Linux PCI subsystem development
 help / color / mirror / Atom feed
From: Pavol Sakac <sakacpav@amazon.de>
To: Joerg Roedel <joro@8bytes.org>, Will Deacon <will@kernel.org>
Cc: Robin Murphy <robin.murphy@arm.com>, <iommu@lists.linux.dev>,
	<linux-kernel@vger.kernel.org>,
	Bjorn Helgaas <bhelgaas@google.com>, <linux-pci@vger.kernel.org>,
	<nh-open-source@amazon.com>
Subject: [RFC PATCH 1/3] iommu: split sysfs link publication out of iommu_group_alloc_device()
Date: Fri, 11 Sep 2026 14:58:32 +0200	[thread overview]
Message-ID: <20260911125907.67105-1-sakacpav@amazon.de> (raw)
In-Reply-To: <20260911-vfopt-s2-v1-0-fff3db7e01c2@amazon.de>

iommu_group_alloc_device() both allocates a group_device and publishes
it in sysfs (the "iommu_group" link and the group "devices/" member
link with its .%d rename loop), while the iommu instance links are
published separately in iommu_init_device() and removed in
iommu_deinit_device().

Gather all per-member publication into one helper,
iommu_group_link_device(), run under group->mutex, and record success
in a new group_device::linked flag. Teardown moves next to the member
link removal in __iommu_group_free_device(), which consults the flag so
an unpublished member skips sysfs.

No functional change intended; this gives publication a single seam so
a later commit can move it out of iommu_probe_device_lock.

Assisted-by: LLM
Signed-off-by: Pavol Sakac <sakacpav@amazon.de>
---
 drivers/iommu/iommu.c | 91 +++++++++++++++++++++++++++++++------------
 1 file changed, 67 insertions(+), 24 deletions(-)

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index cd1bca7ede9a..5f92981d9f34 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -77,6 +77,8 @@ struct group_device {
 	struct list_head list;
 	struct device *dev;
 	char *name;
+	/* Membership published in sysfs; set under group->mutex */
+	bool linked;
 	/*
 	 * Device is blocked for a pending recovery while its group->domain is
 	 * retained. This can happen when:
@@ -166,6 +168,8 @@ static ssize_t iommu_group_store_type(struct iommu_group *group,
 				      const char *buf, size_t count);
 static struct group_device *iommu_group_alloc_device(struct iommu_group *group,
 						     struct device *dev);
+static int iommu_group_link_device(struct iommu_group *group,
+				   struct group_device *device);
 static void __iommu_group_free_device(struct iommu_group *group,
 				      struct group_device *grp_dev);
 static void iommu_domain_init(struct iommu_domain *domain, unsigned int type,
@@ -515,16 +519,12 @@ static int iommu_init_device(struct device *dev)
 	}
 	dev->iommu->iommu_dev = iommu_dev;
 
-	ret = iommu_device_link(iommu_dev, dev);
-	if (ret)
-		goto err_release;
-
 	group = ops->device_group(dev);
 	if (WARN_ON_ONCE(group == NULL))
 		group = ERR_PTR(-EINVAL);
 	if (IS_ERR(group)) {
 		ret = PTR_ERR(group);
-		goto err_unlink;
+		goto err_release;
 	}
 	dev->iommu_group = group;
 
@@ -533,8 +533,6 @@ static int iommu_init_device(struct device *dev)
 		dev->iommu->attach_deferred = ops->is_attach_deferred(dev);
 	return 0;
 
-err_unlink:
-	iommu_device_unlink(iommu_dev, dev);
 err_release:
 	if (ops->release_device)
 		ops->release_device(dev);
@@ -553,8 +551,6 @@ static void iommu_deinit_device(struct device *dev)
 
 	lockdep_assert_held(&group->mutex);
 
-	iommu_device_unlink(dev->iommu->iommu_dev, dev);
-
 	/*
 	 * release_device() must stop using any attached domain on the device.
 	 * If there are still other devices in the group, they are not affected
@@ -667,6 +663,11 @@ static int __iommu_probe_device(struct device *dev, struct list_head *group_list
 	 */
 	list_add_tail(&gdev->list, &group->devices);
 	WARN_ON(group->default_domain && !group->domain);
+
+	ret = iommu_group_link_device(group, gdev);
+	if (ret)
+		goto err_remove_gdev;
+
 	if (group->default_domain)
 		iommu_create_device_direct_mappings(group->default_domain, dev);
 	if (group->domain) {
@@ -729,10 +730,14 @@ static void __iommu_group_free_device(struct iommu_group *group,
 {
 	struct device *dev = grp_dev->dev;
 
-	sysfs_remove_link(group->devices_kobj, grp_dev->name);
-	sysfs_remove_link(&dev->kobj, "iommu_group");
+	if (grp_dev->linked) {
+		if (dev_has_iommu(dev))
+			iommu_device_unlink(dev->iommu->iommu_dev, dev);
+		sysfs_remove_link(group->devices_kobj, grp_dev->name);
+		sysfs_remove_link(&dev->kobj, "iommu_group");
 
-	trace_remove_device_from_group(group->id, dev);
+		trace_remove_device_from_group(group->id, dev);
+	}
 
 	/*
 	 * If the group has become empty then ownership must have been
@@ -1266,7 +1271,6 @@ static int iommu_create_device_direct_mappings(struct iommu_domain *domain,
 static struct group_device *iommu_group_alloc_device(struct iommu_group *group,
 						     struct device *dev)
 {
-	int ret, i = 0;
 	struct group_device *device;
 
 	device = kzalloc_obj(*device);
@@ -1275,11 +1279,40 @@ static struct group_device *iommu_group_alloc_device(struct iommu_group *group,
 
 	device->dev = dev;
 
+	device->name = kasprintf(GFP_KERNEL, "%s", kobject_name(&dev->kobj));
+	if (!device->name) {
+		kfree(device);
+		dev_err(dev, "Failed to add to iommu group %d: %d\n",
+			group->id, -ENOMEM);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return device;
+}
+
+/*
+ * Publish a member's sysfs links under group->mutex.  All-or-nothing:
+ * on failure nothing is left behind and gdev->linked stays false, so
+ * __iommu_group_free_device() removes only what was published.
+ */
+static int iommu_group_link_device(struct iommu_group *group,
+				   struct group_device *device)
+{
+	struct device *dev = device->dev;
+	int ret, i = 0;
+
+	lockdep_assert_held(&group->mutex);
+
+	if (dev_has_iommu(dev)) {
+		ret = iommu_device_link(dev->iommu->iommu_dev, dev);
+		if (ret)
+			goto err_out;
+	}
+
 	ret = sysfs_create_link(&dev->kobj, &group->kobj, "iommu_group");
 	if (ret)
-		goto err_free_device;
+		goto err_unlink_iommu;
 
-	device->name = kasprintf(GFP_KERNEL, "%s", kobject_name(&dev->kobj));
 rename:
 	if (!device->name) {
 		ret = -ENOMEM;
@@ -1299,23 +1332,25 @@ static struct group_device *iommu_group_alloc_device(struct iommu_group *group,
 						 kobject_name(&dev->kobj), i++);
 			goto rename;
 		}
-		goto err_free_name;
+		goto err_remove_link;
 	}
 
+	device->linked = true;
+
 	trace_add_device_to_group(group->id, dev);
 
 	dev_info(dev, "Adding to iommu group %d\n", group->id);
 
-	return device;
+	return 0;
 
-err_free_name:
-	kfree(device->name);
 err_remove_link:
 	sysfs_remove_link(&dev->kobj, "iommu_group");
-err_free_device:
-	kfree(device);
+err_unlink_iommu:
+	if (dev_has_iommu(dev))
+		iommu_device_unlink(dev->iommu->iommu_dev, dev);
+err_out:
 	dev_err(dev, "Failed to add to iommu group %d: %d\n", group->id, ret);
-	return ERR_PTR(ret);
+	return ret;
 }
 
 /**
@@ -1329,15 +1364,23 @@ static struct group_device *iommu_group_alloc_device(struct iommu_group *group,
 int iommu_group_add_device(struct iommu_group *group, struct device *dev)
 {
 	struct group_device *gdev;
+	int ret;
 
 	gdev = iommu_group_alloc_device(group, dev);
 	if (IS_ERR(gdev))
 		return PTR_ERR(gdev);
 
+	mutex_lock(&group->mutex);
+	ret = iommu_group_link_device(group, gdev);
+	if (ret) {
+		mutex_unlock(&group->mutex);
+		kfree(gdev->name);
+		kfree(gdev);
+		return ret;
+	}
+
 	iommu_group_ref_get(group);
 	dev->iommu_group = group;
-
-	mutex_lock(&group->mutex);
 	list_add_tail(&gdev->list, &group->devices);
 	mutex_unlock(&group->mutex);
 	return 0;
-- 
2.47.3


  reply	other threads:[~2026-09-11 12:59 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-11 12:58 [RFC PATCH 0/3] iommu: Reduce iommu_probe_device_lock contention Pavol Sakac
2026-09-11 12:58 ` Pavol Sakac [this message]
2026-09-11 13:14   ` [RFC PATCH 1/3] iommu: split sysfs link publication out of iommu_group_alloc_device() sashiko-bot
2026-09-11 12:58 ` [RFC PATCH 2/3] iommu: create device sysfs links outside iommu_probe_device_lock Pavol Sakac
2026-09-11 13:13   ` sashiko-bot
2026-09-11 12:58 ` [RFC PATCH 3/3] iommu: set up the default domain " Pavol Sakac
2026-09-11 13:15   ` sashiko-bot
2026-09-11 17:45 ` [RFC PATCH 0/3] iommu: Reduce iommu_probe_device_lock contention Robin Murphy

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=20260911125907.67105-1-sakacpav@amazon.de \
    --to=sakacpav@amazon.de \
    --cc=bhelgaas@google.com \
    --cc=iommu@lists.linux.dev \
    --cc=joro@8bytes.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=nh-open-source@amazon.com \
    --cc=robin.murphy@arm.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