*/
#define DOMAIN_FLAG_LOSE_CHILDREN BIT(1)
+/*
+ * When VT-d works in the scalable mode, it allows DMA translation to
+ * happen through either first level or second level page table. This
+ * bit marks that the DMA translation for the domain goes through the
+ * first level page table, otherwise, it goes through the second level.
+ */
+#define DOMAIN_FLAG_USE_FIRST_LEVEL BIT(2)
+
+/*
+ * Domain represents a virtual machine which demands iommu nested
+ * translation mode support.
+ */
+#define DOMAIN_FLAG_NESTING_MODE BIT(3)
+
#define for_each_domain_iommu(idx, domain) \
for (idx = 0; idx < g_num_of_iommus; idx++) \
if (domain->iommu_refcnt[idx])
int dmar_disabled = 0;
#else
int dmar_disabled = 1;
-#endif /*CONFIG_INTEL_IOMMU_DEFAULT_ON*/
+#endif /* CONFIG_INTEL_IOMMU_DEFAULT_ON */
+#ifdef INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON
+int intel_iommu_sm = 1;
+#else
int intel_iommu_sm;
+#endif /* INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON */
+
int intel_iommu_enabled = 0;
EXPORT_SYMBOL_GPL(intel_iommu_enabled);
static int iommu_identity_mapping;
static int intel_no_bounce;
-#define IDENTMAP_ALL 1
#define IDENTMAP_GFX 2
#define IDENTMAP_AZALIA 4
#define DUMMY_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-1))
#define DEFER_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-2))
-static DEFINE_SPINLOCK(device_domain_lock);
+DEFINE_SPINLOCK(device_domain_lock);
static LIST_HEAD(device_domain_list);
#define device_needs_bounce(d) (!intel_no_bounce && dev_is_pci(d) && \
return domain->flags & DOMAIN_FLAG_STATIC_IDENTITY;
}
+static inline bool domain_use_first_level(struct dmar_domain *domain)
+{
+ return domain->flags & DOMAIN_FLAG_USE_FIRST_LEVEL;
+}
+
static inline int domain_pfn_supported(struct dmar_domain *domain,
unsigned long pfn)
{
return ret;
}
-static int domain_update_iommu_superpage(struct intel_iommu *skip)
+static int domain_update_iommu_superpage(struct dmar_domain *domain,
+ struct intel_iommu *skip)
{
struct dmar_drhd_unit *drhd;
struct intel_iommu *iommu;
- int mask = 0xf;
+ int mask = 0x3;
if (!intel_iommu_superpage) {
return 0;
rcu_read_lock();
for_each_active_iommu(iommu, drhd) {
if (iommu != skip) {
- mask &= cap_super_page_val(iommu->cap);
+ if (domain && domain_use_first_level(domain)) {
+ if (!cap_fl1gp_support(iommu->cap))
+ mask = 0x1;
+ } else {
+ mask &= cap_super_page_val(iommu->cap);
+ }
+
if (!mask)
break;
}
{
domain_update_iommu_coherency(domain);
domain->iommu_snooping = domain_update_iommu_snooping(NULL);
- domain->iommu_superpage = domain_update_iommu_superpage(NULL);
+ domain->iommu_superpage = domain_update_iommu_superpage(domain, NULL);
}
struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE);
pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE;
+ if (domain_use_first_level(domain))
+ pteval |= DMA_FL_PTE_XD;
if (cmpxchg64(&pte->val, 0ULL, pteval))
/* Someone else set it while we were thinking; use theirs. */
free_pgtable_page(tmp_page);
spin_unlock_irqrestore(&device_domain_lock, flags);
}
+static void domain_flush_piotlb(struct intel_iommu *iommu,
+ struct dmar_domain *domain,
+ u64 addr, unsigned long npages, bool ih)
+{
+ u16 did = domain->iommu_did[iommu->seq_id];
+
+ if (domain->default_pasid)
+ qi_flush_piotlb(iommu, did, domain->default_pasid,
+ addr, npages, ih);
+
+ if (!list_empty(&domain->devices))
+ qi_flush_piotlb(iommu, did, PASID_RID2PASID, addr, npages, ih);
+}
+
static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
struct dmar_domain *domain,
unsigned long pfn, unsigned int pages,
if (ih)
ih = 1 << 6;
- /*
- * Fallback to domain selective flush if no PSI support or the size is
- * too big.
- * PSI requires page size to be 2 ^ x, and the base address is naturally
- * aligned to the size
- */
- if (!cap_pgsel_inv(iommu->cap) || mask > cap_max_amask_val(iommu->cap))
- iommu->flush.flush_iotlb(iommu, did, 0, 0,
- DMA_TLB_DSI_FLUSH);
- else
- iommu->flush.flush_iotlb(iommu, did, addr | ih, mask,
- DMA_TLB_PSI_FLUSH);
+
+ if (domain_use_first_level(domain)) {
+ domain_flush_piotlb(iommu, domain, addr, pages, ih);
+ } else {
+ /*
+ * Fallback to domain selective flush if no PSI support or
+ * the size is too big. PSI requires page size to be 2 ^ x,
+ * and the base address is naturally aligned to the size.
+ */
+ if (!cap_pgsel_inv(iommu->cap) ||
+ mask > cap_max_amask_val(iommu->cap))
+ iommu->flush.flush_iotlb(iommu, did, 0, 0,
+ DMA_TLB_DSI_FLUSH);
+ else
+ iommu->flush.flush_iotlb(iommu, did, addr | ih, mask,
+ DMA_TLB_PSI_FLUSH);
+ }
/*
* In caching mode, changes of pages from non-present to present require
struct dmar_domain *domain,
unsigned long pfn, unsigned int pages)
{
- /* It's a non-present to present mapping. Only flush if caching mode */
- if (cap_caching_mode(iommu->cap))
+ /*
+ * It's a non-present to present mapping. Only flush if caching mode
+ * and second level.
+ */
+ if (cap_caching_mode(iommu->cap) && !domain_use_first_level(domain))
iommu_flush_iotlb_psi(iommu, domain, pfn, pages, 0, 1);
else
iommu_flush_write_buffer(iommu);
struct intel_iommu *iommu = g_iommus[idx];
u16 did = domain->iommu_did[iommu->seq_id];
- iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
+ if (domain_use_first_level(domain))
+ domain_flush_piotlb(iommu, domain, 0, -1, 0);
+ else
+ iommu->flush.flush_iotlb(iommu, did, 0, 0,
+ DMA_TLB_DSI_FLUSH);
if (!cap_caching_mode(iommu->cap))
iommu_flush_dev_iotlb(get_iommu_domain(iommu, did),
#endif
}
+/*
+ * Check and return whether first level is used by default for
+ * DMA translation.
+ */
+static bool first_level_by_default(void)
+{
+ struct dmar_drhd_unit *drhd;
+ struct intel_iommu *iommu;
+ static int first_level_support = -1;
+
+ if (likely(first_level_support != -1))
+ return first_level_support;
+
+ first_level_support = 1;
+
+ rcu_read_lock();
+ for_each_active_iommu(iommu, drhd) {
+ if (!sm_supported(iommu) || !ecap_flts(iommu->ecap)) {
+ first_level_support = 0;
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return first_level_support;
+}
+
static struct dmar_domain *alloc_domain(int flags)
{
struct dmar_domain *domain;
memset(domain, 0, sizeof(*domain));
domain->nid = NUMA_NO_NODE;
domain->flags = flags;
+ if (first_level_by_default())
+ domain->flags |= DOMAIN_FLAG_USE_FIRST_LEVEL;
domain->has_iotlb_device = false;
INIT_LIST_HEAD(&domain->devices);
{
int adjust_width, agaw;
unsigned long sagaw;
- int err;
+ int ret;
init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN);
- err = init_iova_flush_queue(&domain->iovad,
- iommu_flush_iova, iova_entry_free);
- if (err)
- return err;
+ if (!intel_iommu_strict) {
+ ret = init_iova_flush_queue(&domain->iovad,
+ iommu_flush_iova, iova_entry_free);
+ if (ret)
+ pr_info("iova flush queue initialization failed\n");
+ }
domain_reserve_special_ranges(domain);
unsigned long sg_res = 0;
unsigned int largepage_lvl = 0;
unsigned long lvl_pages = 0;
+ u64 attr;
BUG_ON(!domain_pfn_supported(domain, iov_pfn + nr_pages - 1));
if ((prot & (DMA_PTE_READ|DMA_PTE_WRITE)) == 0)
return -EINVAL;
- prot &= DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP;
+ attr = prot & (DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP);
+ if (domain_use_first_level(domain))
+ attr |= DMA_FL_PTE_PRESENT | DMA_FL_PTE_XD;
if (!sg) {
sg_res = nr_pages;
- pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot;
+ pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | attr;
}
while (nr_pages > 0) {
sg_res = aligned_nrpages(sg->offset, sg->length);
sg->dma_address = ((dma_addr_t)iov_pfn << VTD_PAGE_SHIFT) + pgoff;
sg->dma_length = sg->length;
- pteval = (sg_phys(sg) - pgoff) | prot;
+ pteval = (sg_phys(sg) - pgoff) | attr;
phys_pfn = pteval >> VTD_PAGE_SHIFT;
}
spin_unlock_irqrestore(&device_domain_lock, flags);
}
-static struct dmar_domain *find_domain(struct device *dev)
+struct dmar_domain *find_domain(struct device *dev)
{
struct device_domain_info *info;
return NULL;
}
+static int domain_setup_first_level(struct intel_iommu *iommu,
+ struct dmar_domain *domain,
+ struct device *dev,
+ int pasid)
+{
+ int flags = PASID_FLAG_SUPERVISOR_MODE;
+ struct dma_pte *pgd = domain->pgd;
+ int agaw, level;
+
+ /*
+ * Skip top levels of page tables for iommu which has
+ * less agaw than default. Unnecessary for PT mode.
+ */
+ for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
+ pgd = phys_to_virt(dma_pte_addr(pgd));
+ if (!dma_pte_present(pgd))
+ return -ENOMEM;
+ }
+
+ level = agaw_to_level(agaw);
+ if (level != 4 && level != 5)
+ return -EINVAL;
+
+ flags |= (level == 5) ? PASID_FLAG_FL5LP : 0;
+
+ return intel_pasid_setup_first_level(iommu, dev, (pgd_t *)pgd, pasid,
+ domain->iommu_did[iommu->seq_id],
+ flags);
+}
+
static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
int bus, int devfn,
struct device *dev,
if (hw_pass_through && domain_type_is_si(domain))
ret = intel_pasid_setup_pass_through(iommu, domain,
dev, PASID_RID2PASID);
+ else if (domain_use_first_level(domain))
+ ret = domain_setup_first_level(iommu, domain, dev,
+ PASID_RID2PASID);
else
ret = intel_pasid_setup_second_level(iommu, domain,
dev, PASID_RID2PASID);
}
/*
- * Normally we use DMA domains for devices which have RMRRs. But we
- * loose this requirement for graphic and usb devices. Identity map
- * the RMRRs for graphic and USB devices so that they could use the
- * si_domain.
+ * Identity map the RMRRs so that devices with RMRRs could also use
+ * the si_domain.
*/
for_each_rmrr_units(rmrr) {
for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt,
unsigned long long start = rmrr->base_address;
unsigned long long end = rmrr->end_address;
- if (device_is_rmrr_locked(dev))
- continue;
-
if (WARN_ON(end < start ||
end >> agaw_to_width(si_domain->agaw)))
continue;
if (dev_is_pci(dev)) {
struct pci_dev *pdev = to_pci_dev(dev);
- if (device_is_rmrr_locked(dev))
- return IOMMU_DOMAIN_DMA;
-
/*
* Prevent any device marked as untrusted from getting
* placed into the statically identity mapping domain.
return IOMMU_DOMAIN_DMA;
} else if (pci_pcie_type(pdev) == PCI_EXP_TYPE_PCI_BRIDGE)
return IOMMU_DOMAIN_DMA;
- } else {
- if (device_has_rmrr(dev))
- return IOMMU_DOMAIN_DMA;
}
- return (iommu_identity_mapping & IDENTMAP_ALL) ?
- IOMMU_DOMAIN_IDENTITY : 0;
+ return 0;
}
static void intel_iommu_init_qi(struct intel_iommu *iommu)
if (!ecap_pass_through(iommu->ecap))
hw_pass_through = 0;
-#ifdef CONFIG_INTEL_IOMMU_SVM
- if (pasid_supported(iommu))
- intel_svm_init(iommu);
-#endif
+ intel_svm_check(iommu);
}
/*
iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
}
- if (iommu_default_passthrough())
- iommu_identity_mapping |= IDENTMAP_ALL;
-
#ifdef CONFIG_INTEL_IOMMU_BROKEN_GFX_WA
dmar_map_gfx = 0;
#endif
{
unsigned long iova_pfn;
- /* Restrict dma_mask to the width that the iommu can handle */
- dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw), dma_mask);
+ /*
+ * Restrict dma_mask to the width that the iommu can handle.
+ * First-level translation restricts the input-address to a
+ * canonical address (i.e., address bits 63:N have the same
+ * value as address bit [N-1], where N is 48-bits with 4-level
+ * paging and 57-bits with 5-level paging). Hence, skip bit
+ * [N-1].
+ */
+ if (domain_use_first_level(domain))
+ dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw - 1),
+ dma_mask);
+ else
+ dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw),
+ dma_mask);
+
/* Ensure we reserve the whole size-aligned region */
nrpages = __roundup_pow_of_two(nrpages);
iova_pfn = alloc_iova_fast(&domain->iovad, nrpages,
IOVA_PFN(dma_mask), true);
if (unlikely(!iova_pfn)) {
- dev_err(dev, "Allocating %ld-page iova failed", nrpages);
+ dev_err_once(dev, "Allocating %ld-page iova failed\n",
+ nrpages);
return 0;
}
return 0;
}
- trace_map_sg(dev, iova_pfn << PAGE_SHIFT,
- sg_phys(sglist), size << VTD_PAGE_SHIFT);
+ for_each_sg(sglist, sg, nelems, i)
+ trace_map_sg(dev, i + 1, nelems, sg);
return nelems;
}
sg_dma_len(sg) = sg->length;
}
+ for_each_sg(sglist, sg, nelems, i)
+ trace_bounce_map_sg(dev, i + 1, nelems, sg);
+
return nelems;
out_unmap:
static inline void init_iommu_pm_ops(void) {}
#endif /* CONFIG_PM */
+static int rmrr_sanity_check(struct acpi_dmar_reserved_memory *rmrr)
+{
+ if (!IS_ALIGNED(rmrr->base_address, PAGE_SIZE) ||
+ !IS_ALIGNED(rmrr->end_address + 1, PAGE_SIZE) ||
+ rmrr->end_address <= rmrr->base_address ||
+ arch_rmrr_sanity_check(rmrr))
+ return -EINVAL;
+
+ return 0;
+}
+
int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg)
{
struct acpi_dmar_reserved_memory *rmrr;
struct dmar_rmrr_unit *rmrru;
- int ret;
rmrr = (struct acpi_dmar_reserved_memory *)header;
- ret = arch_rmrr_sanity_check(rmrr);
- if (ret)
- return ret;
+ if (rmrr_sanity_check(rmrr))
+ WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND,
+ "Your BIOS is broken; bad RMRR [%#018Lx-%#018Lx]\n"
+ "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+ rmrr->base_address, rmrr->end_address,
+ dmi_get_system_info(DMI_BIOS_VENDOR),
+ dmi_get_system_info(DMI_BIOS_VERSION),
+ dmi_get_system_info(DMI_PRODUCT_VERSION));
rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL);
if (!rmrru)
iommu->name);
return -ENXIO;
}
- sp = domain_update_iommu_superpage(iommu) - 1;
+ sp = domain_update_iommu_superpage(NULL, iommu) - 1;
if (sp >= 0 && !(cap_super_page_val(iommu->cap) & (1 << sp))) {
pr_warn("%s: Doesn't support large page.\n",
iommu->name);
if (ret)
goto out;
-#ifdef CONFIG_INTEL_IOMMU_SVM
- if (pasid_supported(iommu))
- intel_svm_init(iommu);
-#endif
+ intel_svm_check(iommu);
if (dmaru->ignored) {
/*
* map for all devices except those marked as being untrusted.
*/
if (dmar_disabled)
- iommu_identity_mapping |= IDENTMAP_ALL;
+ iommu_set_default_passthrough(false);
dmar_disabled = 0;
no_iommu = 0;
{
struct dmar_domain *dmar_domain;
struct iommu_domain *domain;
+ int ret;
switch (type) {
case IOMMU_DOMAIN_DMA:
return NULL;
}
- if (type == IOMMU_DOMAIN_DMA &&
- init_iova_flush_queue(&dmar_domain->iovad,
- iommu_flush_iova, iova_entry_free)) {
- pr_warn("iova flush queue initialization failed\n");
- intel_iommu_strict = 1;
+ if (!intel_iommu_strict && type == IOMMU_DOMAIN_DMA) {
+ ret = init_iova_flush_queue(&dmar_domain->iovad,
+ iommu_flush_iova,
+ iova_entry_free);
+ if (ret)
+ pr_info("iova flush queue initialization failed\n");
}
domain_update_iommu_cap(dmar_domain);
domain->auxd_refcnt--;
if (!domain->auxd_refcnt && domain->default_pasid > 0)
- intel_pasid_free_id(domain->default_pasid);
+ ioasid_free(domain->default_pasid);
}
static int aux_domain_add_dev(struct dmar_domain *domain,
if (domain->default_pasid <= 0) {
int pasid;
- pasid = intel_pasid_alloc_id(domain, PASID_MIN,
- pci_max_pasids(to_pci_dev(dev)),
- GFP_KERNEL);
- if (pasid <= 0) {
+ /* No private data needed for the default pasid */
+ pasid = ioasid_alloc(NULL, PASID_MIN,
+ pci_max_pasids(to_pci_dev(dev)) - 1,
+ NULL);
+ if (pasid == INVALID_IOASID) {
pr_err("Can't allocate default pasid\n");
return -ENODEV;
}
goto attach_failed;
/* Setup the PASID entry for mediated devices: */
- ret = intel_pasid_setup_second_level(iommu, domain, dev,
- domain->default_pasid);
+ if (domain_use_first_level(domain))
+ ret = domain_setup_first_level(iommu, domain, dev,
+ domain->default_pasid);
+ else
+ ret = intel_pasid_setup_second_level(iommu, domain, dev,
+ domain->default_pasid);
if (ret)
goto table_failed;
spin_unlock(&iommu->lock);
spin_unlock(&iommu->lock);
spin_unlock_irqrestore(&device_domain_lock, flags);
if (!domain->auxd_refcnt && domain->default_pasid > 0)
- intel_pasid_free_id(domain->default_pasid);
+ ioasid_free(domain->default_pasid);
return ret;
}
return ret;
}
+static inline bool nested_mode_support(void)
+{
+ struct dmar_drhd_unit *drhd;
+ struct intel_iommu *iommu;
+ bool ret = true;
+
+ rcu_read_lock();
+ for_each_active_iommu(iommu, drhd) {
+ if (!sm_supported(iommu) || !ecap_nest(iommu->ecap)) {
+ ret = false;
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return ret;
+}
+
static bool intel_iommu_capable(enum iommu_cap cap)
{
if (cap == IOMMU_CAP_CACHE_COHERENCY)
list_add_tail(®->list, head);
}
-static void intel_iommu_put_resv_regions(struct device *dev,
- struct list_head *head)
-{
- struct iommu_resv_region *entry, *next;
-
- list_for_each_entry_safe(entry, next, head, list)
- kfree(entry);
-}
-
int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev)
{
struct device_domain_info *info;
return dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO;
}
+static int
+intel_iommu_domain_set_attr(struct iommu_domain *domain,
+ enum iommu_attr attr, void *data)
+{
+ struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+ unsigned long flags;
+ int ret = 0;
+
+ if (domain->type != IOMMU_DOMAIN_UNMANAGED)
+ return -EINVAL;
+
+ switch (attr) {
+ case DOMAIN_ATTR_NESTING:
+ spin_lock_irqsave(&device_domain_lock, flags);
+ if (nested_mode_support() &&
+ list_empty(&dmar_domain->devices)) {
+ dmar_domain->flags |= DOMAIN_FLAG_NESTING_MODE;
+ dmar_domain->flags &= ~DOMAIN_FLAG_USE_FIRST_LEVEL;
+ } else {
+ ret = -ENODEV;
+ }
+ spin_unlock_irqrestore(&device_domain_lock, flags);
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
const struct iommu_ops intel_iommu_ops = {
.capable = intel_iommu_capable,
.domain_alloc = intel_iommu_domain_alloc,
.domain_free = intel_iommu_domain_free,
+ .domain_set_attr = intel_iommu_domain_set_attr,
.attach_dev = intel_iommu_attach_device,
.detach_dev = intel_iommu_detach_device,
.aux_attach_dev = intel_iommu_aux_attach_device,
.add_device = intel_iommu_add_device,
.remove_device = intel_iommu_remove_device,
.get_resv_regions = intel_iommu_get_resv_regions,
- .put_resv_regions = intel_iommu_put_resv_regions,
+ .put_resv_regions = generic_iommu_put_resv_regions,
.apply_resv_region = intel_iommu_apply_resv_region,
.device_group = intel_iommu_device_group,
.dev_has_feat = intel_iommu_dev_has_feat,
projects / linux-2.6-microblaze.git / blobdiff