[PATCH v2 0/3] iommu/vt-d: Misc fixes on scalable mode

[PATCH v2 0/3] iommu/vt-d: Misc fixes on scalable mode

[Liu Yi L]

This patchset aims to fix a bug regards to native SVM usage, and
also several bugs around subdevice (attached to device via auxiliary
manner) tracking and ineffective device_tlb flush.

Liu Yi L (3):
  iommu/vt-d: Move intel_iommu info from struct intel_svm to struct
    intel_svm_dev
  iommu/vt-d: Track device aux-attach with subdevice_domain_info
  iommu/vt-d: Fix ineffective devTLB invalidation for subdevices

 drivers/iommu/intel/iommu.c | 158 +++++++++++++++++++++++++++---------
 drivers/iommu/intel/svm.c   |   9 +-
 include/linux/intel-iommu.h |  18 ++--
 3 files changed, 135 insertions(+), 50 deletions(-)

-- 
2.25.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH v2 1/3] iommu/vt-d: Move intel_iommu info from struct intel_svm to struct intel_svm_dev

[Liu Yi L]

Current struct intel_svm has a field to record the struct intel_iommu
pointer for a PASID bind. And struct intel_svm will be shared by all
the devices bind to the same process. The devices may be behind different
DMAR units. As the iommu driver code uses the intel_iommu pointer stored
in intel_svm struct to do cache invalidations, it may only flush the cache
on a single DMAR unit, for others, the cache invalidation is missed.

As intel_svm struct already has a device list, this patch just moves the
intel_iommu pointer to be a field of intel_svm_dev struct.

Fixes: 1c4f88b7f1f92 ("iommu/vt-d: Shared virtual address in scalable mode")
Cc: Lu Baolu <baolu.lu@linux.intel.com>
Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Raj Ashok <ashok.raj@intel.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Reported-by: Guo Kaijie <Kaijie.Guo@intel.com>
Reported-by: Xin Zeng <xin.zeng@intel.com>
Signed-off-by: Guo Kaijie <Kaijie.Guo@intel.com>
Signed-off-by: Xin Zeng <xin.zeng@intel.com>
Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
Tested-by: Guo Kaijie <Kaijie.Guo@intel.com>
---
 drivers/iommu/intel/svm.c   | 9 +++++----
 include/linux/intel-iommu.h | 2 +-
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 3242ebd0bca3..4a10c9ff368c 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -142,7 +142,7 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d
 	}
 	desc.qw2 = 0;
 	desc.qw3 = 0;
-	qi_submit_sync(svm->iommu, &desc, 1, 0);
+	qi_submit_sync(sdev->iommu, &desc, 1, 0);
 
 	if (sdev->dev_iotlb) {
 		desc.qw0 = QI_DEV_EIOTLB_PASID(svm->pasid) |
@@ -166,7 +166,7 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d
 		}
 		desc.qw2 = 0;
 		desc.qw3 = 0;
-		qi_submit_sync(svm->iommu, &desc, 1, 0);
+		qi_submit_sync(sdev->iommu, &desc, 1, 0);
 	}
 }
 
@@ -211,7 +211,7 @@ 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,
+		intel_pasid_tear_down_entry(sdev->iommu, sdev->dev,
 					    svm->pasid, true);
 	rcu_read_unlock();
 
@@ -363,6 +363,7 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 	}
 	sdev->dev = dev;
 	sdev->sid = PCI_DEVID(info->bus, info->devfn);
+	sdev->iommu = iommu;
 
 	/* Only count users if device has aux domains */
 	if (iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX))
@@ -546,6 +547,7 @@ intel_svm_bind_mm(struct device *dev, unsigned int flags,
 		goto out;
 	}
 	sdev->dev = dev;
+	sdev->iommu = iommu;
 
 	ret = intel_iommu_enable_pasid(iommu, dev);
 	if (ret) {
@@ -575,7 +577,6 @@ intel_svm_bind_mm(struct device *dev, unsigned int flags,
 			kfree(sdev);
 			goto out;
 		}
-		svm->iommu = iommu;
 
 		if (pasid_max > intel_pasid_max_id)
 			pasid_max = intel_pasid_max_id;
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index d956987ed032..94522685a0d9 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -758,6 +758,7 @@ struct intel_svm_dev {
 	struct list_head list;
 	struct rcu_head rcu;
 	struct device *dev;
+	struct intel_iommu *iommu;
 	struct svm_dev_ops *ops;
 	struct iommu_sva sva;
 	u32 pasid;
@@ -771,7 +772,6 @@ struct intel_svm {
 	struct mmu_notifier notifier;
 	struct mm_struct *mm;
 
-	struct intel_iommu *iommu;
 	unsigned int flags;
 	u32 pasid;
 	int gpasid; /* In case that guest PASID is different from host PASID */
-- 
2.25.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH v2 2/3] iommu/vt-d: Track device aux-attach with subdevice_domain_info

[Liu Yi L]

In the existing code, loop all devices attached to a domain does not
include sub-devices attached via iommu_aux_attach_device().

This was found by when I'm working on the belwo patch, There is no
device in the domain->devices list, thus unable to get the cap and
ecap of iommu unit. But this domain actually has subdevice which is
attached via aux-manner. But it is tracked by domain. This patch is
going to fix it.

https://lore.kernel.org/kvm/1599734733-6431-17-git-send-email-yi.l.liu@intel.com/

And this fix goes beyond the patch above, such sub-device tracking is
necessary for other cases. For example, flushing device_iotlb for a
domain which has sub-devices attached by auxiliary manner.

Co-developed-by: Xin Zeng <xin.zeng@intel.com>
Signed-off-by: Xin Zeng <xin.zeng@intel.com>
Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
---
 drivers/iommu/intel/iommu.c | 95 +++++++++++++++++++++++++++----------
 include/linux/intel-iommu.h | 16 +++++--
 2 files changed, 82 insertions(+), 29 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index a49afa11673c..acfe0a5b955e 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1881,6 +1881,7 @@ static struct dmar_domain *alloc_domain(int flags)
 		domain->flags |= DOMAIN_FLAG_USE_FIRST_LEVEL;
 	domain->has_iotlb_device = false;
 	INIT_LIST_HEAD(&domain->devices);
+	INIT_LIST_HEAD(&domain->subdevices);
 
 	return domain;
 }
@@ -2632,7 +2633,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 	info->iommu = iommu;
 	info->pasid_table = NULL;
 	info->auxd_enabled = 0;
-	INIT_LIST_HEAD(&info->auxiliary_domains);
+	INIT_LIST_HEAD(&info->subdevices);
 
 	if (dev && dev_is_pci(dev)) {
 		struct pci_dev *pdev = to_pci_dev(info->dev);
@@ -5172,33 +5173,61 @@ is_aux_domain(struct device *dev, struct iommu_domain *domain)
 			domain->type == IOMMU_DOMAIN_UNMANAGED;
 }
 
-static void auxiliary_link_device(struct dmar_domain *domain,
-				  struct device *dev)
+static inline struct subdev_domain_info *
+lookup_subdev_info(struct dmar_domain *domain, struct device *dev)
+{
+	struct subdev_domain_info *sinfo;
+
+	if (!list_empty(&domain->subdevices)) {
+		list_for_each_entry(sinfo, &domain->subdevices, link_domain) {
+			if (sinfo->pdev == dev)
+				return sinfo;
+		}
+	}
+
+	return NULL;
+}
+
+static int auxiliary_link_device(struct dmar_domain *domain,
+				 struct device *dev)
 {
 	struct device_domain_info *info = get_domain_info(dev);
+	struct subdev_domain_info *sinfo = lookup_subdev_info(domain, dev);
 
 	assert_spin_locked(&device_domain_lock);
 	if (WARN_ON(!info))
-		return;
+		return -EINVAL;
+
+	if (!sinfo) {
+		sinfo = kzalloc(sizeof(*sinfo), GFP_ATOMIC);
+		sinfo->domain = domain;
+		sinfo->pdev = dev;
+		list_add(&sinfo->link_phys, &info->subdevices);
+		list_add(&sinfo->link_domain, &domain->subdevices);
+	}
 
-	domain->auxd_refcnt++;
-	list_add(&domain->auxd, &info->auxiliary_domains);
+	return ++sinfo->users;
 }
 
-static void auxiliary_unlink_device(struct dmar_domain *domain,
-				    struct device *dev)
+static int auxiliary_unlink_device(struct dmar_domain *domain,
+				   struct device *dev)
 {
 	struct device_domain_info *info = get_domain_info(dev);
+	struct subdev_domain_info *sinfo = lookup_subdev_info(domain, dev);
+	int ret;
 
 	assert_spin_locked(&device_domain_lock);
-	if (WARN_ON(!info))
-		return;
+	if (WARN_ON(!info || !sinfo || sinfo->users <= 0))
+		return -EINVAL;
 
-	list_del(&domain->auxd);
-	domain->auxd_refcnt--;
+	ret = --sinfo->users;
+	if (!ret) {
+		list_del(&sinfo->link_phys);
+		list_del(&sinfo->link_domain);
+		kfree(sinfo);
+	}
 
-	if (!domain->auxd_refcnt && domain->default_pasid > 0)
-		ioasid_free(domain->default_pasid);
+	return ret;
 }
 
 static int aux_domain_add_dev(struct dmar_domain *domain,
@@ -5227,6 +5256,19 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
 	}
 
 	spin_lock_irqsave(&device_domain_lock, flags);
+	ret = auxiliary_link_device(domain, dev);
+	if (ret <= 0)
+		goto link_failed;
+
+	/*
+	 * Subdevices from the same physical device can be attached to the
+	 * same domain. For such cases, only the first subdevice attachment
+	 * needs to go through the full steps in this function. So if ret >
+	 * 1, just goto out.
+	 */
+	if (ret > 1)
+		goto out;
+
 	/*
 	 * iommu->lock must be held to attach domain to iommu and setup the
 	 * pasid entry for second level translation.
@@ -5245,10 +5287,9 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
 						     domain->default_pasid);
 	if (ret)
 		goto table_failed;
-	spin_unlock(&iommu->lock);
-
-	auxiliary_link_device(domain, dev);
 
+	spin_unlock(&iommu->lock);
+out:
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 
 	return 0;
@@ -5257,8 +5298,10 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
 	domain_detach_iommu(domain, iommu);
 attach_failed:
 	spin_unlock(&iommu->lock);
+	auxiliary_unlink_device(domain, dev);
+link_failed:
 	spin_unlock_irqrestore(&device_domain_lock, flags);
-	if (!domain->auxd_refcnt && domain->default_pasid > 0)
+	if (list_empty(&domain->subdevices) && domain->default_pasid > 0)
 		ioasid_free(domain->default_pasid);
 
 	return ret;
@@ -5278,14 +5321,18 @@ static void aux_domain_remove_dev(struct dmar_domain *domain,
 	info = get_domain_info(dev);
 	iommu = info->iommu;
 
-	auxiliary_unlink_device(domain, dev);
-
-	spin_lock(&iommu->lock);
-	intel_pasid_tear_down_entry(iommu, dev, domain->default_pasid, false);
-	domain_detach_iommu(domain, iommu);
-	spin_unlock(&iommu->lock);
+	if (!auxiliary_unlink_device(domain, dev)) {
+		spin_lock(&iommu->lock);
+		intel_pasid_tear_down_entry(iommu, dev,
+					    domain->default_pasid, false);
+		domain_detach_iommu(domain, iommu);
+		spin_unlock(&iommu->lock);
+	}
 
 	spin_unlock_irqrestore(&device_domain_lock, flags);
+
+	if (list_empty(&domain->subdevices) && domain->default_pasid > 0)
+		ioasid_free(domain->default_pasid);
 }
 
 static int prepare_domain_attach_device(struct iommu_domain *domain,
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 94522685a0d9..09c6a0bf3892 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -533,11 +533,10 @@ struct dmar_domain {
 					/* Domain ids per IOMMU. Use u16 since
 					 * domain ids are 16 bit wide according
 					 * to VT-d spec, section 9.3 */
-	unsigned int	auxd_refcnt;	/* Refcount of auxiliary attaching */
 
 	bool has_iotlb_device;
 	struct list_head devices;	/* all devices' list */
-	struct list_head auxd;		/* link to device's auxiliary list */
+	struct list_head subdevices;	/* all subdevices' list */
 	struct iova_domain iovad;	/* iova's that belong to this domain */
 
 	struct dma_pte	*pgd;		/* virtual address */
@@ -610,14 +609,21 @@ struct intel_iommu {
 	struct dmar_drhd_unit *drhd;
 };
 
+/* Per subdevice private data */
+struct subdev_domain_info {
+	struct list_head link_phys;	/* link to phys device siblings */
+	struct list_head link_domain;	/* link to domain siblings */
+	struct device *pdev;		/* physical device derived from */
+	struct dmar_domain *domain;	/* aux-domain */
+	int users;			/* user count */
+};
+
 /* PCI domain-device relationship */
 struct device_domain_info {
 	struct list_head link;	/* link to domain siblings */
 	struct list_head global; /* link to global list */
 	struct list_head table;	/* link to pasid table */
-	struct list_head auxiliary_domains; /* auxiliary domains
-					     * attached to this device
-					     */
+	struct list_head subdevices; /* subdevices sibling */
 	u32 segment;		/* PCI segment number */
 	u8 bus;			/* PCI bus number */
 	u8 devfn;		/* PCI devfn number */
-- 
2.25.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH v2 3/3] iommu/vt-d: Fix ineffective devTLB invalidation for subdevices

[Liu Yi L]

iommu_flush_dev_iotlb() is called to invalidate caches on device. It only
loops the devices which are full-attached to the domain. For sub-devices,
this is ineffective. This results in invalid caching entries left on the
device. Fix it by adding loop for subdevices as well. Also, the domain->
has_iotlb_device needs to be updated when attaching to subdevices.

Fixes: 67b8e02b5e761 ("iommu/vt-d: Aux-domain specific domain attach/detach")
Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
---
 drivers/iommu/intel/iommu.c | 63 +++++++++++++++++++++++++++----------
 1 file changed, 47 insertions(+), 16 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index acfe0a5b955e..e97c5ac1d7fc 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -726,6 +726,8 @@ static int domain_update_device_node(struct dmar_domain *domain)
 	return nid;
 }
 
+static void domain_update_iotlb(struct dmar_domain *domain);
+
 /* Some capabilities may be different across iommus */
 static void domain_update_iommu_cap(struct dmar_domain *domain)
 {
@@ -739,6 +741,8 @@ static void domain_update_iommu_cap(struct dmar_domain *domain)
 	 */
 	if (domain->nid == NUMA_NO_NODE)
 		domain->nid = domain_update_device_node(domain);
+
+	domain_update_iotlb(domain);
 }
 
 struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
@@ -1459,6 +1463,18 @@ iommu_support_dev_iotlb (struct dmar_domain *domain, struct intel_iommu *iommu,
 	return NULL;
 }
 
+static bool dev_iotlb_enabled(struct device_domain_info *info)
+{
+	struct pci_dev *pdev;
+
+	if (!info->dev || !dev_is_pci(info->dev))
+		return false;
+
+	pdev = to_pci_dev(info->dev);
+
+	return !!pdev->ats_enabled;
+}
+
 static void domain_update_iotlb(struct dmar_domain *domain)
 {
 	struct device_domain_info *info;
@@ -1466,17 +1482,20 @@ static void domain_update_iotlb(struct dmar_domain *domain)
 
 	assert_spin_locked(&device_domain_lock);
 
-	list_for_each_entry(info, &domain->devices, link) {
-		struct pci_dev *pdev;
-
-		if (!info->dev || !dev_is_pci(info->dev))
-			continue;
-
-		pdev = to_pci_dev(info->dev);
-		if (pdev->ats_enabled) {
+	list_for_each_entry(info, &domain->devices, link)
+		if (dev_iotlb_enabled(info)) {
 			has_iotlb_device = true;
 			break;
 		}
+
+	if (!has_iotlb_device) {
+		struct subdev_domain_info *sinfo;
+
+		list_for_each_entry(sinfo, &domain->subdevices, link_domain)
+			if (dev_iotlb_enabled(get_domain_info(sinfo->pdev))) {
+				has_iotlb_device = true;
+				break;
+			}
 	}
 
 	domain->has_iotlb_device = has_iotlb_device;
@@ -1557,25 +1576,37 @@ static void iommu_disable_dev_iotlb(struct device_domain_info *info)
 #endif
 }
 
+static void __iommu_flush_dev_iotlb(struct device_domain_info *info,
+				    u64 addr, unsigned int mask)
+{
+	u16 sid, qdep;
+
+	if (!info || !info->ats_enabled)
+		return;
+
+	sid = info->bus << 8 | info->devfn;
+	qdep = info->ats_qdep;
+	qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
+			   qdep, addr, mask);
+}
+
 static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
 				  u64 addr, unsigned mask)
 {
-	u16 sid, qdep;
 	unsigned long flags;
 	struct device_domain_info *info;
+	struct subdev_domain_info *sinfo;
 
 	if (!domain->has_iotlb_device)
 		return;
 
 	spin_lock_irqsave(&device_domain_lock, flags);
-	list_for_each_entry(info, &domain->devices, link) {
-		if (!info->ats_enabled)
-			continue;
+	list_for_each_entry(info, &domain->devices, link)
+		__iommu_flush_dev_iotlb(info, addr, mask);
 
-		sid = info->bus << 8 | info->devfn;
-		qdep = info->ats_qdep;
-		qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
-				qdep, addr, mask);
+	list_for_each_entry(sinfo, &domain->subdevices, link_domain) {
+		__iommu_flush_dev_iotlb(get_domain_info(sinfo->pdev),
+					addr, mask);
 	}
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 }
-- 
2.25.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [PATCH v2 3/3] iommu/vt-d: Fix ineffective devTLB invalidation for subdevices

[Lu Baolu]

Hi Yi,

On 2020/12/23 14:27, Liu Yi L wrote:
> iommu_flush_dev_iotlb() is called to invalidate caches on device. It only
> loops the devices which are full-attached to the domain. For sub-devices,
> this is ineffective. This results in invalid caching entries left on the
> device. Fix it by adding loop for subdevices as well. Also, the domain->
> has_iotlb_device needs to be updated when attaching to subdevices.
> 
> Fixes: 67b8e02b5e761 ("iommu/vt-d: Aux-domain specific domain attach/detach")
> Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
> ---
>   drivers/iommu/intel/iommu.c | 63 +++++++++++++++++++++++++++----------
>   1 file changed, 47 insertions(+), 16 deletions(-)
> 
> diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
> index acfe0a5b955e..e97c5ac1d7fc 100644
> --- a/drivers/iommu/intel/iommu.c
> +++ b/drivers/iommu/intel/iommu.c
> @@ -726,6 +726,8 @@ static int domain_update_device_node(struct dmar_domain *domain)
>   	return nid;
>   }
>   
> +static void domain_update_iotlb(struct dmar_domain *domain);
> +
>   /* Some capabilities may be different across iommus */
>   static void domain_update_iommu_cap(struct dmar_domain *domain)
>   {
> @@ -739,6 +741,8 @@ static void domain_update_iommu_cap(struct dmar_domain *domain)
>   	 */
>   	if (domain->nid == NUMA_NO_NODE)
>   		domain->nid = domain_update_device_node(domain);
> +
> +	domain_update_iotlb(domain);
>   }
>   
>   struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
> @@ -1459,6 +1463,18 @@ iommu_support_dev_iotlb (struct dmar_domain *domain, struct intel_iommu *iommu,
>   	return NULL;
>   }
>   
> +static bool dev_iotlb_enabled(struct device_domain_info *info)
> +{
> +	struct pci_dev *pdev;
> +
> +	if (!info->dev || !dev_is_pci(info->dev))
> +		return false;
> +
> +	pdev = to_pci_dev(info->dev);
> +
> +	return !!pdev->ats_enabled;
> +}

I know this is just separated from below function. But isn't "(info &&
info->ats_enabled)" is enough?

> +
>   static void domain_update_iotlb(struct dmar_domain *domain)
>   {
>   	struct device_domain_info *info;
> @@ -1466,17 +1482,20 @@ static void domain_update_iotlb(struct dmar_domain *domain)
>   
>   	assert_spin_locked(&device_domain_lock);
>   
> -	list_for_each_entry(info, &domain->devices, link) {
> -		struct pci_dev *pdev;
> -
> -		if (!info->dev || !dev_is_pci(info->dev))
> -			continue;
> -
> -		pdev = to_pci_dev(info->dev);
> -		if (pdev->ats_enabled) {
> +	list_for_each_entry(info, &domain->devices, link)
> +		if (dev_iotlb_enabled(info)) {
>   			has_iotlb_device = true;
>   			break;
>   		}
> +
> +	if (!has_iotlb_device) {
> +		struct subdev_domain_info *sinfo;
> +
> +		list_for_each_entry(sinfo, &domain->subdevices, link_domain)
> +			if (dev_iotlb_enabled(get_domain_info(sinfo->pdev))) {

Please make the code easier for reading by:

			info = get_domain_info(sinfo->pdev);
			if (dev_iotlb_enabled(info))
				....

Best regards,
baolu

> +				has_iotlb_device = true;
> +				break;
> +			}
>   	}
>   
>   	domain->has_iotlb_device = has_iotlb_device;
> @@ -1557,25 +1576,37 @@ static void iommu_disable_dev_iotlb(struct device_domain_info *info)
>   #endif
>   }
>   
> +static void __iommu_flush_dev_iotlb(struct device_domain_info *info,
> +				    u64 addr, unsigned int mask)
> +{
> +	u16 sid, qdep;
> +
> +	if (!info || !info->ats_enabled)
> +		return;
> +
> +	sid = info->bus << 8 | info->devfn;
> +	qdep = info->ats_qdep;
> +	qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
> +			   qdep, addr, mask);
> +}
> +
>   static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
>   				  u64 addr, unsigned mask)
>   {
> -	u16 sid, qdep;
>   	unsigned long flags;
>   	struct device_domain_info *info;
> +	struct subdev_domain_info *sinfo;
>   
>   	if (!domain->has_iotlb_device)
>   		return;
>   
>   	spin_lock_irqsave(&device_domain_lock, flags);
> -	list_for_each_entry(info, &domain->devices, link) {
> -		if (!info->ats_enabled)
> -			continue;
> +	list_for_each_entry(info, &domain->devices, link)
> +		__iommu_flush_dev_iotlb(info, addr, mask);
>   
> -		sid = info->bus << 8 | info->devfn;
> -		qdep = info->ats_qdep;
> -		qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
> -				qdep, addr, mask);
> +	list_for_each_entry(sinfo, &domain->subdevices, link_domain) {
> +		__iommu_flush_dev_iotlb(get_domain_info(sinfo->pdev),
> +					addr, mask);
>   	}
>   	spin_unlock_irqrestore(&device_domain_lock, flags);
>   }
> 
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

RE: [PATCH v2 3/3] iommu/vt-d: Fix ineffective devTLB invalidation for subdevices

[Liu, Yi L]

Hi Baolu,

Well received, all comments accepted. thanks.

Regards,
Yi Liu

> From: Lu Baolu <baolu.lu@linux.intel.com>
> Sent: Wednesday, December 23, 2020 6:10 PM
> 
> Hi Yi,
> 
> On 2020/12/23 14:27, Liu Yi L wrote:
> > iommu_flush_dev_iotlb() is called to invalidate caches on device. It only
> > loops the devices which are full-attached to the domain. For sub-devices,
> > this is ineffective. This results in invalid caching entries left on the
> > device. Fix it by adding loop for subdevices as well. Also, the domain->
> > has_iotlb_device needs to be updated when attaching to subdevices.
> >
> > Fixes: 67b8e02b5e761 ("iommu/vt-d: Aux-domain specific domain
> attach/detach")
> > Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
> > ---
> >   drivers/iommu/intel/iommu.c | 63 +++++++++++++++++++++++++++---------
> -
> >   1 file changed, 47 insertions(+), 16 deletions(-)
> >
> > diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
> > index acfe0a5b955e..e97c5ac1d7fc 100644
> > --- a/drivers/iommu/intel/iommu.c
> > +++ b/drivers/iommu/intel/iommu.c
> > @@ -726,6 +726,8 @@ static int domain_update_device_node(struct
> dmar_domain *domain)
> >   	return nid;
> >   }
> >
> > +static void domain_update_iotlb(struct dmar_domain *domain);
> > +
> >   /* Some capabilities may be different across iommus */
> >   static void domain_update_iommu_cap(struct dmar_domain *domain)
> >   {
> > @@ -739,6 +741,8 @@ static void domain_update_iommu_cap(struct
> dmar_domain *domain)
> >   	 */
> >   	if (domain->nid == NUMA_NO_NODE)
> >   		domain->nid = domain_update_device_node(domain);
> > +
> > +	domain_update_iotlb(domain);
> >   }
> >
> >   struct context_entry *iommu_context_addr(struct intel_iommu *iommu,
> u8 bus,
> > @@ -1459,6 +1463,18 @@ iommu_support_dev_iotlb (struct dmar_domain
> *domain, struct intel_iommu *iommu,
> >   	return NULL;
> >   }
> >
> > +static bool dev_iotlb_enabled(struct device_domain_info *info)
> > +{
> > +	struct pci_dev *pdev;
> > +
> > +	if (!info->dev || !dev_is_pci(info->dev))
> > +		return false;
> > +
> > +	pdev = to_pci_dev(info->dev);
> > +
> > +	return !!pdev->ats_enabled;
> > +}
> 
> I know this is just separated from below function. But isn't "(info &&
> info->ats_enabled)" is enough?
> 
> > +
> >   static void domain_update_iotlb(struct dmar_domain *domain)
> >   {
> >   	struct device_domain_info *info;
> > @@ -1466,17 +1482,20 @@ static void domain_update_iotlb(struct
> dmar_domain *domain)
> >
> >   	assert_spin_locked(&device_domain_lock);
> >
> > -	list_for_each_entry(info, &domain->devices, link) {
> > -		struct pci_dev *pdev;
> > -
> > -		if (!info->dev || !dev_is_pci(info->dev))
> > -			continue;
> > -
> > -		pdev = to_pci_dev(info->dev);
> > -		if (pdev->ats_enabled) {
> > +	list_for_each_entry(info, &domain->devices, link)
> > +		if (dev_iotlb_enabled(info)) {
> >   			has_iotlb_device = true;
> >   			break;
> >   		}
> > +
> > +	if (!has_iotlb_device) {
> > +		struct subdev_domain_info *sinfo;
> > +
> > +		list_for_each_entry(sinfo, &domain->subdevices, link_domain)
> > +			if (dev_iotlb_enabled(get_domain_info(sinfo->pdev)))
> {
> 
> Please make the code easier for reading by:
> 
> 			info = get_domain_info(sinfo->pdev);
> 			if (dev_iotlb_enabled(info))
> 				....
> 
> Best regards,
> baolu
> 
> > +				has_iotlb_device = true;
> > +				break;
> > +			}
> >   	}
> >
> >   	domain->has_iotlb_device = has_iotlb_device;
> > @@ -1557,25 +1576,37 @@ static void iommu_disable_dev_iotlb(struct
> device_domain_info *info)
> >   #endif
> >   }
> >
> > +static void __iommu_flush_dev_iotlb(struct device_domain_info *info,
> > +				    u64 addr, unsigned int mask)
> > +{
> > +	u16 sid, qdep;
> > +
> > +	if (!info || !info->ats_enabled)
> > +		return;
> > +
> > +	sid = info->bus << 8 | info->devfn;
> > +	qdep = info->ats_qdep;
> > +	qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
> > +			   qdep, addr, mask);
> > +}
> > +
> >   static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
> >   				  u64 addr, unsigned mask)
> >   {
> > -	u16 sid, qdep;
> >   	unsigned long flags;
> >   	struct device_domain_info *info;
> > +	struct subdev_domain_info *sinfo;
> >
> >   	if (!domain->has_iotlb_device)
> >   		return;
> >
> >   	spin_lock_irqsave(&device_domain_lock, flags);
> > -	list_for_each_entry(info, &domain->devices, link) {
> > -		if (!info->ats_enabled)
> > -			continue;
> > +	list_for_each_entry(info, &domain->devices, link)
> > +		__iommu_flush_dev_iotlb(info, addr, mask);
> >
> > -		sid = info->bus << 8 | info->devfn;
> > -		qdep = info->ats_qdep;
> > -		qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
> > -				qdep, addr, mask);
> > +	list_for_each_entry(sinfo, &domain->subdevices, link_domain) {
> > +		__iommu_flush_dev_iotlb(get_domain_info(sinfo->pdev),
> > +					addr, mask);
> >   	}
> >   	spin_unlock_irqrestore(&device_domain_lock, flags);
> >   }
> >
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu