All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jason Gunthorpe <jgg@nvidia.com>
To: iommu@lists.linux.dev, linux-kselftest@vger.kernel.org
Cc: Lu Baolu <baolu.lu@linux.intel.com>,
	Kevin Tian <kevin.tian@intel.com>,
	kvm@vger.kernel.org, Lixiao Yang <lixiao.yang@intel.com>,
	Matthew Rosato <mjrosato@linux.ibm.com>,
	Nicolin Chen <nicolinc@nvidia.com>, Yi Liu <yi.l.liu@intel.com>
Subject: [PATCH v7 03/19] iommufd: Replace the hwpt->devices list with iommufd_group
Date: Mon, 15 May 2023 11:00:18 -0300	[thread overview]
Message-ID: <3-v7-6c0fd698eda2+5e3-iommufd_alloc_jgg@nvidia.com> (raw)
In-Reply-To: <0-v7-6c0fd698eda2+5e3-iommufd_alloc_jgg@nvidia.com>

The devices list was used as a simple way to avoid having per-group
information. Now that this seems to be unavoidable, just commit to
per-group information fully and remove the devices list from the HWPT.

The iommufd_group stores the currently assigned HWPT for the entire group
and we can manage the per-device attach/detach with a list in the
iommufd_group.

For destruction the flow is organized to make the following patches
easier, the actual call to iommufd_object_destroy_user() is done at the
top of the call chain without holding any locks. The HWPT to be destroyed
is returned out from the locked region to make this possible. Later
patches create locking that requires this.

Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/iommufd/device.c          | 100 +++++++++++-------------
 drivers/iommu/iommufd/hw_pagetable.c    |  22 +-----
 drivers/iommu/iommufd/iommufd_private.h |  13 ++-
 3 files changed, 54 insertions(+), 81 deletions(-)

diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index 8c27f6901446e8..23ebf2065e20de 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -20,9 +20,12 @@ static void iommufd_group_release(struct kref *kref)
 	struct iommufd_group *igroup =
 		container_of(kref, struct iommufd_group, ref);
 
+	WARN_ON(igroup->hwpt || !list_empty(&igroup->device_list));
+
 	xa_cmpxchg(&igroup->ictx->groups, iommu_group_id(igroup->group), igroup,
 		   NULL, GFP_KERNEL);
 	iommu_group_put(igroup->group);
+	mutex_destroy(&igroup->lock);
 	kfree(igroup);
 }
 
@@ -83,6 +86,8 @@ static struct iommufd_group *iommufd_get_group(struct iommufd_ctx *ictx,
 	}
 
 	kref_init(&new_igroup->ref);
+	mutex_init(&new_igroup->lock);
+	INIT_LIST_HEAD(&new_igroup->device_list);
 	/* group reference moves into new_igroup */
 	new_igroup->group = group;
 
@@ -277,29 +282,18 @@ static int iommufd_device_setup_msi(struct iommufd_device *idev,
 	return 0;
 }
 
-static bool iommufd_hw_pagetable_has_group(struct iommufd_hw_pagetable *hwpt,
-					   struct iommufd_group *igroup)
-{
-	struct iommufd_device *cur_dev;
-
-	lockdep_assert_held(&hwpt->devices_lock);
-
-	list_for_each_entry(cur_dev, &hwpt->devices, devices_item)
-		if (cur_dev->igroup->group == igroup->group)
-			return true;
-	return false;
-}
-
 int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt,
 				struct iommufd_device *idev)
 {
 	phys_addr_t sw_msi_start = PHYS_ADDR_MAX;
 	int rc;
 
-	lockdep_assert_held(&hwpt->devices_lock);
+	mutex_lock(&idev->igroup->lock);
 
-	if (WARN_ON(idev->hwpt))
-		return -EINVAL;
+	if (idev->igroup->hwpt != NULL && idev->igroup->hwpt != hwpt) {
+		rc = -EINVAL;
+		goto err_unlock;
+	}
 
 	/*
 	 * Try to upgrade the domain we have, it is an iommu driver bug to
@@ -313,8 +307,9 @@ int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt,
 				hwpt->domain->ops->enforce_cache_coherency(
 					hwpt->domain);
 		if (!hwpt->enforce_cache_coherency) {
-			WARN_ON(list_empty(&hwpt->devices));
-			return -EINVAL;
+			WARN_ON(list_empty(&idev->igroup->device_list));
+			rc = -EINVAL;
+			goto err_unlock;
 		}
 	}
 
@@ -322,51 +317,52 @@ int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt,
 						   idev->igroup->group,
 						   &sw_msi_start);
 	if (rc)
-		return rc;
+		goto err_unlock;
 
 	rc = iommufd_device_setup_msi(idev, hwpt, sw_msi_start);
 	if (rc)
 		goto err_unresv;
 
 	/*
-	 * FIXME: Hack around missing a device-centric iommu api, only attach to
-	 * the group once for the first device that is in the group.
+	 * Only attach to the group once for the first device that is in the
+	 * group. All the other devices will follow this attachment. The user
+	 * should attach every device individually to the hwpt as the per-device
+	 * reserved regions are only updated during individual device
+	 * attachment.
 	 */
-	if (!iommufd_hw_pagetable_has_group(hwpt, idev->igroup)) {
+	if (list_empty(&idev->igroup->device_list)) {
 		rc = iommu_attach_group(hwpt->domain, idev->igroup->group);
 		if (rc)
 			goto err_unresv;
+		idev->igroup->hwpt = hwpt;
 	}
+	refcount_inc(&hwpt->obj.users);
+	list_add_tail(&idev->group_item, &idev->igroup->device_list);
+	mutex_unlock(&idev->igroup->lock);
 	return 0;
 err_unresv:
 	iopt_remove_reserved_iova(&hwpt->ioas->iopt, idev->dev);
+err_unlock:
+	mutex_unlock(&idev->igroup->lock);
 	return rc;
 }
 
-void iommufd_hw_pagetable_detach(struct iommufd_hw_pagetable *hwpt,
-				 struct iommufd_device *idev)
+struct iommufd_hw_pagetable *
+iommufd_hw_pagetable_detach(struct iommufd_device *idev)
 {
-	if (!iommufd_hw_pagetable_has_group(hwpt, idev->igroup))
+	struct iommufd_hw_pagetable *hwpt = idev->igroup->hwpt;
+
+	mutex_lock(&idev->igroup->lock);
+	list_del(&idev->group_item);
+	if (list_empty(&idev->igroup->device_list)) {
 		iommu_detach_group(hwpt->domain, idev->igroup->group);
+		idev->igroup->hwpt = NULL;
+	}
 	iopt_remove_reserved_iova(&hwpt->ioas->iopt, idev->dev);
-}
+	mutex_unlock(&idev->igroup->lock);
 
-static int iommufd_device_do_attach(struct iommufd_device *idev,
-				    struct iommufd_hw_pagetable *hwpt)
-{
-	int rc;
-
-	mutex_lock(&hwpt->devices_lock);
-	rc = iommufd_hw_pagetable_attach(hwpt, idev);
-	if (rc)
-		goto out_unlock;
-
-	idev->hwpt = hwpt;
-	refcount_inc(&hwpt->obj.users);
-	list_add(&idev->devices_item, &hwpt->devices);
-out_unlock:
-	mutex_unlock(&hwpt->devices_lock);
-	return rc;
+	/* Caller must destroy hwpt */
+	return hwpt;
 }
 
 /*
@@ -375,7 +371,7 @@ static int iommufd_device_do_attach(struct iommufd_device *idev,
  * Automatic domain selection will never pick a manually created domain.
  */
 static int iommufd_device_auto_get_domain(struct iommufd_device *idev,
-					  struct iommufd_ioas *ioas)
+					  struct iommufd_ioas *ioas, u32 *pt_id)
 {
 	struct iommufd_hw_pagetable *hwpt;
 	int rc;
@@ -392,7 +388,7 @@ static int iommufd_device_auto_get_domain(struct iommufd_device *idev,
 
 		if (!iommufd_lock_obj(&hwpt->obj))
 			continue;
-		rc = iommufd_device_do_attach(idev, hwpt);
+		rc = iommufd_hw_pagetable_attach(hwpt, idev);
 		iommufd_put_object(&hwpt->obj);
 
 		/*
@@ -402,6 +398,7 @@ static int iommufd_device_auto_get_domain(struct iommufd_device *idev,
 		 */
 		if (rc == -EINVAL)
 			continue;
+		*pt_id = hwpt->obj.id;
 		goto out_unlock;
 	}
 
@@ -411,6 +408,7 @@ static int iommufd_device_auto_get_domain(struct iommufd_device *idev,
 		goto out_unlock;
 	}
 	hwpt->auto_domain = true;
+	*pt_id = hwpt->obj.id;
 
 	mutex_unlock(&ioas->mutex);
 	iommufd_object_finalize(idev->ictx, &hwpt->obj);
@@ -446,7 +444,7 @@ int iommufd_device_attach(struct iommufd_device *idev, u32 *pt_id)
 		struct iommufd_hw_pagetable *hwpt =
 			container_of(pt_obj, struct iommufd_hw_pagetable, obj);
 
-		rc = iommufd_device_do_attach(idev, hwpt);
+		rc = iommufd_hw_pagetable_attach(hwpt, idev);
 		if (rc)
 			goto out_put_pt_obj;
 		break;
@@ -455,7 +453,7 @@ int iommufd_device_attach(struct iommufd_device *idev, u32 *pt_id)
 		struct iommufd_ioas *ioas =
 			container_of(pt_obj, struct iommufd_ioas, obj);
 
-		rc = iommufd_device_auto_get_domain(idev, ioas);
+		rc = iommufd_device_auto_get_domain(idev, ioas, pt_id);
 		if (rc)
 			goto out_put_pt_obj;
 		break;
@@ -466,7 +464,6 @@ int iommufd_device_attach(struct iommufd_device *idev, u32 *pt_id)
 	}
 
 	refcount_inc(&idev->obj.users);
-	*pt_id = idev->hwpt->obj.id;
 	rc = 0;
 
 out_put_pt_obj:
@@ -484,14 +481,9 @@ EXPORT_SYMBOL_NS_GPL(iommufd_device_attach, IOMMUFD);
  */
 void iommufd_device_detach(struct iommufd_device *idev)
 {
-	struct iommufd_hw_pagetable *hwpt = idev->hwpt;
-
-	mutex_lock(&hwpt->devices_lock);
-	list_del(&idev->devices_item);
-	idev->hwpt = NULL;
-	iommufd_hw_pagetable_detach(hwpt, idev);
-	mutex_unlock(&hwpt->devices_lock);
+	struct iommufd_hw_pagetable *hwpt;
 
+	hwpt = iommufd_hw_pagetable_detach(idev);
 	if (hwpt->auto_domain)
 		iommufd_object_destroy_user(idev->ictx, &hwpt->obj);
 	else
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index 6cdb6749d359f3..bdb76cdb1dc347 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -11,8 +11,6 @@ void iommufd_hw_pagetable_destroy(struct iommufd_object *obj)
 	struct iommufd_hw_pagetable *hwpt =
 		container_of(obj, struct iommufd_hw_pagetable, obj);
 
-	WARN_ON(!list_empty(&hwpt->devices));
-
 	if (!list_empty(&hwpt->hwpt_item)) {
 		mutex_lock(&hwpt->ioas->mutex);
 		list_del(&hwpt->hwpt_item);
@@ -25,7 +23,6 @@ void iommufd_hw_pagetable_destroy(struct iommufd_object *obj)
 		iommu_domain_free(hwpt->domain);
 
 	refcount_dec(&hwpt->ioas->obj.users);
-	mutex_destroy(&hwpt->devices_lock);
 }
 
 /**
@@ -52,9 +49,7 @@ iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
 	if (IS_ERR(hwpt))
 		return hwpt;
 
-	INIT_LIST_HEAD(&hwpt->devices);
 	INIT_LIST_HEAD(&hwpt->hwpt_item);
-	mutex_init(&hwpt->devices_lock);
 	/* Pairs with iommufd_hw_pagetable_destroy() */
 	refcount_inc(&ioas->obj.users);
 	hwpt->ioas = ioas;
@@ -65,8 +60,6 @@ iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
 		goto out_abort;
 	}
 
-	mutex_lock(&hwpt->devices_lock);
-
 	/*
 	 * immediate_attach exists only to accommodate iommu drivers that cannot
 	 * directly allocate a domain. These drivers do not finish creating the
@@ -76,29 +69,18 @@ iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
 	if (immediate_attach) {
 		rc = iommufd_hw_pagetable_attach(hwpt, idev);
 		if (rc)
-			goto out_unlock;
+			goto out_abort;
 	}
 
 	rc = iopt_table_add_domain(&hwpt->ioas->iopt, hwpt->domain);
 	if (rc)
 		goto out_detach;
 	list_add_tail(&hwpt->hwpt_item, &hwpt->ioas->hwpt_list);
-
-	if (immediate_attach) {
-		/* See iommufd_device_do_attach() */
-		refcount_inc(&hwpt->obj.users);
-		idev->hwpt = hwpt;
-		list_add(&idev->devices_item, &hwpt->devices);
-	}
-
-	mutex_unlock(&hwpt->devices_lock);
 	return hwpt;
 
 out_detach:
 	if (immediate_attach)
-		iommufd_hw_pagetable_detach(hwpt, idev);
-out_unlock:
-	mutex_unlock(&hwpt->devices_lock);
+		iommufd_hw_pagetable_detach(idev);
 out_abort:
 	iommufd_object_abort_and_destroy(ictx, &hwpt->obj);
 	return ERR_PTR(rc);
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index f45615f19798e6..e2eb1db5f8f8ce 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -250,8 +250,6 @@ struct iommufd_hw_pagetable {
 	bool msi_cookie : 1;
 	/* Head at iommufd_ioas::hwpt_list */
 	struct list_head hwpt_item;
-	struct mutex devices_lock;
-	struct list_head devices;
 };
 
 struct iommufd_hw_pagetable *
@@ -259,14 +257,17 @@ iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
 			   struct iommufd_device *idev, bool immediate_attach);
 int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt,
 				struct iommufd_device *idev);
-void iommufd_hw_pagetable_detach(struct iommufd_hw_pagetable *hwpt,
-				 struct iommufd_device *idev);
+struct iommufd_hw_pagetable *
+iommufd_hw_pagetable_detach(struct iommufd_device *idev);
 void iommufd_hw_pagetable_destroy(struct iommufd_object *obj);
 
 struct iommufd_group {
 	struct kref ref;
+	struct mutex lock;
 	struct iommufd_ctx *ictx;
 	struct iommu_group *group;
+	struct iommufd_hw_pagetable *hwpt;
+	struct list_head device_list;
 };
 
 /*
@@ -278,9 +279,7 @@ struct iommufd_device {
 	struct iommufd_object obj;
 	struct iommufd_ctx *ictx;
 	struct iommufd_group *igroup;
-	struct iommufd_hw_pagetable *hwpt;
-	/* Head at iommufd_hw_pagetable::devices */
-	struct list_head devices_item;
+	struct list_head group_item;
 	/* always the physical device */
 	struct device *dev;
 	bool enforce_cache_coherency;
-- 
2.40.1


  parent reply	other threads:[~2023-05-15 14:00 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-05-15 14:00 [PATCH v7 00/19] Add iommufd physical device operations for replace and alloc hwpt Jason Gunthorpe
2023-05-15 14:00 ` [PATCH v7 01/19] iommufd: Move isolated msi enforcement to iommufd_device_bind() Jason Gunthorpe
2023-05-16  4:07   ` Baolu Lu
2023-05-15 14:00 ` [PATCH v7 02/19] iommufd: Add iommufd_group Jason Gunthorpe
2023-05-16  2:43   ` Baolu Lu
2023-05-16 12:54     ` Jason Gunthorpe
2023-05-17  4:18       ` Baolu Lu
2023-05-15 14:00 ` Jason Gunthorpe [this message]
2023-05-16  3:00   ` [PATCH v7 03/19] iommufd: Replace the hwpt->devices list with iommufd_group Baolu Lu
2023-05-16 12:27     ` Jason Gunthorpe
2023-05-17  4:15       ` Baolu Lu
2023-05-17  6:33         ` Tian, Kevin
2023-05-17 12:43           ` Jason Gunthorpe
2023-05-18  7:05             ` Baolu Lu
2023-05-18 12:02               ` Jason Gunthorpe
2023-05-19  2:03                 ` Baolu Lu
2023-05-19  7:51                   ` Tian, Kevin
2023-05-19 11:42                   ` Jason Gunthorpe
2023-05-15 14:00 ` [PATCH v7 04/19] iommu: Export iommu_get_resv_regions() Jason Gunthorpe
2023-05-15 14:00 ` [PATCH v7 05/19] iommufd: Keep track of each device's reserved regions instead of groups Jason Gunthorpe
2023-05-15 14:00 ` [PATCH v7 06/19] iommufd: Use the iommufd_group to avoid duplicate MSI setup Jason Gunthorpe
2023-05-15 14:00 ` [PATCH v7 07/19] iommufd: Make sw_msi_start a group global Jason Gunthorpe
2023-05-15 14:00 ` [PATCH v7 08/19] iommufd: Move putting a hwpt to a helper function Jason Gunthorpe
2023-05-15 14:00 ` [PATCH v7 09/19] iommufd: Add enforced_cache_coherency to iommufd_hw_pagetable_alloc() Jason Gunthorpe
2023-05-15 14:00 ` [PATCH v7 10/19] iommufd: Allow a hwpt to be aborted after allocation Jason Gunthorpe
2023-05-15 14:00 ` [PATCH v7 11/19] iommufd: Fix locking around hwpt allocation Jason Gunthorpe
2023-05-15 14:00 ` [PATCH v7 12/19] iommufd: Reorganize iommufd_device_attach into iommufd_device_change_pt Jason Gunthorpe
2023-05-15 14:00 ` [PATCH v7 13/19] iommu: Introduce a new iommu_group_replace_domain() API Jason Gunthorpe
2023-05-15 14:00 ` [PATCH v7 14/19] iommufd: Add iommufd_device_replace() Jason Gunthorpe
2023-07-07  8:00   ` Liu, Yi L
2023-07-10 16:46     ` Jason Gunthorpe
2023-05-15 14:00 ` [PATCH v7 15/19] iommufd: Make destroy_rwsem use a lock class per object type Jason Gunthorpe
2023-05-15 14:00 ` [PATCH v7 16/19] iommufd/selftest: Test iommufd_device_replace() Jason Gunthorpe
2023-05-15 14:00 ` [PATCH v7 17/19] iommufd: Add IOMMU_HWPT_ALLOC Jason Gunthorpe
2023-05-15 14:00 ` [PATCH v7 18/19] iommufd/selftest: Return the real idev id from selftest mock_domain Jason Gunthorpe
2023-05-15 14:00 ` [PATCH v7 19/19] iommufd/selftest: Add a selftest for IOMMU_HWPT_ALLOC Jason Gunthorpe
2023-05-17 23:57 ` [PATCH v7 00/19] Add iommufd physical device operations for replace and alloc hwpt Nicolin Chen

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=3-v7-6c0fd698eda2+5e3-iommufd_alloc_jgg@nvidia.com \
    --to=jgg@nvidia.com \
    --cc=baolu.lu@linux.intel.com \
    --cc=iommu@lists.linux.dev \
    --cc=kevin.tian@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=lixiao.yang@intel.com \
    --cc=mjrosato@linux.ibm.com \
    --cc=nicolinc@nvidia.com \
    --cc=yi.l.liu@intel.com \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.