* [PATCH v2 0/3] iommu/vt-d: Misc fixes on scalable mode
@ 2020-12-23 6:27 ` Liu Yi L
0 siblings, 0 replies; 12+ messages in thread
From: Liu Yi L @ 2020-12-23 6:27 UTC (permalink / raw)
To: baolu.lu, joro, will, jacob.jun.pan
Cc: kevin.tian, ashok.raj, jun.j.tian, iommu, linux-kernel, yi.y.sun
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
^ permalink raw reply [flat|nested] 12+ messages in thread* [PATCH v2 1/3] iommu/vt-d: Move intel_iommu info from struct intel_svm to struct intel_svm_dev
2020-12-23 6:27 ` Liu Yi L
@ 2020-12-23 6:27 ` Liu Yi L
-1 siblings, 0 replies; 12+ messages in thread
From: Liu Yi L @ 2020-12-23 6:27 UTC (permalink / raw)
To: baolu.lu, joro, will, jacob.jun.pan
Cc: kevin.tian, ashok.raj, yi.l.liu, jun.j.tian, yi.y.sun, iommu,
linux-kernel, David Woodhouse, Guo Kaijie, Xin Zeng
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
^ permalink raw reply related [flat|nested] 12+ messages in thread* [PATCH v2 1/3] iommu/vt-d: Move intel_iommu info from struct intel_svm to struct intel_svm_dev
@ 2020-12-23 6:27 ` Liu Yi L
0 siblings, 0 replies; 12+ messages in thread
From: Liu Yi L @ 2020-12-23 6:27 UTC (permalink / raw)
To: baolu.lu, joro, will, jacob.jun.pan
Cc: kevin.tian, ashok.raj, jun.j.tian, iommu, linux-kernel, yi.y.sun,
Guo Kaijie, David Woodhouse
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
^ permalink raw reply related [flat|nested] 12+ messages in thread
* [PATCH v2 2/3] iommu/vt-d: Track device aux-attach with subdevice_domain_info
2020-12-23 6:27 ` Liu Yi L
@ 2020-12-23 6:27 ` Liu Yi L
-1 siblings, 0 replies; 12+ messages in thread
From: Liu Yi L @ 2020-12-23 6:27 UTC (permalink / raw)
To: baolu.lu, joro, will, jacob.jun.pan
Cc: kevin.tian, ashok.raj, yi.l.liu, jun.j.tian, yi.y.sun, iommu,
linux-kernel, Xin Zeng
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
^ permalink raw reply related [flat|nested] 12+ messages in thread* [PATCH v2 2/3] iommu/vt-d: Track device aux-attach with subdevice_domain_info
@ 2020-12-23 6:27 ` Liu Yi L
0 siblings, 0 replies; 12+ messages in thread
From: Liu Yi L @ 2020-12-23 6:27 UTC (permalink / raw)
To: baolu.lu, joro, will, jacob.jun.pan
Cc: kevin.tian, ashok.raj, jun.j.tian, iommu, linux-kernel, yi.y.sun
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
^ permalink raw reply related [flat|nested] 12+ messages in thread
* [PATCH v2 3/3] iommu/vt-d: Fix ineffective devTLB invalidation for subdevices
2020-12-23 6:27 ` Liu Yi L
@ 2020-12-23 6:27 ` Liu Yi L
-1 siblings, 0 replies; 12+ messages in thread
From: Liu Yi L @ 2020-12-23 6:27 UTC (permalink / raw)
To: baolu.lu, joro, will, jacob.jun.pan
Cc: kevin.tian, ashok.raj, yi.l.liu, jun.j.tian, yi.y.sun, iommu,
linux-kernel
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
^ permalink raw reply related [flat|nested] 12+ messages in thread* [PATCH v2 3/3] iommu/vt-d: Fix ineffective devTLB invalidation for subdevices
@ 2020-12-23 6:27 ` Liu Yi L
0 siblings, 0 replies; 12+ messages in thread
From: Liu Yi L @ 2020-12-23 6:27 UTC (permalink / raw)
To: baolu.lu, joro, will, jacob.jun.pan
Cc: kevin.tian, ashok.raj, jun.j.tian, iommu, linux-kernel, yi.y.sun
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
^ permalink raw reply related [flat|nested] 12+ messages in thread* Re: [PATCH v2 3/3] iommu/vt-d: Fix ineffective devTLB invalidation for subdevices
2020-12-23 6:27 ` Liu Yi L
@ 2020-12-23 10:09 ` Lu Baolu
-1 siblings, 0 replies; 12+ messages in thread
From: Lu Baolu @ 2020-12-23 10:09 UTC (permalink / raw)
To: Liu Yi L, joro, will, jacob.jun.pan
Cc: baolu.lu, kevin.tian, ashok.raj, jun.j.tian, yi.y.sun, iommu,
linux-kernel
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);
> }
>
^ permalink raw reply [flat|nested] 12+ messages in thread* Re: [PATCH v2 3/3] iommu/vt-d: Fix ineffective devTLB invalidation for subdevices
@ 2020-12-23 10:09 ` Lu Baolu
0 siblings, 0 replies; 12+ messages in thread
From: Lu Baolu @ 2020-12-23 10:09 UTC (permalink / raw)
To: Liu Yi L, joro, will, jacob.jun.pan
Cc: kevin.tian, ashok.raj, jun.j.tian, iommu, linux-kernel, yi.y.sun
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
^ permalink raw reply [flat|nested] 12+ messages in thread* RE: [PATCH v2 3/3] iommu/vt-d: Fix ineffective devTLB invalidation for subdevices
2020-12-23 10:09 ` Lu Baolu
@ 2020-12-25 8:23 ` Liu, Yi L
-1 siblings, 0 replies; 12+ messages in thread
From: Liu, Yi L @ 2020-12-25 8:23 UTC (permalink / raw)
To: Lu Baolu, joro, will, jacob.jun.pan
Cc: Tian, Kevin, Raj, Ashok, Tian, Jun J, Sun, Yi Y, iommu, linux-kernel
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);
> > }
> >
^ permalink raw reply [flat|nested] 12+ messages in thread* RE: [PATCH v2 3/3] iommu/vt-d: Fix ineffective devTLB invalidation for subdevices
@ 2020-12-25 8:23 ` Liu, Yi L
0 siblings, 0 replies; 12+ messages in thread
From: Liu, Yi L @ 2020-12-25 8:23 UTC (permalink / raw)
To: Lu Baolu, joro, will, jacob.jun.pan
Cc: Tian, Kevin, Raj, Ashok, Tian, Jun J, iommu, linux-kernel, Sun, Yi Y
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
^ permalink raw reply [flat|nested] 12+ messages in thread