Merge tag 'pull-vfio-20231219' of https://github.com/legoater/qemu into staging

vfio queue:

* Introduce an IOMMU interface backend for VFIO devices
* Convert IOMMU type1 and sPAPR IOMMU to respective backends
* Introduce a new IOMMUFD backend for ARM, x86_64 and s390x platforms

# -----BEGIN PGP SIGNATURE-----
#
# iQIzBAABCAAdFiEEoPZlSPBIlev+awtgUaNDx8/77KEFAmWB34AACgkQUaNDx8/7
# 7KGOMxAAqXegvAneHqIlu4c8TzTuUR2rkYgev9RdfIHRDuY2XtaX14xlWn/rpTXZ
# qSgeta+iT8Cv4YV1POJeHWFDNs9E29p1w+R7nLcH1qTIIaZHtxwbVVQ3s7kAo1Vb
# 1S1G0/zIznzGVI50a0lj1gO2yQJnu/79nXpnICgA5REW0CscMssnvboQODlwq17V
# ZLNVM8CSAvKl6ppkmzRdfNXCfq6x7bf4MsvnuXsqda4TBbvyyTjAqdo/8sjKiGly
# gSDQqhgy6cvEXIF0UUHPJzFApf0YdXUDlL8hzH90hvRVu4W/t24dPmT7UkVIX9Ek
# TA7RVxv7iJlHtFDqfSTAJFr7nKO9Tm2V9N7xbD1OJUKrMoPZRT6+0R1hMKqsZ5z+
# nG6khqHGzuo/aI9n70YxYIPXt+vs/EHI4WUtslGLUTL0xv8lUzk6cxyIJupFRmDS
# ix6GM9TXOV8RyOveL2knHVymlFnAR6dekkMB+6ljUTuzDwG0oco4vno8z9bi7Vct
# j36bM56U3lhY+w+Ljoy0gPwgrw/FROnGG3mp1mwp1KRHqtEDnUQu8CaLbJOBsBGE
# JJDP6AKAYMczdmYVkd4CvE0WaeSxtOUxW5H5NCPjtaFQt0qEcght2lA2K15g521q
# jeojoJ/QK5949jnNCqm1Z66/YQVL79lPyL0E+mxEohwu+yTORk4=
# =U0x5
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 19 Dec 2023 13:22:56 EST
# gpg:                using RSA key A0F66548F04895EBFE6B0B6051A343C7CFFBECA1
# gpg: Good signature from "Cédric Le Goater <clg@redhat.com>" [unknown]
# gpg:                 aka "Cédric Le Goater <clg@kaod.org>" [unknown]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg:          There is no indication that the signature belongs to the owner.
# Primary key fingerprint: A0F6 6548 F048 95EB FE6B  0B60 51A3 43C7 CFFB ECA1

* tag 'pull-vfio-20231219' of https://github.com/legoater/qemu: (47 commits)
  hw/ppc/Kconfig: Imply VFIO_PCI
  docs/devel: Add VFIO iommufd backend documentation
  vfio: Introduce a helper function to initialize VFIODevice
  vfio/ccw: Move VFIODevice initializations in vfio_ccw_instance_init
  vfio/ap: Move VFIODevice initializations in vfio_ap_instance_init
  vfio/platform: Move VFIODevice initializations in vfio_platform_instance_init
  vfio/pci: Move VFIODevice initializations in vfio_instance_init
  hw/i386: Activate IOMMUFD for q35 machines
  kconfig: Activate IOMMUFD for s390x machines
  hw/arm: Activate IOMMUFD for virt machines
  vfio: Make VFIOContainerBase poiner parameter const in VFIOIOMMUOps callbacks
  vfio/ccw: Make vfio cdev pre-openable by passing a file handle
  vfio/ccw: Allow the selection of a given iommu backend
  vfio/ap: Make vfio cdev pre-openable by passing a file handle
  vfio/ap: Allow the selection of a given iommu backend
  vfio/platform: Make vfio cdev pre-openable by passing a file handle
  vfio/platform: Allow the selection of a given iommu backend
  vfio/pci: Make vfio cdev pre-openable by passing a file handle
  vfio/pci: Allow the selection of a given iommu backend
  vfio/iommufd: Enable pci hot reset through iommufd cdev interface
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

4 files changed, 203 insertions, 68 deletions

diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index a4a22ac..b8aa8a5 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -30,6 +30,7 @@
 #include <linux/vfio.h>
 #endif
 #include "sysemu/sysemu.h"
+#include "hw/vfio/vfio-container-base.h"
 
 #define VFIO_MSG_PREFIX "vfio %s: "
 
@@ -72,54 +73,15 @@ typedef struct VFIOMigration {
     bool initial_data_sent;
 } VFIOMigration;
 
-typedef struct VFIOAddressSpace {
-    AddressSpace *as;
-    QLIST_HEAD(, VFIOContainer) containers;
-    QLIST_ENTRY(VFIOAddressSpace) list;
-} VFIOAddressSpace;
-
 struct VFIOGroup;
 
 typedef struct VFIOContainer {
-    VFIOAddressSpace *space;
+    VFIOContainerBase bcontainer;
     int fd; /* /dev/vfio/vfio, empowered by the attached groups */
-    MemoryListener listener;
-    MemoryListener prereg_listener;
     unsigned iommu_type;
-    Error *error;
-    bool initialized;
-    bool dirty_pages_supported;
-    uint64_t dirty_pgsizes;
-    uint64_t max_dirty_bitmap_size;
-    unsigned long pgsizes;
-    unsigned int dma_max_mappings;
-    QLIST_HEAD(, VFIOGuestIOMMU) giommu_list;
-    QLIST_HEAD(, VFIOHostDMAWindow) hostwin_list;
     QLIST_HEAD(, VFIOGroup) group_list;
-    QLIST_HEAD(, VFIORamDiscardListener) vrdl_list;
-    QLIST_ENTRY(VFIOContainer) next;
-    QLIST_HEAD(, VFIODevice) device_list;
-    GList *iova_ranges;
 } VFIOContainer;
 
-typedef struct VFIOGuestIOMMU {
-    VFIOContainer *container;
-    IOMMUMemoryRegion *iommu_mr;
-    hwaddr iommu_offset;
-    IOMMUNotifier n;
-    QLIST_ENTRY(VFIOGuestIOMMU) giommu_next;
-} VFIOGuestIOMMU;
-
-typedef struct VFIORamDiscardListener {
-    VFIOContainer *container;
-    MemoryRegion *mr;
-    hwaddr offset_within_address_space;
-    hwaddr size;
-    uint64_t granularity;
-    RamDiscardListener listener;
-    QLIST_ENTRY(VFIORamDiscardListener) next;
-} VFIORamDiscardListener;
-
 typedef struct VFIOHostDMAWindow {
     hwaddr min_iova;
     hwaddr max_iova;
@@ -127,6 +89,14 @@ typedef struct VFIOHostDMAWindow {
     QLIST_ENTRY(VFIOHostDMAWindow) hostwin_next;
 } VFIOHostDMAWindow;
 
+typedef struct IOMMUFDBackend IOMMUFDBackend;
+
+typedef struct VFIOIOMMUFDContainer {
+    VFIOContainerBase bcontainer;
+    IOMMUFDBackend *be;
+    uint32_t ioas_id;
+} VFIOIOMMUFDContainer;
+
 typedef struct VFIODeviceOps VFIODeviceOps;
 
 typedef struct VFIODevice {
@@ -134,7 +104,7 @@ typedef struct VFIODevice {
     QLIST_ENTRY(VFIODevice) container_next;
     QLIST_ENTRY(VFIODevice) global_next;
     struct VFIOGroup *group;
-    VFIOContainer *container;
+    VFIOContainerBase *bcontainer;
     char *sysfsdev;
     char *name;
     DeviceState *dev;
@@ -154,6 +124,8 @@ typedef struct VFIODevice {
     OnOffAuto pre_copy_dirty_page_tracking;
     bool dirty_pages_supported;
     bool dirty_tracking;
+    int devid;
+    IOMMUFDBackend *iommufd;
 } VFIODevice;
 
 struct VFIODeviceOps {
@@ -201,31 +173,10 @@ typedef struct VFIODisplay {
     } dmabuf;
 } VFIODisplay;
 
-typedef struct {
-    unsigned long *bitmap;
-    hwaddr size;
-    hwaddr pages;
-} VFIOBitmap;
-
 VFIOAddressSpace *vfio_get_address_space(AddressSpace *as);
 void vfio_put_address_space(VFIOAddressSpace *space);
-bool vfio_devices_all_running_and_saving(VFIOContainer *container);
-
-/* container->fd */
-int vfio_dma_unmap(VFIOContainer *container, hwaddr iova,
-                   ram_addr_t size, IOMMUTLBEntry *iotlb);
-int vfio_dma_map(VFIOContainer *container, hwaddr iova,
-                 ram_addr_t size, void *vaddr, bool readonly);
-int vfio_set_dirty_page_tracking(VFIOContainer *container, bool start);
-int vfio_query_dirty_bitmap(VFIOContainer *container, VFIOBitmap *vbmap,
-                            hwaddr iova, hwaddr size);
 
 /* SPAPR specific */
-int vfio_container_add_section_window(VFIOContainer *container,
-                                      MemoryRegionSection *section,
-                                      Error **errp);
-void vfio_container_del_section_window(VFIOContainer *container,
-                                       MemoryRegionSection *section);
 int vfio_spapr_container_init(VFIOContainer *container, Error **errp);
 void vfio_spapr_container_deinit(VFIOContainer *container);
 
@@ -259,7 +210,8 @@ typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList;
 typedef QLIST_HEAD(VFIODeviceList, VFIODevice) VFIODeviceList;
 extern VFIOGroupList vfio_group_list;
 extern VFIODeviceList vfio_device_list;
-
+extern const VFIOIOMMUOps vfio_legacy_ops;
+extern const VFIOIOMMUOps vfio_iommufd_ops;
 extern const MemoryListener vfio_memory_listener;
 extern int vfio_kvm_device_fd;
 
@@ -292,11 +244,19 @@ bool vfio_migration_realize(VFIODevice *vbasedev, Error **errp);
 void vfio_migration_exit(VFIODevice *vbasedev);
 
 int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size);
-bool vfio_devices_all_running_and_mig_active(VFIOContainer *container);
-bool vfio_devices_all_device_dirty_tracking(VFIOContainer *container);
-int vfio_devices_query_dirty_bitmap(VFIOContainer *container,
+bool
+vfio_devices_all_running_and_mig_active(const VFIOContainerBase *bcontainer);
+bool
+vfio_devices_all_device_dirty_tracking(const VFIOContainerBase *bcontainer);
+int vfio_devices_query_dirty_bitmap(const VFIOContainerBase *bcontainer,
                                     VFIOBitmap *vbmap, hwaddr iova,
                                     hwaddr size);
-int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova,
-                                 uint64_t size, ram_addr_t ram_addr);
+int vfio_get_dirty_bitmap(const VFIOContainerBase *bcontainer, uint64_t iova,
+                          uint64_t size, ram_addr_t ram_addr);
+
+/* Returns 0 on success, or a negative errno. */
+int vfio_device_get_name(VFIODevice *vbasedev, Error **errp);
+void vfio_device_set_fd(VFIODevice *vbasedev, const char *str, Error **errp);
+void vfio_device_init(VFIODevice *vbasedev, int type, VFIODeviceOps *ops,
+                      DeviceState *dev, bool ram_discard);
 #endif /* HW_VFIO_VFIO_COMMON_H */
diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h
new file mode 100644
index 0000000..2ae297c
--- /dev/null
+++ b/include/hw/vfio/vfio-container-base.h
@@ -0,0 +1,121 @@
+/*
+ * VFIO BASE CONTAINER
+ *
+ * Copyright (C) 2023 Intel Corporation.
+ * Copyright Red Hat, Inc. 2023
+ *
+ * Authors: Yi Liu <yi.l.liu@intel.com>
+ *          Eric Auger <eric.auger@redhat.com>
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#ifndef HW_VFIO_VFIO_CONTAINER_BASE_H
+#define HW_VFIO_VFIO_CONTAINER_BASE_H
+
+#include "exec/memory.h"
+
+typedef struct VFIODevice VFIODevice;
+typedef struct VFIOIOMMUOps VFIOIOMMUOps;
+
+typedef struct {
+    unsigned long *bitmap;
+    hwaddr size;
+    hwaddr pages;
+} VFIOBitmap;
+
+typedef struct VFIOAddressSpace {
+    AddressSpace *as;
+    QLIST_HEAD(, VFIOContainerBase) containers;
+    QLIST_ENTRY(VFIOAddressSpace) list;
+} VFIOAddressSpace;
+
+/*
+ * This is the base object for vfio container backends
+ */
+typedef struct VFIOContainerBase {
+    const VFIOIOMMUOps *ops;
+    VFIOAddressSpace *space;
+    MemoryListener listener;
+    Error *error;
+    bool initialized;
+    uint64_t dirty_pgsizes;
+    uint64_t max_dirty_bitmap_size;
+    unsigned long pgsizes;
+    unsigned int dma_max_mappings;
+    bool dirty_pages_supported;
+    QLIST_HEAD(, VFIOGuestIOMMU) giommu_list;
+    QLIST_HEAD(, VFIORamDiscardListener) vrdl_list;
+    QLIST_ENTRY(VFIOContainerBase) next;
+    QLIST_HEAD(, VFIODevice) device_list;
+    GList *iova_ranges;
+} VFIOContainerBase;
+
+typedef struct VFIOGuestIOMMU {
+    VFIOContainerBase *bcontainer;
+    IOMMUMemoryRegion *iommu_mr;
+    hwaddr iommu_offset;
+    IOMMUNotifier n;
+    QLIST_ENTRY(VFIOGuestIOMMU) giommu_next;
+} VFIOGuestIOMMU;
+
+typedef struct VFIORamDiscardListener {
+    VFIOContainerBase *bcontainer;
+    MemoryRegion *mr;
+    hwaddr offset_within_address_space;
+    hwaddr size;
+    uint64_t granularity;
+    RamDiscardListener listener;
+    QLIST_ENTRY(VFIORamDiscardListener) next;
+} VFIORamDiscardListener;
+
+int vfio_container_dma_map(VFIOContainerBase *bcontainer,
+                           hwaddr iova, ram_addr_t size,
+                           void *vaddr, bool readonly);
+int vfio_container_dma_unmap(VFIOContainerBase *bcontainer,
+                             hwaddr iova, ram_addr_t size,
+                             IOMMUTLBEntry *iotlb);
+int vfio_container_add_section_window(VFIOContainerBase *bcontainer,
+                                      MemoryRegionSection *section,
+                                      Error **errp);
+void vfio_container_del_section_window(VFIOContainerBase *bcontainer,
+                                       MemoryRegionSection *section);
+int vfio_container_set_dirty_page_tracking(VFIOContainerBase *bcontainer,
+                                           bool start);
+int vfio_container_query_dirty_bitmap(const VFIOContainerBase *bcontainer,
+                                      VFIOBitmap *vbmap,
+                                      hwaddr iova, hwaddr size);
+
+void vfio_container_init(VFIOContainerBase *bcontainer,
+                         VFIOAddressSpace *space,
+                         const VFIOIOMMUOps *ops);
+void vfio_container_destroy(VFIOContainerBase *bcontainer);
+
+struct VFIOIOMMUOps {
+    /* basic feature */
+    int (*dma_map)(const VFIOContainerBase *bcontainer,
+                   hwaddr iova, ram_addr_t size,
+                   void *vaddr, bool readonly);
+    int (*dma_unmap)(const VFIOContainerBase *bcontainer,
+                     hwaddr iova, ram_addr_t size,
+                     IOMMUTLBEntry *iotlb);
+    int (*attach_device)(const char *name, VFIODevice *vbasedev,
+                         AddressSpace *as, Error **errp);
+    void (*detach_device)(VFIODevice *vbasedev);
+    /* migration feature */
+    int (*set_dirty_page_tracking)(const VFIOContainerBase *bcontainer,
+                                   bool start);
+    int (*query_dirty_bitmap)(const VFIOContainerBase *bcontainer,
+                              VFIOBitmap *vbmap,
+                              hwaddr iova, hwaddr size);
+    /* PCI specific */
+    int (*pci_hot_reset)(VFIODevice *vbasedev, bool single);
+
+    /* SPAPR specific */
+    int (*add_window)(VFIOContainerBase *bcontainer,
+                      MemoryRegionSection *section,
+                      Error **errp);
+    void (*del_window)(VFIOContainerBase *bcontainer,
+                       MemoryRegionSection *section);
+};
+#endif /* HW_VFIO_VFIO_CONTAINER_BASE_H */
diff --git a/include/qemu/chardev_open.h b/include/qemu/chardev_open.h
new file mode 100644
index 0000000..64e8fcf
--- /dev/null
+++ b/include/qemu/chardev_open.h
@@ -0,0 +1,16 @@
+/*
+ * QEMU Chardev Helper
+ *
+ * Copyright (C) 2023 Intel Corporation.
+ *
+ * Authors: Yi Liu <yi.l.liu@intel.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ */
+
+#ifndef QEMU_CHARDEV_OPEN_H
+#define QEMU_CHARDEV_OPEN_H
+
+int open_cdev(const char *devpath, dev_t cdev);
+#endif
diff --git a/include/sysemu/iommufd.h b/include/sysemu/iommufd.h
new file mode 100644
index 0000000..9c5524b
--- /dev/null
+++ b/include/sysemu/iommufd.h
@@ -0,0 +1,38 @@
+#ifndef SYSEMU_IOMMUFD_H
+#define SYSEMU_IOMMUFD_H
+
+#include "qom/object.h"
+#include "qemu/thread.h"
+#include "exec/hwaddr.h"
+#include "exec/cpu-common.h"
+
+#define TYPE_IOMMUFD_BACKEND "iommufd"
+OBJECT_DECLARE_TYPE(IOMMUFDBackend, IOMMUFDBackendClass, IOMMUFD_BACKEND)
+
+struct IOMMUFDBackendClass {
+    ObjectClass parent_class;
+};
+
+struct IOMMUFDBackend {
+    Object parent;
+
+    /*< protected >*/
+    int fd;            /* /dev/iommu file descriptor */
+    bool owned;        /* is the /dev/iommu opened internally */
+    QemuMutex lock;
+    uint32_t users;
+
+    /*< public >*/
+};
+
+int iommufd_backend_connect(IOMMUFDBackend *be, Error **errp);
+void iommufd_backend_disconnect(IOMMUFDBackend *be);
+
+int iommufd_backend_alloc_ioas(IOMMUFDBackend *be, uint32_t *ioas_id,
+                               Error **errp);
+void iommufd_backend_free_id(IOMMUFDBackend *be, uint32_t id);
+int iommufd_backend_map_dma(IOMMUFDBackend *be, uint32_t ioas_id, hwaddr iova,
+                            ram_addr_t size, void *vaddr, bool readonly);
+int iommufd_backend_unmap_dma(IOMMUFDBackend *be, uint32_t ioas_id,
+                              hwaddr iova, ram_addr_t size);
+#endif