KVM Archive on lore.kernel.org
 help / color / Atom feed
From: Liu Yi L <yi.l.liu@intel.com>
To: alex.williamson@redhat.com, eric.auger@redhat.com,
	baolu.lu@linux.intel.com, joro@8bytes.org
Cc: kevin.tian@intel.com, jacob.jun.pan@linux.intel.com,
	ashok.raj@intel.com, yi.l.liu@intel.com, jun.j.tian@intel.com,
	yi.y.sun@intel.com, jean-philippe@linaro.org, peterx@redhat.com,
	hao.wu@intel.com, stefanha@gmail.com,
	iommu@lists.linux-foundation.org, kvm@vger.kernel.org,
	linux-kernel@vger.kernel.org
Subject: [PATCH v4 10/15] vfio/type1: Support binding guest page tables to PASID
Date: Sat,  4 Jul 2020 04:26:24 -0700
Message-ID: <1593861989-35920-11-git-send-email-yi.l.liu@intel.com> (raw)
In-Reply-To: <1593861989-35920-1-git-send-email-yi.l.liu@intel.com>

Nesting translation allows two-levels/stages page tables, with 1st level
for guest translations (e.g. GVA->GPA), 2nd level for host translations
(e.g. GPA->HPA). This patch adds interface for binding guest page tables
to a PASID. This PASID must have been allocated to user space before the
binding request.

Cc: Kevin Tian <kevin.tian@intel.com>
CC: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Eric Auger <eric.auger@redhat.com>
Cc: Jean-Philippe Brucker <jean-philippe@linaro.org>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.com>
Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
---
v3 -> v4:
*) address comments from Alex on v3

v2 -> v3:
*) use __iommu_sva_unbind_gpasid() for unbind call issued by VFIO
https://lore.kernel.org/linux-iommu/1592931837-58223-6-git-send-email-jacob.jun.pan@linux.intel.com/

v1 -> v2:
*) rename subject from "vfio/type1: Bind guest page tables to host"
*) remove VFIO_IOMMU_BIND, introduce VFIO_IOMMU_NESTING_OP to support bind/
   unbind guet page table
*) replaced vfio_iommu_for_each_dev() with a group level loop since this
   series enforces one group per container w/ nesting type as start.
*) rename vfio_bind/unbind_gpasid_fn() to vfio_dev_bind/unbind_gpasid_fn()
*) vfio_dev_unbind_gpasid() always successful
*) use vfio_mm->pasid_lock to avoid race between PASID free and page table
   bind/unbind
---
 drivers/vfio/vfio_iommu_type1.c | 166 ++++++++++++++++++++++++++++++++++++++++
 drivers/vfio/vfio_pasid.c       |  30 ++++++++
 include/linux/vfio.h            |  20 +++++
 include/uapi/linux/vfio.h       |  30 ++++++++
 4 files changed, 246 insertions(+)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 29726ca..6de0b8e 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -149,6 +149,30 @@ struct vfio_regions {
 #define DIRTY_BITMAP_PAGES_MAX	 ((u64)INT_MAX)
 #define DIRTY_BITMAP_SIZE_MAX	 DIRTY_BITMAP_BYTES(DIRTY_BITMAP_PAGES_MAX)
 
+struct domain_capsule {
+	struct vfio_group *group;
+	struct iommu_domain *domain;
+	void *data;
+};
+
+/* iommu->lock must be held */
+static struct vfio_group *vfio_find_nesting_group(struct vfio_iommu *iommu)
+{
+	struct vfio_domain *d;
+	struct vfio_group *group = NULL;
+
+	if (!iommu->nesting_info)
+		return NULL;
+
+	/* only support singleton container with nesting type */
+	list_for_each_entry(d, &iommu->domain_list, next) {
+		list_for_each_entry(group, &d->group_list, next) {
+			break;
+		}
+	}
+	return group;
+}
+
 static int put_pfn(unsigned long pfn, int prot);
 
 static struct vfio_group *vfio_iommu_find_iommu_group(struct vfio_iommu *iommu,
@@ -2352,6 +2376,48 @@ static int vfio_iommu_resv_refresh(struct vfio_iommu *iommu,
 	return ret;
 }
 
+static int vfio_dev_bind_gpasid_fn(struct device *dev, void *data)
+{
+	struct domain_capsule *dc = (struct domain_capsule *)data;
+	unsigned long arg = *(unsigned long *) dc->data;
+
+	return iommu_sva_bind_gpasid(dc->domain, dev, (void __user *) arg);
+}
+
+static int vfio_dev_unbind_gpasid_fn(struct device *dev, void *data)
+{
+	struct domain_capsule *dc = (struct domain_capsule *)data;
+	unsigned long arg = *(unsigned long *) dc->data;
+
+	iommu_sva_unbind_gpasid(dc->domain, dev, (void __user *) arg);
+	return 0;
+}
+
+static int __vfio_dev_unbind_gpasid_fn(struct device *dev, void *data)
+{
+	struct domain_capsule *dc = (struct domain_capsule *)data;
+	struct iommu_gpasid_bind_data *unbind_data =
+				(struct iommu_gpasid_bind_data *) dc->data;
+
+	__iommu_sva_unbind_gpasid(dc->domain, dev, unbind_data);
+	return 0;
+}
+
+static void vfio_group_unbind_gpasid_fn(ioasid_t pasid, void *data)
+{
+	struct domain_capsule *dc = (struct domain_capsule *) data;
+	struct iommu_gpasid_bind_data unbind_data;
+
+	unbind_data.argsz = offsetof(struct iommu_gpasid_bind_data, vendor);
+	unbind_data.flags = 0;
+	unbind_data.hpasid = pasid;
+
+	dc->data = &unbind_data;
+
+	iommu_group_for_each_dev(dc->group->iommu_group,
+				 dc, __vfio_dev_unbind_gpasid_fn);
+}
+
 static void vfio_iommu_type1_detach_group(void *iommu_data,
 					  struct iommu_group *iommu_group)
 {
@@ -2395,6 +2461,21 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 		if (!group)
 			continue;
 
+		if (iommu->nesting_info && iommu->vmm &&
+		    (iommu->nesting_info->features &
+					IOMMU_NESTING_FEAT_BIND_PGTBL)) {
+			struct domain_capsule dc = { .group = group,
+						     .domain = domain->domain,
+						     .data = NULL };
+
+			/*
+			 * Unbind page tables bound with system wide PASIDs
+			 * which are allocated to user space.
+			 */
+			vfio_mm_for_each_pasid(iommu->vmm, &dc,
+					       vfio_group_unbind_gpasid_fn);
+		}
+
 		vfio_iommu_detach_group(domain, group);
 		update_dirty_scope = !group->pinned_page_dirty_scope;
 		list_del(&group->next);
@@ -2942,6 +3023,89 @@ static int vfio_iommu_type1_pasid_request(struct vfio_iommu *iommu,
 	}
 }
 
+static long vfio_iommu_handle_pgtbl_op(struct vfio_iommu *iommu,
+				       bool is_bind, unsigned long arg)
+{
+	struct iommu_nesting_info *info;
+	struct domain_capsule dc = { .data = &arg };
+	struct vfio_group *group;
+	struct vfio_domain *domain;
+	int ret;
+
+	mutex_lock(&iommu->lock);
+
+	info = iommu->nesting_info;
+	if (!info || !(info->features & IOMMU_NESTING_FEAT_BIND_PGTBL)) {
+		ret = -EOPNOTSUPP;
+		goto out_unlock_iommu;
+	}
+
+	if (!iommu->vmm) {
+		ret = -EINVAL;
+		goto out_unlock_iommu;
+	}
+
+	group = vfio_find_nesting_group(iommu);
+	if (!group) {
+		ret = -EINVAL;
+		goto out_unlock_iommu;
+	}
+
+	domain = list_first_entry(&iommu->domain_list,
+				      struct vfio_domain, next);
+	dc.group = group;
+	dc.domain = domain->domain;
+
+	/* Avoid race with other containers within the same process */
+	vfio_mm_pasid_lock(iommu->vmm);
+
+	if (is_bind) {
+		ret = iommu_group_for_each_dev(group->iommu_group, &dc,
+					       vfio_dev_bind_gpasid_fn);
+		if (ret)
+			iommu_group_for_each_dev(group->iommu_group, &dc,
+						 vfio_dev_unbind_gpasid_fn);
+	} else {
+		iommu_group_for_each_dev(group->iommu_group,
+					 &dc, vfio_dev_unbind_gpasid_fn);
+		ret = 0;
+	}
+
+	vfio_mm_pasid_unlock(iommu->vmm);
+out_unlock_iommu:
+	mutex_unlock(&iommu->lock);
+	return ret;
+}
+
+static long vfio_iommu_type1_nesting_op(struct vfio_iommu *iommu,
+					unsigned long arg)
+{
+	struct vfio_iommu_type1_nesting_op hdr;
+	unsigned int minsz;
+	int ret;
+
+	minsz = offsetofend(struct vfio_iommu_type1_nesting_op, flags);
+
+	if (copy_from_user(&hdr, (void __user *)arg, minsz))
+		return -EFAULT;
+
+	if (hdr.argsz < minsz || hdr.flags & ~VFIO_NESTING_OP_MASK)
+		return -EINVAL;
+
+	switch (hdr.flags & VFIO_NESTING_OP_MASK) {
+	case VFIO_IOMMU_NESTING_OP_BIND_PGTBL:
+		ret = vfio_iommu_handle_pgtbl_op(iommu, true, arg + minsz);
+		break;
+	case VFIO_IOMMU_NESTING_OP_UNBIND_PGTBL:
+		ret = vfio_iommu_handle_pgtbl_op(iommu, false, arg + minsz);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
 static long vfio_iommu_type1_ioctl(void *iommu_data,
 				   unsigned int cmd, unsigned long arg)
 {
@@ -2960,6 +3124,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 		return vfio_iommu_type1_dirty_pages(iommu, arg);
 	case VFIO_IOMMU_PASID_REQUEST:
 		return vfio_iommu_type1_pasid_request(iommu, arg);
+	case VFIO_IOMMU_NESTING_OP:
+		return vfio_iommu_type1_nesting_op(iommu, arg);
 	}
 
 	return -ENOTTY;
diff --git a/drivers/vfio/vfio_pasid.c b/drivers/vfio/vfio_pasid.c
index 6f907db..bbfbea8 100644
--- a/drivers/vfio/vfio_pasid.c
+++ b/drivers/vfio/vfio_pasid.c
@@ -29,6 +29,7 @@ struct vfio_mm_token {
 struct vfio_mm {
 	struct kref		kref;
 	int			ioasid_sid;
+	struct mutex		pasid_lock;
 	struct list_head	next;
 	struct vfio_mm_token	token;
 };
@@ -98,6 +99,7 @@ struct vfio_mm *vfio_mm_get_from_task(struct task_struct *task)
 
 	kref_init(&vmm->kref);
 	vmm->token.val = val;
+	mutex_init(&vmm->pasid_lock);
 
 	list_add(&vmm->next, &vfio_pasid.vfio_mm_list);
 out:
@@ -135,12 +137,40 @@ void vfio_pasid_free_range(struct vfio_mm *vmm,
 	 * IOASID core will notify PASID users (e.g. IOMMU driver) to
 	 * teardown necessary structures depending on the to-be-freed
 	 * PASID.
+	 * Hold pasid_lock to avoid race with PASID usages like bind/
+	 * unbind page tables to requested PASID.
 	 */
+	mutex_lock(&vmm->pasid_lock);
 	for (; pasid <= max; pasid++)
 		ioasid_free(pasid);
+	mutex_unlock(&vmm->pasid_lock);
 }
 EXPORT_SYMBOL_GPL(vfio_pasid_free_range);
 
+int vfio_mm_for_each_pasid(struct vfio_mm *vmm, void *data,
+			   void (*fn)(ioasid_t id, void *data))
+{
+	int ret;
+
+	mutex_lock(&vmm->pasid_lock);
+	ret = ioasid_set_for_each_ioasid(vmm->ioasid_sid, fn, data);
+	mutex_unlock(&vmm->pasid_lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(vfio_mm_for_each_pasid);
+
+void vfio_mm_pasid_lock(struct vfio_mm *vmm)
+{
+	mutex_lock(&vmm->pasid_lock);
+}
+EXPORT_SYMBOL_GPL(vfio_mm_pasid_lock);
+
+void vfio_mm_pasid_unlock(struct vfio_mm *vmm)
+{
+	mutex_unlock(&vmm->pasid_lock);
+}
+EXPORT_SYMBOL_GPL(vfio_mm_pasid_unlock);
+
 static int __init vfio_pasid_init(void)
 {
 	mutex_init(&vfio_pasid.vfio_mm_lock);
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 35c922a..8052f1c2 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -105,6 +105,11 @@ int vfio_mm_ioasid_sid(struct vfio_mm *vmm);
 extern int vfio_pasid_alloc(struct vfio_mm *vmm, int min, int max);
 extern void vfio_pasid_free_range(struct vfio_mm *vmm,
 					ioasid_t min, ioasid_t max);
+extern int vfio_mm_for_each_pasid(struct vfio_mm *vmm, void *data,
+				  void (*fn)(ioasid_t id, void *data));
+extern void vfio_mm_pasid_lock(struct vfio_mm *vmm);
+extern void vfio_mm_pasid_unlock(struct vfio_mm *vmm);
+
 #else
 static inline struct vfio_mm *vfio_mm_get_from_task(struct task_struct *task)
 {
@@ -129,6 +134,21 @@ static inline void vfio_pasid_free_range(struct vfio_mm *vmm,
 					  ioasid_t min, ioasid_t max)
 {
 }
+
+static inline int vfio_mm_for_each_pasid(struct vfio_mm *vmm, void *data,
+					 void (*fn)(ioasid_t id, void *data))
+{
+	return -ENOTTY;
+}
+
+static inline void vfio_mm_pasid_lock(struct vfio_mm *vmm)
+{
+}
+
+static inline void vfio_mm_pasid_unlock(struct vfio_mm *vmm)
+{
+}
+
 #endif /* CONFIG_VFIO_PASID */
 
 /*
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index fe267b8e..095a52a 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -1205,6 +1205,36 @@ struct vfio_iommu_type1_pasid_request {
 
 #define VFIO_IOMMU_PASID_REQUEST	_IO(VFIO_TYPE, VFIO_BASE + 18)
 
+/**
+ * VFIO_IOMMU_NESTING_OP - _IOW(VFIO_TYPE, VFIO_BASE + 19,
+ *				struct vfio_iommu_type1_nesting_op)
+ *
+ * This interface allows user space to utilize the nesting IOMMU
+ * capabilities as reported through VFIO_IOMMU_GET_INFO.
+ *
+ * @data[] types defined for each op:
+ * +=================+===============================================+
+ * | NESTING OP      |      @data[]                                  |
+ * +=================+===============================================+
+ * | BIND_PGTBL      |      struct iommu_gpasid_bind_data            |
+ * +-----------------+-----------------------------------------------+
+ * | UNBIND_PGTBL    |      struct iommu_gpasid_bind_data            |
+ * +-----------------+-----------------------------------------------+
+ *
+ * returns: 0 on success, -errno on failure.
+ */
+struct vfio_iommu_type1_nesting_op {
+	__u32	argsz;
+	__u32	flags;
+#define VFIO_NESTING_OP_MASK	(0xffff) /* lower 16-bits for op */
+	__u8	data[];
+};
+
+#define VFIO_IOMMU_NESTING_OP_BIND_PGTBL	(0)
+#define VFIO_IOMMU_NESTING_OP_UNBIND_PGTBL	(1)
+
+#define VFIO_IOMMU_NESTING_OP		_IO(VFIO_TYPE, VFIO_BASE + 19)
+
 /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
 
 /*
-- 
2.7.4


  parent reply index

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-04 11:26 [PATCH v4 00/15] vfio: expose virtual Shared Virtual Addressing to VMs Liu Yi L
2020-07-04 11:26 ` [PATCH v4 01/15] vfio/type1: Refactor vfio_iommu_type1_ioctl() Liu Yi L
2020-07-06  9:34   ` Auger Eric
2020-07-06 12:27     ` Liu, Yi L
2020-07-06 12:55       ` Auger Eric
2020-07-06 13:00         ` Liu, Yi L
2020-07-04 11:26 ` [PATCH v4 02/15] iommu: Report domain nesting info Liu Yi L
2020-07-06  9:34   ` Auger Eric
2020-07-06 12:20     ` Liu, Yi L
2020-07-06 13:00       ` Auger Eric
2020-07-06 13:17         ` Liu, Yi L
2020-07-04 11:26 ` [PATCH v4 03/15] iommu/smmu: Report empty " Liu Yi L
2020-07-06 10:37   ` Auger Eric
2020-07-06 12:46     ` Liu, Yi L
2020-07-06 13:21       ` Auger Eric
2020-07-06 13:26         ` Liu, Yi L
2020-07-04 11:26 ` [PATCH v4 04/15] vfio/type1: Report iommu nesting info to userspace Liu Yi L
2020-07-06 10:37   ` Auger Eric
2020-07-06 13:10     ` Liu, Yi L
2020-07-06 13:45       ` Auger Eric
2020-07-07  9:31         ` Liu, Yi L
2020-07-08  8:08           ` Liu, Yi L
2020-07-08 19:29             ` Alex Williamson
2020-07-09  0:25               ` Liu, Yi L
2020-07-06 14:06   ` Auger Eric
2020-07-07  9:34     ` Liu, Yi L
2020-07-04 11:26 ` [PATCH v4 05/15] vfio: Add PASID allocation/free support Liu Yi L
2020-07-06 14:52   ` Auger Eric
2020-07-07  9:45     ` Liu, Yi L
2020-07-04 11:26 ` [PATCH v4 06/15] iommu/vt-d: Support setting ioasid set to domain Liu Yi L
2020-07-06 14:52   ` Auger Eric
2020-07-07  9:37     ` Liu, Yi L
2020-07-04 11:26 ` [PATCH v4 07/15] vfio/type1: Add VFIO_IOMMU_PASID_REQUEST (alloc/free) Liu Yi L
2020-07-06 15:17   ` Auger Eric
2020-07-07  9:51     ` Liu, Yi L
2020-07-04 11:26 ` [PATCH v4 08/15] iommu: Pass domain to sva_unbind_gpasid() Liu Yi L
2020-07-04 11:26 ` [PATCH v4 09/15] iommu/vt-d: Check ownership for PASIDs from user-space Liu Yi L
2020-07-04 11:26 ` Liu Yi L [this message]
2020-07-04 11:26 ` [PATCH v4 11/15] vfio/type1: Allow invalidating first-level/stage IOMMU cache Liu Yi L
2020-07-04 11:26 ` [PATCH v4 12/15] vfio/type1: Add vSVA support for IOMMU-backed mdevs Liu Yi L
2020-07-04 11:26 ` [PATCH v4 13/15] vfio/pci: Expose PCIe PASID capability to guest Liu Yi L
2020-07-04 11:26 ` [PATCH v4 14/15] vfio: Document dual stage control Liu Yi L
2020-07-04 11:26 ` [PATCH v4 15/15] iommu/vt-d: Support reporting nesting capability info Liu Yi L

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=1593861989-35920-11-git-send-email-yi.l.liu@intel.com \
    --to=yi.l.liu@intel.com \
    --cc=alex.williamson@redhat.com \
    --cc=ashok.raj@intel.com \
    --cc=baolu.lu@linux.intel.com \
    --cc=eric.auger@redhat.com \
    --cc=hao.wu@intel.com \
    --cc=iommu@lists.linux-foundation.org \
    --cc=jacob.jun.pan@linux.intel.com \
    --cc=jean-philippe@linaro.org \
    --cc=joro@8bytes.org \
    --cc=jun.j.tian@intel.com \
    --cc=kevin.tian@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peterx@redhat.com \
    --cc=stefanha@gmail.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

KVM Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/kvm/0 kvm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 kvm kvm/ https://lore.kernel.org/kvm \
		kvm@vger.kernel.org
	public-inbox-index kvm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.kvm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git