iommu: Replace per-group resetting_domain with per-gdev blocked flag

The core tracks device resetting states with a per-group resetting_domain,
while a reset is actually per group-device. Such a mismatch might lead to
confusion and even difficulty to untangle per-gdev handling requirement.

Shuai found that cxl_reset_bus_function() calls pci_reset_bus_function()
internally while both are calling pci_dev_reset_iommu_prepare/done(). And
the solution requires the core to track at the group_device level as well.

Introduce a 'blocked' flag to struct group_device, to allow a multi-device
group to isolate concurrent device resets independently.

As the reset routine is per gdev, it cannot clear group->resetting_domain
without iterating over the device list to ensure no other device is being
reset. Simplify it by replacing the resetting_domain with a 'recovery_cnt'
in the struct iommu_group.

No functional change. But this is essential to apply following bug fixes.

Fixes: c279e83953d9 ("iommu: Introduce pci_dev_reset_iommu_prepare/done()")
Cc: stable@vger.kernel.org
Reported-by: Shuai Xue <xueshuai@linux.alibaba.com>
Closes: https://lore.kernel.org/all/absKsk7qQOwzhpzv@Asurada-Nvidia/
Reviewed-by: Shuai Xue <xueshuai@linux.alibaba.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>

1 files changed, 78 insertions, 24 deletions

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 66659e5d1ec2..2515786d4156 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -62,14 +62,14 @@ struct iommu_group {
 	int id;
 	struct iommu_domain *default_domain;
 	struct iommu_domain *blocking_domain;
-	/*
-	 * During a group device reset, @resetting_domain points to the physical
-	 * domain, while @domain points to the attached domain before the reset.
-	 */
-	struct iommu_domain *resetting_domain;
 	struct iommu_domain *domain;
 	struct list_head entry;
 	unsigned int owner_cnt;
+	/*
+	 * Number of devices in the group undergoing or awaiting recovery.
+	 * If non-zero, concurrent domain attachments are rejected.
+	 */
+	unsigned int recovery_cnt;
 	void *owner;
 };
 
@@ -77,12 +77,32 @@ struct group_device {
 	struct list_head list;
 	struct device *dev;
 	char *name;
+	/*
+	 * Device is blocked for a pending recovery while its group->domain is
+	 * retained. This can happen when:
+	 *  - Device is undergoing a reset
+	 */
+	bool blocked;
 };
 
 /* Iterate over each struct group_device in a struct iommu_group */
 #define for_each_group_device(group, pos) \
 	list_for_each_entry(pos, &(group)->devices, list)
 
+static struct group_device *__dev_to_gdev(struct device *dev)
+{
+	struct iommu_group *group = dev->iommu_group;
+	struct group_device *gdev;
+
+	lockdep_assert_held(&group->mutex);
+
+	for_each_group_device(group, gdev) {
+		if (gdev->dev == dev)
+			return gdev;
+	}
+	return NULL;
+}
+
 struct iommu_group_attribute {
 	struct attribute attr;
 	ssize_t (*show)(struct iommu_group *group, char *buf);
@@ -2196,6 +2216,8 @@ EXPORT_SYMBOL_GPL(iommu_attach_device);
 
 int iommu_deferred_attach(struct device *dev, struct iommu_domain *domain)
 {
+	struct group_device *gdev;
+
 	/*
 	 * This is called on the dma mapping fast path so avoid locking. This is
 	 * racy, but we have an expectation that the driver will setup its DMAs
@@ -2206,14 +2228,18 @@ int iommu_deferred_attach(struct device *dev, struct iommu_domain *domain)
 
 	guard(mutex)(&dev->iommu_group->mutex);
 
+	gdev = __dev_to_gdev(dev);
+	if (WARN_ON(!gdev))
+		return -ENODEV;
+
 	/*
-	 * This is a concurrent attach during a device reset. Reject it until
+	 * This is a concurrent attach during device recovery. Reject it until
 	 * pci_dev_reset_iommu_done() attaches the device to group->domain.
 	 *
 	 * Note that this might fail the iommu_dma_map(). But there's nothing
 	 * more we can do here.
 	 */
-	if (dev->iommu_group->resetting_domain)
+	if (gdev->blocked)
 		return -EBUSY;
 	return __iommu_attach_device(domain, dev, NULL);
 }
@@ -2270,19 +2296,24 @@ EXPORT_SYMBOL_GPL(iommu_get_domain_for_dev);
 struct iommu_domain *iommu_driver_get_domain_for_dev(struct device *dev)
 {
 	struct iommu_group *group = dev->iommu_group;
+	struct group_device *gdev;
 
 	lockdep_assert_held(&group->mutex);
 
+	gdev = __dev_to_gdev(dev);
+	if (WARN_ON(!gdev))
+		return NULL;
+
 	/*
 	 * Driver handles the low-level __iommu_attach_device(), including the
 	 * one invoked by pci_dev_reset_iommu_done() re-attaching the device to
 	 * the cached group->domain. In this case, the driver must get the old
-	 * domain from group->resetting_domain rather than group->domain. This
+	 * domain from group->blocking_domain rather than group->domain. This
 	 * prevents it from re-attaching the device from group->domain (old) to
 	 * group->domain (new).
 	 */
-	if (group->resetting_domain)
-		return group->resetting_domain;
+	if (gdev->blocked)
+		return group->blocking_domain;
 
 	return group->domain;
 }
@@ -2441,10 +2472,10 @@ static int __iommu_group_set_domain_internal(struct iommu_group *group,
 		return -EINVAL;
 
 	/*
-	 * This is a concurrent attach during a device reset. Reject it until
+	 * This is a concurrent attach during device recovery. Reject it until
 	 * pci_dev_reset_iommu_done() attaches the device to group->domain.
 	 */
-	if (group->resetting_domain)
+	if (group->recovery_cnt)
 		return -EBUSY;
 
 	/*
@@ -3615,10 +3646,10 @@ int iommu_attach_device_pasid(struct iommu_domain *domain,
 	mutex_lock(&group->mutex);
 
 	/*
-	 * This is a concurrent attach during a device reset. Reject it until
+	 * This is a concurrent attach during device recovery. Reject it until
 	 * pci_dev_reset_iommu_done() attaches the device to group->domain.
 	 */
-	if (group->resetting_domain) {
+	if (group->recovery_cnt) {
 		ret = -EBUSY;
 		goto out_unlock;
 	}
@@ -3708,10 +3739,10 @@ int iommu_replace_device_pasid(struct iommu_domain *domain,
 	mutex_lock(&group->mutex);
 
 	/*
-	 * This is a concurrent attach during a device reset. Reject it until
+	 * This is a concurrent attach during device recovery. Reject it until
 	 * pci_dev_reset_iommu_done() attaches the device to group->domain.
 	 */
-	if (group->resetting_domain) {
+	if (group->recovery_cnt) {
 		ret = -EBUSY;
 		goto out_unlock;
 	}
@@ -3982,12 +4013,12 @@ EXPORT_SYMBOL_NS_GPL(iommu_replace_group_handle, "IOMMUFD_INTERNAL");
  * routine wants to block any IOMMU activity: translation and ATS invalidation.
  *
  * This function attaches the device's RID/PASID(s) the group->blocking_domain,
- * setting the group->resetting_domain. This allows the IOMMU driver pausing any
+ * incrementing the group->recovery_cnt, to allow the IOMMU driver pausing any
  * IOMMU activity while leaving the group->domain pointer intact. Later when the
  * reset is finished, pci_dev_reset_iommu_done() can restore everything.
  *
  * Caller must use pci_dev_reset_iommu_prepare() with pci_dev_reset_iommu_done()
- * before/after the core-level reset routine, to unset the resetting_domain.
+ * before/after the core-level reset routine, to decrement the recovery_cnt.
  *
  * Return: 0 on success or negative error code if the preparation failed.
  *
@@ -4000,6 +4031,7 @@ EXPORT_SYMBOL_NS_GPL(iommu_replace_group_handle, "IOMMUFD_INTERNAL");
 int pci_dev_reset_iommu_prepare(struct pci_dev *pdev)
 {
 	struct iommu_group *group = pdev->dev.iommu_group;
+	struct group_device *gdev;
 	unsigned long pasid;
 	void *entry;
 	int ret;
@@ -4009,8 +4041,12 @@ int pci_dev_reset_iommu_prepare(struct pci_dev *pdev)
 
 	guard(mutex)(&group->mutex);
 
+	gdev = __dev_to_gdev(&pdev->dev);
+	if (WARN_ON(!gdev))
+		return -ENODEV;
+
 	/* Re-entry is not allowed */
-	if (WARN_ON(group->resetting_domain))
+	if (WARN_ON(gdev->blocked))
 		return -EBUSY;
 
 	ret = __iommu_group_alloc_blocking_domain(group);
@@ -4026,6 +4062,13 @@ int pci_dev_reset_iommu_prepare(struct pci_dev *pdev)
 	}
 
 	/*
+	 * Update gdev->blocked upon the domain change, as it is used to return
+	 * the correct domain in iommu_driver_get_domain_for_dev() that might be
+	 * called in a set_dev_pasid callback function.
+	 */
+	gdev->blocked = true;
+
+	/*
 	 * Stage PASID domains at blocking_domain while retaining pasid_array.
 	 *
 	 * The pasid_array is mostly fenced by group->mutex, except one reader
@@ -4035,7 +4078,7 @@ int pci_dev_reset_iommu_prepare(struct pci_dev *pdev)
 		iommu_remove_dev_pasid(&pdev->dev, pasid,
 				       pasid_array_entry_to_domain(entry));
 
-	group->resetting_domain = group->blocking_domain;
+	group->recovery_cnt++;
 	return ret;
 }
 EXPORT_SYMBOL_GPL(pci_dev_reset_iommu_prepare);
@@ -4057,6 +4100,7 @@ EXPORT_SYMBOL_GPL(pci_dev_reset_iommu_prepare);
 void pci_dev_reset_iommu_done(struct pci_dev *pdev)
 {
 	struct iommu_group *group = pdev->dev.iommu_group;
+	struct group_device *gdev;
 	unsigned long pasid;
 	void *entry;
 
@@ -4065,11 +4109,13 @@ void pci_dev_reset_iommu_done(struct pci_dev *pdev)
 
 	guard(mutex)(&group->mutex);
 
-	/* pci_dev_reset_iommu_prepare() was bypassed for the device */
-	if (!group->resetting_domain)
+	gdev = __dev_to_gdev(&pdev->dev);
+	if (WARN_ON(!gdev))
+		return;
+
+	if (!gdev->blocked)
 		return;
 
-	/* pci_dev_reset_iommu_prepare() was not successfully called */
 	if (WARN_ON(!group->blocking_domain))
 		return;
 
@@ -4085,6 +4131,13 @@ void pci_dev_reset_iommu_done(struct pci_dev *pdev)
 	}
 
 	/*
+	 * Update gdev->blocked upon the domain change, as it is used to return
+	 * the correct domain in iommu_driver_get_domain_for_dev() that might be
+	 * called in a set_dev_pasid callback function.
+	 */
+	gdev->blocked = false;
+
+	/*
 	 * Re-attach PASID domains back to the domains retained in pasid_array.
 	 *
 	 * The pasid_array is mostly fenced by group->mutex, except one reader
@@ -4095,7 +4148,8 @@ void pci_dev_reset_iommu_done(struct pci_dev *pdev)
 			pasid_array_entry_to_domain(entry), group, pasid,
 			group->blocking_domain));
 
-	group->resetting_domain = NULL;
+	if (!WARN_ON(group->recovery_cnt == 0))
+		group->recovery_cnt--;
 }
 EXPORT_SYMBOL_GPL(pci_dev_reset_iommu_done);