1 files changed, 165 insertions, 8 deletions

diff --git a/backends/iommufd.c b/backends/iommufd.c
index d57da44..2a33c7a 100644
--- a/backends/iommufd.c
+++ b/backends/iommufd.c
@@ -16,12 +16,18 @@
 #include "qemu/module.h"
 #include "qom/object_interfaces.h"
 #include "qemu/error-report.h"
+#include "migration/cpr.h"
 #include "monitor/monitor.h"
 #include "trace.h"
-#include "hw/vfio/vfio-common.h"
+#include "hw/vfio/vfio-device.h"
 #include <sys/ioctl.h>
 #include <linux/iommufd.h>
 
+static const char *iommufd_fd_name(IOMMUFDBackend *be)
+{
+    return object_get_canonical_path_component(OBJECT(be));
+}
+
 static void iommufd_backend_init(Object *obj)
 {
     IOMMUFDBackend *be = IOMMUFD_BACKEND(obj);
@@ -64,26 +70,73 @@ static bool iommufd_backend_can_be_deleted(UserCreatable *uc)
     return !be->users;
 }
 
-static void iommufd_backend_class_init(ObjectClass *oc, void *data)
+static void iommufd_backend_complete(UserCreatable *uc, Error **errp)
+{
+    IOMMUFDBackend *be = IOMMUFD_BACKEND(uc);
+    const char *name = iommufd_fd_name(be);
+
+    if (!be->owned) {
+        /* fd came from the command line. Fetch updated value from cpr state. */
+        if (cpr_is_incoming()) {
+            be->fd = cpr_find_fd(name, 0);
+        } else {
+            cpr_save_fd(name, 0, be->fd);
+        }
+    }
+}
+
+static void iommufd_backend_class_init(ObjectClass *oc, const void *data)
 {
     UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
 
     ucc->can_be_deleted = iommufd_backend_can_be_deleted;
+    ucc->complete = iommufd_backend_complete;
 
     object_class_property_add_str(oc, "fd", NULL, iommufd_backend_set_fd);
 }
 
+bool iommufd_change_process_capable(IOMMUFDBackend *be)
+{
+    struct iommu_ioas_change_process args = {.size = sizeof(args)};
+
+    /*
+     * Call IOMMU_IOAS_CHANGE_PROCESS to verify it is a recognized ioctl.
+     * This is a no-op if the process has not changed since DMA was mapped.
+     */
+    return !ioctl(be->fd, IOMMU_IOAS_CHANGE_PROCESS, &args);
+}
+
+bool iommufd_change_process(IOMMUFDBackend *be, Error **errp)
+{
+    struct iommu_ioas_change_process args = {.size = sizeof(args)};
+    bool ret = !ioctl(be->fd, IOMMU_IOAS_CHANGE_PROCESS, &args);
+
+    if (!ret) {
+        error_setg_errno(errp, errno, "IOMMU_IOAS_CHANGE_PROCESS fd %d failed",
+                         be->fd);
+    }
+    trace_iommufd_change_process(be->fd, ret);
+    return ret;
+}
+
 bool iommufd_backend_connect(IOMMUFDBackend *be, Error **errp)
 {
     int fd;
 
     if (be->owned && !be->users) {
-        fd = qemu_open("/dev/iommu", O_RDWR, errp);
+        fd = cpr_open_fd("/dev/iommu", O_RDWR, iommufd_fd_name(be), 0, errp);
         if (fd < 0) {
             return false;
         }
         be->fd = fd;
     }
+    if (!be->users && !vfio_iommufd_cpr_register_iommufd(be, errp)) {
+        if (be->owned) {
+            close(be->fd);
+            be->fd = -1;
+        }
+        return false;
+    }
     be->users++;
 
     trace_iommufd_backend_connect(be->fd, be->owned, be->users);
@@ -96,9 +149,13 @@ void iommufd_backend_disconnect(IOMMUFDBackend *be)
         goto out;
     }
     be->users--;
-    if (!be->users && be->owned) {
-        close(be->fd);
-        be->fd = -1;
+    if (!be->users) {
+        vfio_iommufd_cpr_unregister_iommufd(be);
+        if (be->owned) {
+            cpr_delete_fd(iommufd_fd_name(be), 0);
+            close(be->fd);
+            be->fd = -1;
+        }
     }
 out:
     trace_iommufd_backend_disconnect(be->fd, be->users);
@@ -172,6 +229,44 @@ int iommufd_backend_map_dma(IOMMUFDBackend *be, uint32_t ioas_id, hwaddr iova,
     return ret;
 }
 
+int iommufd_backend_map_file_dma(IOMMUFDBackend *be, uint32_t ioas_id,
+                                 hwaddr iova, ram_addr_t size,
+                                 int mfd, unsigned long start, bool readonly)
+{
+    int ret, fd = be->fd;
+    struct iommu_ioas_map_file map = {
+        .size = sizeof(map),
+        .flags = IOMMU_IOAS_MAP_READABLE |
+                 IOMMU_IOAS_MAP_FIXED_IOVA,
+        .ioas_id = ioas_id,
+        .fd = mfd,
+        .start = start,
+        .iova = iova,
+        .length = size,
+    };
+
+    if (cpr_is_incoming()) {
+        return 0;
+    }
+
+    if (!readonly) {
+        map.flags |= IOMMU_IOAS_MAP_WRITEABLE;
+    }
+
+    ret = ioctl(fd, IOMMU_IOAS_MAP_FILE, &map);
+    trace_iommufd_backend_map_file_dma(fd, ioas_id, iova, size, mfd, start,
+                                       readonly, ret);
+    if (ret) {
+        ret = -errno;
+
+        /* TODO: Not support mapping hardware PCI BAR region for now. */
+        if (errno == EFAULT) {
+            warn_report("IOMMU_IOAS_MAP_FILE failed: %m, PCI BAR?");
+        }
+    }
+    return ret;
+}
+
 int iommufd_backend_unmap_dma(IOMMUFDBackend *be, uint32_t ioas_id,
                               hwaddr iova, ram_addr_t size)
 {
@@ -183,6 +278,10 @@ int iommufd_backend_unmap_dma(IOMMUFDBackend *be, uint32_t ioas_id,
         .length = size,
     };
 
+    if (cpr_is_incoming()) {
+        return 0;
+    }
+
     ret = ioctl(fd, IOMMU_IOAS_UNMAP, &unmap);
     /*
      * IOMMUFD takes mapping as some kind of object, unmapping
@@ -311,6 +410,62 @@ bool iommufd_backend_get_device_info(IOMMUFDBackend *be, uint32_t devid,
     return true;
 }
 
+bool iommufd_backend_invalidate_cache(IOMMUFDBackend *be, uint32_t id,
+                                      uint32_t data_type, uint32_t entry_len,
+                                      uint32_t *entry_num, void *data,
+                                      Error **errp)
+{
+    int ret, fd = be->fd;
+    uint32_t total_entries = *entry_num;
+    struct iommu_hwpt_invalidate cache = {
+        .size = sizeof(cache),
+        .hwpt_id = id,
+        .data_type = data_type,
+        .entry_len = entry_len,
+        .entry_num = total_entries,
+        .data_uptr = (uintptr_t)data,
+    };
+
+    ret = ioctl(fd, IOMMU_HWPT_INVALIDATE, &cache);
+    trace_iommufd_backend_invalidate_cache(fd, id, data_type, entry_len,
+                                           total_entries, cache.entry_num,
+                                           (uintptr_t)data, ret ? errno : 0);
+    *entry_num = cache.entry_num;
+
+    if (ret) {
+        error_setg_errno(errp, errno, "IOMMU_HWPT_INVALIDATE failed:"
+                         " total %d entries, processed %d entries",
+                         total_entries, cache.entry_num);
+    } else if (total_entries != cache.entry_num) {
+        error_setg(errp, "IOMMU_HWPT_INVALIDATE succeed but with unprocessed"
+                         " entries: total %d entries, processed %d entries."
+                         " Kernel BUG?!", total_entries, cache.entry_num);
+        return false;
+    }
+
+    return !ret;
+}
+
+bool host_iommu_device_iommufd_attach_hwpt(HostIOMMUDeviceIOMMUFD *idev,
+                                           uint32_t hwpt_id, Error **errp)
+{
+    HostIOMMUDeviceIOMMUFDClass *idevc =
+        HOST_IOMMU_DEVICE_IOMMUFD_GET_CLASS(idev);
+
+    g_assert(idevc->attach_hwpt);
+    return idevc->attach_hwpt(idev, hwpt_id, errp);
+}
+
+bool host_iommu_device_iommufd_detach_hwpt(HostIOMMUDeviceIOMMUFD *idev,
+                                           Error **errp)
+{
+    HostIOMMUDeviceIOMMUFDClass *idevc =
+        HOST_IOMMU_DEVICE_IOMMUFD_GET_CLASS(idev);
+
+    g_assert(idevc->detach_hwpt);
+    return idevc->detach_hwpt(idev, errp);
+}
+
 static int hiod_iommufd_get_cap(HostIOMMUDevice *hiod, int cap, Error **errp)
 {
     HostIOMMUDeviceCaps *caps = &hiod->caps;
@@ -326,7 +481,7 @@ static int hiod_iommufd_get_cap(HostIOMMUDevice *hiod, int cap, Error **errp)
     }
 }
 
-static void hiod_iommufd_class_init(ObjectClass *oc, void *data)
+static void hiod_iommufd_class_init(ObjectClass *oc, const void *data)
 {
     HostIOMMUDeviceClass *hioc = HOST_IOMMU_DEVICE_CLASS(oc);
 
@@ -342,13 +497,15 @@ static const TypeInfo types[] = {
         .instance_finalize = iommufd_backend_finalize,
         .class_size = sizeof(IOMMUFDBackendClass),
         .class_init = iommufd_backend_class_init,
-        .interfaces = (InterfaceInfo[]) {
+        .interfaces = (const InterfaceInfo[]) {
             { TYPE_USER_CREATABLE },
             { }
         }
     }, {
         .name = TYPE_HOST_IOMMU_DEVICE_IOMMUFD,
         .parent = TYPE_HOST_IOMMU_DEVICE,
+        .instance_size = sizeof(HostIOMMUDeviceIOMMUFD),
+        .class_size = sizeof(HostIOMMUDeviceIOMMUFDClass),
         .class_init = hiod_iommufd_class_init,
         .abstract = true,
     }