[Qemu-devel] [RFC v4 13/29] pci: introduce PCIPASIDOps to PCIDevice

[Eric Auger]

From: Liu Yi L <address@hidden>

This patch introduces PCIPASIDOps for IOMMU related operations.

https://lists.gnu.org/archive/html/qemu-devel/2018-03/msg00078.html
https://lists.gnu.org/archive/html/qemu-devel/2018-03/msg00940.html

So far, to setup virt-SVA for assigned SVA capable device, needs to
configure host translation structures for specific pasid. (e.g. bind
guest page table to host and enable nested translation in host).
Besides, vIOMMU emulator needs to forward guest's cache invalidation
to host since host nested translation is enabled. e.g. on VT-d, guest
owns 1st level translation table, thus cache invalidation for 1st
level should be propagated to host.

This patch adds two functions: alloc_pasid and free_pasid to support
guest pasid allocation and free. The implementations of the callbacks
would be device passthru modules. Like vfio.

Cc: Kevin Tian <address@hidden>
Cc: Jacob Pan <address@hidden>
Cc: Peter Xu <address@hidden>
Cc: Eric Auger <address@hidden>
Cc: Yi Sun <address@hidden>
Cc: David Gibson <address@hidden>
Signed-off-by: Liu Yi L <address@hidden>
Signed-off-by: Yi Sun <address@hidden>
---
 hw/pci/pci.c             | 34 ++++++++++++++++++++++++++++++++++
 include/hw/iommu/iommu.h |  3 +++
 include/hw/pci/pci.h     | 11 +++++++++++
 3 files changed, 48 insertions(+)

diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index 8076a80ab3..43c0cef2f6 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -2626,6 +2626,40 @@ void pci_setup_iommu(PCIBus *bus, PCIIOMMUFunc fn, void 
*opaque)
     bus->iommu_opaque = opaque;
 }
 
+void pci_setup_pasid_ops(PCIDevice *dev, PCIPASIDOps *ops)
+{
+    assert(ops && !dev->pasid_ops);
+    dev->pasid_ops = ops;
+}
+
+bool pci_device_is_pasid_ops_set(PCIBus *bus, int32_t devfn)
+{
+    PCIDevice *dev;
+
+    if (!bus) {
+        return false;
+    }
+
+    dev = bus->devices[devfn];
+    return !!(dev && dev->pasid_ops);
+}
+
+int pci_device_set_pasid_table(PCIBus *bus, int32_t devfn,
+                               IOMMUConfig *config)
+{
+    PCIDevice *dev;
+
+    if (!bus) {
+        return -EINVAL;
+    }
+
+    dev = bus->devices[devfn];
+    if (dev && dev->pasid_ops && dev->pasid_ops->set_pasid_table) {
+        return dev->pasid_ops->set_pasid_table(bus, devfn, config);
+    }
+    return -ENOENT;
+}
+
 static void pci_dev_get_w64(PCIBus *b, PCIDevice *dev, void *opaque)
 {
     Range *range = opaque;
diff --git a/include/hw/iommu/iommu.h b/include/hw/iommu/iommu.h
index 9e60ece160..12092bda7b 100644
--- a/include/hw/iommu/iommu.h
+++ b/include/hw/iommu/iommu.h
@@ -12,6 +12,9 @@
 
 #ifndef QEMU_HW_IOMMU_IOMMU_H
 #define QEMU_HW_IOMMU_IOMMU_H
+#ifdef __linux__
+#include <linux/iommu.h>
+#endif
 
 typedef struct IOMMUConfig {
     union {
diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
index aaf1b9f70d..84be2847a5 100644
--- a/include/hw/pci/pci.h
+++ b/include/hw/pci/pci.h
@@ -9,6 +9,7 @@
 #include "hw/isa/isa.h"
 
 #include "hw/pci/pcie.h"
+#include "hw/iommu/iommu.h"
 
 extern bool pci_available;
 
@@ -263,6 +264,11 @@ struct PCIReqIDCache {
 };
 typedef struct PCIReqIDCache PCIReqIDCache;
 
+typedef struct PCIPASIDOps PCIPASIDOps;
+struct PCIPASIDOps {
+    int (*set_pasid_table)(PCIBus *bus, int32_t devfn, IOMMUConfig *config);
+};
+
 struct PCIDevice {
     DeviceState qdev;
 
@@ -352,6 +358,7 @@ struct PCIDevice {
     MSIVectorUseNotifier msix_vector_use_notifier;
     MSIVectorReleaseNotifier msix_vector_release_notifier;
     MSIVectorPollNotifier msix_vector_poll_notifier;
+    PCIPASIDOps *pasid_ops;
 };
 
 void pci_register_bar(PCIDevice *pci_dev, int region_num,
@@ -485,6 +492,10 @@ typedef AddressSpace *(*PCIIOMMUFunc)(PCIBus *, void *, 
int);
 AddressSpace *pci_device_iommu_address_space(PCIDevice *dev);
 void pci_setup_iommu(PCIBus *bus, PCIIOMMUFunc fn, void *opaque);
 
+void pci_setup_pasid_ops(PCIDevice *dev, PCIPASIDOps *ops);
+bool pci_device_is_pasid_ops_set(PCIBus *bus, int32_t devfn);
+int pci_device_set_pasid_table(PCIBus *bus, int32_t devfn, IOMMUConfig 
*config);
+
 static inline void
 pci_set_byte(uint8_t *config, uint8_t val)
 {
-- 
2.20.1