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:   Niklas Schnelle <schnelle@linux.ibm.com>
To:     Matthew Rosato <mjrosato@linux.ibm.com>,
        Pierre Morel <pmorel@linux.ibm.com>, iommu@lists.linux.dev
Cc:     linux-s390@vger.kernel.org, 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 v3 3/5] iommu/s390: Fix potential s390_domain aperture shrinking
Date:   Thu, 29 Sep 2022 17:33:00 +0200
Message-Id: <20220929153302.3195115-4-schnelle@linux.ibm.com>
In-Reply-To: <20220929153302.3195115-1-schnelle@linux.ibm.com>
References: <20220929153302.3195115-1-schnelle@linux.ibm.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

The s390 IOMMU driver currently sets the IOMMU domain's aperture to
match the device specific DMA address range of the device that is first
attached. This is not ideal. For one if the domain has no device
attached in the meantime the aperture could be shrunk allowing
translations outside the aperture to exist in the translation tables.
Also this is a bit of a misuse of the aperture which really should
describe what addresses can be translated and not some device specific
limitations.

Instead of misusing the aperture like this we can instead create
reserved ranges for the ranges inaccessible to the attached devices
allowing devices with overlapping ranges to still share an IOMMU domain.
This also significantly simplifies s390_iommu_attach_device() allowing
us to move the aperture check to the beginning of the function and
removing the need to hold the device list's lock to check the aperture.

Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
---
 drivers/iommu/s390-iommu.c | 50 +++++++++++++++++++++++++++-----------
 1 file changed, 36 insertions(+), 14 deletions(-)

diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c
index 8c4b180b3247..ed0e64f478cf 100644
--- a/drivers/iommu/s390-iommu.c
+++ b/drivers/iommu/s390-iommu.c
@@ -62,6 +62,9 @@ static struct iommu_domain *s390_domain_alloc(unsigned domain_type)
 		kfree(s390_domain);
 		return NULL;
 	}
+	s390_domain->domain.geometry.force_aperture = true;
+	s390_domain->domain.geometry.aperture_start = 0;
+	s390_domain->domain.geometry.aperture_end = ZPCI_TABLE_SIZE_RT - 1;
 
 	spin_lock_init(&s390_domain->dma_table_lock);
 	spin_lock_init(&s390_domain->list_lock);
@@ -107,30 +110,24 @@ static int s390_iommu_attach_device(struct iommu_domain *domain,
 	if (!zdev)
 		return -ENODEV;
 
+	if (domain->geometry.aperture_start > zdev->end_dma ||
+	    domain->geometry.aperture_end < zdev->start_dma)
+		return -EINVAL;
+
 	if (zdev->s390_domain)
 		__s390_iommu_detach_device(zdev->s390_domain, zdev);
 	else if (zdev->dma_table)
 		zpci_dma_exit_device(zdev);
 
-	zdev->dma_table = s390_domain->dma_table;
 	cc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
-				virt_to_phys(zdev->dma_table));
+				virt_to_phys(s390_domain->dma_table));
 	if (cc)
 		return -EIO;
 
-	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) {
-		spin_unlock_irqrestore(&s390_domain->list_lock, flags);
-		return -EINVAL;
-	}
+	zdev->dma_table = s390_domain->dma_table;
 	zdev->s390_domain = s390_domain;
+
+	spin_lock_irqsave(&s390_domain->list_lock, flags);
 	list_add(&zdev->iommu_list, &s390_domain->devices);
 	spin_unlock_irqrestore(&s390_domain->list_lock, flags);
 
@@ -147,6 +144,30 @@ static void s390_iommu_detach_device(struct iommu_domain *domain,
 	zpci_dma_init_device(zdev);
 }
 
+static void s390_iommu_get_resv_regions(struct device *dev,
+					struct list_head *list)
+{
+	struct zpci_dev *zdev = to_zpci_dev(dev);
+	struct iommu_resv_region *region;
+
+	if (zdev->start_dma) {
+		region = iommu_alloc_resv_region(0, zdev->start_dma, 0,
+						 IOMMU_RESV_RESERVED);
+		if (!region)
+			return;
+		list_add_tail(&region->list, list);
+	}
+
+	if (zdev->end_dma < ZPCI_TABLE_SIZE_RT - 1) {
+		region = iommu_alloc_resv_region(zdev->end_dma + 1,
+						 ZPCI_TABLE_SIZE_RT - zdev->end_dma - 1,
+						 0, IOMMU_RESV_RESERVED);
+		if (!region)
+			return;
+		list_add_tail(&region->list, list);
+	}
+}
+
 static struct iommu_device *s390_iommu_probe_device(struct device *dev)
 {
 	struct zpci_dev *zdev = to_zpci_dev(dev);
@@ -340,6 +361,7 @@ static const struct iommu_ops s390_iommu_ops = {
 	.release_device = s390_iommu_release_device,
 	.device_group = generic_device_group,
 	.pgsize_bitmap = S390_IOMMU_PGSIZES,
+	.get_resv_regions = s390_iommu_get_resv_regions,
 	.default_domain_ops = &(const struct iommu_domain_ops) {
 		.attach_dev	= s390_iommu_attach_device,
 		.detach_dev	= s390_iommu_detach_device,
-- 
2.34.1