diff options
Diffstat (limited to 'drivers/iommu')
-rw-r--r-- | drivers/iommu/Kconfig | 1 | ||||
-rw-r--r-- | drivers/iommu/Makefile | 3 | ||||
-rw-r--r-- | drivers/iommu/amd_iommu.c | 135 | ||||
-rw-r--r-- | drivers/iommu/amd_iommu.h | 14 | ||||
-rw-r--r-- | drivers/iommu/amd_iommu_init.c | 5 | ||||
-rw-r--r-- | drivers/iommu/amd_iommu_quirks.c | 92 | ||||
-rw-r--r-- | drivers/iommu/amd_iommu_types.h | 9 | ||||
-rw-r--r-- | drivers/iommu/arm-smmu-v3.c | 7 | ||||
-rw-r--r-- | drivers/iommu/dma-iommu.c | 4 | ||||
-rw-r--r-- | drivers/iommu/dmar.c | 77 | ||||
-rw-r--r-- | drivers/iommu/exynos-iommu.c | 6 | ||||
-rw-r--r-- | drivers/iommu/intel-iommu.c | 411 | ||||
-rw-r--r-- | drivers/iommu/intel-svm.c | 36 | ||||
-rw-r--r-- | drivers/iommu/intel-trace.c | 14 | ||||
-rw-r--r-- | drivers/iommu/intel_irq_remapping.c | 6 | ||||
-rw-r--r-- | drivers/iommu/iommu.c | 193 | ||||
-rw-r--r-- | drivers/iommu/iova.c | 4 | ||||
-rw-r--r-- | drivers/iommu/ipmmu-vmsa.c | 78 | ||||
-rw-r--r-- | drivers/iommu/msm_iommu.c | 1 | ||||
-rw-r--r-- | drivers/iommu/omap-iommu.c | 322 | ||||
-rw-r--r-- | drivers/iommu/omap-iommu.h | 9 | ||||
-rw-r--r-- | drivers/iommu/qcom_iommu.c | 11 |
22 files changed, 1205 insertions, 233 deletions
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index e15cdcd8cb3c..a4ddeade8ac4 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -182,6 +182,7 @@ config INTEL_IOMMU select IOMMU_IOVA select NEED_DMA_MAP_STATE select DMAR_TABLE + select SWIOTLB help DMA remapping (DMAR) devices support enables independent address translations for Direct Memory Access (DMA) from devices. diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index a2729aadd300..4f405f926e73 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -10,13 +10,14 @@ obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o obj-$(CONFIG_IOMMU_IOVA) += iova.o obj-$(CONFIG_OF_IOMMU) += of_iommu.o obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o -obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o +obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o amd_iommu_quirks.o obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd_iommu_debugfs.o obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o obj-$(CONFIG_ARM_SMMU) += arm-smmu.o arm-smmu-impl.o obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o obj-$(CONFIG_DMAR_TABLE) += dmar.o obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o intel-pasid.o +obj-$(CONFIG_INTEL_IOMMU) += intel-trace.o obj-$(CONFIG_INTEL_IOMMU_DEBUGFS) += intel-iommu-debugfs.o obj-$(CONFIG_INTEL_IOMMU_SVM) += intel-svm.o obj-$(CONFIG_IPMMU_VMSA) += ipmmu-vmsa.o diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 29eeea914660..1ed3b98324ba 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -436,7 +436,7 @@ static int iommu_init_device(struct device *dev) * invalid address), we ignore the capability for the device so * it'll be forced to go into translation mode. */ - if ((iommu_pass_through || !amd_iommu_force_isolation) && + if ((iommu_default_passthrough() || !amd_iommu_force_isolation) && dev_is_pci(dev) && pci_iommuv2_capable(to_pci_dev(dev))) { struct amd_iommu *iommu; @@ -1143,6 +1143,17 @@ static void amd_iommu_flush_tlb_all(struct amd_iommu *iommu) iommu_completion_wait(iommu); } +static void amd_iommu_flush_tlb_domid(struct amd_iommu *iommu, u32 dom_id) +{ + struct iommu_cmd cmd; + + build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, + dom_id, 1); + iommu_queue_command(iommu, &cmd); + + iommu_completion_wait(iommu); +} + static void amd_iommu_flush_all(struct amd_iommu *iommu) { struct iommu_cmd cmd; @@ -1424,18 +1435,21 @@ static void free_pagetable(struct protection_domain *domain) * another level increases the size of the address space by 9 bits to a size up * to 64 bits. */ -static bool increase_address_space(struct protection_domain *domain, +static void increase_address_space(struct protection_domain *domain, gfp_t gfp) { + unsigned long flags; u64 *pte; - if (domain->mode == PAGE_MODE_6_LEVEL) + spin_lock_irqsave(&domain->lock, flags); + + if (WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL)) /* address space already 64 bit large */ - return false; + goto out; pte = (void *)get_zeroed_page(gfp); if (!pte) - return false; + goto out; *pte = PM_LEVEL_PDE(domain->mode, iommu_virt_to_phys(domain->pt_root)); @@ -1443,7 +1457,10 @@ static bool increase_address_space(struct protection_domain *domain, domain->mode += 1; domain->updated = true; - return true; +out: + spin_unlock_irqrestore(&domain->lock, flags); + + return; } static u64 *alloc_pte(struct protection_domain *domain, @@ -1873,6 +1890,7 @@ static void set_dte_entry(u16 devid, struct protection_domain *domain, { u64 pte_root = 0; u64 flags = 0; + u32 old_domid; if (domain->mode != PAGE_MODE_NONE) pte_root = iommu_virt_to_phys(domain->pt_root); @@ -1922,8 +1940,20 @@ static void set_dte_entry(u16 devid, struct protection_domain *domain, flags &= ~DEV_DOMID_MASK; flags |= domain->id; + old_domid = amd_iommu_dev_table[devid].data[1] & DEV_DOMID_MASK; amd_iommu_dev_table[devid].data[1] = flags; amd_iommu_dev_table[devid].data[0] = pte_root; + + /* + * A kdump kernel might be replacing a domain ID that was copied from + * the previous kernel--if so, it needs to flush the translation cache + * entries for the old domain ID that is being overwritten + */ + if (old_domid) { + struct amd_iommu *iommu = amd_iommu_rlookup_table[devid]; + + amd_iommu_flush_tlb_domid(iommu, old_domid); + } } static void clear_dte_entry(u16 devid) @@ -2226,7 +2256,7 @@ static int amd_iommu_add_device(struct device *dev) BUG_ON(!dev_data); - if (iommu_pass_through || dev_data->iommu_v2) + if (dev_data->iommu_v2) iommu_request_dm_for_dev(dev); /* Domains are initialized for this device - have a look what we ended up with */ @@ -2547,7 +2577,9 @@ static int map_sg(struct device *dev, struct scatterlist *sglist, bus_addr = address + s->dma_address + (j << PAGE_SHIFT); phys_addr = (sg_phys(s) & PAGE_MASK) + (j << PAGE_SHIFT); - ret = iommu_map_page(domain, bus_addr, phys_addr, PAGE_SIZE, prot, GFP_ATOMIC); + ret = iommu_map_page(domain, bus_addr, phys_addr, + PAGE_SIZE, prot, + GFP_ATOMIC | __GFP_NOWARN); if (ret) goto out_unmap; @@ -2805,7 +2837,7 @@ int __init amd_iommu_init_api(void) int __init amd_iommu_init_dma_ops(void) { - swiotlb = (iommu_pass_through || sme_me_mask) ? 1 : 0; + swiotlb = (iommu_default_passthrough() || sme_me_mask) ? 1 : 0; iommu_detected = 1; if (amd_iommu_unmap_flush) @@ -4314,13 +4346,62 @@ static const struct irq_domain_ops amd_ir_domain_ops = { .deactivate = irq_remapping_deactivate, }; +int amd_iommu_activate_guest_mode(void *data) +{ + struct amd_ir_data *ir_data = (struct amd_ir_data *)data; + struct irte_ga *entry = (struct irte_ga *) ir_data->entry; + + if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || + !entry || entry->lo.fields_vapic.guest_mode) + return 0; + + entry->lo.val = 0; + entry->hi.val = 0; + + entry->lo.fields_vapic.guest_mode = 1; + entry->lo.fields_vapic.ga_log_intr = 1; + entry->hi.fields.ga_root_ptr = ir_data->ga_root_ptr; + entry->hi.fields.vector = ir_data->ga_vector; + entry->lo.fields_vapic.ga_tag = ir_data->ga_tag; + + return modify_irte_ga(ir_data->irq_2_irte.devid, + ir_data->irq_2_irte.index, entry, NULL); +} +EXPORT_SYMBOL(amd_iommu_activate_guest_mode); + +int amd_iommu_deactivate_guest_mode(void *data) +{ + struct amd_ir_data *ir_data = (struct amd_ir_data *)data; + struct irte_ga *entry = (struct irte_ga *) ir_data->entry; + struct irq_cfg *cfg = ir_data->cfg; + + if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || + !entry || !entry->lo.fields_vapic.guest_mode) + return 0; + + entry->lo.val = 0; + entry->hi.val = 0; + + entry->lo.fields_remap.dm = apic->irq_dest_mode; + entry->lo.fields_remap.int_type = apic->irq_delivery_mode; + entry->hi.fields.vector = cfg->vector; + entry->lo.fields_remap.destination = + APICID_TO_IRTE_DEST_LO(cfg->dest_apicid); + entry->hi.fields.destination = + APICID_TO_IRTE_DEST_HI(cfg->dest_apicid); + + return modify_irte_ga(ir_data->irq_2_irte.devid, + ir_data->irq_2_irte.index, entry, NULL); +} +EXPORT_SYMBOL(amd_iommu_deactivate_guest_mode); + static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info) { + int ret; struct amd_iommu *iommu; struct amd_iommu_pi_data *pi_data = vcpu_info; struct vcpu_data *vcpu_pi_info = pi_data->vcpu_data; struct amd_ir_data *ir_data = data->chip_data; - struct irte_ga *irte = (struct irte_ga *) ir_data->entry; struct irq_2_irte *irte_info = &ir_data->irq_2_irte; struct iommu_dev_data *dev_data = search_dev_data(irte_info->devid); @@ -4331,6 +4412,7 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info) if (!dev_data || !dev_data->use_vapic) return 0; + ir_data->cfg = irqd_cfg(data); pi_data->ir_data = ir_data; /* Note: @@ -4349,37 +4431,24 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info) pi_data->prev_ga_tag = ir_data->cached_ga_tag; if (pi_data->is_guest_mode) { - /* Setting */ - irte->hi.fields.ga_root_ptr = (pi_data->base >> 12); - irte->hi.fields.vector = vcpu_pi_info->vector; - irte->lo.fields_vapic.ga_log_intr = 1; - irte->lo.fields_vapic.guest_mode = 1; - irte->lo.fields_vapic.ga_tag = pi_data->ga_tag; - - ir_data->cached_ga_tag = pi_data->ga_tag; + ir_data->ga_root_ptr = (pi_data->base >> 12); + ir_data->ga_vector = vcpu_pi_info->vector; + ir_data->ga_tag = pi_data->ga_tag; + ret = amd_iommu_activate_guest_mode(ir_data); + if (!ret) + ir_data->cached_ga_tag = pi_data->ga_tag; } else { - /* Un-Setting */ - struct irq_cfg *cfg = irqd_cfg(data); - - irte->hi.val = 0; - irte->lo.val = 0; - irte->hi.fields.vector = cfg->vector; - irte->lo.fields_remap.guest_mode = 0; - irte->lo.fields_remap.destination = - APICID_TO_IRTE_DEST_LO(cfg->dest_apicid); - irte->hi.fields.destination = - APICID_TO_IRTE_DEST_HI(cfg->dest_apicid); - irte->lo.fields_remap.int_type = apic->irq_delivery_mode; - irte->lo.fields_remap.dm = apic->irq_dest_mode; + ret = amd_iommu_deactivate_guest_mode(ir_data); /* * This communicates the ga_tag back to the caller * so that it can do all the necessary clean up. */ - ir_data->cached_ga_tag = 0; + if (!ret) + ir_data->cached_ga_tag = 0; } - return modify_irte_ga(irte_info->devid, irte_info->index, irte, ir_data); + return ret; } diff --git a/drivers/iommu/amd_iommu.h b/drivers/iommu/amd_iommu.h new file mode 100644 index 000000000000..12d540d9b59b --- /dev/null +++ b/drivers/iommu/amd_iommu.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef AMD_IOMMU_H +#define AMD_IOMMU_H + +int __init add_special_device(u8 type, u8 id, u16 *devid, bool cmd_line); + +#ifdef CONFIG_DMI +void amd_iommu_apply_ivrs_quirks(void); +#else +static void amd_iommu_apply_ivrs_quirks(void) { } +#endif + +#endif diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 4413aa67000e..568c52317757 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -32,6 +32,7 @@ #include <asm/irq_remapping.h> #include <linux/crash_dump.h> +#include "amd_iommu.h" #include "amd_iommu_proto.h" #include "amd_iommu_types.h" #include "irq_remapping.h" @@ -1002,7 +1003,7 @@ static void __init set_dev_entry_from_acpi(struct amd_iommu *iommu, set_iommu_for_device(iommu, devid); } -static int __init add_special_device(u8 type, u8 id, u16 *devid, bool cmd_line) +int __init add_special_device(u8 type, u8 id, u16 *devid, bool cmd_line) { struct devid_map *entry; struct list_head *list; @@ -1153,6 +1154,8 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu, if (ret) return ret; + amd_iommu_apply_ivrs_quirks(); + /* * First save the recommended feature enable bits from ACPI */ diff --git a/drivers/iommu/amd_iommu_quirks.c b/drivers/iommu/amd_iommu_quirks.c new file mode 100644 index 000000000000..c235f79b7a20 --- /dev/null +++ b/drivers/iommu/amd_iommu_quirks.c @@ -0,0 +1,92 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +/* + * Quirks for AMD IOMMU + * + * Copyright (C) 2019 Kai-Heng Feng <kai.heng.feng@canonical.com> + */ + +#ifdef CONFIG_DMI +#include <linux/dmi.h> + +#include "amd_iommu.h" + +#define IVHD_SPECIAL_IOAPIC 1 + +struct ivrs_quirk_entry { + u8 id; + u16 devid; +}; + +enum { + DELL_INSPIRON_7375 = 0, + DELL_LATITUDE_5495, + LENOVO_IDEAPAD_330S_15ARR, +}; + +static const struct ivrs_quirk_entry ivrs_ioapic_quirks[][3] __initconst = { + /* ivrs_ioapic[4]=00:14.0 ivrs_ioapic[5]=00:00.2 */ + [DELL_INSPIRON_7375] = { + { .id = 4, .devid = 0xa0 }, + { .id = 5, .devid = 0x2 }, + {} + }, + /* ivrs_ioapic[4]=00:14.0 */ + [DELL_LATITUDE_5495] = { + { .id = 4, .devid = 0xa0 }, + {} + }, + /* ivrs_ioapic[32]=00:14.0 */ + [LENOVO_IDEAPAD_330S_15ARR] = { + { .id = 32, .devid = 0xa0 }, + {} + }, + {} +}; + +static int __init ivrs_ioapic_quirk_cb(const struct dmi_system_id *d) +{ + const struct ivrs_quirk_entry *i; + + for (i = d->driver_data; i->id != 0 && i->devid != 0; i++) + add_special_device(IVHD_SPECIAL_IOAPIC, i->id, (u16 *)&i->devid, 0); + + return 0; +} + +static const struct dmi_system_id ivrs_quirks[] __initconst = { + { + .callback = ivrs_ioapic_quirk_cb, + .ident = "Dell Inspiron 7375", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7375"), + }, + .driver_data = (void *)&ivrs_ioapic_quirks[DELL_INSPIRON_7375], + }, + { + .callback = ivrs_ioapic_quirk_cb, + .ident = "Dell Latitude 5495", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude 5495"), + }, + .driver_data = (void *)&ivrs_ioapic_quirks[DELL_LATITUDE_5495], + }, + { + .callback = ivrs_ioapic_quirk_cb, + .ident = "Lenovo ideapad 330S-15ARR", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "81FB"), + }, + .driver_data = (void *)&ivrs_ioapic_quirks[LENOVO_IDEAPAD_330S_15ARR], + }, + {} +}; + +void __init amd_iommu_apply_ivrs_quirks(void) +{ + dmi_check_system(ivrs_quirks); +} +#endif diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index 64edd5a9694c..9ac229e92b07 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -873,6 +873,15 @@ struct amd_ir_data { struct msi_msg msi_entry; void *entry; /* Pointer to union irte or struct irte_ga */ void *ref; /* Pointer to the actual irte */ + + /** + * Store information for activate/de-activate + * Guest virtual APIC mode during runtime. + */ + struct irq_cfg *cfg; + int ga_vector; + int ga_root_ptr; + int ga_tag; }; struct amd_irte_ops { diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 29b773e186c8..4aa414843557 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -2311,6 +2311,7 @@ static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master) } } +#ifdef CONFIG_PCI_ATS static bool arm_smmu_ats_supported(struct arm_smmu_master *master) { struct pci_dev *pdev; @@ -2324,6 +2325,12 @@ static bool arm_smmu_ats_supported(struct arm_smmu_master *master) pdev = to_pci_dev(master->dev); return !pdev->untrusted && pdev->ats_cap; } +#else +static bool arm_smmu_ats_supported(struct arm_smmu_master *master) +{ + return false; +} +#endif static void arm_smmu_enable_ats(struct arm_smmu_master *master) { diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index de68b4a02aea..8f412af84247 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -303,13 +303,15 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, u64 size, struct device *dev) { struct iommu_dma_cookie *cookie = domain->iova_cookie; - struct iova_domain *iovad = &cookie->iovad; unsigned long order, base_pfn; + struct iova_domain *iovad; int attr; if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE) return -EINVAL; + iovad = &cookie->iovad; + /* Use the smallest supported page size for IOVA granularity */ order = __ffs(domain->pgsize_bitmap); base_pfn = max_t(unsigned long, 1, base >> order); diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 5d0754ed5fa0..eecd6a421667 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -1519,6 +1519,64 @@ static const char *dma_remap_fault_reasons[] = "PCE for translation request specifies blocking", }; +static const char * const dma_remap_sm_fault_reasons[] = { + "SM: Invalid Root Table Address", + "SM: TTM 0 for request with PASID", + "SM: TTM 0 for page group request", + "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x33-0x37 */ + "SM: Error attempting to access Root Entry", + "SM: Present bit in Root Entry is clear", + "SM: Non-zero reserved field set in Root Entry", + "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x3B-0x3F */ + "SM: Error attempting to access Context Entry", + "SM: Present bit in Context Entry is clear", + "SM: Non-zero reserved field set in the Context Entry", + "SM: Invalid Context Entry", + "SM: DTE field in Context Entry is clear", + "SM: PASID Enable field in Context Entry is clear", + "SM: PASID is larger than the max in Context Entry", + "SM: PRE field in Context-Entry is clear", + "SM: RID_PASID field error in Context-Entry", + "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x49-0x4F */ + "SM: Error attempting to access the PASID Directory Entry", + "SM: Present bit in Directory Entry is clear", + "SM: Non-zero reserved field set in PASID Directory Entry", + "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x53-0x57 */ + "SM: Error attempting to access PASID Table Entry", + "SM: Present bit in PASID Table Entry is clear", + "SM: Non-zero reserved field set in PASID Table Entry", + "SM: Invalid Scalable-Mode PASID Table Entry", + "SM: ERE field is clear in PASID Table Entry", + "SM: SRE field is clear in PASID Table Entry", + "Unknown", "Unknown",/* 0x5E-0x5F */ + "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x60-0x67 */ + "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x68-0x6F */ + "SM: Error attempting to access first-level paging entry", + "SM: Present bit in first-level paging entry is clear", + "SM: Non-zero reserved field set in first-level paging entry", + "SM: Error attempting to access FL-PML4 entry", + "SM: First-level entry address beyond MGAW in Nested translation", + "SM: Read permission error in FL-PML4 entry in Nested translation", + "SM: Read permission error in first-level paging entry in Nested translation", + "SM: Write permission error in first-level paging entry in Nested translation", + "SM: Error attempting to access second-level paging entry", + "SM: Read/Write permission error in second-level paging entry", + "SM: Non-zero reserved field set in second-level paging entry", + "SM: Invalid second-level page table pointer", + "SM: A/D bit update needed in second-level entry when set up in no snoop", + "Unknown", "Unknown", "Unknown", /* 0x7D-0x7F */ + "SM: Address in first-level translation is not canonical", + "SM: U/S set 0 for first-level translation with user privilege", + "SM: No execute permission for request with PASID and ER=1", + "SM: Address beyond the DMA hardware max", + "SM: Second-level entry address beyond the max", + "SM: No write permission for Write/AtomicOp request", + "SM: No read permission for Read/AtomicOp request", + "SM: Invalid address-interrupt address", + "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x88-0x8F */ + "SM: A/D bit update needed in first-level entry when set up in no snoop", +}; + static const char *irq_remap_fault_reasons[] = { "Detected reserved fields in the decoded interrupt-remapped request", @@ -1536,6 +1594,10 @@ static const char *dmar_get_fault_reason(u8 fault_reason, int *fault_type) ARRAY_SIZE(irq_remap_fault_reasons))) { *fault_type = INTR_REMAP; return irq_remap_fault_reasons[fault_reason - 0x20]; + } else if (fault_reason >= 0x30 && (fault_reason - 0x30 < + ARRAY_SIZE(dma_remap_sm_fault_reasons))) { + *fault_type = DMA_REMAP; + return dma_remap_sm_fault_reasons[fault_reason - 0x30]; } else if (fault_reason < ARRAY_SIZE(dma_remap_fault_reasons)) { *fault_type = DMA_REMAP; return dma_remap_fault_reasons[fault_reason]; @@ -1611,7 +1673,8 @@ void dmar_msi_read(int irq, struct msi_msg *msg) } static int dmar_fault_do_one(struct intel_iommu *iommu, int type, - u8 fault_reason, u16 source_id, unsigned long long addr) + u8 fault_reason, int pasid, u16 source_id, + unsigned long long addr) { const char *reason; int fault_type; @@ -1624,10 +1687,11 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type, PCI_FUNC(source_id & 0xFF), addr >> 48, fault_reason, reason); else - pr_err("[%s] Request device [%02x:%02x.%d] fault addr %llx [fault reason %02d] %s\n", + pr_err("[%s] Request device [%02x:%02x.%d] PASID %x fault addr %llx [fault reason %02d] %s\n", type ? "DMA Read" : "DMA Write", source_id >> 8, PCI_SLOT(source_id & 0xFF), - PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason); + PCI_FUNC(source_id & 0xFF), pasid, addr, + fault_reason, reason); return 0; } @@ -1659,8 +1723,9 @@ irqreturn_t dmar_fault(int irq, void *dev_id) u8 fault_reason; u16 source_id; u64 guest_addr; - int type; + int type, pasid; u32 data; + bool pasid_present; /* highest 32 bits */ data = readl(iommu->reg + reg + @@ -1672,10 +1737,12 @@ irqreturn_t dmar_fault(int irq, void *dev_id) fault_reason = dma_frcd_fault_reason(data); type = dma_frcd_type(data); + pasid = dma_frcd_pasid_value(data); data = readl(iommu->reg + reg + fault_index * PRIMARY_FAULT_REG_LEN + 8); source_id = dma_frcd_source_id(data); + pasid_present = dma_frcd_pasid_present(data); guest_addr = dmar_readq(iommu->reg + reg + fault_index * PRIMARY_FAULT_REG_LEN); guest_addr = dma_frcd_page_addr(guest_addr); @@ -1688,7 +1755,9 @@ irqreturn_t dmar_fault(int irq, void *dev_id) raw_spin_unlock_irqrestore(&iommu->register_lock, flag); if (!ratelimited) + /* Using pasid -1 if pasid is not present */ dmar_fault_do_one(iommu, type, fault_reason, + pasid_present ? pasid : -1, source_id, guest_addr); fault_index++; diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index cf5af34cb681..9c94e16fb127 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -566,7 +566,7 @@ static void sysmmu_tlb_invalidate_entry(struct sysmmu_drvdata *data, static const struct iommu_ops exynos_iommu_ops; -static int __init exynos_sysmmu_probe(struct platform_device *pdev) +static int exynos_sysmmu_probe(struct platform_device *pdev) { int irq, ret; struct device *dev = &pdev->dev; @@ -583,10 +583,8 @@ static int __init exynos_sysmmu_probe(struct platform_device *pdev) return PTR_ERR(data->sfrbase); irq = platform_get_irq(pdev, 0); - if (irq <= 0) { - dev_err(dev, "Unable to find IRQ resource\n"); + if (irq <= 0) return irq; - } ret = devm_request_irq(dev, irq, exynos_sysmmu_irq, 0, dev_name(dev), data); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index b7454ca4a87c..87de0b975672 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -41,9 +41,11 @@ #include <linux/dma-direct.h> #include <linux/crash_dump.h> #include <linux/numa.h> +#include <linux/swiotlb.h> #include <asm/irq_remapping.h> #include <asm/cacheflush.h> #include <asm/iommu.h> +#include <trace/events/intel_iommu.h> #include "irq_remapping.h" #include "intel-pasid.h" @@ -339,11 +341,15 @@ static void domain_exit(struct dmar_domain *domain); static void domain_remove_dev_info(struct dmar_domain *domain); static void dmar_remove_one_dev_info(struct device *dev); static void __dmar_remove_one_dev_info(struct device_domain_info *info); +static void domain_context_clear(struct intel_iommu *iommu, + struct device *dev); static int domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu); static bool device_is_rmrr_locked(struct device *dev); static int intel_iommu_attach_device(struct iommu_domain *domain, struct device *dev); +static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain, + dma_addr_t iova); #ifdef CONFIG_INTEL_IOMMU_DEFAULT_ON int dmar_disabled = 0; @@ -360,6 +366,7 @@ static int dmar_forcedac; static int intel_iommu_strict; static int intel_iommu_superpage = 1; static int iommu_identity_mapping; +static int intel_no_bounce; #define IDENTMAP_ALL 1 #define IDENTMAP_GFX 2 @@ -373,6 +380,9 @@ EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped); static DEFINE_SPINLOCK(device_domain_lock); static LIST_HEAD(device_domain_list); +#define device_needs_bounce(d) (!intel_no_bounce && dev_is_pci(d) && \ + to_pci_dev(d)->untrusted) + /* * Iterate over elements in device_domain_list and call the specified * callback @fn against each element. @@ -455,6 +465,9 @@ static int __init intel_iommu_setup(char *str) printk(KERN_INFO "Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n"); intel_iommu_tboot_noforce = 1; + } else if (!strncmp(str, "nobounce", 8)) { + pr_info("Intel-IOMMU: No bounce buffer. This could expose security risks of DMA attacks\n"); + intel_no_bounce = 1; } str += strcspn(str, ","); @@ -2105,9 +2118,26 @@ out_unlock: return ret; } +struct domain_context_mapping_data { + struct dmar_domain *domain; + struct intel_iommu *iommu; + struct pasid_table *table; +}; + +static int domain_context_mapping_cb(struct pci_dev *pdev, + u16 alias, void *opaque) +{ + struct domain_context_mapping_data *data = opaque; + + return domain_context_mapping_one(data->domain, data->iommu, + data->table, PCI_BUS_NUM(alias), + alias & 0xff); +} + static int domain_context_mapping(struct dmar_domain *domain, struct device *dev) { + struct domain_context_mapping_data data; struct pasid_table *table; struct intel_iommu *iommu; u8 bus, devfn; @@ -2117,7 +2147,17 @@ domain_context_mapping(struct dmar_domain *domain, struct device *dev) return -ENODEV; table = intel_pasid_get_table(dev); - return domain_context_mapping_one(domain, iommu, table, bus, devfn); + + if (!dev_is_pci(dev)) + return domain_context_mapping_one(domain, iommu, table, + bus, devfn); + + data.domain = domain; + data.iommu = iommu; + data.table = table; + + return pci_for_each_dma_alias(to_pci_dev(dev), + &domain_context_mapping_cb, &data); } static int domain_context_mapped_cb(struct pci_dev *pdev, @@ -3267,7 +3307,7 @@ static int __init init_dmars(void) iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH); } - if (iommu_pass_through) + if (iommu_default_passthrough()) iommu_identity_mapping |= IDENTMAP_ALL; #ifdef CONFIG_INTEL_IOMMU_BROKEN_GFX_WA @@ -3505,6 +3545,9 @@ static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr, start_paddr = (phys_addr_t)iova_pfn << PAGE_SHIFT; start_paddr += paddr & ~PAGE_MASK; + + trace_map_single(dev, start_paddr, paddr, size << VTD_PAGE_SHIFT); + return start_paddr; error: @@ -3560,10 +3603,7 @@ static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size) if (dev_is_pci(dev)) pdev = to_pci_dev(dev); - dev_dbg(dev, "Device unmapping: pfn %lx-%lx\n", start_pfn, last_pfn); - freelist = domain_unmap(domain, start_pfn, last_pfn); - if (intel_iommu_strict || (pdev && pdev->untrusted) || !has_iova_flush_queue(&domain->iovad)) { iommu_flush_iotlb_psi(iommu, domain, start_pfn, @@ -3579,6 +3619,8 @@ static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size) * cpu used up by the iotlb flush operation... */ } + + trace_unmap_single(dev, dev_addr, size); } static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr, @@ -3669,6 +3711,8 @@ static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist, } intel_unmap(dev, startaddr, nrpages << VTD_PAGE_SHIFT); + + trace_unmap_sg(dev, startaddr, nrpages << VTD_PAGE_SHIFT); } static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nelems, @@ -3725,6 +3769,9 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele return 0; } + trace_map_sg(dev, iova_pfn << PAGE_SHIFT, + sg_phys(sglist), size << VTD_PAGE_SHIFT); + return nelems; } @@ -3740,6 +3787,252 @@ static const struct dma_map_ops intel_dma_ops = { .dma_supported = dma_direct_supported, }; +static void +bounce_sync_single(struct device *dev, dma_addr_t addr, size_t size, + enum dma_data_direction dir, enum dma_sync_target target) +{ + struct dmar_domain *domain; + phys_addr_t tlb_addr; + + domain = find_domain(dev); + if (WARN_ON(!domain)) + return; + + tlb_addr = intel_iommu_iova_to_phys(&domain->domain, addr); + if (is_swiotlb_buffer(tlb_addr)) + swiotlb_tbl_sync_single(dev, tlb_addr, size, dir, target); +} + +static dma_addr_t +bounce_map_single(struct device *dev, phys_addr_t paddr, size_t size, + enum dma_data_direction dir, unsigned long attrs, + u64 dma_mask) +{ + size_t aligned_size = ALIGN(size, VTD_PAGE_SIZE); + struct dmar_domain *domain; + struct intel_iommu *iommu; + unsigned long iova_pfn; + unsigned long nrpages; + phys_addr_t tlb_addr; + int prot = 0; + int ret; + + domain = find_domain(dev); + if (WARN_ON(dir == DMA_NONE || !domain)) + return DMA_MAPPING_ERROR; + + iommu = domain_get_iommu(domain); + if (WARN_ON(!iommu)) + return DMA_MAPPING_ERROR; + + nrpages = aligned_nrpages(0, size); + iova_pfn = intel_alloc_iova(dev, domain, + dma_to_mm_pfn(nrpages), dma_mask); + if (!iova_pfn) + return DMA_MAPPING_ERROR; + + /* + * Check if DMAR supports zero-length reads on write only + * mappings.. + */ + if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL || + !cap_zlr(iommu->cap)) + prot |= DMA_PTE_READ; + if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) + prot |= DMA_PTE_WRITE; + + /* + * If both the physical buffer start address and size are + * page aligned, we don't need to use a bounce page. + */ + if (!IS_ALIGNED(paddr | size, VTD_PAGE_SIZE)) { + tlb_addr = swiotlb_tbl_map_single(dev, + __phys_to_dma(dev, io_tlb_start), + paddr, size, aligned_size, dir, attrs); + if (tlb_addr == DMA_MAPPING_ERROR) { + goto swiotlb_error; + } else { + /* Cleanup the padding area. */ + void *padding_start = phys_to_virt(tlb_addr); + size_t padding_size = aligned_size; + + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && + (dir == DMA_TO_DEVICE || + dir == DMA_BIDIRECTIONAL)) { + padding_start += size; + padding_size -= size; + } + + memset(padding_start, 0, padding_size); + } + } else { + tlb_addr = paddr; + } + + ret = domain_pfn_mapping(domain, mm_to_dma_pfn(iova_pfn), + tlb_addr >> VTD_PAGE_SHIFT, nrpages, prot); + if (ret) + goto mapping_error; + + trace_bounce_map_single(dev, iova_pfn << PAGE_SHIFT, paddr, size); + + return (phys_addr_t)iova_pfn << PAGE_SHIFT; + +mapping_error: + if (is_swiotlb_buffer(tlb_addr)) + swiotlb_tbl_unmap_single(dev, tlb_addr, size, + aligned_size, dir, attrs); +swiotlb_error: + free_iova_fast(&domain->iovad, iova_pfn, dma_to_mm_pfn(nrpages)); + dev_err(dev, "Device bounce map: %zx@%llx dir %d --- failed\n", + size, (unsigned long long)paddr, dir); + + return DMA_MAPPING_ERROR; +} + +static void +bounce_unmap_single(struct device *dev, dma_addr_t dev_addr, size_t size, + enum dma_data_direction dir, unsigned long attrs) +{ + size_t aligned_size = ALIGN(size, VTD_PAGE_SIZE); + struct dmar_domain *domain; + phys_addr_t tlb_addr; + + domain = find_domain(dev); + if (WARN_ON(!domain)) + return; + + tlb_addr = intel_iommu_iova_to_phys(&domain->domain, dev_addr); + if (WARN_ON(!tlb_addr)) + return; + + intel_unmap(dev, dev_addr, size); + if (is_swiotlb_buffer(tlb_addr)) + swiotlb_tbl_unmap_single(dev, tlb_addr, size, + aligned_size, dir, attrs); + + trace_bounce_unmap_single(dev, dev_addr, size); +} + +static dma_addr_t +bounce_map_page(struct device *dev, struct page *page, unsigned long offset, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ + return bounce_map_single(dev, page_to_phys(page) + offset, + size, dir, attrs, *dev->dma_mask); +} + +static dma_addr_t +bounce_map_resource(struct device *dev, phys_addr_t phys_addr, size_t size, + enum dma_data_direction dir, unsigned long attrs) +{ + return bounce_map_single(dev, phys_addr, size, + dir, attrs, *dev->dma_mask); +} + +static void +bounce_unmap_page(struct device *dev, dma_addr_t dev_addr, size_t size, + enum dma_data_direction dir, unsigned long attrs) +{ + bounce_unmap_single(dev, dev_addr, size, dir, attrs); +} + +static void +bounce_unmap_resource(struct device *dev, dma_addr_t dev_addr, size_t size, + enum dma_data_direction dir, unsigned long attrs) +{ + bounce_unmap_single(dev, dev_addr, size, dir, attrs); +} + +static void +bounce_unmap_sg(struct device *dev, struct scatterlist *sglist, int nelems, + enum dma_data_direction dir, unsigned long attrs) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sglist, sg, nelems, i) + bounce_unmap_page(dev, sg->dma_address, + sg_dma_len(sg), dir, attrs); +} + +static int +bounce_map_sg(struct device *dev, struct scatterlist *sglist, int nelems, + enum dma_data_direction dir, unsigned long attrs) +{ + int i; + struct scatterlist *sg; + + for_each_sg(sglist, sg, nelems, i) { + sg->dma_address = bounce_map_page(dev, sg_page(sg), + sg->offset, sg->length, + dir, attrs); + if (sg->dma_address == DMA_MAPPING_ERROR) + goto out_unmap; + sg_dma_len(sg) = sg->length; + } + + return nelems; + +out_unmap: + bounce_unmap_sg(dev, sglist, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC); + return 0; +} + +static void +bounce_sync_single_for_cpu(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ + bounce_sync_single(dev, addr, size, dir, SYNC_FOR_CPU); +} + +static void +bounce_sync_single_for_device(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ + bounce_sync_single(dev, addr, size, dir, SYNC_FOR_DEVICE); +} + +static void +bounce_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, + int nelems, enum dma_data_direction dir) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sglist, sg, nelems, i) + bounce_sync_single(dev, sg_dma_address(sg), + sg_dma_len(sg), dir, SYNC_FOR_CPU); +} + +static void +bounce_sync_sg_for_device(struct device *dev, struct scatterlist *sglist, + int nelems, enum dma_data_direction dir) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sglist, sg, nelems, i) + bounce_sync_single(dev, sg_dma_address(sg), + sg_dma_len(sg), dir, SYNC_FOR_DEVICE); +} + +static const struct dma_map_ops bounce_dma_ops = { + .alloc = intel_alloc_coherent, + .free = intel_free_coherent, + .map_sg = bounce_map_sg, + .unmap_sg = bounce_unmap_sg, + .map_page = bounce_map_page, + .unmap_page = bounce_unmap_page, + .sync_single_for_cpu = bounce_sync_single_for_cpu, + .sync_single_for_device = bounce_sync_single_for_device, + .sync_sg_for_cpu = bounce_sync_sg_for_cpu, + .sync_sg_for_device = bounce_sync_sg_for_device, + .map_resource = bounce_map_resource, + .unmap_resource = bounce_unmap_resource, + .dma_supported = dma_direct_supported, +}; + static inline int iommu_domain_cache_init(void) { int ret = 0; @@ -4540,22 +4833,20 @@ const struct attribute_group *intel_iommu_groups[] = { NULL, }; -static int __init platform_optin_force_iommu(void) +static inline bool has_untrusted_dev(void) { struct pci_dev *pdev = NULL; - bool has_untrusted_dev = false; - if (!dmar_platform_optin() || no_platform_optin) - return 0; + for_each_pci_dev(pdev) + if (pdev->untrusted) + return true; - for_each_pci_dev(pdev) { - if (pdev->untrusted) { - has_untrusted_dev = true; - break; - } - } + return false; +} - if (!has_untrusted_dev) +static int __init platform_optin_force_iommu(void) +{ + if (!dmar_platform_optin() || no_platform_optin || !has_untrusted_dev()) return 0; if (no_iommu || dmar_disabled) @@ -4569,9 +4860,6 @@ static int __init platform_optin_force_iommu(void) iommu_identity_mapping |= IDENTMAP_ALL; dmar_disabled = 0; -#if defined(CONFIG_X86) && defined(CONFIG_SWIOTLB) - swiotlb = 0; -#endif no_iommu = 0; return 1; @@ -4711,7 +4999,14 @@ int __init intel_iommu_init(void) up_write(&dmar_global_lock); #if defined(CONFIG_X86) && defined(CONFIG_SWIOTLB) - swiotlb = 0; + /* + * If the system has no untrusted device or the user has decided + * to disable the bounce page mechanisms, we don't need swiotlb. + * Mark this and the pre-allocated bounce pages will be released + * later. + */ + if (!has_untrusted_dev() || intel_no_bounce) + swiotlb = 0; #endif dma_ops = &intel_dma_ops; @@ -4759,6 +5054,28 @@ out_free_dmar: return ret; } +static int domain_context_clear_one_cb(struct pci_dev *pdev, u16 alias, void *opaque) +{ + struct intel_iommu *iommu = opaque; + + domain_context_clear_one(iommu, PCI_BUS_NUM(alias), alias & 0xff); + return 0; +} + +/* + * NB - intel-iommu lacks any sort of reference counting for the users of + * dependent devices. If multiple endpoints have intersecting dependent + * devices, unbinding the driver from any one of them will possibly leave + * the others unable to operate. + */ +static void domain_context_clear(struct intel_iommu *iommu, struct device *dev) +{ + if (!iommu || !dev || !dev_is_pci(dev)) + return; + + pci_for_each_dma_alias(to_pci_dev(dev), &domain_context_clear_one_cb, iommu); +} + static void __dmar_remove_one_dev_info(struct device_domain_info *info) { struct dmar_domain *domain; @@ -4779,7 +5096,7 @@ static void __dmar_remove_one_dev_info(struct device_domain_info *info) PASID_RID2PASID); iommu_disable_dev_iotlb(info); - domain_context_clear_one(iommu, info->bus, info->devfn); + domain_context_clear(iommu, info->dev); intel_pasid_free_table(info->dev); } @@ -5310,6 +5627,11 @@ static int intel_iommu_add_device(struct device *dev) } } + if (device_needs_bounce(dev)) { + dev_info(dev, "Use Intel IOMMU bounce page dma_ops\n"); + set_dma_ops(dev, &bounce_dma_ops); + } + return 0; } @@ -5327,6 +5649,9 @@ static void intel_iommu_remove_device(struct device *dev) iommu_group_remove_device(dev); iommu_device_unlink(&iommu->iommu, dev); + + if (device_needs_bounce(dev)) + set_dma_ops(dev, NULL); } static void intel_iommu_get_resv_regions(struct device *device, @@ -5640,20 +5965,46 @@ const struct iommu_ops intel_iommu_ops = { .pgsize_bitmap = INTEL_IOMMU_PGSIZES, }; -static void quirk_iommu_g4x_gfx(struct pci_dev *dev) +static void quirk_iommu_igfx(struct pci_dev *dev) { - /* G4x/GM45 integrated gfx dmar support is totally busted. */ pci_info(dev, "Disabling IOMMU for graphics on this chipset\n"); dmar_map_gfx = 0; } -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_g4x_gfx); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e00, quirk_iommu_g4x_gfx); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e10, quirk_iommu_g4x_gfx); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e20, quirk_iommu_g4x_gfx); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_g4x_gfx); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_g4x_gfx); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_g4x_gfx); +/* G4x/GM45 integrated gfx dmar support is totally busted. */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e00, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e10, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e20, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_igfx); + +/* Broadwell igfx malfunctions with dmar */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1606, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160B, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160E, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1602, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160A, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160D, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1616, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161B, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161E, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1612, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161A, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161D, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1626, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162B, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162E, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1622, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162A, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162D, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1636, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163B, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163E, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1632, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163A, quirk_iommu_igfx); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163D, quirk_iommu_igfx); static void quirk_iommu_rwbf(struct pci_dev *dev) { diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index 780de0caafe8..9b159132405d 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -100,24 +100,19 @@ int intel_svm_finish_prq(struct intel_iommu *iommu) } static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_dev *sdev, - unsigned long address, unsigned long pages, int ih, int gl) + unsigned long address, unsigned long pages, int ih) { struct qi_desc desc; - if (pages == -1) { - /* For global kernel pages we have to flush them in *all* PASIDs - * because that's the only option the hardware gives us. Despite - * the fact that they are actually only accessible through one. */ - if (gl) - desc.qw0 = QI_EIOTLB_PASID(svm->pasid) | - QI_EIOTLB_DID(sdev->did) | - QI_EIOTLB_GRAN(QI_GRAN_ALL_ALL) | - QI_EIOTLB_TYPE; - else - desc.qw0 = QI_EIOTLB_PASID(svm->pasid) | - QI_EIOTLB_DID(sdev->did) | - QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) | - QI_EIOTLB_TYPE; + /* + * Do PASID granu IOTLB invalidation if page selective capability is + * not available. + */ + if (pages == -1 || !cap_pgsel_inv(svm->iommu->cap)) { + desc.qw0 = QI_EIOTLB_PASID(svm->pasid) | + QI_EIOTLB_DID(sdev->did) | + QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) | + QI_EIOTLB_TYPE; desc.qw1 = 0; } else { int mask = ilog2(__roundup_pow_of_two(pages)); @@ -127,7 +122,6 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d QI_EIOTLB_GRAN(QI_GRAN_PSI_PASID) | QI_EIOTLB_TYPE; desc.qw1 = QI_EIOTLB_ADDR(address) | - QI_EIOTLB_GL(gl) | QI_EIOTLB_IH(ih) | QI_EIOTLB_AM(mask); } @@ -162,13 +156,13 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d } static void intel_flush_svm_range(struct intel_svm *svm, unsigned long address, - unsigned long pages, int ih, int gl) + unsigned long pages, int ih) { struct intel_svm_dev *sdev; rcu_read_lock(); list_for_each_entry_rcu(sdev, &svm->devs, list) - intel_flush_svm_range_dev(svm, sdev, address, pages, ih, gl); + intel_flush_svm_range_dev(svm, sdev, address, pages, ih); rcu_read_unlock(); } @@ -180,7 +174,7 @@ static void intel_invalidate_range(struct mmu_notifier *mn, struct intel_svm *svm = container_of(mn, struct intel_svm, notifier); intel_flush_svm_range(svm, start, - (end - start + PAGE_SIZE - 1) >> VTD_PAGE_SHIFT, 0, 0); + (end - start + PAGE_SIZE - 1) >> VTD_PAGE_SHIFT, 0); } static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm) @@ -203,7 +197,7 @@ static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm) rcu_read_lock(); list_for_each_entry_rcu(sdev, &svm->devs, list) { intel_pasid_tear_down_entry(svm->iommu, sdev->dev, svm->pasid); - intel_flush_svm_range_dev(svm, sdev, 0, -1, 0, !svm->mm); + intel_flush_svm_range_dev(svm, sdev, 0, -1, 0); } rcu_read_unlock(); @@ -425,7 +419,7 @@ int intel_svm_unbind_mm(struct device *dev, int pasid) * large and has to be physically contiguous. So it's * hard to be as defensive as we might like. */ intel_pasid_tear_down_entry(iommu, dev, svm->pasid); - intel_flush_svm_range_dev(svm, sdev, 0, -1, 0, !svm->mm); + intel_flush_svm_range_dev(svm, sdev, 0, -1, 0); kfree_rcu(sdev, rcu); if (list_empty(&svm->devs)) { diff --git a/drivers/iommu/intel-trace.c b/drivers/iommu/intel-trace.c new file mode 100644 index 000000000000..bfb6a6e37a88 --- /dev/null +++ b/drivers/iommu/intel-trace.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel IOMMU trace support + * + * Copyright (C) 2019 Intel Corporation + * + * Author: Lu Baolu <baolu.lu@linux.intel.com> + */ + +#include <linux/string.h> +#include <linux/types.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/intel_iommu.h> diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index 4786ca061e31..81e43c1df7ec 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -376,13 +376,13 @@ static int set_msi_sid_cb(struct pci_dev *pdev, u16 alias, void *opaque) { struct set_msi_sid_data *data = opaque; + if (data->count == 0 || PCI_BUS_NUM(alias) == PCI_BUS_NUM(data->alias)) + data->busmatch_count++; + data->pdev = pdev; data->alias = alias; data->count++; - if (PCI_BUS_NUM(alias) == pdev->bus->number) - data->busmatch_count++; - return 0; } diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 70bfbcc09248..d658c7c6a2ab 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -26,12 +26,10 @@ static struct kset *iommu_group_kset; static DEFINE_IDA(iommu_group_ida); -#ifdef CONFIG_IOMMU_DEFAULT_PASSTHROUGH -static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_IDENTITY; -#else -static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_DMA; -#endif + +static unsigned int iommu_def_domain_type __read_mostly; static bool iommu_dma_strict __read_mostly = true; +static u32 iommu_cmd_line __read_mostly; struct iommu_group { struct kobject kobj; @@ -68,6 +66,18 @@ static const char * const iommu_group_resv_type_string[] = { [IOMMU_RESV_SW_MSI] = "msi", }; +#define IOMMU_CMD_LINE_DMA_API BIT(0) + +static void iommu_set_cmd_line_dma_api(void) +{ + iommu_cmd_line |= IOMMU_CMD_LINE_DMA_API; +} + +static bool iommu_cmd_line_dma_api(void) +{ + return !!(iommu_cmd_line & IOMMU_CMD_LINE_DMA_API); +} + #define IOMMU_GROUP_ATTR(_name, _mode, _show, _store) \ struct iommu_group_attribute iommu_group_attr_##_name = \ __ATTR(_name, _mode, _show, _store) @@ -80,12 +90,55 @@ struct iommu_group_attribute iommu_group_attr_##_name = \ static LIST_HEAD(iommu_device_list); static DEFINE_SPINLOCK(iommu_device_lock); +/* + * Use a function instead of an array here because the domain-type is a + * bit-field, so an array would waste memory. + */ +static const char *iommu_domain_type_str(unsigned int t) +{ + switch (t) { + case IOMMU_DOMAIN_BLOCKED: + return "Blocked"; + case IOMMU_DOMAIN_IDENTITY: + return "Passthrough"; + case IOMMU_DOMAIN_UNMANAGED: + return "Unmanaged"; + case IOMMU_DOMAIN_DMA: + return "Translated"; + default: + return "Unknown"; + } +} + +static int __init iommu_subsys_init(void) +{ + bool cmd_line = iommu_cmd_line_dma_api(); + + if (!cmd_line) { + if (IS_ENABLED(CONFIG_IOMMU_DEFAULT_PASSTHROUGH)) + iommu_set_default_passthrough(false); + else + iommu_set_default_translated(false); + + if (iommu_default_passthrough() && mem_encrypt_active()) { + pr_info("Memory encryption detected - Disabling default IOMMU Passthrough\n"); + iommu_set_default_translated(false); + } + } + + pr_info("Default domain type: %s %s\n", + iommu_domain_type_str(iommu_def_domain_type), + cmd_line ? "(set via kernel command line)" : ""); + + return 0; +} +subsys_initcall(iommu_subsys_init); + 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; } @@ -165,7 +218,11 @@ static int __init iommu_set_def_domain_type(char *str) if (ret) return ret; - iommu_def_domain_type = pt ? IOMMU_DOMAIN_IDENTITY : IOMMU_DOMAIN_DMA; + if (pt) + iommu_set_default_passthrough(true); + else + iommu_set_default_translated(true); + return 0; } early_param("iommu.passthrough", iommu_set_def_domain_type); @@ -229,60 +286,58 @@ static ssize_t iommu_group_show_name(struct iommu_group *group, char *buf) * @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. + * Elements are sorted by start address and overlapping segments + * of the same type are merged. */ -static int iommu_insert_resv_region(struct iommu_resv_region *new, - struct list_head *regions) +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) - return 0; - else - pos = pos->next; + struct iommu_resv_region *iter, *tmp, *nr, *top; + LIST_HEAD(stack); + + nr = iommu_alloc_resv_region(new->start, new->length, + new->prot, new->type); + if (!nr) + return -ENOMEM; + + /* First add the new element based on start address sorting */ + list_for_each_entry(iter, regions, list) { + if (nr->start < iter->start || + (nr->start == iter->start && nr->type <= iter->type)) + break; + } + list_add_tail(&nr->list, &iter->list); + + /* Merge overlapping segments of type nr->type in @regions, if any */ + list_for_each_entry_safe(iter, tmp, regions, list) { + phys_addr_t top_end, iter_end = iter->start + iter->length - 1; + + /* no merge needed on elements of different types than @nr */ + if (iter->type != nr->type) { + list_move_tail(&iter->list, &stack); + continue; + } + + /* look for the last stack element of same type as @iter */ + list_for_each_entry_reverse(top, &stack, list) + if (top->type == iter->type) + goto check_overlap; + + list_move_tail(&iter->list, &stack); + continue; + +check_overlap: + top_end = top->start + top->length - 1; + + if (iter->start > top_end + 1) { + list_move_tail(&iter->list, &stack); } else { - if (new->type == type) { - phys_addr_t new_start = min(a, start); - phys_addr_t new_end = max(b, end); - int ret; - - list_del(&entry->list); - entry->start = new_start; - entry->length = new_end - new_start + 1; - ret = iommu_insert_resv_region(entry, regions); - kfree(entry); - return ret; - } else { - pos = pos->next; - } + top->length = max(top_end, iter_end) - top->start + 1; + list_del(&iter->list); + kfree(iter); } } -insert: - region = iommu_alloc_resv_region(new->start, new->length, - new->prot, new->type); - if (!region) - return -ENOMEM; - - list_add_tail(®ion->list, pos); + list_splice(&stack, regions); return 0; } @@ -2145,7 +2200,6 @@ request_default_domain_for_dev(struct device *dev, unsigned long type) mutex_lock(&group->mutex); - /* Check if the default domain is already direct mapped */ ret = 0; if (group->default_domain && group->default_domain->type == type) goto out; @@ -2155,7 +2209,6 @@ request_default_domain_for_dev(struct device *dev, unsigned long type) if (iommu_group_device_count(group) != 1) goto out; - /* Allocate a direct mapped domain */ ret = -ENOMEM; domain = __iommu_domain_alloc(dev->bus, type); if (!domain) @@ -2170,7 +2223,7 @@ request_default_domain_for_dev(struct device *dev, unsigned long type) iommu_group_create_direct_mappings(group, dev); - /* Make the direct mapped domain the default for this group */ + /* Make the domain the default for this group */ if (group->default_domain) iommu_domain_free(group->default_domain); group->default_domain = domain; @@ -2198,6 +2251,28 @@ int iommu_request_dma_domain_for_dev(struct device *dev) return request_default_domain_for_dev(dev, IOMMU_DOMAIN_DMA); } +void iommu_set_default_passthrough(bool cmd_line) +{ + if (cmd_line) + iommu_set_cmd_line_dma_api(); + + iommu_def_domain_type = IOMMU_DOMAIN_IDENTITY; +} + +void iommu_set_default_translated(bool cmd_line) +{ + if (cmd_line) + iommu_set_cmd_line_dma_api(); + + iommu_def_domain_type = IOMMU_DOMAIN_DMA; +} + +bool iommu_default_passthrough(void) +{ + return iommu_def_domain_type == IOMMU_DOMAIN_IDENTITY; +} +EXPORT_SYMBOL_GPL(iommu_default_passthrough); + const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode) { const struct iommu_ops *ops = NULL; diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index 3e1a8a675572..41c605b0058f 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -577,7 +577,9 @@ void queue_iova(struct iova_domain *iovad, spin_unlock_irqrestore(&fq->lock, flags); - if (atomic_cmpxchg(&iovad->fq_timer_on, 0, 1) == 0) + /* Avoid false sharing as much as possible. */ + if (!atomic_read(&iovad->fq_timer_on) && + !atomic_cmpxchg(&iovad->fq_timer_on, 0, 1)) mod_timer(&iovad->fq_timer, jiffies + msecs_to_jiffies(IOVA_FQ_TIMEOUT)); } diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 76a8ec343d53..9da8309f7170 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -49,6 +49,7 @@ struct ipmmu_features { bool setup_imbuscr; bool twobit_imttbcr_sl0; bool reserved_context; + bool cache_snoop; }; struct ipmmu_vmsa_device { @@ -115,45 +116,44 @@ static struct ipmmu_vmsa_device *to_ipmmu(struct device *dev) #define IMTTBCR 0x0008 #define IMTTBCR_EAE (1 << 31) #define IMTTBCR_PMB (1 << 30) -#define IMTTBCR_SH1_NON_SHAREABLE (0 << 28) -#define IMTTBCR_SH1_OUTER_SHAREABLE (2 << 28) -#define IMTTBCR_SH1_INNER_SHAREABLE (3 << 28) -#define IMTTBCR_SH1_MASK (3 << 28) -#define IMTTBCR_ORGN1_NC (0 << 26) -#define IMTTBCR_ORGN1_WB_WA (1 << 26) -#define IMTTBCR_ORGN1_WT (2 << 26) -#define IMTTBCR_ORGN1_WB (3 << 26) -#define IMTTBCR_ORGN1_MASK (3 << 26) -#define IMTTBCR_IRGN1_NC (0 << 24) -#define IMTTBCR_IRGN1_WB_WA (1 << 24) -#define IMTTBCR_IRGN1_WT (2 << 24) -#define IMTTBCR_IRGN1_WB (3 << 24) -#define IMTTBCR_IRGN1_MASK (3 << 24) +#define IMTTBCR_SH1_NON_SHAREABLE (0 << 28) /* R-Car Gen2 only */ +#define IMTTBCR_SH1_OUTER_SHAREABLE (2 << 28) /* R-Car Gen2 only */ +#define IMTTBCR_SH1_INNER_SHAREABLE (3 << 28) /* R-Car Gen2 only */ +#define IMTTBCR_SH1_MASK (3 << 28) /* R-Car Gen2 only */ +#define IMTTBCR_ORGN1_NC (0 << 26) /* R-Car Gen2 only */ +#define IMTTBCR_ORGN1_WB_WA (1 << 26) /* R-Car Gen2 only */ +#define IMTTBCR_ORGN1_WT (2 << 26) /* R-Car Gen2 only */ +#define IMTTBCR_ORGN1_WB (3 << 26) /* R-Car Gen2 only */ +#define IMTTBCR_ORGN1_MASK (3 << 26) /* R-Car Gen2 only */ +#define IMTTBCR_IRGN1_NC (0 << 24) /* R-Car Gen2 only */ +#define IMTTBCR_IRGN1_WB_WA (1 << 24) /* R-Car Gen2 only */ +#define IMTTBCR_IRGN1_WT (2 << 24) /* R-Car Gen2 only */ +#define IMTTBCR_IRGN1_WB (3 << 24) /* R-Car Gen2 only */ +#define IMTTBCR_IRGN1_MASK (3 << 24) /* R-Car Gen2 only */ #define IMTTBCR_TSZ1_MASK (7 << 16) #define IMTTBCR_TSZ1_SHIFT 16 -#define IMTTBCR_SH0_NON_SHAREABLE (0 << 12) -#define IMTTBCR_SH0_OUTER_SHAREABLE (2 << 12) -#define IMTTBCR_SH0_INNER_SHAREABLE (3 << 12) -#define IMTTBCR_SH0_MASK (3 << 12) -#define IMTTBCR_ORGN0_NC (0 << 10) -#define IMTTBCR_ORGN0_WB_WA (1 << 10) -#define IMTTBCR_ORGN0_WT (2 << 10) -#define IMTTBCR_ORGN0_WB (3 << 10) -#define IMTTBCR_ORGN0_MASK (3 << 10) -#define IMTTBCR_IRGN0_NC (0 << 8) -#define IMTTBCR_IRGN0_WB_WA (1 << 8) -#define IMTTBCR_IRGN0_WT (2 << 8) -#define IMTTBCR_IRGN0_WB (3 << 8) -#define IMTTBCR_IRGN0_MASK (3 << 8) +#define IMTTBCR_SH0_NON_SHAREABLE (0 << 12) /* R-Car Gen2 only */ +#define IMTTBCR_SH0_OUTER_SHAREABLE (2 << 12) /* R-Car Gen2 only */ +#define IMTTBCR_SH0_INNER_SHAREABLE (3 << 12) /* R-Car Gen2 only */ +#define IMTTBCR_SH0_MASK (3 << 12) /* R-Car Gen2 only */ +#define IMTTBCR_ORGN0_NC (0 << 10) /* R-Car Gen2 only */ +#define IMTTBCR_ORGN0_WB_WA (1 << 10) /* R-Car Gen2 only */ +#define IMTTBCR_ORGN0_WT (2 << 10) /* R-Car Gen2 only */ +#define IMTTBCR_ORGN0_WB (3 << 10) /* R-Car Gen2 only */ +#define IMTTBCR_ORGN0_MASK (3 << 10) /* R-Car Gen2 only */ +#define IMTTBCR_IRGN0_NC (0 << 8) /* R-Car Gen2 only */ +#define IMTTBCR_IRGN0_WB_WA (1 << 8) /* R-Car Gen2 only */ +#define IMTTBCR_IRGN0_WT (2 << 8) /* R-Car Gen2 only */ +#define IMTTBCR_IRGN0_WB (3 << 8) /* R-Car Gen2 only */ +#define IMTTBCR_IRGN0_MASK (3 << 8) /* R-Car Gen2 only */ +#define IMTTBCR_SL0_TWOBIT_LVL_3 (0 << 6) /* R-Car Gen3 only */ +#define IMTTBCR_SL0_TWOBIT_LVL_2 (1 << 6) /* R-Car Gen3 only */ +#define IMTTBCR_SL0_TWOBIT_LVL_1 (2 << 6) /* R-Car Gen3 only */ #define IMTTBCR_SL0_LVL_2 (0 << 4) #define IMTTBCR_SL0_LVL_1 (1 << 4) #define IMTTBCR_TSZ0_MASK (7 << 0) #define IMTTBCR_TSZ0_SHIFT O -#define IMTTBCR_SL0_TWOBIT_LVL_3 (0 << 6) -#define IMTTBCR_SL0_TWOBIT_LVL_2 (1 << 6) -#define IMTTBCR_SL0_TWOBIT_LVL_1 (2 << 6) - #define IMBUSCR 0x000c #define IMBUSCR_DVM (1 << 2) #define IMBUSCR_BUSSEL_SYS (0 << 0) @@ -422,17 +422,19 @@ static void ipmmu_domain_setup_context(struct ipmmu_vmsa_domain *domain) /* * TTBCR - * We use long descriptors with inner-shareable WBWA tables and allocate - * the whole 32-bit VA space to TTBR0. + * We use long descriptors and allocate the whole 32-bit VA space to + * TTBR0. */ if (domain->mmu->features->twobit_imttbcr_sl0) tmp = IMTTBCR_SL0_TWOBIT_LVL_1; else tmp = IMTTBCR_SL0_LVL_1; - ipmmu_ctx_write_root(domain, IMTTBCR, IMTTBCR_EAE | - IMTTBCR_SH0_INNER_SHAREABLE | IMTTBCR_ORGN0_WB_WA | - IMTTBCR_IRGN0_WB_WA | tmp); + if (domain->mmu->features->cache_snoop) + tmp |= IMTTBCR_SH0_INNER_SHAREABLE | IMTTBCR_ORGN0_WB_WA | + IMTTBCR_IRGN0_WB_WA; + + ipmmu_ctx_write_root(domain, IMTTBCR, IMTTBCR_EAE | tmp); /* MAIR0 */ ipmmu_ctx_write_root(domain, IMMAIR0, @@ -994,6 +996,7 @@ static const struct ipmmu_features ipmmu_features_default = { .setup_imbuscr = true, .twobit_imttbcr_sl0 = false, .reserved_context = false, + .cache_snoop = true, }; static const struct ipmmu_features ipmmu_features_rcar_gen3 = { @@ -1004,6 +1007,7 @@ static const struct ipmmu_features ipmmu_features_rcar_gen3 = { .setup_imbuscr = false, .twobit_imttbcr_sl0 = true, .reserved_context = true, + .cache_snoop = false, }; static const struct of_device_id ipmmu_of_ids[] = { diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index 4c0be5b75c28..be99d408cf35 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -766,7 +766,6 @@ static int msm_iommu_probe(struct platform_device *pdev) iommu->irq = platform_get_irq(pdev, 0); if (iommu->irq < 0) { - dev_err(iommu->dev, "could not get iommu irq\n"); ret = -ENODEV; goto fail; } diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index 8039bc5ee425..09c6e1c680db 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -35,6 +35,15 @@ static const struct iommu_ops omap_iommu_ops; +struct orphan_dev { + struct device *dev; + struct list_head node; +}; + +static LIST_HEAD(orphan_dev_list); + +static DEFINE_SPINLOCK(orphan_lock); + #define to_iommu(dev) ((struct omap_iommu *)dev_get_drvdata(dev)) /* bitmap of the page sizes currently supported */ @@ -53,6 +62,8 @@ static const struct iommu_ops omap_iommu_ops; static struct platform_driver omap_iommu_driver; static struct kmem_cache *iopte_cachep; +static int _omap_iommu_add_device(struct device *dev); + /** * to_omap_domain - Get struct omap_iommu_domain from generic iommu_domain * @dom: generic iommu domain handle @@ -65,6 +76,9 @@ static struct omap_iommu_domain *to_omap_domain(struct iommu_domain *dom) /** * omap_iommu_save_ctx - Save registers for pm off-mode support * @dev: client device + * + * This should be treated as an deprecated API. It is preserved only + * to maintain existing functionality for OMAP3 ISP driver. **/ void omap_iommu_save_ctx(struct device *dev) { @@ -92,6 +106,9 @@ EXPORT_SYMBOL_GPL(omap_iommu_save_ctx); /** * omap_iommu_restore_ctx - Restore registers for pm off-mode support * @dev: client device + * + * This should be treated as an deprecated API. It is preserved only + * to maintain existing functionality for OMAP3 ISP driver. **/ void omap_iommu_restore_ctx(struct device *dev) { @@ -186,36 +203,18 @@ static void omap2_iommu_disable(struct omap_iommu *obj) static int iommu_enable(struct omap_iommu *obj) { - int err; - struct platform_device *pdev = to_platform_device(obj->dev); - struct iommu_platform_data *pdata = dev_get_platdata(&pdev->dev); - - if (pdata && pdata->deassert_reset) { - err = pdata->deassert_reset(pdev, pdata->reset_name); - if (err) { - dev_err(obj->dev, "deassert_reset failed: %d\n", err); - return err; - } - } - - pm_runtime_get_sync(obj->dev); + int ret; - err = omap2_iommu_enable(obj); + ret = pm_runtime_get_sync(obj->dev); + if (ret < 0) + pm_runtime_put_noidle(obj->dev); - return err; + return ret < 0 ? ret : 0; } static void iommu_disable(struct omap_iommu *obj) { - struct platform_device *pdev = to_platform_device(obj->dev); - struct iommu_platform_data *pdata = dev_get_platdata(&pdev->dev); - - omap2_iommu_disable(obj); - pm_runtime_put_sync(obj->dev); - - if (pdata && pdata->assert_reset) - pdata->assert_reset(pdev, pdata->reset_name); } /* @@ -901,15 +900,219 @@ static void omap_iommu_detach(struct omap_iommu *obj) dma_unmap_single(obj->dev, obj->pd_dma, IOPGD_TABLE_SIZE, DMA_TO_DEVICE); - iommu_disable(obj); obj->pd_dma = 0; obj->iopgd = NULL; + iommu_disable(obj); spin_unlock(&obj->iommu_lock); dev_dbg(obj->dev, "%s: %s\n", __func__, obj->name); } +static void omap_iommu_save_tlb_entries(struct omap_iommu *obj) +{ + struct iotlb_lock lock; + struct cr_regs cr; + struct cr_regs *tmp; + int i; + + /* check if there are any locked tlbs to save */ + iotlb_lock_get(obj, &lock); + obj->num_cr_ctx = lock.base; + if (!obj->num_cr_ctx) + return; + + tmp = obj->cr_ctx; + for_each_iotlb_cr(obj, obj->num_cr_ctx, i, cr) + * tmp++ = cr; +} + +static void omap_iommu_restore_tlb_entries(struct omap_iommu *obj) +{ + struct iotlb_lock l; + struct cr_regs *tmp; + int i; + + /* no locked tlbs to restore */ + if (!obj->num_cr_ctx) + return; + + l.base = 0; + tmp = obj->cr_ctx; + for (i = 0; i < obj->num_cr_ctx; i++, tmp++) { + l.vict = i; + iotlb_lock_set(obj, &l); + iotlb_load_cr(obj, tmp); + } + l.base = obj->num_cr_ctx; + l.vict = i; + iotlb_lock_set(obj, &l); +} + +/** + * omap_iommu_domain_deactivate - deactivate attached iommu devices + * @domain: iommu domain attached to the target iommu device + * + * This API allows the client devices of IOMMU devices to suspend + * the IOMMUs they control at runtime, after they are idled and + * suspended all activity. System Suspend will leverage the PM + * driver late callbacks. + **/ +int omap_iommu_domain_deactivate(struct iommu_domain *domain) +{ + struct omap_iommu_domain *omap_domain = to_omap_domain(domain); + struct omap_iommu_device *iommu; + struct omap_iommu *oiommu; + int i; + + if (!omap_domain->dev) + return 0; + + iommu = omap_domain->iommus; + iommu += (omap_domain->num_iommus - 1); + for (i = 0; i < omap_domain->num_iommus; i++, iommu--) { + oiommu = iommu->iommu_dev; + pm_runtime_put_sync(oiommu->dev); + } + + return 0; +} +EXPORT_SYMBOL_GPL(omap_iommu_domain_deactivate); + +/** + * omap_iommu_domain_activate - activate attached iommu devices + * @domain: iommu domain attached to the target iommu device + * + * This API allows the client devices of IOMMU devices to resume the + * IOMMUs they control at runtime, before they can resume operations. + * System Resume will leverage the PM driver late callbacks. + **/ +int omap_iommu_domain_activate(struct iommu_domain *domain) +{ + struct omap_iommu_domain *omap_domain = to_omap_domain(domain); + struct omap_iommu_device *iommu; + struct omap_iommu *oiommu; + int i; + + if (!omap_domain->dev) + return 0; + + iommu = omap_domain->iommus; + for (i = 0; i < omap_domain->num_iommus; i++, iommu++) { + oiommu = iommu->iommu_dev; + pm_runtime_get_sync(oiommu->dev); + } + + return 0; +} +EXPORT_SYMBOL_GPL(omap_iommu_domain_activate); + +/** + * omap_iommu_runtime_suspend - disable an iommu device + * @dev: iommu device + * + * This function performs all that is necessary to disable an + * IOMMU device, either during final detachment from a client + * device, or during system/runtime suspend of the device. This + * includes programming all the appropriate IOMMU registers, and + * managing the associated omap_hwmod's state and the device's + * reset line. This function also saves the context of any + * locked TLBs if suspending. + **/ +static __maybe_unused int omap_iommu_runtime_suspend(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct iommu_platform_data *pdata = dev_get_platdata(dev); + struct omap_iommu *obj = to_iommu(dev); + int ret; + + /* save the TLBs only during suspend, and not for power down */ + if (obj->domain && obj->iopgd) + omap_iommu_save_tlb_entries(obj); + + omap2_iommu_disable(obj); + + if (pdata && pdata->device_idle) + pdata->device_idle(pdev); + + if (pdata && pdata->assert_reset) + pdata->assert_reset(pdev, pdata->reset_name); + + if (pdata && pdata->set_pwrdm_constraint) { + ret = pdata->set_pwrdm_constraint(pdev, false, &obj->pwrst); + if (ret) { + dev_warn(obj->dev, "pwrdm_constraint failed to be reset, status = %d\n", + ret); + } + } + + return 0; +} + +/** + * omap_iommu_runtime_resume - enable an iommu device + * @dev: iommu device + * + * This function performs all that is necessary to enable an + * IOMMU device, either during initial attachment to a client + * device, or during system/runtime resume of the device. This + * includes programming all the appropriate IOMMU registers, and + * managing the associated omap_hwmod's state and the device's + * reset line. The function also restores any locked TLBs if + * resuming after a suspend. + **/ +static __maybe_unused int omap_iommu_runtime_resume(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct iommu_platform_data *pdata = dev_get_platdata(dev); + struct omap_iommu *obj = to_iommu(dev); + int ret = 0; + + if (pdata && pdata->set_pwrdm_constraint) { + ret = pdata->set_pwrdm_constraint(pdev, true, &obj->pwrst); + if (ret) { + dev_warn(obj->dev, "pwrdm_constraint failed to be set, status = %d\n", + ret); + } + } + + if (pdata && pdata->deassert_reset) { + ret = pdata->deassert_reset(pdev, pdata->reset_name); + if (ret) { + dev_err(dev, "deassert_reset failed: %d\n", ret); + return ret; + } + } + + if (pdata && pdata->device_enable) + pdata->device_enable(pdev); + + /* restore the TLBs only during resume, and not for power up */ + if (obj->domain) + omap_iommu_restore_tlb_entries(obj); + + ret = omap2_iommu_enable(obj); + + return ret; +} + +/** + * omap_iommu_suspend_prepare - prepare() dev_pm_ops implementation + * @dev: iommu device + * + * This function performs the necessary checks to determine if the IOMMU + * device needs suspending or not. The function checks if the runtime_pm + * status of the device is suspended, and returns 1 in that case. This + * results in the PM core to skip invoking any of the Sleep PM callbacks + * (suspend, suspend_late, resume, resume_early etc). + */ +static int omap_iommu_prepare(struct device *dev) +{ + if (pm_runtime_status_suspended(dev)) + return 1; + return 0; +} + static bool omap_iommu_can_register(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; @@ -974,6 +1177,7 @@ static int omap_iommu_probe(struct platform_device *pdev) struct omap_iommu *obj; struct resource *res; struct device_node *of = pdev->dev.of_node; + struct orphan_dev *orphan_dev, *tmp; if (!of) { pr_err("%s: only DT-based devices are supported\n", __func__); @@ -984,6 +1188,15 @@ static int omap_iommu_probe(struct platform_device *pdev) if (!obj) return -ENOMEM; + /* + * self-manage the ordering dependencies between omap_device_enable/idle + * and omap_device_assert/deassert_hardreset API + */ + if (pdev->dev.pm_domain) { + dev_dbg(&pdev->dev, "device pm_domain is being reset\n"); + pdev->dev.pm_domain = NULL; + } + obj->name = dev_name(&pdev->dev); obj->nr_tlb_entries = 32; err = of_property_read_u32(of, "ti,#tlb-entries", &obj->nr_tlb_entries); @@ -996,6 +1209,11 @@ static int omap_iommu_probe(struct platform_device *pdev) obj->dev = &pdev->dev; obj->ctx = (void *)obj + sizeof(*obj); + obj->cr_ctx = devm_kzalloc(&pdev->dev, + sizeof(*obj->cr_ctx) * obj->nr_tlb_entries, + GFP_KERNEL); + if (!obj->cr_ctx) + return -ENOMEM; spin_lock_init(&obj->iommu_lock); spin_lock_init(&obj->page_table_lock); @@ -1036,13 +1254,20 @@ static int omap_iommu_probe(struct platform_device *pdev) goto out_sysfs; } - pm_runtime_irq_safe(obj->dev); pm_runtime_enable(obj->dev); omap_iommu_debugfs_add(obj); dev_info(&pdev->dev, "%s registered\n", obj->name); + list_for_each_entry_safe(orphan_dev, tmp, &orphan_dev_list, node) { + err = _omap_iommu_add_device(orphan_dev->dev); + if (!err) { + list_del(&orphan_dev->node); + kfree(orphan_dev); + } + } + return 0; out_sysfs: @@ -1072,6 +1297,14 @@ static int omap_iommu_remove(struct platform_device *pdev) return 0; } +static const struct dev_pm_ops omap_iommu_pm_ops = { + .prepare = omap_iommu_prepare, + SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) + SET_RUNTIME_PM_OPS(omap_iommu_runtime_suspend, + omap_iommu_runtime_resume, NULL) +}; + static const struct of_device_id omap_iommu_of_match[] = { { .compatible = "ti,omap2-iommu" }, { .compatible = "ti,omap4-iommu" }, @@ -1085,6 +1318,7 @@ static struct platform_driver omap_iommu_driver = { .remove = omap_iommu_remove, .driver = { .name = "omap-iommu", + .pm = &omap_iommu_pm_ops, .of_match_table = of_match_ptr(omap_iommu_of_match), }, }; @@ -1423,7 +1657,7 @@ static phys_addr_t omap_iommu_iova_to_phys(struct iommu_domain *domain, return ret; } -static int omap_iommu_add_device(struct device *dev) +static int _omap_iommu_add_device(struct device *dev) { struct omap_iommu_arch_data *arch_data, *tmp; struct omap_iommu *oiommu; @@ -1432,6 +1666,8 @@ static int omap_iommu_add_device(struct device *dev) struct platform_device *pdev; int num_iommus, i; int ret; + struct orphan_dev *orphan_dev; + unsigned long flags; /* * Allocate the archdata iommu structure for DT-based devices. @@ -1463,10 +1699,26 @@ static int omap_iommu_add_device(struct device *dev) } pdev = of_find_device_by_node(np); - if (WARN_ON(!pdev)) { + if (!pdev) { of_node_put(np); kfree(arch_data); - return -EINVAL; + spin_lock_irqsave(&orphan_lock, flags); + list_for_each_entry(orphan_dev, &orphan_dev_list, + node) { + if (orphan_dev->dev == dev) + break; + } + spin_unlock_irqrestore(&orphan_lock, flags); + + if (orphan_dev && orphan_dev->dev == dev) + return -EPROBE_DEFER; + + orphan_dev = kzalloc(sizeof(*orphan_dev), GFP_KERNEL); + orphan_dev->dev = dev; + spin_lock_irqsave(&orphan_lock, flags); + list_add(&orphan_dev->node, &orphan_dev_list); + spin_unlock_irqrestore(&orphan_lock, flags); + return -EPROBE_DEFER; } oiommu = platform_get_drvdata(pdev); @@ -1477,6 +1729,7 @@ static int omap_iommu_add_device(struct device *dev) } tmp->iommu_dev = oiommu; + tmp->dev = &pdev->dev; of_node_put(np); } @@ -1511,6 +1764,17 @@ static int omap_iommu_add_device(struct device *dev) return 0; } +static int omap_iommu_add_device(struct device *dev) +{ + int ret; + + ret = _omap_iommu_add_device(dev); + if (ret == -EPROBE_DEFER) + return 0; + + return ret; +} + static void omap_iommu_remove_device(struct device *dev) { struct omap_iommu_arch_data *arch_data = dev->archdata.iommu; @@ -1554,7 +1818,7 @@ static const struct iommu_ops omap_iommu_ops = { static int __init omap_iommu_init(void) { struct kmem_cache *p; - const unsigned long flags = SLAB_HWCACHE_ALIGN; + const slab_flags_t flags = SLAB_HWCACHE_ALIGN; size_t align = 1 << 10; /* L2 pagetable alignement */ struct device_node *np; int ret; diff --git a/drivers/iommu/omap-iommu.h b/drivers/iommu/omap-iommu.h index 09968a02d291..18ee713ede78 100644 --- a/drivers/iommu/omap-iommu.h +++ b/drivers/iommu/omap-iommu.h @@ -73,16 +73,22 @@ struct omap_iommu { void *ctx; /* iommu context: registres saved area */ + struct cr_regs *cr_ctx; + u32 num_cr_ctx; + int has_bus_err_back; u32 id; struct iommu_device iommu; struct iommu_group *group; + + u8 pwrst; }; /** * struct omap_iommu_arch_data - omap iommu private data - * @iommu_dev: handle of the iommu device + * @iommu_dev: handle of the OMAP iommu device + * @dev: handle of the iommu device * * This is an omap iommu private data object, which binds an iommu user * to its iommu device. This object should be placed at the iommu user's @@ -91,6 +97,7 @@ struct omap_iommu { */ struct omap_iommu_arch_data { struct omap_iommu *iommu_dev; + struct device *dev; }; struct cr_regs { diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index fd33cf5981d7..c31e7bc4ccbe 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -725,10 +725,8 @@ static int qcom_iommu_ctx_probe(struct platform_device *pdev) return PTR_ERR(ctx->base); irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(dev, "failed to get irq\n"); + if (irq < 0) return -ENODEV; - } /* clear IRQs before registering fault handler, just in case the * boot-loader left us a surprise: @@ -804,7 +802,7 @@ static int qcom_iommu_device_probe(struct platform_device *pdev) struct qcom_iommu_dev *qcom_iommu; struct device *dev = &pdev->dev; struct resource *res; - int ret, sz, max_asid = 0; + int ret, max_asid = 0; /* find the max asid (which is 1:1 to ctx bank idx), so we know how * many child ctx devices we have: @@ -812,9 +810,8 @@ static int qcom_iommu_device_probe(struct platform_device *pdev) for_each_child_of_node(dev->of_node, child) max_asid = max(max_asid, get_asid(child)); - sz = sizeof(*qcom_iommu) + (max_asid * sizeof(qcom_iommu->ctxs[0])); - - qcom_iommu = devm_kzalloc(dev, sz, GFP_KERNEL); + qcom_iommu = devm_kzalloc(dev, struct_size(qcom_iommu, ctxs, max_asid), + GFP_KERNEL); if (!qcom_iommu) return -ENOMEM; qcom_iommu->num_ctxs = max_asid; |