[PATCH v4 0/3] iommu/vt-d: Misc fixes on scalable mode

[PATCH v4 0/3] iommu/vt-d: Misc fixes on scalable mode

[Liu Yi L]

Hi Baolu, Joerg, Will,

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

v3 -> v4:
- Address comments from Baolu Lu and add acked-by
- Fix issue reported by "Dan Carpenter" and "kernel test robot"
- Add tested-by from Guo Kaijie on patch 1/3
- Rebase to 5.11-rc2
v3: https://lore.kernel.org/linux-iommu/20201229032513.486395-1-yi.l.liu@intel.com/

v2 -> v3:
- Address comments from Baolu Lu against v2
- Rebased to 5.11-rc1
v2: https://lore.kernel.org/linux-iommu/20201223062720.29364-1-yi.l.liu@intel.com/

v1 -> v2:
- Use a more recent Fix tag in "iommu/vt-d: Move intel_iommu info from struct intel_svm to struct intel_svm_dev"
- Refined the "iommu/vt-d: Track device aux-attach with subdevice_domain_info"
- Rename "iommu/vt-d: A fix to iommu_flush_dev_iotlb() for aux-domain" to be
  "iommu/vt-d: Fix ineffective devTLB invalidation for subdevices"
- Refined the commit messages
v1: https://lore.kernel.org/linux-iommu/20201220000352.183523-1-yi.l.liu@intel.com/

Regards,
Yi Liu

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 | 148 ++++++++++++++++++++++++++++++++------------
 drivers/iommu/intel/svm.c   |   9 +--
 include/linux/intel-iommu.h |  18 ++++--
 3 files changed, 125 insertions(+), 50 deletions(-)

-- 
2.7.4

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

[PATCH v4 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>
Cc: stable@vger.kernel.org # v5.0+
Acked-by: Lu Baolu <baolu.lu@linux.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 4fa248b..6956669 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 d956987..9452268 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 */
-- 
2.7.4

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

[PATCH v4 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 below 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.

Fixes: 67b8e02b5e761 ("iommu/vt-d: Aux-domain specific domain attach/detach")
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>
Acked-by: Lu Baolu <baolu.lu@linux.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 788119c..d7720a8 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1877,6 +1877,7 @@ 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;
 }
@@ -2547,7 +2548,7 @@ 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);
@@ -4475,33 +4476,61 @@ 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_put(domain->default_pasid);
+	return ret;
 }
 
 static int aux_domain_add_dev(struct dmar_domain *domain,
@@ -4530,6 +4559,19 @@ 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.
@@ -4548,10 +4590,9 @@ 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;
@@ -4560,8 +4601,10 @@ 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_put(domain->default_pasid);
 
 	return ret;
@@ -4581,14 +4624,18 @@ 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_put(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 9452268..09c6a0b 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 */
-- 
2.7.4

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

Re: [PATCH v4 2/3] iommu/vt-d: Track device aux-attach with subdevice_domain_info

[Will Deacon]

On Thu, Jan 07, 2021 at 12:03:56AM +0800, Liu Yi L wrote:
> 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 below 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.

Sorry, but I'm having a really hard time understanding what this patch is
doing based on this commit message. Baolu -- do you think you could reword
it for me please? No need to resend the patch.

Thanks,

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

Re: [PATCH v4 2/3] iommu/vt-d: Track device aux-attach with subdevice_domain_info

[Lu Baolu]

Hi Will,

On 2021/1/7 21:49, Will Deacon wrote:
> On Thu, Jan 07, 2021 at 12:03:56AM +0800, Liu Yi L wrote:
>> 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 below 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.
> 
> Sorry, but I'm having a really hard time understanding what this patch is
> doing based on this commit message. Baolu -- do you think you could reword
> it for me please? No need to resend the patch.

iommu/vt-d: Fix general protection fault in aux_detach_device()

The aux-domain attach/detach are not tracked, some data structures might
be used after free. This causes general protection faults when multiple
subdevices are created and assigned to a same guest machine.

The symptoms of this look like:
[ 1548.992644] general protection fault, probably for non-canonical
address 0xdead000000000100: 0000 [#1] SMP NOPTI
[ 1549.078610] RIP: 0010:intel_iommu_aux_detach_device+0x12a/0x1f0
[ 1549.095668] Code: 25 88 01 49 8b 8c 24 a0 02 00 00 85 c0 0f 84 b3 00
                      00 00 48 85 c9 0f 84 ac 00 00 00 48 8b 8b 68 f8 ff
                      ff 48 8b 83 70 f8 ff ff <48> 89 41 08 48 89 08 48
                      b9 00 01 00 00 00 00 ad de 48 b8 22 01 00
[ 1549.142717] RSP: 0018:ffffa19eca067b88 EFLAGS: 00010082
[ 1549.157403] RAX: dead000000000122 RBX: ffff8910a1d0a0b8 RCX: 
dead000000000100
[ 1549.175075] RDX: ffff8910ba752b00 RSI: 0000000000000000 RDI: 
ffff8910daee7ea0
[ 1549.192746] RBP: ffffa19eca067bc0 R08: 0000000000000000 R09: 
0000000000000018
[ 1549.208495] R10: ffff8910d5eb03b0 R11: 0000000000000001 R12: 
ffff8910cf3900b8
[ 1549.223652] R13: ffff8910daeba600 R14: 0000000000000246 R15: 
ffff8910a1fe1e58
[ 1549.240158] FS:  00007fc4449cad80(0000) GS:ffff8910de800000(0000) 
knlGS:0000000000000000
[ 1549.257316] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1549.272424] CR2: 00005604b8b90000 CR3: 0000000859542004 CR4: 
0000000003762ee0
[ 1549.288201] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 
0000000000000000
[ 1549.302623] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 
0000000000000400
[ 1549.316768] PKRU: 55555554
[ 1549.327711] Call Trace:
[ 1549.337400]  iommu_aux_detach_device+0x24/0x70
[ 1549.348268]  vfio_mdev_detach_domain+0x3b/0x60
[ 1549.361050]  ? vfio_mdev_set_domain+0x50/0x50
[ 1549.372811]  iommu_group_for_each_dev+0x4f/0x80
[ 1549.386160]  vfio_iommu_detach_group.isra.0+0x22/0x30
[ 1549.398160]  vfio_iommu_type1_detach_group.cold+0x71/0x211
[ 1549.411491]  ? find_exported_symbol_in_section+0x4a/0xd0
[ 1549.423097]  ? each_symbol_section+0x28/0x50
[ 1549.435137]  __vfio_group_unset_container+0x4d/0x150
[ 1549.448735]  vfio_group_try_dissolve_container+0x25/0x30
[ 1549.461213]  vfio_group_put_external_user+0x13/0x20
[ 1549.474632]  kvm_vfio_group_put_external_user+0x27/0x40 [kvm]
[ 1549.488017]  kvm_vfio_destroy+0x45/0xb0 [kvm]
[ 1549.500137]  kvm_put_kvm+0x1bb/0x2e0 [kvm]
[ 1549.509965]  kvm_vm_release+0x22/0x30 [kvm]
[ 1549.520706]  __fput+0xcc/0x260
[ 1549.530202]  ____fput+0xe/0x10
[ 1549.539426]  task_work_run+0x8f/0xb0
[ 1549.549440]  do_exit+0x358/0xaf0
[ 1549.558165]  ? wake_up_state+0x10/0x20
[ 1549.568318]  ? signal_wake_up_state+0x1a/0x30
[ 1549.579739]  do_group_exit+0x47/0xb0
[ 1549.589337]  __x64_sys_exit_group+0x18/0x20
[ 1549.599069]  do_syscall_64+0x57/0x1d0
[ 1549.609082]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[ 1549.619044] RIP: 0033:0x7fc44e7e38a0
[ 1549.627488] Code: Bad RIP value.
[ 1549.635181] RSP: 002b:00007ffd23b6c038 EFLAGS: 00000246 ORIG_RAX: 
00000000000000e7
[ 1549.647761] RAX: ffffffffffffffda RBX: 00007fc44e8f2470 RCX: 
00007fc44e7e38a0
[ 1549.661439] RDX: 0000000000000000 RSI: 000000000000003c RDI: 
0000000000000000
[ 1549.673452] RBP: 00007fc44e8f2470 R08: 00000000000000e7 R09: 
ffffffffffffddb8
[ 1549.686293] R10: 0000000000000000 R11: 0000000000000246 R12: 
0000000000000000
[ 1549.699347] R13: 0000000000000000 R14: 0000000000000304 R15: 
0000000000000000

Fix it by tracking the subdevices when attaching and detaching aux-
domains.

Best regards,
baolu

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

Re: [PATCH v4 2/3] iommu/vt-d: Track device aux-attach with subdevice_domain_info

[Will Deacon]

On Thu, Jan 07, 2021 at 10:16:57PM +0800, Lu Baolu wrote:
> On 2021/1/7 21:49, Will Deacon wrote:
> > On Thu, Jan 07, 2021 at 12:03:56AM +0800, Liu Yi L wrote:
> > > 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 below 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.
> > 
> > Sorry, but I'm having a really hard time understanding what this patch is
> > doing based on this commit message. Baolu -- do you think you could reword
> > it for me please? No need to resend the patch.
> 
> iommu/vt-d: Fix general protection fault in aux_detach_device()

[...]

Thanks! I'll push this out shortly.

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

[PATCH v4 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>
Acked-by: Lu Baolu <baolu.lu@linux.intel.com>
---
 drivers/iommu/intel/iommu.c | 53 +++++++++++++++++++++++++++++++--------------
 1 file changed, 37 insertions(+), 16 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index d7720a8..65cf06d 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -719,6 +719,8 @@ 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)
 {
@@ -744,6 +746,8 @@ static void domain_update_iommu_cap(struct dmar_domain *domain)
 		domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw - 1);
 	else
 		domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw);
+
+	domain_update_iotlb(domain);
 }
 
 struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
@@ -1464,17 +1468,22 @@ 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 (info->ats_enabled) {
 			has_iotlb_device = true;
 			break;
 		}
+
+	if (!has_iotlb_device) {
+		struct subdev_domain_info *sinfo;
+
+		list_for_each_entry(sinfo, &domain->subdevices, link_domain) {
+			info = get_domain_info(sinfo->pdev);
+			if (info && info->ats_enabled) {
+				has_iotlb_device = true;
+				break;
+			}
+		}
 	}
 
 	domain->has_iotlb_device = has_iotlb_device;
@@ -1555,25 +1564,37 @@ 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) {
+		info = get_domain_info(sinfo->pdev);
+		__iommu_flush_dev_iotlb(info, addr, mask);
 	}
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 }
-- 
2.7.4

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