iommu.lists.linux-foundation.org archive mirror
 help / color / mirror / Atom feed
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 v4 1/2] iommu/s390: Fix race with release_device ops
Date: Wed, 31 Aug 2022 16:12:35 -0400	[thread overview]
Message-ID: <20220831201236.77595-2-mjrosato@linux.ibm.com> (raw)
In-Reply-To: <20220831201236.77595-1-mjrosato@linux.ibm.com>

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  | 39 ++++++++++++++++++++++++++++++++++---
 3 files changed, 38 insertions(+), 3 deletions(-)

diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 7b4cdadbc023..080251e7b275 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;
+	struct mutex	dma_domain_lock; /* protects s390_domain value */
 	int		tlb_refresh;
 
 	spinlock_t	iommu_bitmap_lock;
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 73cdc5539384..973edd32ecc9 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);
+	mutex_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..1137d669e849 100644
--- a/drivers/iommu/s390-iommu.c
+++ b/drivers/iommu/s390-iommu.c
@@ -99,6 +99,14 @@ static int s390_iommu_attach_device(struct iommu_domain *domain,
 	if (!domain_device)
 		return -ENOMEM;
 
+	/* Leave now if the device has already been released */
+	mutex_lock(&zdev->dma_domain_lock);
+	if (!dev_iommu_priv_get(dev)) {
+		mutex_unlock(&zdev->dma_domain_lock);
+		kfree(domain_device);
+		return 0;
+	}
+
 	if (zdev->dma_table && !zdev->s390_domain) {
 		cc = zpci_dma_exit_device(zdev);
 		if (cc) {
@@ -132,9 +140,10 @@ static int s390_iommu_attach_device(struct iommu_domain *domain,
 		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);
+	zdev->s390_domain = s390_domain;
+	mutex_unlock(&zdev->dma_domain_lock);
 
 	return 0;
 
@@ -147,6 +156,7 @@ static int s390_iommu_attach_device(struct iommu_domain *domain,
 				   virt_to_phys(zdev->dma_table));
 	}
 out_free:
+	mutex_unlock(&zdev->dma_domain_lock);
 	kfree(domain_device);
 
 	return rc;
@@ -176,17 +186,22 @@ 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)) {
+	mutex_lock(&zdev->dma_domain_lock);
+	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);
 	}
+	mutex_unlock(&zdev->dma_domain_lock);
 }
 
 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;
 }
 
@@ -206,10 +221,28 @@ 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.  Hold the domain lock
+		 * to ensure that attach/detach get a consistent view of
+		 * whether or not the device is released.
+		 */
+		mutex_lock(&zdev->dma_domain_lock);
+		dev_iommu_priv_set(dev, NULL);
+		mutex_unlock(&zdev->dma_domain_lock);
+		/* 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 */
+		mutex_lock(&zdev->dma_domain_lock);
+		if (zdev->s390_domain) {
+			zdev->s390_domain = NULL;
+			zpci_unregister_ioat(zdev, 0);
+			zpci_dma_init_device(zdev);
+		}
+		mutex_unlock(&zdev->dma_domain_lock);
 	}
 }
 
-- 
2.37.2


  reply	other threads:[~2022-08-31 20:12 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-08-31 20:12 [PATCH v4 0/2] iommu/s390: fixes related to repeat attach_dev calls Matthew Rosato
2022-08-31 20:12 ` Matthew Rosato [this message]
2022-09-01  7:56   ` [PATCH v4 1/2] iommu/s390: Fix race with release_device ops Pierre Morel
2022-09-01  9:37     ` Niklas Schnelle
2022-09-01 11:01       ` Robin Murphy
2022-09-01 13:42         ` Niklas Schnelle
2022-09-01 14:17           ` Niklas Schnelle
2022-09-01 14:29           ` Robin Murphy
2022-09-01 14:34             ` Jason Gunthorpe
2022-09-01 15:03               ` Robin Murphy
2022-09-01 15:49                 ` Jason Gunthorpe
2022-09-01 17:00                   ` Robin Murphy
2022-09-01 20:28       ` Matthew Rosato
2022-09-02  7:49         ` Niklas Schnelle
2022-09-01 10:25   ` Robin Murphy
2022-09-01 16:14     ` Matthew Rosato
2022-09-01 20:37       ` Jason Gunthorpe
2022-09-02 17:11         ` Matthew Rosato
2022-09-02 17:21           ` Jason Gunthorpe
2022-09-02 18:20             ` Matthew Rosato
2022-09-05  9:46             ` Robin Murphy
2022-09-06 13:36               ` Jason Gunthorpe
2022-09-02 10:48       ` Robin Murphy
2022-08-31 20:12 ` [PATCH v4 2/2] iommu/s390: fix leak of s390_domain_device Matthew Rosato

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220831201236.77595-2-mjrosato@linux.ibm.com \
    --to=mjrosato@linux.ibm.com \
    --cc=agordeev@linux.ibm.com \
    --cc=borntraeger@linux.ibm.com \
    --cc=gerald.schaefer@linux.ibm.com \
    --cc=gor@linux.ibm.com \
    --cc=hca@linux.ibm.com \
    --cc=iommu@lists.linux.dev \
    --cc=jgg@nvidia.com \
    --cc=joro@8bytes.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-s390@vger.kernel.org \
    --cc=pmorel@linux.ibm.com \
    --cc=robin.murphy@arm.com \
    --cc=schnelle@linux.ibm.com \
    --cc=svens@linux.ibm.com \
    --cc=will@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).