linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Lu Baolu <baolu.lu@linux.intel.com>
To: Joerg Roedel <joro@8bytes.org>,
	David Woodhouse <dwmw2@infradead.org>,
	Alex Williamson <alex.williamson@redhat.com>,
	Kirti Wankhede <kwankhede@nvidia.com>
Cc: ashok.raj@intel.com, sanjay.k.kumar@intel.com,
	jacob.jun.pan@intel.com, kevin.tian@intel.com,
	Jean-Philippe Brucker <jean-philippe.brucker@arm.com>,
	yi.l.liu@intel.com, yi.y.sun@intel.com, peterx@redhat.com,
	tiwei.bie@intel.com, Zeng Xin <xin.zeng@intel.com>,
	iommu@lists.linux-foundation.org, kvm@vger.kernel.org,
	linux-kernel@vger.kernel.org, Lu Baolu <baolu.lu@linux.intel.com>,
	Jacob Pan <jacob.jun.pan@linux.intel.com>
Subject: [PATCH v4 4/8] iommu/vt-d: Attach/detach domains in auxiliary mode
Date: Mon,  5 Nov 2018 15:34:04 +0800	[thread overview]
Message-ID: <20181105073408.21815-5-baolu.lu@linux.intel.com> (raw)
In-Reply-To: <20181105073408.21815-1-baolu.lu@linux.intel.com>

When multiple domains per device has been enabled by the
device driver, the device will tag the default PASID for
the domain to all DMA traffics out of the subset of this
device; and the IOMMU should translate the DMA requests
in PASID granularity.

This extends the intel_iommu_attach/detach_device() ops
to support managing PASID granular translation structures
when the device driver has enabled multiple domains per
device.

Cc: Ashok Raj <ashok.raj@intel.com>
Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Sanjay Kumar <sanjay.k.kumar@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
---
 drivers/iommu/intel-iommu.c | 192 +++++++++++++++++++++++++++++++-----
 include/linux/intel-iommu.h |  10 ++
 2 files changed, 180 insertions(+), 22 deletions(-)

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 2c86ac71c774..a61b25ad0d3b 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -2477,6 +2477,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 	info->iommu = iommu;
 	info->pasid_table = NULL;
 	info->auxd_enabled = 0;
+	INIT_LIST_HEAD(&info->auxiliary_domains);
 
 	if (dev && dev_is_pci(dev)) {
 		struct pci_dev *pdev = to_pci_dev(info->dev);
@@ -5010,35 +5011,134 @@ static void intel_iommu_domain_free(struct iommu_domain *domain)
 	domain_exit(to_dmar_domain(domain));
 }
 
-static int intel_iommu_attach_device(struct iommu_domain *domain,
-				     struct device *dev)
+/*
+ * Check whether a @domain will be attached to the @dev in the
+ * auxiliary mode.
+ */
+static inline bool
+is_device_attach_aux_domain(struct device *dev, struct iommu_domain *domain)
 {
-	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
-	struct intel_iommu *iommu;
-	int addr_width;
-	u8 bus, devfn;
+	struct device_domain_info *info = dev->archdata.iommu;
 
-	if (device_is_rmrr_locked(dev)) {
-		dev_warn(dev, "Device is ineligible for IOMMU domain attach due to platform RMRR requirement.  Contact your platform vendor.\n");
-		return -EPERM;
-	}
+	return info && info->auxd_enabled &&
+			domain->type == IOMMU_DOMAIN_UNMANAGED;
+}
 
-	/* normally dev is not mapped */
-	if (unlikely(domain_context_mapped(dev))) {
-		struct dmar_domain *old_domain;
+static void auxiliary_link_device(struct dmar_domain *domain,
+				  struct device *dev)
+{
+	struct device_domain_info *info = dev->archdata.iommu;
 
-		old_domain = find_domain(dev);
-		if (old_domain) {
-			rcu_read_lock();
-			dmar_remove_one_dev_info(old_domain, dev);
-			rcu_read_unlock();
+	assert_spin_locked(&device_domain_lock);
+	if (WARN_ON(!info))
+		return;
 
-			if (!domain_type_is_vm_or_si(old_domain) &&
-			     list_empty(&old_domain->devices))
-				domain_exit(old_domain);
+	domain->auxd_refcnt++;
+	list_add(&domain->auxd, &info->auxiliary_domains);
+}
+
+static void auxiliary_unlink_device(struct dmar_domain *domain,
+				    struct device *dev)
+{
+	struct device_domain_info *info = dev->archdata.iommu;
+
+	assert_spin_locked(&device_domain_lock);
+	if (WARN_ON(!info))
+		return;
+
+	list_del(&domain->auxd);
+	domain->auxd_refcnt--;
+
+	if (!domain->auxd_refcnt && domain->default_pasid > 0)
+		intel_pasid_free_id(domain->default_pasid);
+}
+
+static int domain_add_dev_auxd(struct dmar_domain *domain,
+			       struct device *dev)
+{
+	int ret;
+	u8 bus, devfn;
+	unsigned long flags;
+	struct intel_iommu *iommu;
+
+	iommu = device_to_iommu(dev, &bus, &devfn);
+	if (!iommu)
+		return -ENODEV;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	if (domain->default_pasid <= 0) {
+		domain->default_pasid = intel_pasid_alloc_id(domain, PASID_MIN,
+				pci_max_pasids(to_pci_dev(dev)), GFP_ATOMIC);
+		if (domain->default_pasid < 0) {
+			pr_err("Can't allocate default pasid\n");
+			ret = -ENODEV;
+			goto pasid_failed;
 		}
 	}
 
+	spin_lock(&iommu->lock);
+	ret = domain_attach_iommu(domain, iommu);
+	if (ret)
+		goto attach_failed;
+
+	/* Setup the PASID entry for mediated devices: */
+	ret = intel_pasid_setup_second_level(iommu, domain, dev,
+					     domain->default_pasid);
+	if (ret)
+		goto table_failed;
+	spin_unlock(&iommu->lock);
+
+	auxiliary_link_device(domain, dev);
+
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+
+	return 0;
+
+table_failed:
+	domain_detach_iommu(domain, iommu);
+attach_failed:
+	spin_unlock(&iommu->lock);
+	if (!domain->auxd_refcnt && domain->default_pasid > 0)
+		intel_pasid_free_id(domain->default_pasid);
+pasid_failed:
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+
+	return ret;
+}
+
+static void domain_remove_dev_aux(struct dmar_domain *domain,
+				  struct device *dev)
+{
+	struct device_domain_info *info;
+	struct intel_iommu *iommu;
+	unsigned long flags;
+
+	if (!is_device_attach_aux_domain(dev, &domain->domain))
+		return;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	info = dev->archdata.iommu;
+	iommu = info->iommu;
+
+	intel_pasid_tear_down_entry(iommu, dev, domain->default_pasid);
+
+	auxiliary_unlink_device(domain, dev);
+
+	spin_lock(&iommu->lock);
+	domain_detach_iommu(domain, iommu);
+	spin_unlock(&iommu->lock);
+
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+}
+
+static int __intel_iommu_attach_device(struct iommu_domain *domain,
+				       struct device *dev)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	struct intel_iommu *iommu;
+	int addr_width;
+	u8 bus, devfn;
+
 	iommu = device_to_iommu(dev, &bus, &devfn);
 	if (!iommu)
 		return -ENODEV;
@@ -5071,7 +5171,47 @@ static int intel_iommu_attach_device(struct iommu_domain *domain,
 		dmar_domain->agaw--;
 	}
 
-	return domain_add_dev_info(dmar_domain, dev);
+	if (is_device_attach_aux_domain(dev, domain))
+		return domain_add_dev_auxd(dmar_domain, dev);
+	else
+		return domain_add_dev_info(dmar_domain, dev);
+}
+
+static int intel_iommu_attach_device(struct iommu_domain *domain,
+				     struct device *dev)
+{
+	if (device_is_rmrr_locked(dev)) {
+		dev_warn(dev, "Device is ineligible for IOMMU domain attach due to platform RMRR requirement.  Contact your platform vendor.\n");
+		return -EPERM;
+	}
+
+	if (is_device_attach_aux_domain(dev, domain))
+		return -EPERM;
+
+	/* normally dev is not mapped */
+	if (unlikely(domain_context_mapped(dev))) {
+		struct dmar_domain *old_domain;
+
+		old_domain = find_domain(dev);
+		if (old_domain) {
+			rcu_read_lock();
+			dmar_remove_one_dev_info(old_domain, dev);
+			rcu_read_unlock();
+
+			if (!domain_type_is_vm_or_si(old_domain) &&
+			    list_empty(&old_domain->devices))
+				domain_exit(old_domain);
+		}
+	}
+
+	return __intel_iommu_attach_device(domain, dev);
+}
+
+static int intel_iommu_attach_device_aux(struct iommu_domain *domain,
+					 struct device *dev)
+{
+	return is_device_attach_aux_domain(dev, domain) ?
+			__intel_iommu_attach_device(domain, dev) : -EPERM;
 }
 
 static void intel_iommu_detach_device(struct iommu_domain *domain,
@@ -5080,6 +5220,12 @@ static void intel_iommu_detach_device(struct iommu_domain *domain,
 	dmar_remove_one_dev_info(to_dmar_domain(domain), dev);
 }
 
+static void intel_iommu_detach_device_aux(struct iommu_domain *domain,
+					  struct device *dev)
+{
+	domain_remove_dev_aux(to_dmar_domain(domain), dev);
+}
+
 static int intel_iommu_map(struct iommu_domain *domain,
 			   unsigned long iova, phys_addr_t hpa,
 			   size_t size, int iommu_prot)
@@ -5436,6 +5582,8 @@ const struct iommu_ops intel_iommu_ops = {
 	.domain_free		= intel_iommu_domain_free,
 	.attach_dev		= intel_iommu_attach_device,
 	.detach_dev		= intel_iommu_detach_device,
+	.attach_dev_aux		= intel_iommu_attach_device_aux,
+	.detach_dev_aux		= intel_iommu_detach_device_aux,
 	.map			= intel_iommu_map,
 	.unmap			= intel_iommu_unmap,
 	.iova_to_phys		= intel_iommu_iova_to_phys,
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 6b198e13e75e..678c7fb05e74 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -473,9 +473,11 @@ struct dmar_domain {
 					/* Domain ids per IOMMU. Use u16 since
 					 * domain ids are 16 bit wide according
 					 * to VT-d spec, section 9.3 */
+	unsigned int	auxd_refcnt;	/* Refcount of auxiliary attaching */
 
 	bool has_iotlb_device;
 	struct list_head devices;	/* all devices' list */
+	struct list_head auxd;		/* link to device's auxiliary list */
 	struct iova_domain iovad;	/* iova's that belong to this domain */
 
 	struct dma_pte	*pgd;		/* virtual address */
@@ -494,6 +496,11 @@ struct dmar_domain {
 					   2 == 1GiB, 3 == 512GiB, 4 == 1TiB */
 	u64		max_addr;	/* maximum mapped address */
 
+	int		default_pasid;	/*
+					 * The default pasid used for non-SVM
+					 * traffic on mediated devices.
+					 */
+
 	struct iommu_domain domain;	/* generic domain data structure for
 					   iommu core */
 };
@@ -543,6 +550,9 @@ struct device_domain_info {
 	struct list_head link;	/* link to domain siblings */
 	struct list_head global; /* link to global list */
 	struct list_head table;	/* link to pasid table */
+	struct list_head auxiliary_domains; /* auxiliary domains
+					     * attached to this device
+					     */
 	u8 bus;			/* PCI bus number */
 	u8 devfn;		/* PCI devfn number */
 	u16 pfsid;		/* SRIOV physical function source ID */
-- 
2.17.1


  parent reply	other threads:[~2018-11-05  7:37 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-11-05  7:34 [PATCH v4 0/8] vfio/mdev: IOMMU aware mediated device Lu Baolu
2018-11-05  7:34 ` [PATCH v4 1/8] iommu: Add APIs for multiple domains per device Lu Baolu
2018-11-23 10:50   ` Auger Eric
2018-11-26  2:04     ` Lu Baolu
2018-11-05  7:34 ` [PATCH v4 2/8] iommu/vt-d: Add multiple domains per device query Lu Baolu
2018-11-23 10:49   ` Auger Eric
2018-11-26  2:10     ` Lu Baolu
2018-11-05  7:34 ` [PATCH v4 3/8] iommu/vt-d: Enable/disable multiple domains per device Lu Baolu
2018-11-05  7:34 ` Lu Baolu [this message]
2018-11-23 10:49   ` [PATCH v4 4/8] iommu/vt-d: Attach/detach domains in auxiliary mode Auger Eric
2018-11-26  2:37     ` Lu Baolu
2018-11-05  7:34 ` [PATCH v4 5/8] iommu/vt-d: Return ID associated with an auxiliary domain Lu Baolu
2018-11-05  7:34 ` [PATCH v4 6/8] vfio/mdev: Add iommu place holders in mdev_device Lu Baolu
2018-11-05 14:51   ` Christoph Hellwig
2018-11-05 23:33     ` Lu Baolu
2018-11-06 23:53   ` Alex Williamson
2018-11-07  1:48     ` Lu Baolu
2018-11-15 21:31       ` Kirti Wankhede
2018-11-16  1:20         ` Lu Baolu
2018-11-16  8:57           ` Christoph Hellwig
2018-11-17  2:37             ` Lu Baolu
2018-11-20 20:52             ` Kirti Wankhede
2018-11-21  8:45               ` Christoph Hellwig
2018-12-03 16:27                 ` Kirti Wankhede
2018-11-05  7:34 ` [PATCH v4 7/8] vfio/type1: Add domain at(de)taching group helpers Lu Baolu
2018-11-23 14:13   ` Auger Eric
2018-11-26  3:05     ` Lu Baolu
2018-11-05  7:34 ` [PATCH v4 8/8] vfio/type1: Handle different mdev isolation type Lu Baolu
2018-11-23 14:23   ` Auger Eric
2018-11-26  3:09     ` Lu Baolu
2018-12-04  3:46 ` [PATCH v4 0/8] vfio/mdev: IOMMU aware mediated device Xu Zaibo
2018-12-04  6:20   ` Lu Baolu
2018-12-04  6:50     ` Xu Zaibo

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=20181105073408.21815-5-baolu.lu@linux.intel.com \
    --to=baolu.lu@linux.intel.com \
    --cc=alex.williamson@redhat.com \
    --cc=ashok.raj@intel.com \
    --cc=dwmw2@infradead.org \
    --cc=iommu@lists.linux-foundation.org \
    --cc=jacob.jun.pan@intel.com \
    --cc=jacob.jun.pan@linux.intel.com \
    --cc=jean-philippe.brucker@arm.com \
    --cc=joro@8bytes.org \
    --cc=kevin.tian@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=kwankhede@nvidia.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peterx@redhat.com \
    --cc=sanjay.k.kumar@intel.com \
    --cc=tiwei.bie@intel.com \
    --cc=xin.zeng@intel.com \
    --cc=yi.l.liu@intel.com \
    --cc=yi.y.sun@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 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).