From e65a6897be5e4939d477c4969a05e12d90b08409 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Thu, 1 Dec 2022 12:01:24 +0800 Subject: iommu/vt-d: Add a fix for devices need extra dtlb flush QAT devices on Intel Sapphire Rapids and Emerald Rapids have a defect in address translation service (ATS). These devices may inadvertently issue ATS invalidation completion before posted writes initiated with translated address that utilized translations matching the invalidation address range, violating the invalidation completion ordering. This patch adds an extra device TLB invalidation for the affected devices, it is needed to ensure no more posted writes with translated address following the invalidation completion. Therefore, the ordering is preserved and data-corruption is prevented. Device TLBs are invalidated under the following six conditions: 1. Device driver does DMA API unmap IOVA 2. Device driver unbind a PASID from a process, sva_unbind_device() 3. PASID is torn down, after PASID cache is flushed. e.g. process exit_mmap() due to crash 4. Under SVA usage, called by mmu_notifier.invalidate_range() where VM has to free pages that were unmapped 5. userspace driver unmaps a DMA buffer 6. Cache invalidation in vSVA usage (upcoming) For #1 and #2, device drivers are responsible for stopping DMA traffic before unmap/unbind. For #3, iommu driver gets mmu_notifier to invalidate TLB the same way as normal user unmap which will do an extra invalidation. The dTLB invalidation after PASID cache flush does not need an extra invalidation. Therefore, we only need to deal with #4 and #5 in this patch. #1 is also covered by this patch due to common code path with #5. Tested-by: Yuzhang Luo Reviewed-by: Ashok Raj Reviewed-by: Kevin Tian Signed-off-by: Jacob Pan Link: https://lore.kernel.org/r/20221130062449.1360063-1-jacob.jun.pan@linux.intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 69 +++++++++++++++++++++++++++++++++++++++++++-- drivers/iommu/intel/iommu.h | 4 +++ drivers/iommu/intel/svm.c | 5 +++- 3 files changed, 75 insertions(+), 3 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 996a8b5ee5ee..587eebe39820 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1396,6 +1396,24 @@ static void domain_update_iotlb(struct dmar_domain *domain) spin_unlock_irqrestore(&domain->lock, flags); } +/* + * The extra devTLB flush quirk impacts those QAT devices with PCI device + * IDs ranging from 0x4940 to 0x4943. It is exempted from risky_device() + * check because it applies only to the built-in QAT devices and it doesn't + * grant additional privileges. + */ +#define BUGGY_QAT_DEVID_MASK 0x494c +static bool dev_needs_extra_dtlb_flush(struct pci_dev *pdev) +{ + if (pdev->vendor != PCI_VENDOR_ID_INTEL) + return false; + + if ((pdev->device & 0xfffc) != BUGGY_QAT_DEVID_MASK) + return false; + + return true; +} + static void iommu_enable_pci_caps(struct device_domain_info *info) { struct pci_dev *pdev; @@ -1478,6 +1496,7 @@ static void __iommu_flush_dev_iotlb(struct device_domain_info *info, qdep = info->ats_qdep; qi_flush_dev_iotlb(info->iommu, sid, info->pfsid, qdep, addr, mask); + quirk_extra_dev_tlb_flush(info, addr, mask, PASID_RID2PASID, qdep); } static void iommu_flush_dev_iotlb(struct dmar_domain *domain, @@ -4490,9 +4509,10 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev) if (dev_is_pci(dev)) { if (ecap_dev_iotlb_support(iommu->ecap) && pci_ats_supported(pdev) && - dmar_ats_supported(pdev, iommu)) + dmar_ats_supported(pdev, iommu)) { info->ats_supported = 1; - + info->dtlb_extra_inval = dev_needs_extra_dtlb_flush(pdev); + } if (sm_supported(iommu)) { if (pasid_supported(iommu)) { int features = pci_pasid_features(pdev); @@ -4931,3 +4951,48 @@ static void __init check_tylersburg_isoch(void) pr_warn("Recommended TLB entries for ISOCH unit is 16; your BIOS set %d\n", vtisochctrl); } + +/* + * Here we deal with a device TLB defect where device may inadvertently issue ATS + * invalidation completion before posted writes initiated with translated address + * that utilized translations matching the invalidation address range, violating + * the invalidation completion ordering. + * Therefore, any use cases that cannot guarantee DMA is stopped before unmap is + * vulnerable to this defect. In other words, any dTLB invalidation initiated not + * under the control of the trusted/privileged host device driver must use this + * quirk. + * Device TLBs are invalidated under the following six conditions: + * 1. Device driver does DMA API unmap IOVA + * 2. Device driver unbind a PASID from a process, sva_unbind_device() + * 3. PASID is torn down, after PASID cache is flushed. e.g. process + * exit_mmap() due to crash + * 4. Under SVA usage, called by mmu_notifier.invalidate_range() where + * VM has to free pages that were unmapped + * 5. Userspace driver unmaps a DMA buffer + * 6. Cache invalidation in vSVA usage (upcoming) + * + * For #1 and #2, device drivers are responsible for stopping DMA traffic + * before unmap/unbind. For #3, iommu driver gets mmu_notifier to + * invalidate TLB the same way as normal user unmap which will use this quirk. + * The dTLB invalidation after PASID cache flush does not need this quirk. + * + * As a reminder, #6 will *NEED* this quirk as we enable nested translation. + */ +void quirk_extra_dev_tlb_flush(struct device_domain_info *info, + unsigned long address, unsigned long mask, + u32 pasid, u16 qdep) +{ + u16 sid; + + if (likely(!info->dtlb_extra_inval)) + return; + + sid = PCI_DEVID(info->bus, info->devfn); + if (pasid == PASID_RID2PASID) { + qi_flush_dev_iotlb(info->iommu, sid, info->pfsid, + qdep, address, mask); + } else { + qi_flush_dev_iotlb_pasid(info->iommu, sid, info->pfsid, + pasid, qdep, address, mask); + } +} diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index 92023dff9513..db9df7c3790c 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -623,6 +623,7 @@ struct device_domain_info { u8 pri_enabled:1; u8 ats_supported:1; u8 ats_enabled:1; + u8 dtlb_extra_inval:1; /* Quirk for devices need extra flush */ u8 ats_qdep; struct device *dev; /* it's NULL for PCIe-to-PCI bridge */ struct intel_iommu *iommu; /* IOMMU used by this device */ @@ -728,6 +729,9 @@ void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr, void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid, u32 pasid, u16 qdep, u64 addr, unsigned int size_order); +void quirk_extra_dev_tlb_flush(struct device_domain_info *info, + unsigned long address, unsigned long pages, + u32 pasid, u16 qdep); void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu, u32 pasid); diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 7d08eb034f2d..fe615c53479c 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -184,10 +184,13 @@ static void __flush_svm_range_dev(struct intel_svm *svm, return; qi_flush_piotlb(sdev->iommu, sdev->did, svm->pasid, address, pages, ih); - if (info->ats_enabled) + if (info->ats_enabled) { qi_flush_dev_iotlb_pasid(sdev->iommu, sdev->sid, info->pfsid, svm->pasid, sdev->qdep, address, order_base_2(pages)); + quirk_extra_dev_tlb_flush(info, address, order_base_2(pages), + svm->pasid, sdev->qdep); + } } static void intel_flush_svm_range_dev(struct intel_svm *svm, -- cgit v1.2.3 From 6927d352380797ddbee18631491ec428741696e2 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 1 Dec 2022 12:01:25 +0800 Subject: iommu/vt-d: Fix PCI device refcount leak in prq_event_thread() As comment of pci_get_domain_bus_and_slot() says, it returns a pci device with refcount increment, when finish using it, the caller must decrease the reference count by calling pci_dev_put(). So call pci_dev_put() after using the 'pdev' to avoid refcount leak. Besides, if the 'pdev' is null or intel_svm_prq_report() returns error, there is no need to trace this fault. Fixes: 06f4b8d09dba ("iommu/vt-d: Remove unnecessary SVA data accesses in page fault path") Suggested-by: Lu Baolu Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221119144028.2452731-1-yangyingliang@huawei.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/svm.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index fe615c53479c..03b25358946c 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -748,12 +748,16 @@ bad_req: * If prq is to be handled outside iommu driver via receiver of * the fault notifiers, we skip the page response here. */ - if (!pdev || intel_svm_prq_report(iommu, &pdev->dev, req)) - handle_bad_prq_event(iommu, req, QI_RESP_INVALID); + if (!pdev) + goto bad_req; - trace_prq_report(iommu, &pdev->dev, req->qw_0, req->qw_1, - req->priv_data[0], req->priv_data[1], - iommu->prq_seq_number++); + if (intel_svm_prq_report(iommu, &pdev->dev, req)) + handle_bad_prq_event(iommu, req, QI_RESP_INVALID); + else + trace_prq_report(iommu, &pdev->dev, req->qw_0, req->qw_1, + req->priv_data[0], req->priv_data[1], + iommu->prq_seq_number++); + pci_dev_put(pdev); prq_advance: head = (head + sizeof(*req)) & PRQ_RING_MASK; } -- cgit v1.2.3 From afca9e19cc720bfafc75dc5ce429c185ca93f31d Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Thu, 1 Dec 2022 12:01:26 +0800 Subject: iommu/vt-d: Fix PCI device refcount leak in has_external_pci() for_each_pci_dev() is implemented by pci_get_device(). The comment of pci_get_device() says that it will increase the reference count for the returned pci_dev and also decrease the reference count for the input pci_dev @from if it is not NULL. If we break for_each_pci_dev() loop with pdev not NULL, we need to call pci_dev_put() to decrease the reference count. Add the missing pci_dev_put() before 'return true' to avoid reference count leak. Fixes: 89a6079df791 ("iommu/vt-d: Force IOMMU on for platform opt in hint") Signed-off-by: Xiongfeng Wang Link: https://lore.kernel.org/r/20221121113649.190393-2-wangxiongfeng2@huawei.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/iommu') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 587eebe39820..5287efe247b1 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -3873,8 +3873,10 @@ static inline bool has_external_pci(void) struct pci_dev *pdev = NULL; for_each_pci_dev(pdev) - if (pdev->external_facing) + if (pdev->external_facing) { + pci_dev_put(pdev); return true; + } return false; } -- cgit v1.2.3 From 4bedbbd782ebbe7287231fea862c158d4f08a9e3 Mon Sep 17 00:00:00 2001 From: Xiongfeng Wang Date: Thu, 1 Dec 2022 12:01:27 +0800 Subject: iommu/vt-d: Fix PCI device refcount leak in dmar_dev_scope_init() for_each_pci_dev() is implemented by pci_get_device(). The comment of pci_get_device() says that it will increase the reference count for the returned pci_dev and also decrease the reference count for the input pci_dev @from if it is not NULL. If we break for_each_pci_dev() loop with pdev not NULL, we need to call pci_dev_put() to decrease the reference count. Add the missing pci_dev_put() for the error path to avoid reference count leak. Fixes: 2e4552893038 ("iommu/vt-d: Unify the way to process DMAR device scope array") Signed-off-by: Xiongfeng Wang Link: https://lore.kernel.org/r/20221121113649.190393-3-wangxiongfeng2@huawei.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/dmar.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/iommu') diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 5a8f780e7ffd..bc94059a5b87 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -820,6 +820,7 @@ int __init dmar_dev_scope_init(void) info = dmar_alloc_pci_notify_info(dev, BUS_NOTIFY_ADD_DEVICE); if (!info) { + pci_dev_put(dev); return dmar_dev_scope_status; } else { dmar_pci_bus_add_dev(info); -- cgit v1.2.3