1 files changed, 9 insertions, 184 deletions

diff --git a/migration/rdma.c b/migration/rdma.c
index d9603ab..2d839fc 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -768,156 +768,12 @@ static void qemu_rdma_dump_gid(const char *who, struct rdma_cm_id *id)
 }
 
 /*
- * As of now, IPv6 over RoCE / iWARP is not supported by linux.
- * We will try the next addrinfo struct, and fail if there are
- * no other valid addresses to bind against.
- *
- * If user is listening on '[::]', then we will not have a opened a device
- * yet and have no way of verifying if the device is RoCE or not.
- *
- * In this case, the source VM will throw an error for ALL types of
- * connections (both IPv4 and IPv6) if the destination machine does not have
- * a regular infiniband network available for use.
- *
- * The only way to guarantee that an error is thrown for broken kernels is
- * for the management software to choose a *specific* interface at bind time
- * and validate what time of hardware it is.
- *
- * Unfortunately, this puts the user in a fix:
- *
- *  If the source VM connects with an IPv4 address without knowing that the
- *  destination has bound to '[::]' the migration will unconditionally fail
- *  unless the management software is explicitly listening on the IPv4
- *  address while using a RoCE-based device.
- *
- *  If the source VM connects with an IPv6 address, then we're OK because we can
- *  throw an error on the source (and similarly on the destination).
- *
- *  But in mixed environments, this will be broken for a while until it is fixed
- *  inside linux.
- *
- * We do provide a *tiny* bit of help in this function: We can list all of the
- * devices in the system and check to see if all the devices are RoCE or
- * Infiniband.
- *
- * If we detect that we have a *pure* RoCE environment, then we can safely
- * thrown an error even if the management software has specified '[::]' as the
- * bind address.
- *
- * However, if there is are multiple hetergeneous devices, then we cannot make
- * this assumption and the user just has to be sure they know what they are
- * doing.
- *
- * Patches are being reviewed on linux-rdma.
- */
-static int qemu_rdma_broken_ipv6_kernel(struct ibv_context *verbs, Error **errp)
-{
-    /* This bug only exists in linux, to our knowledge. */
-#ifdef CONFIG_LINUX
-    struct ibv_port_attr port_attr;
-
-    /*
-     * Verbs are only NULL if management has bound to '[::]'.
-     *
-     * Let's iterate through all the devices and see if there any pure IB
-     * devices (non-ethernet).
-     *
-     * If not, then we can safely proceed with the migration.
-     * Otherwise, there are no guarantees until the bug is fixed in linux.
-     */
-    if (!verbs) {
-        int num_devices;
-        struct ibv_device **dev_list = ibv_get_device_list(&num_devices);
-        bool roce_found = false;
-        bool ib_found = false;
-
-        for (int x = 0; x < num_devices; x++) {
-            verbs = ibv_open_device(dev_list[x]);
-            /*
-             * ibv_open_device() is not documented to set errno.  If
-             * it does, it's somebody else's doc bug.  If it doesn't,
-             * the use of errno below is wrong.
-             * TODO Find out whether ibv_open_device() sets errno.
-             */
-            if (!verbs) {
-                if (errno == EPERM) {
-                    continue;
-                } else {
-                    error_setg_errno(errp, errno,
-                                     "could not open RDMA device context");
-                    return -1;
-                }
-            }
-
-            if (ibv_query_port(verbs, 1, &port_attr)) {
-                ibv_close_device(verbs);
-                error_setg(errp,
-                           "RDMA ERROR: Could not query initial IB port");
-                return -1;
-            }
-
-            if (port_attr.link_layer == IBV_LINK_LAYER_INFINIBAND) {
-                ib_found = true;
-            } else if (port_attr.link_layer == IBV_LINK_LAYER_ETHERNET) {
-                roce_found = true;
-            }
-
-            ibv_close_device(verbs);
-
-        }
-
-        if (roce_found) {
-            if (ib_found) {
-                warn_report("migrations may fail:"
-                            " IPv6 over RoCE / iWARP in linux"
-                            " is broken. But since you appear to have a"
-                            " mixed RoCE / IB environment, be sure to only"
-                            " migrate over the IB fabric until the kernel "
-                            " fixes the bug.");
-            } else {
-                error_setg(errp, "RDMA ERROR: "
-                           "You only have RoCE / iWARP devices in your systems"
-                           " and your management software has specified '[::]'"
-                           ", but IPv6 over RoCE / iWARP is not supported in Linux.");
-                return -1;
-            }
-        }
-
-        return 0;
-    }
-
-    /*
-     * If we have a verbs context, that means that some other than '[::]' was
-     * used by the management software for binding. In which case we can
-     * actually warn the user about a potentially broken kernel.
-     */
-
-    /* IB ports start with 1, not 0 */
-    if (ibv_query_port(verbs, 1, &port_attr)) {
-        error_setg(errp, "RDMA ERROR: Could not query initial IB port");
-        return -1;
-    }
-
-    if (port_attr.link_layer == IBV_LINK_LAYER_ETHERNET) {
-        error_setg(errp, "RDMA ERROR: "
-                   "Linux kernel's RoCE / iWARP does not support IPv6 "
-                   "(but patches on linux-rdma in progress)");
-        return -1;
-    }
-
-#endif
-
-    return 0;
-}
-
-/*
  * Figure out which RDMA device corresponds to the requested IP hostname
  * Also create the initial connection manager identifiers for opening
  * the connection.
  */
 static int qemu_rdma_resolve_host(RDMAContext *rdma, Error **errp)
 {
-    Error *err = NULL;
     int ret;
     struct rdma_addrinfo *res;
     char port_str[16];
@@ -953,9 +809,8 @@ static int qemu_rdma_resolve_host(RDMAContext *rdma, Error **errp)
         goto err_resolve_get_addr;
     }
 
-    /* Try all addresses, saving the first error in @err */
+    /* Try all addresses, exit loop on first success of resolving address */
     for (struct rdma_addrinfo *e = res; e != NULL; e = e->ai_next) {
-        Error **local_errp = err ? NULL : &err;
 
         inet_ntop(e->ai_family,
             &((struct sockaddr_in *) e->ai_dst_addr)->sin_addr, ip, sizeof ip);
@@ -964,25 +819,12 @@ static int qemu_rdma_resolve_host(RDMAContext *rdma, Error **errp)
         ret = rdma_resolve_addr(rdma->cm_id, NULL, e->ai_dst_addr,
                 RDMA_RESOLVE_TIMEOUT_MS);
         if (ret >= 0) {
-            if (e->ai_family == AF_INET6) {
-                ret = qemu_rdma_broken_ipv6_kernel(rdma->cm_id->verbs,
-                                                   local_errp);
-                if (ret < 0) {
-                    continue;
-                }
-            }
-            error_free(err);
             goto route;
         }
     }
 
     rdma_freeaddrinfo(res);
-    if (err) {
-        error_propagate(errp, err);
-    } else {
-        error_setg(errp, "RDMA ERROR: could not resolve address %s",
-                   rdma->host);
-    }
+    error_setg(errp, "RDMA ERROR: could not resolve address %s", rdma->host);
     goto err_resolve_get_addr;
 
 route:
@@ -2611,7 +2453,6 @@ err_rdma_source_connect:
 
 static int qemu_rdma_dest_init(RDMAContext *rdma, Error **errp)
 {
-    Error *err = NULL;
     int ret;
     struct rdma_cm_id *listen_id;
     char ip[40] = "unknown";
@@ -2661,9 +2502,8 @@ static int qemu_rdma_dest_init(RDMAContext *rdma, Error **errp)
         goto err_dest_init_bind_addr;
     }
 
-    /* Try all addresses, saving the first error in @err */
+    /* Try all addresses */
     for (e = res; e != NULL; e = e->ai_next) {
-        Error **local_errp = err ? NULL : &err;
 
         inet_ntop(e->ai_family,
             &((struct sockaddr_in *) e->ai_dst_addr)->sin_addr, ip, sizeof ip);
@@ -2672,24 +2512,12 @@ static int qemu_rdma_dest_init(RDMAContext *rdma, Error **errp)
         if (ret < 0) {
             continue;
         }
-        if (e->ai_family == AF_INET6) {
-            ret = qemu_rdma_broken_ipv6_kernel(listen_id->verbs,
-                                               local_errp);
-            if (ret < 0) {
-                continue;
-            }
-        }
-        error_free(err);
         break;
     }
 
     rdma_freeaddrinfo(res);
     if (!e) {
-        if (err) {
-            error_propagate(errp, err);
-        } else {
-            error_setg(errp, "RDMA ERROR: Error: could not rdma_bind_addr!");
-        }
+        error_setg(errp, "RDMA ERROR: Error: could not rdma_bind_addr!");
         goto err_dest_init_bind_addr;
     }
 
@@ -3284,14 +3112,11 @@ err:
 int rdma_control_save_page(QEMUFile *f, ram_addr_t block_offset,
                            ram_addr_t offset, size_t size)
 {
-    if (!migrate_rdma() || migration_in_postcopy()) {
-        return RAM_SAVE_CONTROL_NOT_SUPP;
-    }
+    assert(migrate_rdma());
 
     int ret = qemu_rdma_save_page(f, block_offset, offset, size);
 
-    if (ret != RAM_SAVE_CONTROL_DELAYED &&
-        ret != RAM_SAVE_CONTROL_NOT_SUPP) {
+    if (ret != RAM_SAVE_CONTROL_DELAYED) {
         if (ret < 0) {
             qemu_file_set_error(f, ret);
         }
@@ -3829,7 +3654,7 @@ int rdma_block_notification_handle(QEMUFile *f, const char *name)
 
 int rdma_registration_start(QEMUFile *f, uint64_t flags)
 {
-    if (!migrate_rdma() || migration_in_postcopy()) {
+    if (!migrate_rdma()) {
         return 0;
     }
 
@@ -3861,7 +3686,7 @@ int rdma_registration_stop(QEMUFile *f, uint64_t flags)
     RDMAControlHeader head = { .len = 0, .repeat = 1 };
     int ret;
 
-    if (!migrate_rdma() || migration_in_postcopy()) {
+    if (!migrate_rdma()) {
         return 0;
     }
 
@@ -3985,7 +3810,7 @@ static void qio_channel_rdma_finalize(Object *obj)
 }
 
 static void qio_channel_rdma_class_init(ObjectClass *klass,
-                                        void *class_data G_GNUC_UNUSED)
+                                        const void *class_data G_GNUC_UNUSED)
 {
     QIOChannelClass *ioc_klass = QIO_CHANNEL_CLASS(klass);