ group = iommu_group_get_for_dev(dev); if (IS_ERR(group)) @@ -471,37 +460,27 @@ static int mtk_iommu_add_device(struct device *dev) static void mtk_iommu_remove_device(struct device *dev) { - struct mtk_iommu_client_priv *head, *cur, *next; - - head = dev->archdata.iommu; - if (!head) + if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops) return; - list_for_each_entry_safe(cur, next, &head->client, client) { - list_del(&cur->client); - kfree(cur); - } - kfree(head); - dev->archdata.iommu = NULL; - iommu_group_remove_device(dev); + iommu_fwspec_free(dev); } static struct iommu_group *mtk_iommu_device_group(struct device *dev) { - struct mtk_iommu_data *data; - struct mtk_iommu_client_priv *priv; + struct mtk_iommu_data *data = dev->iommu_fwspec->iommu_priv; - priv = dev->archdata.iommu; - if (!priv) + if (!data) return ERR_PTR(-ENODEV); /* All the client devices are in the same m4u iommu-group */ - data = dev_get_drvdata(priv->m4udev); if (!data->m4u_group) { data->m4u_group = iommu_group_alloc(); if (IS_ERR(data->m4u_group)) dev_err(dev, "Failed to allocate M4U IOMMU group\n"); + } else { + iommu_group_ref_get(data->m4u_group); } return data->m4u_group; } @@ -624,17 +603,19 @@ static int mtk_iommu_probe(struct platform_device *pdev) continue; plarbdev = of_find_device_by_node(larb_spec.np); - of_node_put(larb_spec.np); if (!plarbdev) { plarbdev = of_platform_device_create( larb_spec.np, NULL, platform_bus_type.dev_root); - if (!plarbdev) + if (!plarbdev) { + of_node_put(larb_spec.np); return -EPROBE_DEFER; + } } data->smi_imu.larb_imu[larb_nr].dev = &plarbdev->dev; - component_match_add(dev, &match, compare_of, larb_spec.np); + component_match_add_release(dev, &match, release_of, + compare_of, larb_spec.np); larb_nr++; } diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c index 5b82862f571f..2683e9fc0dcf 100644 --- a/drivers/iommu/of_iommu.c +++ b/drivers/iommu/of_iommu.c @@ -96,45 +96,6 @@ int of_get_dma_window(struct device_node *dn, const char *prefix, int index, } EXPORT_SYMBOL_GPL(of_get_dma_window); -struct of_iommu_node { - struct list_head list; - struct device_node *np; - const struct iommu_ops *ops; -}; -static LIST_HEAD(of_iommu_list); -static DEFINE_SPINLOCK(of_iommu_lock); - -void of_iommu_set_ops(struct device_node *np, const struct iommu_ops *ops) -{ - struct of_iommu_node *iommu = kzalloc(sizeof(*iommu), GFP_KERNEL); - - if (WARN_ON(!iommu)) - return; - - of_node_get(np); - INIT_LIST_HEAD(&iommu->list); - iommu->np = np; - iommu->ops = ops; - spin_lock(&of_iommu_lock); - list_add_tail(&iommu->list, &of_iommu_list); - spin_unlock(&of_iommu_lock); -} - -const struct iommu_ops *of_iommu_get_ops(struct device_node *np) -{ - struct of_iommu_node *node; - const struct iommu_ops *ops = NULL; - - spin_lock(&of_iommu_lock); - list_for_each_entry(node, &of_iommu_list, list) - if (node->np == np) { - ops = node->ops; - break; - } - spin_unlock(&of_iommu_lock); - return ops; -} - static int __get_pci_rid(struct pci_dev *pdev, u16 alias, void *data) { struct of_phandle_args *iommu_spec = data; @@ -166,7 +127,7 @@ static const struct iommu_ops "iommu-map-mask", &iommu_spec.np, iommu_spec.args)) return NULL; - ops = of_iommu_get_ops(iommu_spec.np); + ops = iommu_ops_from_fwnode(&iommu_spec.np->fwnode); if (!ops || !ops->of_xlate || iommu_fwspec_init(&pdev->dev, &iommu_spec.np->fwnode, ops) || ops->of_xlate(&pdev->dev, &iommu_spec)) @@ -196,7 +157,7 @@ const struct iommu_ops *of_iommu_configure(struct device *dev, "#iommu-cells", idx, &iommu_spec)) { np = iommu_spec.np; - ops = of_iommu_get_ops(np); + ops = iommu_ops_from_fwnode(&np->fwnode); if (!ops || !ops->of_xlate || iommu_fwspec_init(dev, &np->fwnode, ops) || diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c index 3b44b1d82f3b..179e636a4d91 100644 --- a/drivers/iommu/s390-iommu.c +++ b/drivers/iommu/s390-iommu.c @@ -8,7 +8,6 @@ #include <linux/pci.h> #include <linux/iommu.h> #include <linux/iommu-helper.h> -#include <linux/pci.h> #include <linux/sizes.h> #include <asm/pci_dma.h> |