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>

1 files changed, 46 insertions, 172 deletions

diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index c62c02f7b6..1874ec1aba 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -19,6 +19,7 @@
  */
 
 #include "qemu/osdep.h"
+#include CONFIG_DEVICES /* CONFIG_IOMMUFD */
 #include <linux/vfio.h>
 #include <sys/ioctl.h>
 
@@ -42,6 +43,7 @@
 #include "qapi/error.h"
 #include "migration/blocker.h"
 #include "migration/qemu-file.h"
+#include "sysemu/iommufd.h"
 
 #define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug"
 
@@ -2374,7 +2376,7 @@ static int vfio_add_capabilities(VFIOPCIDevice *vdev, Error **errp)
     return 0;
 }
 
-static void vfio_pci_pre_reset(VFIOPCIDevice *vdev)
+void vfio_pci_pre_reset(VFIOPCIDevice *vdev)
 {
     PCIDevice *pdev = &vdev->pdev;
     uint16_t cmd;
@@ -2411,7 +2413,7 @@ static void vfio_pci_pre_reset(VFIOPCIDevice *vdev)
     vfio_pci_write_config(pdev, PCI_COMMAND, cmd, 2);
 }
 
-static void vfio_pci_post_reset(VFIOPCIDevice *vdev)
+void vfio_pci_post_reset(VFIOPCIDevice *vdev)
 {
     Error *err = NULL;
     int nr;
@@ -2435,7 +2437,7 @@ static void vfio_pci_post_reset(VFIOPCIDevice *vdev)
     vfio_quirk_reset(vdev);
 }
 
-static bool vfio_pci_host_match(PCIHostDeviceAddress *addr, const char *name)
+bool vfio_pci_host_match(PCIHostDeviceAddress *addr, const char *name)
 {
     char tmp[13];
 
@@ -2445,22 +2447,13 @@ static bool vfio_pci_host_match(PCIHostDeviceAddress *addr, const char *name)
     return (strcmp(tmp, name) == 0);
 }
 
-static int vfio_pci_hot_reset(VFIOPCIDevice *vdev, bool single)
+int vfio_pci_get_pci_hot_reset_info(VFIOPCIDevice *vdev,
+                                    struct vfio_pci_hot_reset_info **info_p)
 {
-    VFIOGroup *group;
     struct vfio_pci_hot_reset_info *info;
-    struct vfio_pci_dependent_device *devices;
-    struct vfio_pci_hot_reset *reset;
-    int32_t *fds;
-    int ret, i, count;
-    bool multi = false;
+    int ret, count;
 
-    trace_vfio_pci_hot_reset(vdev->vbasedev.name, single ? "one" : "multi");
-
-    if (!single) {
-        vfio_pci_pre_reset(vdev);
-    }
-    vdev->vbasedev.needs_reset = false;
+    assert(info_p && !*info_p);
 
     info = g_malloc0(sizeof(*info));
     info->argsz = sizeof(*info);
@@ -2468,163 +2461,36 @@ static int vfio_pci_hot_reset(VFIOPCIDevice *vdev, bool single)
     ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_PCI_HOT_RESET_INFO, info);
     if (ret && errno != ENOSPC) {
         ret = -errno;
+        g_free(info);
         if (!vdev->has_pm_reset) {
             error_report("vfio: Cannot reset device %s, "
                          "no available reset mechanism.", vdev->vbasedev.name);
         }
-        goto out_single;
+        return ret;
     }
 
     count = info->count;
-    info = g_realloc(info, sizeof(*info) + (count * sizeof(*devices)));
-    info->argsz = sizeof(*info) + (count * sizeof(*devices));
-    devices = &info->devices[0];
+    info = g_realloc(info, sizeof(*info) + (count * sizeof(info->devices[0])));
+    info->argsz = sizeof(*info) + (count * sizeof(info->devices[0]));
 
     ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_PCI_HOT_RESET_INFO, info);
     if (ret) {
         ret = -errno;
+        g_free(info);
         error_report("vfio: hot reset info failed: %m");
-        goto out_single;
-    }
-
-    trace_vfio_pci_hot_reset_has_dep_devices(vdev->vbasedev.name);
-
-    /* Verify that we have all the groups required */
-    for (i = 0; i < info->count; i++) {
-        PCIHostDeviceAddress host;
-        VFIOPCIDevice *tmp;
-        VFIODevice *vbasedev_iter;
-
-        host.domain = devices[i].segment;
-        host.bus = devices[i].bus;
-        host.slot = PCI_SLOT(devices[i].devfn);
-        host.function = PCI_FUNC(devices[i].devfn);
-
-        trace_vfio_pci_hot_reset_dep_devices(host.domain,
-                host.bus, host.slot, host.function, devices[i].group_id);
-
-        if (vfio_pci_host_match(&host, vdev->vbasedev.name)) {
-            continue;
-        }
-
-        QLIST_FOREACH(group, &vfio_group_list, next) {
-            if (group->groupid == devices[i].group_id) {
-                break;
-            }
-        }
-
-        if (!group) {
-            if (!vdev->has_pm_reset) {
-                error_report("vfio: Cannot reset device %s, "
-                             "depends on group %d which is not owned.",
-                             vdev->vbasedev.name, devices[i].group_id);
-            }
-            ret = -EPERM;
-            goto out;
-        }
-
-        /* Prep dependent devices for reset and clear our marker. */
-        QLIST_FOREACH(vbasedev_iter, &group->device_list, next) {
-            if (!vbasedev_iter->dev->realized ||
-                vbasedev_iter->type != VFIO_DEVICE_TYPE_PCI) {
-                continue;
-            }
-            tmp = container_of(vbasedev_iter, VFIOPCIDevice, vbasedev);
-            if (vfio_pci_host_match(&host, tmp->vbasedev.name)) {
-                if (single) {
-                    ret = -EINVAL;
-                    goto out_single;
-                }
-                vfio_pci_pre_reset(tmp);
-                tmp->vbasedev.needs_reset = false;
-                multi = true;
-                break;
-            }
-        }
-    }
-
-    if (!single && !multi) {
-        ret = -EINVAL;
-        goto out_single;
-    }
-
-    /* Determine how many group fds need to be passed */
-    count = 0;
-    QLIST_FOREACH(group, &vfio_group_list, next) {
-        for (i = 0; i < info->count; i++) {
-            if (group->groupid == devices[i].group_id) {
-                count++;
-                break;
-            }
-        }
-    }
-
-    reset = g_malloc0(sizeof(*reset) + (count * sizeof(*fds)));
-    reset->argsz = sizeof(*reset) + (count * sizeof(*fds));
-    fds = &reset->group_fds[0];
-
-    /* Fill in group fds */
-    QLIST_FOREACH(group, &vfio_group_list, next) {
-        for (i = 0; i < info->count; i++) {
-            if (group->groupid == devices[i].group_id) {
-                fds[reset->count++] = group->fd;
-                break;
-            }
-        }
+        return ret;
     }
 
-    /* Bus reset! */
-    ret = ioctl(vdev->vbasedev.fd, VFIO_DEVICE_PCI_HOT_RESET, reset);
-    g_free(reset);
-
-    trace_vfio_pci_hot_reset_result(vdev->vbasedev.name,
-                                    ret ? strerror(errno) : "Success");
-
-out:
-    /* Re-enable INTx on affected devices */
-    for (i = 0; i < info->count; i++) {
-        PCIHostDeviceAddress host;
-        VFIOPCIDevice *tmp;
-        VFIODevice *vbasedev_iter;
-
-        host.domain = devices[i].segment;
-        host.bus = devices[i].bus;
-        host.slot = PCI_SLOT(devices[i].devfn);
-        host.function = PCI_FUNC(devices[i].devfn);
-
-        if (vfio_pci_host_match(&host, vdev->vbasedev.name)) {
-            continue;
-        }
-
-        QLIST_FOREACH(group, &vfio_group_list, next) {
-            if (group->groupid == devices[i].group_id) {
-                break;
-            }
-        }
-
-        if (!group) {
-            break;
-        }
+    *info_p = info;
+    return 0;
+}
 
-        QLIST_FOREACH(vbasedev_iter, &group->device_list, next) {
-            if (!vbasedev_iter->dev->realized ||
-                vbasedev_iter->type != VFIO_DEVICE_TYPE_PCI) {
-                continue;
-            }
-            tmp = container_of(vbasedev_iter, VFIOPCIDevice, vbasedev);
-            if (vfio_pci_host_match(&host, tmp->vbasedev.name)) {
-                vfio_pci_post_reset(tmp);
-                break;
-            }
-        }
-    }
-out_single:
-    if (!single) {
-        vfio_pci_post_reset(vdev);
-    }
-    g_free(info);
+static int vfio_pci_hot_reset(VFIOPCIDevice *vdev, bool single)
+{
+    VFIODevice *vbasedev = &vdev->vbasedev;
+    const VFIOIOMMUOps *ops = vbasedev->bcontainer->ops;
 
-    return ret;
+    return ops->pci_hot_reset(vbasedev, single);
 }
 
 /*
@@ -3078,17 +2944,19 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
     VFIODevice *vbasedev = &vdev->vbasedev;
     char *tmp, *subsys;
     Error *err = NULL;
-    struct stat st;
     int i, ret;
     bool is_mdev;
     char uuid[UUID_STR_LEN];
     char *name;
 
-    if (!vbasedev->sysfsdev) {
+    if (vbasedev->fd < 0 && !vbasedev->sysfsdev) {
         if (!(~vdev->host.domain || ~vdev->host.bus ||
               ~vdev->host.slot || ~vdev->host.function)) {
             error_setg(errp, "No provided host device");
             error_append_hint(errp, "Use -device vfio-pci,host=DDDD:BB:DD.F "
+#ifdef CONFIG_IOMMUFD
+                              "or -device vfio-pci,fd=DEVICE_FD "
+#endif
                               "or -device vfio-pci,sysfsdev=PATH_TO_DEVICE\n");
             return;
         }
@@ -3098,17 +2966,10 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
                             vdev->host.slot, vdev->host.function);
     }
 
-    if (stat(vbasedev->sysfsdev, &st) < 0) {
-        error_setg_errno(errp, errno, "no such host device");
-        error_prepend(errp, VFIO_MSG_PREFIX, vbasedev->sysfsdev);
+    if (vfio_device_get_name(vbasedev, errp) < 0) {
         return;
     }
 
-    vbasedev->name = g_path_get_basename(vbasedev->sysfsdev);
-    vbasedev->ops = &vfio_pci_ops;
-    vbasedev->type = VFIO_DEVICE_TYPE_PCI;
-    vbasedev->dev = DEVICE(vdev);
-
     /*
      * Mediated devices *might* operate compatibly with discarding of RAM, but
      * we cannot know for certain, it depends on whether the mdev vendor driver
@@ -3456,6 +3317,7 @@ static void vfio_instance_init(Object *obj)
 {
     PCIDevice *pci_dev = PCI_DEVICE(obj);
     VFIOPCIDevice *vdev = VFIO_PCI(obj);
+    VFIODevice *vbasedev = &vdev->vbasedev;
 
     device_add_bootindex_property(obj, &vdev->bootindex,
                                   "bootindex", NULL,
@@ -3465,6 +3327,9 @@ static void vfio_instance_init(Object *obj)
     vdev->host.slot = ~0U;
     vdev->host.function = ~0U;
 
+    vfio_device_init(vbasedev, VFIO_DEVICE_TYPE_PCI, &vfio_pci_ops,
+                     DEVICE(vdev), false);
+
     vdev->nv_gpudirect_clique = 0xFF;
 
     /* QEMU_PCI_CAP_EXPRESS initialization does not depend on QEMU command
@@ -3517,14 +3382,20 @@ static Property vfio_pci_dev_properties[] = {
                                    qdev_prop_nv_gpudirect_clique, uint8_t),
     DEFINE_PROP_OFF_AUTO_PCIBAR("x-msix-relocation", VFIOPCIDevice, msix_relo,
                                 OFF_AUTOPCIBAR_OFF),
-    /*
-     * TODO - support passed fds... is this necessary?
-     * DEFINE_PROP_STRING("vfiofd", VFIOPCIDevice, vfiofd_name),
-     * DEFINE_PROP_STRING("vfiogroupfd, VFIOPCIDevice, vfiogroupfd_name),
-     */
+#ifdef CONFIG_IOMMUFD
+    DEFINE_PROP_LINK("iommufd", VFIOPCIDevice, vbasedev.iommufd,
+                     TYPE_IOMMUFD_BACKEND, IOMMUFDBackend *),
+#endif
     DEFINE_PROP_END_OF_LIST(),
 };
 
+#ifdef CONFIG_IOMMUFD
+static void vfio_pci_set_fd(Object *obj, const char *str, Error **errp)
+{
+    vfio_device_set_fd(&VFIO_PCI(obj)->vbasedev, str, errp);
+}
+#endif
+
 static void vfio_pci_dev_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
@@ -3532,6 +3403,9 @@ static void vfio_pci_dev_class_init(ObjectClass *klass, void *data)
 
     dc->reset = vfio_pci_reset;
     device_class_set_props(dc, vfio_pci_dev_properties);
+#ifdef CONFIG_IOMMUFD
+    object_class_property_add_str(klass, "fd", NULL, vfio_pci_set_fd);
+#endif
     dc->desc = "VFIO-based PCI device assignment";
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
     pdc->realize = vfio_realize;