Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Matthew Rosato <mjrosato@linux.ibm.com>
To:     iommu@lists.linux.dev
Cc:     linux-s390@vger.kernel.org, schnelle@linux.ibm.com,
        pmorel@linux.ibm.com, borntraeger@linux.ibm.com, hca@linux.ibm.com,
        gor@linux.ibm.com, gerald.schaefer@linux.ibm.com,
        agordeev@linux.ibm.com, svens@linux.ibm.com, joro@8bytes.org,
        will@kernel.org, robin.murphy@arm.com, jgg@nvidia.com,
        linux-kernel@vger.kernel.org
Subject: [PATCH] iommu/s390: Fix race with release_device ops
Date:   Tue, 23 Aug 2022 16:30:59 -0400
Message-Id: <20220823203059.81919-1-mjrosato@linux.ibm.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

With commit fa7e9ecc5e1c ("iommu/s390: Tolerate repeat attach_dev
calls") s390-iommu is supposed to handle dynamic switching between IOMMU
domains and the DMA API handling.  However, this commit does not
sufficiently handle the case where the device is released via a call
to the release_device op as it may occur at the same time as an opposing
attach_dev or detach_dev since the group mutex is not held over
release_device.  This was observed if the device is deconfigured during a
small window during vfio-pci initialization and can result in WARNs and
potential kernel panics.

Handle this by tracking when the device is probed/released via
dev_iommu_priv_set/get().  Ensure that once the device is released only
release_device handles the re-init of the device DMA.

Fixes: fa7e9ecc5e1c ("iommu/s390: Tolerate repeat attach_dev calls")
Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
---
 arch/s390/include/asm/pci.h |  1 +
 arch/s390/pci/pci.c         |  1 +
 drivers/iommu/s390-iommu.c  | 68 ++++++++++++++++++++++++++++---------
 3 files changed, 54 insertions(+), 16 deletions(-)

diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 7b4cdadbc023..1295b6900e4b 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -157,6 +157,7 @@ struct zpci_dev {
 	/* DMA stuff */
 	unsigned long	*dma_table;
 	spinlock_t	dma_table_lock;
+	spinlock_t	dma_domain_lock;
 	int		tlb_refresh;
 
 	spinlock_t	iommu_bitmap_lock;
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 73cdc5539384..61901c1be3cc 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -832,6 +832,7 @@ struct zpci_dev *zpci_create_device(u32 fid, u32 fh, enum zpci_state state)
 	kref_init(&zdev->kref);
 	mutex_init(&zdev->lock);
 	mutex_init(&zdev->kzdev_lock);
+	spin_lock_init(&zdev->dma_domain_lock);
 
 	rc = zpci_init_iommu(zdev);
 	if (rc)
diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c
index c898bcbbce11..513a7ebd23b3 100644
--- a/drivers/iommu/s390-iommu.c
+++ b/drivers/iommu/s390-iommu.c
@@ -90,15 +90,39 @@ static int s390_iommu_attach_device(struct iommu_domain *domain,
 	struct zpci_dev *zdev = to_zpci_dev(dev);
 	struct s390_domain_device *domain_device;
 	unsigned long flags;
-	int cc, rc;
+	int cc, rc = 0;
 
 	if (!zdev)
 		return -ENODEV;
 
+	/* First check compatibility */
+	spin_lock_irqsave(&s390_domain->list_lock, flags);
+	/* First device defines the DMA range limits */
+	if (list_empty(&s390_domain->devices)) {
+		domain->geometry.aperture_start = zdev->start_dma;
+		domain->geometry.aperture_end = zdev->end_dma;
+		domain->geometry.force_aperture = true;
+	/* Allow only devices with identical DMA range limits */
+	} else if (domain->geometry.aperture_start != zdev->start_dma ||
+		   domain->geometry.aperture_end != zdev->end_dma) {
+		rc = -EINVAL;
+	}
+	spin_unlock_irqrestore(&s390_domain->list_lock, flags);
+	if (rc)
+		return rc;
+
 	domain_device = kzalloc(sizeof(*domain_device), GFP_KERNEL);
 	if (!domain_device)
 		return -ENOMEM;
 
+	/* Leave now if the device has already been released */
+	spin_lock_irqsave(&zdev->dma_domain_lock, flags);
+	if (!dev_iommu_priv_get(dev)) {
+		spin_unlock_irqrestore(&zdev->dma_domain_lock, flags);
+		kfree(domain_device);
+		return 0;
+	}
+
 	if (zdev->dma_table && !zdev->s390_domain) {
 		cc = zpci_dma_exit_device(zdev);
 		if (cc) {
@@ -117,22 +141,11 @@ static int s390_iommu_attach_device(struct iommu_domain *domain,
 		rc = -EIO;
 		goto out_restore;
 	}
+	zdev->s390_domain = s390_domain;
+	spin_unlock_irqrestore(&zdev->dma_domain_lock, flags);
 
 	spin_lock_irqsave(&s390_domain->list_lock, flags);
-	/* First device defines the DMA range limits */
-	if (list_empty(&s390_domain->devices)) {
-		domain->geometry.aperture_start = zdev->start_dma;
-		domain->geometry.aperture_end = zdev->end_dma;
-		domain->geometry.force_aperture = true;
-	/* Allow only devices with identical DMA range limits */
-	} else if (domain->geometry.aperture_start != zdev->start_dma ||
-		   domain->geometry.aperture_end != zdev->end_dma) {
-		rc = -EINVAL;
-		spin_unlock_irqrestore(&s390_domain->list_lock, flags);
-		goto out_restore;
-	}
 	domain_device->zdev = zdev;
-	zdev->s390_domain = s390_domain;
 	list_add(&domain_device->list, &s390_domain->devices);
 	spin_unlock_irqrestore(&s390_domain->list_lock, flags);
 
@@ -147,6 +160,7 @@ static int s390_iommu_attach_device(struct iommu_domain *domain,
 				   virt_to_phys(zdev->dma_table));
 	}
 out_free:
+	spin_unlock_irqrestore(&zdev->dma_domain_lock, flags);
 	kfree(domain_device);
 
 	return rc;
@@ -176,17 +190,22 @@ static void s390_iommu_detach_device(struct iommu_domain *domain,
 	}
 	spin_unlock_irqrestore(&s390_domain->list_lock, flags);
 
-	if (found && (zdev->s390_domain == s390_domain)) {
+	spin_lock_irqsave(&zdev->dma_domain_lock, flags);
+	if (found && (zdev->s390_domain == s390_domain) &&
+	    dev_iommu_priv_get(dev)) {
 		zdev->s390_domain = NULL;
 		zpci_unregister_ioat(zdev, 0);
 		zpci_dma_init_device(zdev);
 	}
+	spin_unlock_irqrestore(&zdev->dma_domain_lock, flags);
 }
 
 static struct iommu_device *s390_iommu_probe_device(struct device *dev)
 {
 	struct zpci_dev *zdev = to_zpci_dev(dev);
 
+	dev_iommu_priv_set(dev, zdev);
+
 	return &zdev->iommu_dev;
 }
 
@@ -194,6 +213,7 @@ static void s390_iommu_release_device(struct device *dev)
 {
 	struct zpci_dev *zdev = to_zpci_dev(dev);
 	struct iommu_domain *domain;
+	unsigned long flags;
 
 	/*
 	 * This is a workaround for a scenario where the IOMMU API common code
@@ -206,10 +226,26 @@ static void s390_iommu_release_device(struct device *dev)
 	 *
 	 * So let's call detach_dev from here if it hasn't been called before.
 	 */
-	if (zdev && zdev->s390_domain) {
+	if (zdev) {
+		/*
+		 * Clear priv to block further attaches for this device,
+		 * ensure detaches don't init DMA
+		 */
+		spin_lock_irqsave(&zdev->dma_domain_lock, flags);
+		dev_iommu_priv_set(dev, NULL);
+		spin_unlock_irqrestore(&zdev->dma_domain_lock, flags);
+		/* Make sure this device is removed from the domain list */
 		domain = iommu_get_domain_for_dev(dev);
 		if (domain)
 			s390_iommu_detach_device(domain, dev);
+		/* Now ensure DMA is initialized from here */
+		spin_lock_irqsave(&zdev->dma_domain_lock, flags);
+		if (zdev->s390_domain) {
+			zdev->s390_domain = NULL;
+			zpci_unregister_ioat(zdev, 0);
+			zpci_dma_init_device(zdev);
+		}
+		spin_unlock_irqrestore(&zdev->dma_domain_lock, flags);
 	}
 }
 
-- 
2.31.1