[PATCH v12 03/13] vfio: VFIO_IOMMU_SET_MSI_BINDING

[Eric Auger]

This patch adds the VFIO_IOMMU_SET_MSI_BINDING ioctl which aim
to (un)register the guest MSI binding to the host. This latter
then can use those stage 1 bindings to build a nested stage
binding targeting the physical MSIs.

Signed-off-by: Eric Auger <eric.auger@xxxxxxxxxx>

---

v11 -> v12:
- Share VFIO_BASE + 20 with VFIO_IOMMU_SPAPR_TCE_REMOVE
- rework returned values

v10 -> v11:
- renamed ustruct into msi_binding
- return 0 on unbind

v8 -> v9:
- merge VFIO_IOMMU_BIND_MSI/VFIO_IOMMU_UNBIND_MSI into a single
  VFIO_IOMMU_SET_MSI_BINDING ioctl
- ioctl id changed

v6 -> v7:
- removed the dev arg

v3 -> v4:
- add UNBIND
- unwind on BIND error

v2 -> v3:
- adapt to new proto of bind_guest_msi
- directly use vfio_iommu_for_each_dev

v1 -> v2:
- s/vfio_iommu_type1_guest_msi_binding/vfio_iommu_type1_bind_guest_msi
---
 drivers/vfio/vfio_iommu_type1.c | 62 +++++++++++++++++++++++++++++++++
 include/uapi/linux/vfio.h       | 20 +++++++++++
 2 files changed, 82 insertions(+)

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index b4057ce809b0..0e6af4fe8c3d 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -2655,6 +2655,41 @@ static int vfio_cache_inv_fn(struct device *dev, void *data)
 	return iommu_uapi_cache_invalidate(dc->domain, dev, (void __user *)arg);
 }
 
+static int
+vfio_bind_msi(struct vfio_iommu *iommu,
+	      dma_addr_t giova, phys_addr_t gpa, size_t size)
+{
+	struct vfio_domain *d;
+	int ret = 0;
+
+	mutex_lock(&iommu->lock);
+
+	list_for_each_entry(d, &iommu->domain_list, next) {
+		ret = iommu_bind_guest_msi(d->domain, giova, gpa, size);
+		if (ret)
+			goto unwind;
+	}
+	goto unlock;
+unwind:
+	list_for_each_entry_continue_reverse(d, &iommu->domain_list, next) {
+		iommu_unbind_guest_msi(d->domain, giova);
+	}
+unlock:
+	mutex_unlock(&iommu->lock);
+	return ret;
+}
+
+static void
+vfio_unbind_msi(struct vfio_iommu *iommu, dma_addr_t giova)
+{
+	struct vfio_domain *d;
+
+	mutex_lock(&iommu->lock);
+	list_for_each_entry(d, &iommu->domain_list, next)
+		iommu_unbind_guest_msi(d->domain, giova);
+	mutex_unlock(&iommu->lock);
+}
+
 static int vfio_iommu_migration_build_caps(struct vfio_iommu *iommu,
 					   struct vfio_info_cap *caps)
 {
@@ -2859,6 +2894,31 @@ static int vfio_iommu_type1_cache_invalidate(struct vfio_iommu *iommu,
 	return ret;
 }
 
+static int vfio_iommu_type1_set_msi_binding(struct vfio_iommu *iommu,
+					    unsigned long arg)
+{
+	struct vfio_iommu_type1_set_msi_binding msi_binding;
+	unsigned long minsz;
+
+	minsz = offsetofend(struct vfio_iommu_type1_set_msi_binding,
+			    size);
+
+	if (copy_from_user(&msi_binding, (void __user *)arg, minsz))
+		return -EFAULT;
+
+	if (msi_binding.argsz < minsz)
+		return -EINVAL;
+
+	if (msi_binding.flags == VFIO_IOMMU_UNBIND_MSI) {
+		vfio_unbind_msi(iommu, msi_binding.iova);
+		return 0;
+	} else if (msi_binding.flags == VFIO_IOMMU_BIND_MSI) {
+		return vfio_bind_msi(iommu, msi_binding.iova,
+				     msi_binding.gpa, msi_binding.size);
+	}
+	return -EINVAL;
+}
+
 static int vfio_iommu_type1_dirty_pages(struct vfio_iommu *iommu,
 					unsigned long arg)
 {
@@ -2983,6 +3043,8 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 		return vfio_iommu_type1_set_pasid_table(iommu, arg);
 	case VFIO_IOMMU_CACHE_INVALIDATE:
 		return vfio_iommu_type1_cache_invalidate(iommu, arg);
+	case VFIO_IOMMU_SET_MSI_BINDING:
+		return vfio_iommu_type1_set_msi_binding(iommu, arg);
 	default:
 		return -ENOTTY;
 	}
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index ee6747ff8006..4c82e8f21618 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -1213,6 +1213,26 @@ struct vfio_iommu_type1_cache_invalidate {
 };
 #define VFIO_IOMMU_CACHE_INVALIDATE      _IO(VFIO_TYPE, VFIO_BASE + 19)
 
+/**
+ * VFIO_IOMMU_SET_MSI_BINDING - _IOWR(VFIO_TYPE, VFIO_BASE + 20,
+ *			struct vfio_iommu_type1_set_msi_binding)
+ *
+ * Pass a stage 1 MSI doorbell mapping to the host so that this
+ * latter can build a nested stage2 mapping. Or conversely tear
+ * down a previously bound stage 1 MSI binding.
+ */
+struct vfio_iommu_type1_set_msi_binding {
+	__u32   argsz;
+	__u32   flags;
+#define VFIO_IOMMU_BIND_MSI	(1 << 0)
+#define VFIO_IOMMU_UNBIND_MSI	(1 << 1)
+	__u64	iova;	/* MSI guest IOVA */
+	/* Fields below are used on BIND */
+	__u64	gpa;	/* MSI guest physical address */
+	__u64	size;	/* size of stage1 mapping (bytes) */
+};
+#define VFIO_IOMMU_SET_MSI_BINDING      _IO(VFIO_TYPE, VFIO_BASE + 20)
+
 /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
 
 /*
-- 
2.26.2