[Qemu-devel] [PATCH qemu v5 04/12] spapr_pci_vfio: Enable multiple groups per container

[Alexey Kardashevskiy <aik@ozlabs.ru>]

This enables multiple IOMMU groups in one VFIO container which means
that multiple devices from different groups can share the same IOMMU
table (or tables if DDW).

This removes a group id from vfio_container_ioctl(). The kernel support
is required for this; if the host kernel does not have the support,
it will allow only one group per container. The PHB's "iommuid" property
is ignored.

This adds a sanity check that there is just one VFIO container per
PHB address space.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
 hw/ppc/spapr_pci_vfio.c | 17 ++++++-----------
 hw/vfio/common.c        | 28 ++++++++++++++--------------
 include/hw/vfio/vfio.h  |  2 +-
 3 files changed, 21 insertions(+), 26 deletions(-)

diff --git a/hw/ppc/spapr_pci_vfio.c b/hw/ppc/spapr_pci_vfio.c
index 99a1be5..f8b503e 100644
--- a/hw/ppc/spapr_pci_vfio.c
+++ b/hw/ppc/spapr_pci_vfio.c
@@ -35,12 +35,7 @@ static void spapr_phb_vfio_finish_realize(sPAPRPHBState *sphb, Error **errp)
     sPAPRTCETable *tcet;
     uint32_t liobn = svphb->phb.dma_liobn;
 
-    if (svphb->iommugroupid == -1) {
-        error_setg(errp, "Wrong IOMMU group ID %d", svphb->iommugroupid);
-        return;
-    }
-
-    ret = vfio_container_ioctl(&svphb->phb.iommu_as, svphb->iommugroupid,
+    ret = vfio_container_ioctl(&svphb->phb.iommu_as,
                                VFIO_CHECK_EXTENSION,
                                (void *) VFIO_SPAPR_TCE_IOMMU);
     if (ret != 1) {
@@ -49,7 +44,7 @@ static void spapr_phb_vfio_finish_realize(sPAPRPHBState *sphb, Error **errp)
         return;
     }
 
-    ret = vfio_container_ioctl(&svphb->phb.iommu_as, svphb->iommugroupid,
+    ret = vfio_container_ioctl(&sphb->iommu_as,
                                VFIO_IOMMU_SPAPR_TCE_GET_INFO, &info);
     if (ret) {
         error_setg_errno(errp, -ret,
@@ -116,7 +111,7 @@ static int spapr_phb_vfio_eeh_set_option(sPAPRPHBState *sphb,
         return RTAS_OUT_PARAM_ERROR;
     }
 
-    ret = vfio_container_ioctl(&svphb->phb.iommu_as, svphb->iommugroupid,
+    ret = vfio_container_ioctl(&svphb->phb.iommu_as,
                                VFIO_EEH_PE_OP, &op);
     if (ret < 0) {
         return RTAS_OUT_HW_ERROR;
@@ -132,7 +127,7 @@ static int spapr_phb_vfio_eeh_get_state(sPAPRPHBState *sphb, int *state)
     int ret;
 
     op.op = VFIO_EEH_PE_GET_STATE;
-    ret = vfio_container_ioctl(&svphb->phb.iommu_as, svphb->iommugroupid,
+    ret = vfio_container_ioctl(&svphb->phb.iommu_as,
                                VFIO_EEH_PE_OP, &op);
     if (ret < 0) {
         return RTAS_OUT_PARAM_ERROR;
@@ -162,7 +157,7 @@ static int spapr_phb_vfio_eeh_reset(sPAPRPHBState *sphb, int option)
         return RTAS_OUT_PARAM_ERROR;
     }
 
-    ret = vfio_container_ioctl(&svphb->phb.iommu_as, svphb->iommugroupid,
+    ret = vfio_container_ioctl(&svphb->phb.iommu_as,
                                VFIO_EEH_PE_OP, &op);
     if (ret < 0) {
         return RTAS_OUT_HW_ERROR;
@@ -178,7 +173,7 @@ static int spapr_phb_vfio_eeh_configure(sPAPRPHBState *sphb)
     int ret;
 
     op.op = VFIO_EEH_PE_CONFIGURE;
-    ret = vfio_container_ioctl(&svphb->phb.iommu_as, svphb->iommugroupid,
+    ret = vfio_container_ioctl(&svphb->phb.iommu_as,
                                VFIO_EEH_PE_OP, &op);
     if (ret < 0) {
         return RTAS_OUT_PARAM_ERROR;
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index b012620..99e1900 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -915,21 +915,23 @@ void vfio_put_base_device(VFIODevice *vbasedev)
     close(vbasedev->fd);
 }
 
-static int vfio_container_do_ioctl(AddressSpace *as, int32_t groupid,
+static int vfio_container_do_ioctl(AddressSpace *as,
                                    int req, void *param)
 {
-    VFIOGroup *group;
     VFIOContainer *container;
-    int ret = -1;
+    int ret;
+    VFIOAddressSpace *space;
 
-    group = vfio_get_group(groupid, as);
-    if (!group) {
-        error_report("vfio: group %d not registered", groupid);
-        return ret;
-    }
+    space = vfio_get_address_space(as);
+    container = QLIST_FIRST(&space->containers);
 
-    container = group->container;
-    if (group->container) {
+    if (!container) {
+        error_report("vfio: container is not set");
+        return -1;
+    } else if (QLIST_NEXT(container, next)) {
+        error_report("vfio: multiple containers per PHB are not supported");
+        return -1;
+    } else {
         ret = ioctl(container->fd, req, param);
         if (ret < 0) {
             error_report("vfio: failed to ioctl %d to container: ret=%d, %s",
@@ -937,12 +939,10 @@ static int vfio_container_do_ioctl(AddressSpace *as, int32_t groupid,
         }
     }
 
-    vfio_put_group(group);
-
     return ret;
 }
 
-int vfio_container_ioctl(AddressSpace *as, int32_t groupid,
+int vfio_container_ioctl(AddressSpace *as,
                          int req, void *param)
 {
     /* We allow only certain ioctls to the container */
@@ -957,5 +957,5 @@ int vfio_container_ioctl(AddressSpace *as, int32_t groupid,
         return -1;
     }
 
-    return vfio_container_do_ioctl(as, groupid, req, param);
+    return vfio_container_do_ioctl(as, req, param);
 }
diff --git a/include/hw/vfio/vfio.h b/include/hw/vfio/vfio.h
index 0b26cd8..76b5744 100644
--- a/include/hw/vfio/vfio.h
+++ b/include/hw/vfio/vfio.h
@@ -3,7 +3,7 @@
 
 #include "qemu/typedefs.h"
 
-extern int vfio_container_ioctl(AddressSpace *as, int32_t groupid,
+extern int vfio_container_ioctl(AddressSpace *as,
                                 int req, void *param);
 
 #endif
-- 
2.0.0