Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Eric Auger <eric.auger@redhat.com>
To:     eric.auger.pro@gmail.com, eric.auger@redhat.com,
        iommu@lists.linux-foundation.org, linux-kernel@vger.kernel.org,
        kvm@vger.kernel.org, kvmarm@lists.cs.columbia.edu, will@kernel.org,
        joro@8bytes.org, maz@kernel.org, robin.murphy@arm.com
Cc:     jean-philippe@linaro.org, zhangfei.gao@linaro.org,
        shameerali.kolothum.thodi@huawei.com, alex.williamson@redhat.com,
        jacob.jun.pan@linux.intel.com, yi.l.liu@intel.com,
        peter.maydell@linaro.org, zhangfei.gao@gmail.com, tn@semihalf.com,
        zhangfei.gao@foxmail.com, bbhushan2@marvell.com
Subject: [PATCH v11 02/13] iommu: Introduce bind/unbind_guest_msi
Date:   Tue, 14 Apr 2020 17:05:56 +0200
Message-Id: <20200414150607.28488-3-eric.auger@redhat.com>
In-Reply-To: <20200414150607.28488-1-eric.auger@redhat.com>
References: <20200414150607.28488-1-eric.auger@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: quoted-printable
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On ARM, MSI are translated by the SMMU. An IOVA is allocated
for each MSI doorbell. If both the host and the guest are exposed
with SMMUs, we end up with 2 different IOVAs allocated by each.
guest allocates an IOVA (gIOVA) to map onto the guest MSI
doorbell (gDB). The Host allocates another IOVA (hIOVA) to map
onto the physical doorbell (hDB).

So we end up with 2 untied mappings:
         S1            S2
gIOVA    ->    gDB
              hIOVA    ->    hDB

Currently the PCI device is programmed by the host with hIOVA
as MSI doorbell. So this does not work.

This patch introduces an API to pass gIOVA/gDB to the host so
that gIOVA can be reused by the host instead of re-allocating
a new IOVA. So the goal is to create the following nested mapping:

         S1            S2
gIOVA    ->    gDB     ->    hDB

and program the PCI device with gIOVA MSI doorbell.

In case we have several devices attached to this nested domain
(devices belonging to the same group), they cannot be isolated
on guest side either. So they should also end up in the same domain
on guest side. We will enforce that all the devices attached to
the host iommu domain use the same physical doorbell and similarly
a single virtual doorbell mapping gets registered (1 single
virtual doorbell is used on guest as well).

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

---
v7 -> v8:
- dummy iommu_unbind_guest_msi turned into a void function

v6 -> v7:
- remove the device handle parameter.
- Add comments saying there can only be a single MSI binding
  registered per iommu_domain
v5 -> v6:
-fix compile issue when IOMMU_API is not set

v3 -> v4:
- add unbind

v2 -> v3:
- add a struct device handle
---
 drivers/iommu/iommu.c | 37 +++++++++++++++++++++++++++++++++++++
 include/linux/iommu.h | 20 ++++++++++++++++++++
 2 files changed, 57 insertions(+)

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index b71ad56f8c99..16068bd4d47b 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1756,6 +1756,43 @@ static void __iommu_detach_device(struct iommu_dom=
ain *domain,
 	trace_detach_device_from_domain(dev);
 }
=20
+/**
+ * iommu_bind_guest_msi - Passes the stage1 GIOVA/GPA mapping of a
+ * virtual doorbell
+ *
+ * @domain: iommu domain the stage 1 mapping will be attached to
+ * @iova: iova allocated by the guest
+ * @gpa: guest physical address of the virtual doorbell
+ * @size: granule size used for the mapping
+ *
+ * The associated IOVA can be reused by the host to create a nested
+ * stage2 binding mapping translating into the physical doorbell used
+ * by the devices attached to the domain.
+ *
+ * All devices within the domain must share the same physical doorbell.
+ * A single MSI GIOVA/GPA mapping can be attached to an iommu_domain.
+ */
+
+int iommu_bind_guest_msi(struct iommu_domain *domain,
+			 dma_addr_t giova, phys_addr_t gpa, size_t size)
+{
+	if (unlikely(!domain->ops->bind_guest_msi))
+		return -ENODEV;
+
+	return domain->ops->bind_guest_msi(domain, giova, gpa, size);
+}
+EXPORT_SYMBOL_GPL(iommu_bind_guest_msi);
+
+void iommu_unbind_guest_msi(struct iommu_domain *domain,
+			    dma_addr_t iova)
+{
+	if (unlikely(!domain->ops->unbind_guest_msi))
+		return;
+
+	domain->ops->unbind_guest_msi(domain, iova);
+}
+EXPORT_SYMBOL_GPL(iommu_unbind_guest_msi);
+
 void iommu_detach_device(struct iommu_domain *domain, struct device *dev=
)
 {
 	struct iommu_group *group;
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 3e1057c3585a..31b3c74f5fe2 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -250,6 +250,8 @@ struct iommu_iotlb_gather {
  * @sva_unbind_gpasid: unbind guest pasid and mm
  * @attach_pasid_table: attach a pasid table
  * @detach_pasid_table: detach the pasid table
+ * @bind_guest_msi: provides a stage1 giova/gpa MSI doorbell mapping
+ * @unbind_guest_msi: withdraw a stage1 giova/gpa MSI doorbell mapping
  * @pgsize_bitmap: bitmap of all possible supported page sizes
  * @owner: Driver module providing these ops
  */
@@ -323,6 +325,10 @@ struct iommu_ops {
=20
 	int (*sva_unbind_gpasid)(struct device *dev, int pasid);
=20
+	int (*bind_guest_msi)(struct iommu_domain *domain,
+			      dma_addr_t giova, phys_addr_t gpa, size_t size);
+	void (*unbind_guest_msi)(struct iommu_domain *domain, dma_addr_t giova)=
;
+
 	unsigned long pgsize_bitmap;
 	struct module *owner;
 };
@@ -454,6 +460,10 @@ extern int iommu_sva_unbind_gpasid(struct iommu_doma=
in *domain,
 extern int iommu_attach_pasid_table(struct iommu_domain *domain,
 				    struct iommu_pasid_table_config *cfg);
 extern void iommu_detach_pasid_table(struct iommu_domain *domain);
+extern int iommu_bind_guest_msi(struct iommu_domain *domain,
+				dma_addr_t giova, phys_addr_t gpa, size_t size);
+extern void iommu_unbind_guest_msi(struct iommu_domain *domain,
+				   dma_addr_t giova);
 extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev)=
;
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
@@ -1110,6 +1120,16 @@ static inline struct iommu_fwspec *dev_iommu_fwspe=
c_get(struct device *dev)
 {
 	return NULL;
 }
+
+static inline
+int iommu_bind_guest_msi(struct iommu_domain *domain,
+			 dma_addr_t giova, phys_addr_t gpa, size_t size)
+{
+	return -ENODEV;
+}
+static inline
+void iommu_unbind_guest_msi(struct iommu_domain *domain, dma_addr_t giov=
a) {}
+
 #endif /* CONFIG_IOMMU_API */
=20
 #ifdef CONFIG_IOMMU_DEBUGFS
--=20
2.20.1