diff options
Diffstat (limited to 'drivers/iommu')
| -rw-r--r-- | drivers/iommu/amd_iommu.c | 99 | ||||
| -rw-r--r-- | drivers/iommu/amd_iommu_init.c | 569 | ||||
| -rw-r--r-- | drivers/iommu/amd_iommu_types.h | 13 | ||||
| -rw-r--r-- | drivers/iommu/amd_iommu_v2.c | 4 | ||||
| -rw-r--r-- | drivers/iommu/exynos-iommu.c | 4 | ||||
| -rw-r--r-- | drivers/iommu/intel-iommu.c | 93 | ||||
| -rw-r--r-- | drivers/iommu/iommu.c | 611 | ||||
| -rw-r--r-- | drivers/iommu/irq_remapping.c | 5 | ||||
| -rw-r--r-- | drivers/iommu/msm_iommu.c | 5 | ||||
| -rw-r--r-- | drivers/iommu/omap-iommu.c | 4 | ||||
| -rw-r--r-- | drivers/iommu/tegra-gart.c | 5 | ||||
| -rw-r--r-- | drivers/iommu/tegra-smmu.c | 5 |
12 files changed, 1087 insertions, 330 deletions
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 625626391f2d..6d1cbdfc9b2a 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -256,11 +256,21 @@ static bool check_device(struct device *dev) return true; } +static void swap_pci_ref(struct pci_dev **from, struct pci_dev *to) +{ + pci_dev_put(*from); + *from = to; +} + +#define REQ_ACS_FLAGS (PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF) + static int iommu_init_device(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); + struct pci_dev *dma_pdev, *pdev = to_pci_dev(dev); struct iommu_dev_data *dev_data; + struct iommu_group *group; u16 alias; + int ret; if (dev->archdata.iommu) return 0; @@ -281,8 +291,43 @@ static int iommu_init_device(struct device *dev) return -ENOTSUPP; } dev_data->alias_data = alias_data; + + dma_pdev = pci_get_bus_and_slot(alias >> 8, alias & 0xff); + } else + dma_pdev = pci_dev_get(pdev); + + swap_pci_ref(&dma_pdev, pci_get_dma_source(dma_pdev)); + + if (dma_pdev->multifunction && + !pci_acs_enabled(dma_pdev, REQ_ACS_FLAGS)) + swap_pci_ref(&dma_pdev, + pci_get_slot(dma_pdev->bus, + PCI_DEVFN(PCI_SLOT(dma_pdev->devfn), + 0))); + + while (!pci_is_root_bus(dma_pdev->bus)) { + if (pci_acs_path_enabled(dma_pdev->bus->self, + NULL, REQ_ACS_FLAGS)) + break; + + swap_pci_ref(&dma_pdev, pci_dev_get(dma_pdev->bus->self)); + } + + group = iommu_group_get(&dma_pdev->dev); + pci_dev_put(dma_pdev); + if (!group) { + group = iommu_group_alloc(); + if (IS_ERR(group)) + return PTR_ERR(group); } + ret = iommu_group_add_device(group, dev); + + iommu_group_put(group); + + if (ret) + return ret; + if (pci_iommuv2_capable(pdev)) { struct amd_iommu *iommu; @@ -311,6 +356,8 @@ static void iommu_ignore_device(struct device *dev) static void iommu_uninit_device(struct device *dev) { + iommu_group_remove_device(dev); + /* * Nothing to do here - we keep dev_data around for unplugged devices * and reuse it when the device is re-plugged - not doing so would @@ -384,7 +431,6 @@ DECLARE_STATS_COUNTER(invalidate_iotlb); DECLARE_STATS_COUNTER(invalidate_iotlb_all); DECLARE_STATS_COUNTER(pri_requests); - static struct dentry *stats_dir; static struct dentry *de_fflush; @@ -2073,7 +2119,7 @@ out_err: /* FIXME: Move this to PCI code */ #define PCI_PRI_TLP_OFF (1 << 15) -bool pci_pri_tlp_required(struct pci_dev *pdev) +static bool pci_pri_tlp_required(struct pci_dev *pdev) { u16 status; int pos; @@ -2254,6 +2300,18 @@ static int device_change_notifier(struct notifier_block *nb, iommu_init_device(dev); + /* + * dev_data is still NULL and + * got initialized in iommu_init_device + */ + dev_data = get_dev_data(dev); + + if (iommu_pass_through || dev_data->iommu_v2) { + dev_data->passthrough = true; + attach_device(dev, pt_domain); + break; + } + domain = domain_for_device(dev); /* allocate a protection domain if a device is added */ @@ -2271,10 +2329,7 @@ static int device_change_notifier(struct notifier_block *nb, dev_data = get_dev_data(dev); - if (!dev_data->passthrough) - dev->archdata.dma_ops = &amd_iommu_dma_ops; - else - dev->archdata.dma_ops = &nommu_dma_ops; + dev->archdata.dma_ops = &amd_iommu_dma_ops; break; case BUS_NOTIFY_DEL_DEVICE: @@ -2972,6 +3027,11 @@ int __init amd_iommu_init_dma_ops(void) amd_iommu_stats_init(); + if (amd_iommu_unmap_flush) + pr_info("AMD-Vi: IO/TLB flush on unmap enabled\n"); + else + pr_info("AMD-Vi: Lazy IO/TLB flushing enabled\n"); + return 0; free_domains: @@ -3078,6 +3138,10 @@ static int amd_iommu_domain_init(struct iommu_domain *dom) dom->priv = domain; + dom->geometry.aperture_start = 0; + dom->geometry.aperture_end = ~0ULL; + dom->geometry.force_aperture = true; + return 0; out_free: @@ -3236,26 +3300,6 @@ static int amd_iommu_domain_has_cap(struct iommu_domain *domain, return 0; } -static int amd_iommu_device_group(struct device *dev, unsigned int *groupid) -{ - struct iommu_dev_data *dev_data = dev->archdata.iommu; - struct pci_dev *pdev = to_pci_dev(dev); - u16 devid; - - if (!dev_data) - return -ENODEV; - - if (pdev->is_virtfn || !iommu_group_mf) - devid = dev_data->devid; - else - devid = calc_devid(pdev->bus->number, - PCI_DEVFN(PCI_SLOT(pdev->devfn), 0)); - - *groupid = amd_iommu_alias_table[devid]; - - return 0; -} - static struct iommu_ops amd_iommu_ops = { .domain_init = amd_iommu_domain_init, .domain_destroy = amd_iommu_domain_destroy, @@ -3265,7 +3309,6 @@ static struct iommu_ops amd_iommu_ops = { .unmap = amd_iommu_unmap, .iova_to_phys = amd_iommu_iova_to_phys, .domain_has_cap = amd_iommu_domain_has_cap, - .device_group = amd_iommu_device_group, .pgsize_bitmap = AMD_IOMMU_PGSIZES, }; diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index a33612f3206f..500e7f15f5c2 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -26,6 +26,8 @@ #include <linux/msi.h> #include <linux/amd-iommu.h> #include <linux/export.h> +#include <linux/acpi.h> +#include <acpi/acpi.h> #include <asm/pci-direct.h> #include <asm/iommu.h> #include <asm/gart.h> @@ -122,7 +124,7 @@ struct ivmd_header { bool amd_iommu_dump; -static int __initdata amd_iommu_detected; +static bool amd_iommu_detected; static bool __initdata amd_iommu_disabled; u16 amd_iommu_last_bdf; /* largest PCI device id we have @@ -149,11 +151,6 @@ bool amd_iommu_v2_present __read_mostly; bool amd_iommu_force_isolation __read_mostly; /* - * The ACPI table parsing functions set this variable on an error - */ -static int __initdata amd_iommu_init_err; - -/* * List of protection domains - used during resume */ LIST_HEAD(amd_iommu_pd_list); @@ -190,13 +187,23 @@ static u32 dev_table_size; /* size of the device table */ static u32 alias_table_size; /* size of the alias table */ static u32 rlookup_table_size; /* size if the rlookup table */ -/* - * This function flushes all internal caches of - * the IOMMU used by this driver. - */ -extern void iommu_flush_all_caches(struct amd_iommu *iommu); +enum iommu_init_state { + IOMMU_START_STATE, + IOMMU_IVRS_DETECTED, + IOMMU_ACPI_FINISHED, + IOMMU_ENABLED, + IOMMU_PCI_INIT, + IOMMU_INTERRUPTS_EN, + IOMMU_DMA_OPS, + IOMMU_INITIALIZED, + IOMMU_NOT_FOUND, + IOMMU_INIT_ERROR, +}; + +static enum iommu_init_state init_state = IOMMU_START_STATE; static int amd_iommu_enable_interrupts(void); +static int __init iommu_go_to_state(enum iommu_init_state state); static inline void update_last_devid(u16 devid) { @@ -321,23 +328,6 @@ static void iommu_set_inv_tlb_timeout(struct amd_iommu *iommu, int timeout) /* Function to enable the hardware */ static void iommu_enable(struct amd_iommu *iommu) { - static const char * const feat_str[] = { - "PreF", "PPR", "X2APIC", "NX", "GT", "[5]", - "IA", "GA", "HE", "PC", NULL - }; - int i; - - printk(KERN_INFO "AMD-Vi: Enabling IOMMU at %s cap 0x%hx", - dev_name(&iommu->dev->dev), iommu->cap_ptr); - - if (iommu->cap & (1 << IOMMU_CAP_EFR)) { - printk(KERN_CONT " extended features: "); - for (i = 0; feat_str[i]; ++i) - if (iommu_feature(iommu, (1ULL << i))) - printk(KERN_CONT " %s", feat_str[i]); - } - printk(KERN_CONT "\n"); - iommu_feature_enable(iommu, CONTROL_IOMMU_EN); } @@ -358,7 +348,7 @@ static void iommu_disable(struct amd_iommu *iommu) * mapping and unmapping functions for the IOMMU MMIO space. Each AMD IOMMU in * the system has one. */ -static u8 * __init iommu_map_mmio_space(u64 address) +static u8 __iomem * __init iommu_map_mmio_space(u64 address) { if (!request_mem_region(address, MMIO_REGION_LENGTH, "amd_iommu")) { pr_err("AMD-Vi: Can not reserve memory region %llx for mmio\n", @@ -367,7 +357,7 @@ static u8 * __init iommu_map_mmio_space(u64 address) return NULL; } - return ioremap_nocache(address, MMIO_REGION_LENGTH); + return (u8 __iomem *)ioremap_nocache(address, MMIO_REGION_LENGTH); } static void __init iommu_unmap_mmio_space(struct amd_iommu *iommu) @@ -463,11 +453,9 @@ static int __init find_last_devid_acpi(struct acpi_table_header *table) */ for (i = 0; i < table->length; ++i) checksum += p[i]; - if (checksum != 0) { + if (checksum != 0) /* ACPI table corrupt */ - amd_iommu_init_err = -ENODEV; - return 0; - } + return -ENODEV; p += IVRS_HEADER_LENGTH; @@ -726,90 +714,6 @@ static void __init set_device_exclusion_range(u16 devid, struct ivmd_header *m) } /* - * This function reads some important data from the IOMMU PCI space and - * initializes the driver data structure with it. It reads the hardware - * capabilities and the first/last device entries - */ -static void __init init_iommu_from_pci(struct amd_iommu *iommu) -{ - int cap_ptr = iommu->cap_ptr; - u32 range, misc, low, high; - int i, j; - - pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET, - &iommu->cap); - pci_read_config_dword(iommu->dev, cap_ptr + MMIO_RANGE_OFFSET, - &range); - pci_read_config_dword(iommu->dev, cap_ptr + MMIO_MISC_OFFSET, - &misc); - - iommu->first_device = calc_devid(MMIO_GET_BUS(range), - MMIO_GET_FD(range)); - iommu->last_device = calc_devid(MMIO_GET_BUS(range), - MMIO_GET_LD(range)); - iommu->evt_msi_num = MMIO_MSI_NUM(misc); - - if (!(iommu->cap & (1 << IOMMU_CAP_IOTLB))) - amd_iommu_iotlb_sup = false; - - /* read extended feature bits */ - low = readl(iommu->mmio_base + MMIO_EXT_FEATURES); - high = readl(iommu->mmio_base + MMIO_EXT_FEATURES + 4); - - iommu->features = ((u64)high << 32) | low; - - if (iommu_feature(iommu, FEATURE_GT)) { - int glxval; - u32 pasids; - u64 shift; - - shift = iommu->features & FEATURE_PASID_MASK; - shift >>= FEATURE_PASID_SHIFT; - pasids = (1 << shift); - - amd_iommu_max_pasids = min(amd_iommu_max_pasids, pasids); - - glxval = iommu->features & FEATURE_GLXVAL_MASK; - glxval >>= FEATURE_GLXVAL_SHIFT; - - if (amd_iommu_max_glx_val == -1) - amd_iommu_max_glx_val = glxval; - else - amd_iommu_max_glx_val = min(amd_iommu_max_glx_val, glxval); - } - - if (iommu_feature(iommu, FEATURE_GT) && - iommu_feature(iommu, FEATURE_PPR)) { - iommu->is_iommu_v2 = true; - amd_iommu_v2_present = true; - } - - if (!is_rd890_iommu(iommu->dev)) - return; - - /* - * Some rd890 systems may not be fully reconfigured by the BIOS, so - * it's necessary for us to store this information so it can be - * reprogrammed on resume - */ - - pci_read_config_dword(iommu->dev, iommu->cap_ptr + 4, - &iommu->stored_addr_lo); - pci_read_config_dword(iommu->dev, iommu->cap_ptr + 8, - &iommu->stored_addr_hi); - - /* Low bit locks writes to configuration space */ - iommu->stored_addr_lo &= ~1; - - for (i = 0; i < 6; i++) - for (j = 0; j < 0x12; j++) - iommu->stored_l1[i][j] = iommu_read_l1(iommu, i, j); - - for (i = 0; i < 0x83; i++) - iommu->stored_l2[i] = iommu_read_l2(iommu, i); -} - -/* * Takes a pointer to an AMD IOMMU entry in the ACPI table and * initializes the hardware and our data structures with it. */ @@ -1025,13 +929,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h) /* * Copy data from ACPI table entry to the iommu struct */ - iommu->dev = pci_get_bus_and_slot(PCI_BUS(h->devid), h->devid & 0xff); - if (!iommu->dev) - return 1; - - iommu->root_pdev = pci_get_bus_and_slot(iommu->dev->bus->number, - PCI_DEVFN(0, 0)); - + iommu->devid = h->devid; iommu->cap_ptr = h->cap_ptr; iommu->pci_seg = h->pci_seg; iommu->mmio_phys = h->mmio_phys; @@ -1049,20 +947,10 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h) iommu->int_enabled = false; - init_iommu_from_pci(iommu); init_iommu_from_acpi(iommu, h); init_iommu_devices(iommu); - if (iommu_feature(iommu, FEATURE_PPR)) { - iommu->ppr_log = alloc_ppr_log(iommu); - if (!iommu->ppr_log) - return -ENOMEM; - } - - if (iommu->cap & (1UL << IOMMU_CAP_NPCACHE)) - amd_iommu_np_cache = true; - - return pci_enable_device(iommu->dev); + return 0; } /* @@ -1093,16 +981,12 @@ static int __init init_iommu_all(struct acpi_table_header *table) h->mmio_phys); iommu = kzalloc(sizeof(struct amd_iommu), GFP_KERNEL); - if (iommu == NULL) { - amd_iommu_init_err = -ENOMEM; - return 0; - } + if (iommu == NULL) + return -ENOMEM; ret = init_iommu_one(iommu, h); - if (ret) { - amd_iommu_init_err = ret; - return 0; - } + if (ret) + return ret; break; default: break; @@ -1115,6 +999,148 @@ static int __init init_iommu_all(struct acpi_table_header *table) return 0; } +static int iommu_init_pci(struct amd_iommu *iommu) +{ + int cap_ptr = iommu->cap_ptr; + u32 range, misc, low, high; + + iommu->dev = pci_get_bus_and_slot(PCI_BUS(iommu->devid), + iommu->devid & 0xff); + if (!iommu->dev) + return -ENODEV; + + pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET, + &iommu->cap); + pci_read_config_dword(iommu->dev, cap_ptr + MMIO_RANGE_OFFSET, + &range); + pci_read_config_dword(iommu->dev, cap_ptr + MMIO_MISC_OFFSET, + &misc); + + iommu->first_device = calc_devid(MMIO_GET_BUS(range), + MMIO_GET_FD(range)); + iommu->last_device = calc_devid(MMIO_GET_BUS(range), + MMIO_GET_LD(range)); + + if (!(iommu->cap & (1 << IOMMU_CAP_IOTLB))) + amd_iommu_iotlb_sup = false; + + /* read extended feature bits */ + low = readl(iommu->mmio_base + MMIO_EXT_FEATURES); + high = readl(iommu->mmio_base + MMIO_EXT_FEATURES + 4); + + iommu->features = ((u64)high << 32) | low; + + if (iommu_feature(iommu, FEATURE_GT)) { + int glxval; + u32 pasids; + u64 shift; + + shift = iommu->features & FEATURE_PASID_MASK; + shift >>= FEATURE_PASID_SHIFT; + pasids = (1 << shift); + + amd_iommu_max_pasids = min(amd_iommu_max_pasids, pasids); + + glxval = iommu->features & FEATURE_GLXVAL_MASK; + glxval >>= FEATURE_GLXVAL_SHIFT; + + if (amd_iommu_max_glx_val == -1) + amd_iommu_max_glx_val = glxval; + else + amd_iommu_max_glx_val = min(amd_iommu_max_glx_val, glxval); + } + + if (iommu_feature(iommu, FEATURE_GT) && + iommu_feature(iommu, FEATURE_PPR)) { + iommu->is_iommu_v2 = true; + amd_iommu_v2_present = true; + } + + if (iommu_feature(iommu, FEATURE_PPR)) { + iommu->ppr_log = alloc_ppr_log(iommu); + if (!iommu->ppr_log) + return -ENOMEM; + } + + if (iommu->cap & (1UL << IOMMU_CAP_NPCACHE)) + amd_iommu_np_cache = true; + + if (is_rd890_iommu(iommu->dev)) { + int i, j; + + iommu->root_pdev = pci_get_bus_and_slot(iommu->dev->bus->number, + PCI_DEVFN(0, 0)); + + /* + * Some rd890 systems may not be fully reconfigured by the + * BIOS, so it's necessary for us to store this information so + * it can be reprogrammed on resume + */ + pci_read_config_dword(iommu->dev, iommu->cap_ptr + 4, + &iommu->stored_addr_lo); + pci_read_config_dword(iommu->dev, iommu->cap_ptr + 8, + &iommu->stored_addr_hi); + + /* Low bit locks writes to configuration space */ + iommu->stored_addr_lo &= ~1; + + for (i = 0; i < 6; i++) + for (j = 0; j < 0x12; j++) + iommu->stored_l1[i][j] = iommu_read_l1(iommu, i, j); + + for (i = 0; i < 0x83; i++) + iommu->stored_l2[i] = iommu_read_l2(iommu, i); + } + + return pci_enable_device(iommu->dev); +} + +static void print_iommu_info(void) +{ + static const char * const feat_str[] = { + "PreF", "PPR", "X2APIC", "NX", "GT", "[5]", + "IA", "GA", "HE", "PC" + }; + struct amd_iommu *iommu; + + for_each_iommu(iommu) { + int i; + + pr_info("AMD-Vi: Found IOMMU at %s cap 0x%hx\n", + dev_name(&iommu->dev->dev), iommu->cap_ptr); + + if (iommu->cap & (1 << IOMMU_CAP_EFR)) { + pr_info("AMD-Vi: Extended features: "); + for (i = 0; ARRAY_SIZE(feat_str); ++i) { + if (iommu_feature(iommu, (1ULL << i))) + pr_cont(" %s", feat_str[i]); + } + } + pr_cont("\n"); + } +} + +static int __init amd_iommu_init_pci(void) +{ + struct amd_iommu *iommu; + int ret = 0; + + for_each_iommu(iommu) { + ret = iommu_init_pci(iommu); + if (ret) + break; + } + + /* Make sure ACS will be enabled */ + pci_request_acs(); + + ret = amd_iommu_init_devices(); + + print_iommu_info(); + + return ret; +} + /**************************************************************************** * * The following functions initialize the MSI interrupts for all IOMMUs @@ -1217,7 +1243,7 @@ static int __init init_exclusion_range(struct ivmd_header *m) /* called for unity map ACPI definition */ static int __init init_unity_map_range(struct ivmd_header *m) { - struct unity_map_entry *e = 0; + struct unity_map_entry *e = NULL; char *s; e = kzalloc(sizeof(*e), GFP_KERNEL); @@ -1369,7 +1395,7 @@ static void iommu_apply_resume_quirks(struct amd_iommu *iommu) * This function finally enables all IOMMUs found in the system after * they have been initialized */ -static void enable_iommus(void) +static void early_enable_iommus(void) { struct amd_iommu *iommu; @@ -1379,14 +1405,29 @@ static void enable_iommus(void) iommu_set_device_table(iommu); iommu_enable_command_buffer(iommu); iommu_enable_event_buffer(iommu); - iommu_enable_ppr_log(iommu); - iommu_enable_gt(iommu); iommu_set_exclusion_range(iommu); iommu_enable(iommu); iommu_flush_all_caches(iommu); } } +static void enable_iommus_v2(void) +{ + struct amd_iommu *iommu; + + for_each_iommu(iommu) { + iommu_enable_ppr_log(iommu); + iommu_enable_gt(iommu); + } +} + +static void enable_iommus(void) +{ + early_enable_iommus(); + + enable_iommus_v2(); +} + static void disable_iommus(void) { struct amd_iommu *iommu; @@ -1481,16 +1522,23 @@ static void __init free_on_init_error(void) * After everything is set up the IOMMUs are enabled and the necessary * hotplug and suspend notifiers are registered. */ -int __init amd_iommu_init_hardware(void) +static int __init early_amd_iommu_init(void) { + struct acpi_table_header *ivrs_base; + acpi_size ivrs_size; + acpi_status status; int i, ret = 0; if (!amd_iommu_detected) return -ENODEV; - if (amd_iommu_dev_table != NULL) { - /* Hardware already initialized */ - return 0; + status = acpi_get_table_with_size("IVRS", 0, &ivrs_base, &ivrs_size); + if (status == AE_NOT_FOUND) + return -ENODEV; + else if (ACPI_FAILURE(status)) { + const char *err = acpi_format_exception(status); + pr_err("AMD-Vi: IVRS table error: %s\n", err); + return -EINVAL; } /* @@ -1498,10 +1546,7 @@ int __init amd_iommu_init_hardware(void) * we need to handle. Upon this information the shared data * structures for the IOMMUs in the system will be allocated */ - if (acpi_table_parse("IVRS", find_last_devid_acpi) != 0) - return -ENODEV; - - ret = amd_iommu_init_err; + ret = find_last_devid_acpi(ivrs_base); if (ret) goto out; @@ -1523,20 +1568,20 @@ int __init amd_iommu_init_hardware(void) amd_iommu_alias_table = (void *)__get_free_pages(GFP_KERNEL, get_order(alias_table_size)); if (amd_iommu_alias_table == NULL) - goto free; + goto out; /* IOMMU rlookup table - find the IOMMU for a specific device */ amd_iommu_rlookup_table = (void *)__get_free_pages( GFP_KERNEL | __GFP_ZERO, get_order(rlookup_table_size)); if (amd_iommu_rlookup_table == NULL) - goto free; + goto out; amd_iommu_pd_alloc_bitmap = (void *)__get_free_pages( GFP_KERNEL | __GFP_ZERO, get_order(MAX_DOMAIN_ID/8)); if (amd_iommu_pd_alloc_bitmap == NULL) - goto free; + goto out; /* init the device table */ init_device_table(); @@ -1559,38 +1604,18 @@ int __init amd_iommu_init_hardware(void) * now the data structures are allocated and basically initialized * start the real acpi table scan */ - ret = -ENODEV; - if (acpi_table_parse("IVRS", init_iommu_all) != 0) - goto free; - - if (amd_iommu_init_err) { - ret = amd_iommu_init_err; - goto free; - } - - if (acpi_table_parse("IVRS", init_memory_definitions) != 0) - goto free; - - if (amd_iommu_init_err) { - ret = amd_iommu_init_err; - goto free; - } - - ret = amd_iommu_init_devices(); + ret = init_iommu_all(ivrs_base); if (ret) - goto free; - - enable_iommus(); - - amd_iommu_init_notifier(); + goto out; - register_syscore_ops(&amd_iommu_syscore_ops); + ret = init_memory_definitions(ivrs_base); + if (ret) + goto out; out: - return ret; - -free: - free_on_init_error(); + /* Don't leak any ACPI memory */ + early_acpi_os_unmap_memory((char __iomem *)ivrs_base, ivrs_size); + ivrs_base = NULL; return ret; } @@ -1610,26 +1635,29 @@ out: return ret; } -/* - * This is the core init function for AMD IOMMU hardware in the system. - * This function is called from the generic x86 DMA layer initialization - * code. - * - * The function calls amd_iommu_init_hardware() to setup and enable the - * IOMMU hardware if this has not happened yet. After that the driver - * registers for the DMA-API and for the IOMMU-API as necessary. - */ -static int __init amd_iommu_init(void) +static bool detect_ivrs(void) { - int ret = 0; + struct acpi_table_header *ivrs_base; + acpi_size ivrs_size; + acpi_status status; - ret = amd_iommu_init_hardware(); - if (ret) - goto out; + status = acpi_get_table_with_size("IVRS", 0, &ivrs_base, &ivrs_size); + if (status == AE_NOT_FOUND) + return false; + else if (ACPI_FAILURE(status)) { + const char *err = acpi_format_exception(status); + pr_err("AMD-Vi: IVRS table error: %s\n", err); + return false; + } - ret = amd_iommu_enable_interrupts(); - if (ret) - goto free; + early_acpi_os_unmap_memory((char __iomem *)ivrs_base, ivrs_size); + + return true; +} + +static int amd_iommu_init_dma(void) +{ + int ret; if (iommu_pass_through) ret = amd_iommu_init_passthrough(); @@ -1637,29 +1665,108 @@ static int __init amd_iommu_init(void) ret = amd_iommu_init_dma_ops(); if (ret) - goto free; + return ret; amd_iommu_init_api(); - x86_platform.iommu_shutdown = disable_iommus; + amd_iommu_init_notifier(); - if (iommu_pass_through) - goto out; + return 0; +} - if (amd_iommu_unmap_flush) - printk(KERN_INFO "AMD-Vi: IO/TLB flush on unmap enabled\n"); - else - printk(KERN_INFO "AMD-Vi: Lazy IO/TLB flushing enabled\n"); +/**************************************************************************** + * + * AMD IOMMU Initialization State Machine + * + ****************************************************************************/ + +static int __init state_next(void) +{ + int ret = 0; + + switch (init_state) { + case IOMMU_START_STATE: + if (!detect_ivrs()) { + init_state = IOMMU_NOT_FOUND; + ret = -ENODEV; + } else { + init_state = IOMMU_IVRS_DETECTED; + } + break; + case IOMMU_IVRS_DETECTED: + ret = early_amd_iommu_init(); + init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED; + break; + case IOMMU_ACPI_FINISHED: + early_enable_iommus(); + register_syscore_ops(&amd_iommu_syscore_ops); + x86_platform.iommu_shutdown = disable_iommus; + init_state = IOMMU_ENABLED; + break; + case IOMMU_ENABLED: + ret = amd_iommu_init_pci(); + init_state = ret ? IOMMU_INIT_ERROR : IOMMU_PCI_INIT; + enable_iommus_v2(); + break; + case IOMMU_PCI_INIT: + ret = amd_iommu_enable_interrupts(); + init_state = ret ? IOMMU_INIT_ERROR : IOMMU_INTERRUPTS_EN; + break; + case IOMMU_INTERRUPTS_EN: + ret = amd_iommu_init_dma(); + init_state = ret ? IOMMU_INIT_ERROR : IOMMU_DMA_OPS; + break; + case IOMMU_DMA_OPS: + init_state = IOMMU_INITIALIZED; + break; + case IOMMU_INITIALIZED: + /* Nothing to do */ + break; + case IOMMU_NOT_FOUND: + case IOMMU_INIT_ERROR: + /* Error states => do nothing */ + ret = -EINVAL; + break; + default: + /* Unknown state */ + BUG(); + } -out: return ret; +} -free: - disable_iommus(); +static int __init iommu_go_to_state(enum iommu_init_state state) +{ + int ret = 0; + + while (init_state != state) { + ret = state_next(); + if (init_state == IOMMU_NOT_FOUND || + init_state == IOMMU_INIT_ERROR) + break; + } + + return ret; +} + + + +/* + * This is the core init function for AMD IOMMU hardware in the system. + * This function is called from the generic x86 DMA layer initialization + * code. + */ +static int __init amd_iommu_init(void) +{ + int ret; - free_on_init_error(); + ret = iommu_go_to_state(IOMMU_INITIALIZED); + if (ret) { + disable_iommus(); + free_on_init_error(); + } - goto out; + return ret; } /**************************************************************************** @@ -1669,29 +1776,25 @@ free: * IOMMUs * ****************************************************************************/ -static int __init early_amd_iommu_detect(struct acpi_table_header *table) -{ - return 0; -} - int __init amd_iommu_detect(void) { + int ret; + if (no_iommu || (iommu_detected && !gart_iommu_aperture)) return -ENODEV; if (amd_iommu_disabled) return -ENODEV; - if (acpi_table_parse("IVRS", early_amd_iommu_detect) == 0) { - iommu_detected = 1; - amd_iommu_detected = 1; - x86_init.iommu.iommu_init = amd_iommu_init; + ret = iommu_go_to_state(IOMMU_IVRS_DETECTED); + if (ret) + return ret; - /* Make sure ACS will be enabled */ - pci_request_acs(); - return 1; - } - return -ENODEV; + amd_iommu_detected = true; + iommu_detected = 1; + x86_init.iommu.iommu_init = amd_iommu_init; + + return 0; } /**************************************************************************** @@ -1727,8 +1830,8 @@ __setup("amd_iommu=", parse_amd_iommu_options); IOMMU_INIT_FINISH(amd_iommu_detect, gart_iommu_hole_init, - 0, - 0); + NULL, + NULL); bool amd_iommu_v2_supported(void) { diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index c1b1d489817e..d0dab865a8b8 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -487,7 +487,7 @@ struct amd_iommu { /* physical address of MMIO space */ u64 mmio_phys; /* virtual address of MMIO space */ - u8 *mmio_base; + u8 __iomem *mmio_base; /* capabilities of that IOMMU read from ACPI */ u32 cap; @@ -501,6 +501,9 @@ struct amd_iommu { /* IOMMUv2 */ bool is_iommu_v2; + /* PCI device id of the IOMMU device */ + u16 devid; + /* * Capability pointer. There could be more than one IOMMU per PCI * device function if there are more than one AMD IOMMU capability @@ -530,8 +533,6 @@ struct amd_iommu { u32 evt_buf_size; /* event buffer virtual address */ u8 *evt_buf; - /* MSI number for event interrupt */ - u16 evt_msi_num; /* Base of the PPR log, if present */ u8 *ppr_log; @@ -664,6 +665,12 @@ extern bool amd_iommu_force_isolation; /* Max levels of glxval supported */ extern int amd_iommu_max_glx_val; +/* + * This function flushes all internal caches of + * the IOMMU used by this driver. + */ +extern void iommu_flush_all_caches(struct amd_iommu *iommu); + /* takes bus and device/function and returns the device id * FIXME: should that be in generic PCI code? */ static inline u16 calc_devid(u8 bus, u8 devfn) diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c index 036fe9bf157e..0d50f9afd37f 100644 --- a/drivers/iommu/amd_iommu_v2.c +++ b/drivers/iommu/amd_iommu_v2.c @@ -81,7 +81,7 @@ struct fault { u16 flags; }; -struct device_state **state_table; +static struct device_state **state_table; static spinlock_t state_lock; /* List and lock for all pasid_states */ @@ -681,6 +681,8 @@ int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid, atomic_set(&pasid_state->count, 1); init_waitqueue_head(&pasid_state->wq); + spin_lock_init(&pasid_state->lock); + pasid_state->task = task; pasid_state->mm = get_task_mm(task); pasid_state->device_state = dev_state; diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index 9a114b9ff170..5c40937e9988 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -732,6 +732,10 @@ static int exynos_iommu_domain_init(struct iommu_domain *domain) spin_lock_init(&priv->pgtablelock); INIT_LIST_HEAD(&priv->clients); + dom->geometry.aperture_start = 0; + dom->geometry.aperture_end = ~0UL; + dom->geometry.force_aperture = true; + domain->priv = priv; return 0; diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index b12af2ff8c54..d4b018e51592 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -3932,6 +3932,10 @@ static int intel_iommu_domain_init(struct iommu_domain *domain) domain_update_iommu_cap(dmar_domain); domain->priv = dmar_domain; + domain->geometry.aperture_start = 0; + domain->geometry.aperture_end = __DOMAIN_MAX_ADDR(dmar_domain->gaw); + domain->geometry.force_aperture = true; + return 0; } @@ -4090,52 +4094,70 @@ static int intel_iommu_domain_has_cap(struct iommu_domain *domain, return 0; } -/* - * Group numbers are arbitrary. Device with the same group number - * indicate the iommu cannot differentiate between them. To avoid - * tracking used groups we just use the seg|bus|devfn of the lowest - * level we're able to differentiate devices - */ -static int intel_iommu_device_group(struct device *dev, unsigned int *groupid) +static void swap_pci_ref(struct pci_dev **from, struct pci_dev *to) { - struct pci_dev *pdev = to_pci_dev(dev); - struct pci_dev *bridge; - union { - struct { - u8 devfn; - u8 bus; - u16 segment; - } pci; - u32 group; - } id; + pci_dev_put(*from); + *from = to; +} - if (iommu_no_mapping(dev)) - return -ENODEV; +#define REQ_ACS_FLAGS (PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF) - id.pci.segment = pci_domain_nr(pdev->bus); - id.pci.bus = pdev->bus->number; - id.pci.devfn = pdev->devfn; +static int intel_iommu_add_device(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct pci_dev *bridge, *dma_pdev; + struct iommu_group *group; + int ret; - if (!device_to_iommu(id.pci.segment, id.pci.bus, id.pci.devfn)) + if (!device_to_iommu(pci_domain_nr(pdev->bus), + pdev->bus->number, pdev->devfn)) return -ENODEV; bridge = pci_find_upstream_pcie_bridge(pdev); if (bridge) { - if (pci_is_pcie(bridge)) { - id.pci.bus = bridge->subordinate->number; - id.pci.devfn = 0; - } else { - id.pci.bus = bridge->bus->number; - id.pci.devfn = bridge->devfn; - } + if (pci_is_pcie(bridge)) + dma_pdev = pci_get_domain_bus_and_slot( + pci_domain_nr(pdev->bus), + bridge->subordinate->number, 0); + else + dma_pdev = pci_dev_get(bridge); + } else + dma_pdev = pci_dev_get(pdev); + + swap_pci_ref(&dma_pdev, pci_get_dma_source(dma_pdev)); + + if (dma_pdev->multifunction && + !pci_acs_enabled(dma_pdev, REQ_ACS_FLAGS)) + swap_pci_ref(&dma_pdev, + pci_get_slot(dma_pdev->bus, + PCI_DEVFN(PCI_SLOT(dma_pdev->devfn), + 0))); + + while (!pci_is_root_bus(dma_pdev->bus)) { + if (pci_acs_path_enabled(dma_pdev->bus->self, + NULL, REQ_ACS_FLAGS)) + break; + + swap_pci_ref(&dma_pdev, pci_dev_get(dma_pdev->bus->self)); + } + + group = iommu_group_get(&dma_pdev->dev); + pci_dev_put(dma_pdev); + if (!group) { + group = iommu_group_alloc(); + if (IS_ERR(group)) + return PTR_ERR(group); } - if (!pdev->is_virtfn && iommu_group_mf) - id.pci.devfn = PCI_DEVFN(PCI_SLOT(id.pci.devfn), 0); + ret = iommu_group_add_device(group, dev); - *groupid = id.group; + iommu_group_put(group); + return ret; +} - return 0; +static void intel_iommu_remove_device(struct device *dev) +{ + iommu_group_remove_device(dev); } static struct iommu_ops intel_iommu_ops = { @@ -4147,7 +4169,8 @@ static struct iommu_ops intel_iommu_ops = { .unmap = intel_iommu_unmap, .iova_to_phys = intel_iommu_iova_to_phys, .domain_has_cap = intel_iommu_domain_has_cap, - .device_group = intel_iommu_device_group, + .add_device = intel_iommu_add_device, + .remove_device = intel_iommu_remove_device, .pgsize_bitmap = INTEL_IOMMU_PGSIZES, }; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 8b9ded88e6f5..ddbdacad7768 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -26,60 +26,535 @@ #include <linux/slab.h> #include <linux/errno.h> #include <linux/iommu.h> +#include <linux/idr.h> +#include <linux/notifier.h> +#include <linux/err.h> + +static struct kset *iommu_group_kset; +static struct ida iommu_group_ida; +static struct mutex iommu_group_mutex; + +struct iommu_group { + struct kobject kobj; + struct kobject *devices_kobj; + struct list_head devices; + struct mutex mutex; + struct blocking_notifier_head notifier; + void *iommu_data; + void (*iommu_data_release)(void *iommu_data); + char *name; + int id; +}; + +struct iommu_device { + struct list_head list; + struct device *dev; + char *name; +}; + +struct iommu_group_attribute { + struct attribute attr; + ssize_t (*show)(struct iommu_group *group, char *buf); + ssize_t (*store)(struct iommu_group *group, + const char *buf, size_t count); +}; + +#define IOMMU_GROUP_ATTR(_name, _mode, _show, _store) \ +struct iommu_group_attribute iommu_group_attr_##_name = \ + __ATTR(_name, _mode, _show, _store) + +#define to_iommu_group_attr(_attr) \ + container_of(_attr, struct iommu_group_attribute, attr) +#define to_iommu_group(_kobj) \ + container_of(_kobj, struct iommu_group, kobj) -static ssize_t show_iommu_group(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t iommu_group_attr_show(struct kobject *kobj, + struct attribute *__attr, char *buf) { - unsigned int groupid; + struct iommu_group_attribute *attr = to_iommu_group_attr(__attr); + struct iommu_group *group = to_iommu_group(kobj); + ssize_t ret = -EIO; - if (iommu_device_group(dev, &groupid)) - return 0; + if (attr->show) + ret = attr->show(group, buf); + return ret; +} + +static ssize_t iommu_group_attr_store(struct kobject *kobj, + struct attribute *__attr, + const char *buf, size_t count) +{ + struct iommu_group_attribute *attr = to_iommu_group_attr(__attr); + struct iommu_group *group = to_iommu_group(kobj); + ssize_t ret = -EIO; + + if (attr->store) + ret = attr->store(group, buf, count); + return ret; +} + +static const struct sysfs_ops iommu_group_sysfs_ops = { + .show = iommu_group_attr_show, + .store = iommu_group_attr_store, +}; - return sprintf(buf, "%u", groupid); +static int iommu_group_create_file(struct iommu_group *group, + struct iommu_group_attribute *attr) +{ + return sysfs_create_file(&group->kobj, &attr->attr); } -static DEVICE_ATTR(iommu_group, S_IRUGO, show_iommu_group, NULL); -static int add_iommu_group(struct device *dev, void *data) +static void iommu_group_remove_file(struct iommu_group *group, + struct iommu_group_attribute *attr) +{ + sysfs_remove_file(&group->kobj, &attr->attr); +} + +static ssize_t iommu_group_show_name(struct iommu_group *group, char *buf) +{ + return sprintf(buf, "%s\n", group->name); +} + +static IOMMU_GROUP_ATTR(name, S_IRUGO, iommu_group_show_name, NULL); + +static void iommu_group_release(struct kobject *kobj) +{ + struct iommu_group *group = to_iommu_group(kobj); + + if (group->iommu_data_release) + group->iommu_data_release(group->iommu_data); + + mutex_lock(&iommu_group_mutex); + ida_remove(&iommu_group_ida, group->id); + mutex_unlock(&iommu_group_mutex); + + kfree(group->name); + kfree(group); +} + +static struct kobj_type iommu_group_ktype = { + .sysfs_ops = &iommu_group_sysfs_ops, + .release = iommu_group_release, +}; + +/** + * iommu_group_alloc - Allocate a new group + * @name: Optional name to associate with group, visible in sysfs + * + * This function is called by an iommu driver to allocate a new iommu + * group. The iommu group represents the minimum granularity of the iommu. + * Upon successful return, the caller holds a reference to the supplied + * group in order to hold the group until devices are added. Use + * iommu_group_put() to release this extra reference count, allowing the + * group to be automatically reclaimed once it has no devices or external + * references. + */ +struct iommu_group *iommu_group_alloc(void) +{ + struct iommu_group *group; + int ret; + + group = kzalloc(sizeof(*group), GFP_KERNEL); + if (!group) + return ERR_PTR(-ENOMEM); + + group->kobj.kset = iommu_group_kset; + mutex_init(&group->mutex); + INIT_LIST_HEAD(&group->devices); + BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier); + + mutex_lock(&iommu_group_mutex); + +again: + if (unlikely(0 == ida_pre_get(&iommu_group_ida, GFP_KERNEL))) { + kfree(group); + mutex_unlock(&iommu_group_mutex); + return ERR_PTR(-ENOMEM); + } + + if (-EAGAIN == ida_get_new(&iommu_group_ida, &group->id)) + goto again; + + mutex_unlock(&iommu_group_mutex); + + ret = kobject_init_and_add(&group->kobj, &iommu_group_ktype, + NULL, "%d", group->id); + if (ret) { + mutex_lock(&iommu_group_mutex); + ida_remove(&iommu_group_ida, group->id); + mutex_unlock(&iommu_group_mutex); + kfree(group); + return ERR_PTR(ret); + } + + group->devices_kobj = kobject_create_and_add("devices", &group->kobj); + if (!group->devices_kobj) { + kobject_put(&group->kobj); /* triggers .release & free */ + return ERR_PTR(-ENOMEM); + } + + /* + * The devices_kobj holds a reference on the group kobject, so + * as long as that exists so will the group. We can therefore + * use the devices_kobj for reference counting. + */ + kobject_put(&group->kobj); + + return group; +} +EXPORT_SYMBOL_GPL(iommu_group_alloc); + +/** + * iommu_group_get_iommudata - retrieve iommu_data registered for a group + * @group: the group + * + * iommu drivers can store data in the group for use when doing iommu + * operations. This function provides a way to retrieve it. Caller + * should hold a group reference. + */ +void *iommu_group_get_iommudata(struct iommu_group *group) +{ + return group->iommu_data; +} +EXPORT_SYMBOL_GPL(iommu_group_get_iommudata); + +/** + * iommu_group_set_iommudata - set iommu_data for a group + * @group: the group + * @iommu_data: new data + * @release: release function for iommu_data + * + * iommu drivers can store data in the group for use when doing iommu + * operations. This function provides a way to set the data after + * the group has been allocated. Caller should hold a group reference. + */ +void iommu_group_set_iommudata(struct iommu_group *group, void *iommu_data, + void (*release)(void *iommu_data)) { - unsigned int groupid; + group->iommu_data = iommu_data; + group->iommu_data_release = release; +} +EXPORT_SYMBOL_GPL(iommu_group_set_iommudata); - if (iommu_device_group(dev, &groupid) == 0) - return device_create_file(dev, &dev_attr_iommu_group); +/** + * iommu_group_set_name - set name for a group + * @group: the group + * @name: name + * + * Allow iommu driver to set a name for a group. When set it will + * appear in a name attribute file under the group in sysfs. + */ +int iommu_group_set_name(struct iommu_group *group, const char *name) +{ + int ret; + + if (group->name) { + iommu_group_remove_file(group, &iommu_group_attr_name); + kfree(group->name); + group->name = NULL; + if (!name) + return 0; + } + + group->name = kstrdup(name, GFP_KERNEL); + if (!group->name) + return -ENOMEM; + + ret = iommu_group_create_file(group, &iommu_group_attr_name); + if (ret) { + kfree(group->name); + group->name = NULL; + return ret; + } return 0; } +EXPORT_SYMBOL_GPL(iommu_group_set_name); + +/** + * iommu_group_add_device - add a device to an iommu group + * @group: the group into which to add the device (reference should be held) + * @dev: the device + * + * This function is called by an iommu driver to add a device into a + * group. Adding a device increments the group reference count. + */ +int iommu_group_add_device(struct iommu_group *group, struct device *dev) +{ + int ret, i = 0; + struct iommu_device *device; + + device = kzalloc(sizeof(*device), GFP_KERNEL); + if (!device) + return -ENOMEM; + + device->dev = dev; + + ret = sysfs_create_link(&dev->kobj, &group->kobj, "iommu_group"); + if (ret) { + kfree(device); + return ret; + } + + 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 = 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. + */ + 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; + } + + kobject_get(group->devices_kobj); + + dev->iommu_group = group; + + mutex_lock(&group->mutex); + list_add_tail(&device->list, &group->devices); + mutex_unlock(&group->mutex); + + /* Notify any listeners about change to group. */ + blocking_notifier_call_chain(&group->notifier, + IOMMU_GROUP_NOTIFY_ADD_DEVICE, dev); + return 0; +} +EXPORT_SYMBOL_GPL(iommu_group_add_device); + +/** + * iommu_group_remove_device - remove a device from it's current group + * @dev: device to be removed + * + * This function is called by an iommu driver to remove the device from + * it's current group. This decrements the iommu group reference count. + */ +void iommu_group_remove_device(struct device *dev) +{ + struct iommu_group *group = dev->iommu_group; + struct iommu_device *tmp_device, *device = NULL; + + /* Pre-notify listeners that a device is being removed. */ + blocking_notifier_call_chain(&group->notifier, + IOMMU_GROUP_NOTIFY_DEL_DEVICE, dev); + + mutex_lock(&group->mutex); + list_for_each_entry(tmp_device, &group->devices, list) { + if (tmp_device->dev == dev) { + device = tmp_device; + list_del(&device->list); + break; + } + } + mutex_unlock(&group->mutex); + + if (!device) + return; + + sysfs_remove_link(group->devices_kobj, device->name); + sysfs_remove_link(&dev->kobj, "iommu_group"); + + kfree(device->name); + kfree(device); + dev->iommu_group = NULL; + kobject_put(group->devices_kobj); +} +EXPORT_SYMBOL_GPL(iommu_group_remove_device); + +/** + * iommu_group_for_each_dev - iterate over each device in the group + * @group: the group + * @data: caller opaque data to be passed to callback function + * @fn: caller supplied callback function + * + * This function is called by group users to iterate over group devices. + * Callers should hold a reference count to the group during callback. + * The group->mutex is held across callbacks, which will block calls to + * iommu_group_add/remove_device. + */ +int iommu_group_for_each_dev(struct iommu_group *group, void *data, + int (*fn)(struct device *, void *)) +{ + struct iommu_device *device; + int ret = 0; + + mutex_lock(&group->mutex); + list_for_each_entry(device, &group->devices, list) { + ret = fn(device->dev, data); + if (ret) + break; + } + mutex_unlock(&group->mutex); + return ret; +} +EXPORT_SYMBOL_GPL(iommu_group_for_each_dev); + +/** + * iommu_group_get - Return the group for a device and increment reference + * @dev: get the group that this device belongs to + * + * This function is called by iommu drivers and users to get the group + * for the specified device. If found, the group is returned and the group + * reference in incremented, else NULL. + */ +struct iommu_group *iommu_group_get(struct device *dev) +{ + struct iommu_group *group = dev->iommu_group; + + if (group) + kobject_get(group->devices_kobj); + + return group; +} +EXPORT_SYMBOL_GPL(iommu_group_get); + +/** + * iommu_group_put - Decrement group reference + * @group: the group to use + * + * This function is called by iommu drivers and users to release the + * iommu group. Once the reference count is zero, the group is released. + */ +void iommu_group_put(struct iommu_group *group) +{ + if (group) + kobject_put(group->devices_kobj); +} +EXPORT_SYMBOL_GPL(iommu_group_put); + +/** + * iommu_group_register_notifier - Register a notifier for group changes + * @group: the group to watch + * @nb: notifier block to signal + * + * This function allows iommu group users to track changes in a group. + * See include/linux/iommu.h for actions sent via this notifier. Caller + * should hold a reference to the group throughout notifier registration. + */ +int iommu_group_register_notifier(struct iommu_group *group, + struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&group->notifier, nb); +} +EXPORT_SYMBOL_GPL(iommu_group_register_notifier); + +/** + * iommu_group_unregister_notifier - Unregister a notifier + * @group: the group to watch + * @nb: notifier block to signal + * + * Unregister a previously registered group notifier block. + */ +int iommu_group_unregister_notifier(struct iommu_group *group, + struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&group->notifier, nb); +} +EXPORT_SYMBOL_GPL(iommu_group_unregister_notifier); + +/** + * iommu_group_id - Return ID for a group + * @group: the group to ID + * + * Return the unique ID for the group matching the sysfs group number. + */ +int iommu_group_id(struct iommu_group *group) +{ + return group->id; +} +EXPORT_SYMBOL_GPL(iommu_group_id); -static int remove_iommu_group(struct device *dev) +static int add_iommu_group(struct device *dev, void *data) { - unsigned int groupid; + struct iommu_ops *ops = data; + + if (!ops->add_device) + return -ENODEV; - if (iommu_device_group(dev, &groupid) == 0) - device_remove_file(dev, &dev_attr_iommu_group); + WARN_ON(dev->iommu_group); + + ops->add_device(dev); return 0; } -static int iommu_device_notifier(struct notifier_block *nb, - unsigned long action, void *data) +static int iommu_bus_notifier(struct notifier_block *nb, + unsigned long action, void *data) { struct device *dev = data; + struct iommu_ops *ops = dev->bus->iommu_ops; + struct iommu_group *group; + unsigned long group_action = 0; + + /* + * ADD/DEL call into iommu driver ops if provided, which may + * result in ADD/DEL notifiers to group->notifier + */ + if (action == BUS_NOTIFY_ADD_DEVICE) { + if (ops->add_device) + return ops->add_device(dev); + } else if (action == BUS_NOTIFY_DEL_DEVICE) { + if (ops->remove_device && dev->iommu_group) { + ops->remove_device(dev); + return 0; + } + } + + /* + * Remaining BUS_NOTIFYs get filtered and republished to the + * group, if anyone is listening + */ + group = iommu_group_get(dev); + if (!group) + return 0; + + switch (action) { + case BUS_NOTIFY_BIND_DRIVER: + group_action = IOMMU_GROUP_NOTIFY_BIND_DRIVER; + break; + case BUS_NOTIFY_BOUND_DRIVER: + group_action = IOMMU_GROUP_NOTIFY_BOUND_DRIVER; + break; + case BUS_NOTIFY_UNBIND_DRIVER: + group_action = IOMMU_GROUP_NOTIFY_UNBIND_DRIVER; + break; + case BUS_NOTIFY_UNBOUND_DRIVER: + group_action = IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER; + break; + } - if (action == BUS_NOTIFY_ADD_DEVICE) - return add_iommu_group(dev, NULL); - else if (action == BUS_NOTIFY_DEL_DEVICE) - return remove_iommu_group(dev); + if (group_action) + blocking_notifier_call_chain(&group->notifier, + group_action, dev); + iommu_group_put(group); return 0; } -static struct notifier_block iommu_device_nb = { - .notifier_call = iommu_device_notifier, +static struct notifier_block iommu_bus_nb = { + .notifier_call = iommu_bus_notifier, }; static void iommu_bus_init(struct bus_type *bus, struct iommu_ops *ops) { - bus_register_notifier(bus, &iommu_device_nb); - bus_for_each_dev(bus, NULL, NULL, add_iommu_group); + bus_register_notifier(bus, &iommu_bus_nb); + bus_for_each_dev(bus, NULL, ops, add_iommu_group); } /** @@ -192,6 +667,45 @@ void iommu_detach_device(struct iommu_domain *domain, struct device *dev) } EXPORT_SYMBOL_GPL(iommu_detach_device); +/* + * IOMMU groups are really the natrual working unit of the IOMMU, but + * the IOMMU API works on domains and devices. Bridge that gap by + * iterating over the devices in a group. Ideally we'd have a single + * device which represents the requestor ID of the group, but we also + * allow IOMMU drivers to create policy defined minimum sets, where + * the physical hardware may be able to distiguish members, but we + * wish to group them at a higher level (ex. untrusted multi-function + * PCI devices). Thus we attach each device. + */ +static int iommu_group_do_attach_device(struct device *dev, void *data) +{ + struct iommu_domain *domain = data; + + return iommu_attach_device(domain, dev); +} + +int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group) +{ + return iommu_group_for_each_dev(group, domain, + iommu_group_do_attach_device); +} +EXPORT_SYMBOL_GPL(iommu_attach_group); + +static int iommu_group_do_detach_device(struct device *dev, void *data) +{ + struct iommu_domain *domain = data; + + iommu_detach_device(domain, dev); + + return 0; +} + +void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group) +{ + iommu_group_for_each_dev(group, domain, iommu_group_do_detach_device); +} +EXPORT_SYMBOL_GPL(iommu_detach_group); + phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, unsigned long iova) { @@ -336,11 +850,48 @@ size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) } EXPORT_SYMBOL_GPL(iommu_unmap); -int iommu_device_group(struct device *dev, unsigned int *groupid) +static int __init iommu_init(void) { - if (iommu_present(dev->bus) && dev->bus->iommu_ops->device_group) - return dev->bus->iommu_ops->device_group(dev, groupid); + iommu_group_kset = kset_create_and_add("iommu_groups", + NULL, kernel_kobj); + ida_init(&iommu_group_ida); + mutex_init(&iommu_group_mutex); + + BUG_ON(!iommu_group_kset); + + return 0; +} +subsys_initcall(iommu_init); + +int iommu_domain_get_attr(struct iommu_domain *domain, + enum iommu_attr attr, void *data) +{ + struct iommu_domain_geometry *geometry; + int ret = 0; + + switch (attr) { + case DOMAIN_ATTR_GEOMETRY: + geometry = data; + *geometry = domain->geometry; + + break; + default: + if (!domain->ops->domain_get_attr) + return -EINVAL; + + ret = domain->ops->domain_get_attr(domain, attr, data); + } + + return ret; +} +EXPORT_SYMBOL_GPL(iommu_domain_get_attr); + +int iommu_domain_set_attr(struct iommu_domain *domain, + enum iommu_attr attr, void *data) +{ + if (!domain->ops->domain_set_attr) + return -EINVAL; - return -ENODEV; + return domain->ops->domain_set_attr(domain, attr, data); } -EXPORT_SYMBOL_GPL(iommu_device_group); +EXPORT_SYMBOL_GPL(iommu_domain_set_attr); diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c index 40cda8e98d87..92769963eac9 100644 --- a/drivers/iommu/irq_remapping.c +++ b/drivers/iommu/irq_remapping.c @@ -1,6 +1,11 @@ #include <linux/kernel.h> #include <linux/string.h> +#include <linux/cpumask.h> #include <linux/errno.h> +#include <linux/msi.h> + +#include <asm/hw_irq.h> +#include <asm/irq_remapping.h> #include "irq_remapping.h" diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index cee307e86606..6a8870a31668 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -226,6 +226,11 @@ static int msm_iommu_domain_init(struct iommu_domain *domain) memset(priv->pgtable, 0, SZ_16K); domain->priv = priv; + + domain->geometry.aperture_start = 0; + domain->geometry.aperture_end = (1ULL << 32) - 1; + domain->geometry.force_aperture = true; + return 0; fail_nomem: diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index e70ee2b59df9..d0b1234581be 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1148,6 +1148,10 @@ static int omap_iommu_domain_init(struct iommu_domain *domain) domain->priv = omap_domain; + domain->geometry.aperture_start = 0; + domain->geometry.aperture_end = (1ULL << 32) - 1; + domain->geometry.force_aperture = true; + return 0; fail_nomem: diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c index 0c0a37792218..c16e8fc8a4bd 100644 --- a/drivers/iommu/tegra-gart.c +++ b/drivers/iommu/tegra-gart.c @@ -165,6 +165,11 @@ static int gart_iommu_attach_dev(struct iommu_domain *domain, return -EINVAL; domain->priv = gart; + domain->geometry.aperture_start = gart->iovmm_base; + domain->geometry.aperture_end = gart->iovmm_base + + gart->page_count * GART_PAGE_SIZE - 1; + domain->geometry.force_aperture = true; + client = devm_kzalloc(gart->dev, sizeof(*c), GFP_KERNEL); if (!client) return -ENOMEM; diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 541d210cb421..4ba325ab6262 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -839,6 +839,11 @@ found: domain->priv = as; + domain->geometry.aperture_start = smmu->iovmm_base; + domain->geometry.aperture_end = smmu->iovmm_base + + smmu->page_count * SMMU_PAGE_SIZE - 1; + domain->geometry.force_aperture = true; + dev_dbg(smmu->dev, "smmu_as@%p\n", as); return 0; |