V3migration for review

hw/net/vhost_net.c

@@ -71,6 +71,8 @@ static const int user_feature_bits[] = {
     VIRTIO_NET_F_MTU,
     VIRTIO_F_IOMMU_PLATFORM,
     VIRTIO_F_RING_PACKED,
+    VIRTIO_NET_F_RSS,
+    VIRTIO_NET_F_HASH_REPORT,
 
     /* This bit implies RARP isn't sent by QEMU out of band */
     VIRTIO_NET_F_GUEST_ANNOUNCE,

hw/net/virtio-net.c

@@ -515,6 +515,15 @@ static RxFilterInfo *virtio_net_query_rxfilter(NetClientState *nc)
     return info;
 }
 
+static void virtio_net_allow_vhost(VirtIONet *n, bool allow)
+{
+    int i;
+    for (i = 0; i < n->max_queues; i++) {
+        NetClientState *nc = qemu_get_subqueue(n->nic, i)->peer;
+        nc->vhost_net_disabled = !allow;
+    }
+}
+
 static void virtio_net_reset(VirtIODevice *vdev)
 {
     VirtIONet *n = VIRTIO_NET(vdev);
@@ -552,6 +561,7 @@ static void virtio_net_reset(VirtIODevice *vdev)
             assert(!virtio_net_get_subqueue(nc)->async_tx.elem);
         }
     }
+    virtio_net_allow_vhost(n, true);
 }
 
 static void peer_test_vnet_hdr(VirtIONet *n)
@@ -596,6 +606,7 @@ static void virtio_net_set_mrg_rx_bufs(VirtIONet *n, int mergeable_rx_bufs,
         n->guest_hdr_len = n->mergeable_rx_bufs ?
             sizeof(struct virtio_net_hdr_mrg_rxbuf) :
             sizeof(struct virtio_net_hdr);
+        n->rss_data.populate_hash = false;
     }
 
     for (i = 0; i < n->max_queues; i++) {
@@ -725,9 +736,8 @@ static uint64_t virtio_net_get_features(VirtIODevice *vdev, uint64_t features,
         return features;
     }
 
-    virtio_clear_feature(&features, VIRTIO_NET_F_RSS);
-    virtio_clear_feature(&features, VIRTIO_NET_F_HASH_REPORT);
     features = vhost_net_get_features(get_vhost_net(nc->peer), features);
+
     vdev->backend_features = features;
 
     if (n->mtu_bypass_backend &&
@@ -877,6 +887,8 @@ static void virtio_net_set_features(VirtIODevice *vdev, uint64_t features)
     VirtIONet *n = VIRTIO_NET(vdev);
     Error *err = NULL;
     int i;
+    NetClientState *nc = qemu_get_queue(n->nic);
+    bool disable_vhost = false;
 
     if (n->mtu_bypass_backend &&
             !virtio_has_feature(vdev->backend_features, VIRTIO_NET_F_MTU)) {
@@ -901,14 +913,30 @@ static void virtio_net_set_features(VirtIODevice *vdev, uint64_t features)
         virtio_has_feature(features, VIRTIO_NET_F_GUEST_TSO6);
     n->rss_data.redirect = virtio_has_feature(features, VIRTIO_NET_F_RSS);
 
+    /*
+     * disable vhost till next reset if there are acked features that
+     * we can't support with vhost
+     */
+    disable_vhost = n->rss_data.redirect && get_vhost_net(nc->peer) &&
+                    !ebpf_rss_is_loaded(&n->ebpf_rss);
+
+    if (n->rss_data.populate_hash && get_vhost_net(nc->peer)) {
+        disable_vhost = true;
+    }
+
+    if (disable_vhost) {
+        warn_report("Not using vhost till next reset");
+        virtio_net_allow_vhost(n, false);
+    }
+
     if (n->has_vnet_hdr) {
         n->curr_guest_offloads =
             virtio_net_guest_offloads_by_features(features);
         virtio_net_apply_guest_offloads(n);
     }
 
     for (i = 0;  i < n->max_queues; i++) {
-        NetClientState *nc = qemu_get_subqueue(n->nic, i);
+        nc = qemu_get_subqueue(n->nic, i);
 
         if (!get_vhost_net(nc->peer)) {
             continue;
@@ -1151,12 +1179,79 @@ static int virtio_net_handle_announce(VirtIONet *n, uint8_t cmd,
     }
 }
 
+static void virtio_net_detach_epbf_rss(VirtIONet *n);
+
 static void virtio_net_disable_rss(VirtIONet *n)
 {
     if (n->rss_data.enabled) {
         trace_virtio_net_rss_disable();
     }
     n->rss_data.enabled = false;
+
+    virtio_net_detach_epbf_rss(n);
+}
+
+static bool virtio_net_attach_ebpf_to_backend(NICState *nic, int prog_fd)
+{
+    NetClientState *nc = qemu_get_peer(qemu_get_queue(nic), 0);
+    if (nc == NULL || nc->info->set_steering_ebpf == NULL) {
+        return false;
+    }
+
+    return nc->info->set_steering_ebpf(nc, prog_fd);
+}
+
+static void rss_data_to_rss_config(struct VirtioNetRssData *data,
+                                   struct EBPFRSSConfig *config)
+{
+    config->redirect = data->redirect;
+    config->populate_hash = data->populate_hash;
+    config->hash_types = data->hash_types;
+    config->indirections_len = data->indirections_len;
+    config->default_queue = data->default_queue;
+}
+
+static bool virtio_net_attach_epbf_rss(VirtIONet *n)
+{
+    struct EBPFRSSConfig config = {};
+
+    if (!ebpf_rss_is_loaded(&n->ebpf_rss)) {
+        return false;
+    }
+
+    rss_data_to_rss_config(&n->rss_data, &config);
+
+    if (!ebpf_rss_set_all(&n->ebpf_rss, &config,
+                          n->rss_data.indirections_table, n->rss_data.key)) {
+        return false;
+    }
+
+    if (!virtio_net_attach_ebpf_to_backend(n->nic, n->ebpf_rss.program_fd)) {
+        return false;
+    }
+
+    return true;
+}
+
+static void virtio_net_detach_epbf_rss(VirtIONet *n)
+{
+    virtio_net_attach_ebpf_to_backend(n->nic, -1);
+}
+
+static bool virtio_net_load_ebpf(VirtIONet *n)
+{
+    if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
+        /* backend does't support steering ebpf */
+        return false;
+    }
+
+    return ebpf_rss_load(&n->ebpf_rss);
+}
+
+static void virtio_net_unload_ebpf(VirtIONet *n)
+{
+    virtio_net_attach_ebpf_to_backend(n->nic, -1);
+    ebpf_rss_unload(&n->ebpf_rss);
 }
 
 static uint16_t virtio_net_handle_rss(VirtIONet *n,
@@ -1271,6 +1366,25 @@ static uint16_t virtio_net_handle_rss(VirtIONet *n,
         goto error;
     }
     n->rss_data.enabled = true;
+
+    if (!n->rss_data.populate_hash) {
+        if (!virtio_net_attach_epbf_rss(n)) {
+            /* EBPF must be loaded for vhost */
+            if (get_vhost_net(qemu_get_queue(n->nic)->peer)) {
+                warn_report("Can't load eBPF RSS for vhost");
+                goto error;
+            }
+            /* fallback to software RSS */
+            warn_report("Can't load eBPF RSS - fallback to software RSS");
+            n->rss_data.enabled_software_rss = true;
+        }
+    } else {
+        /* use software RSS for hash populating */
+        /* and detach eBPF if was loaded before */
+        virtio_net_detach_epbf_rss(n);
+        n->rss_data.enabled_software_rss = true;
+    }
+
     trace_virtio_net_rss_enable(n->rss_data.hash_types,
                                 n->rss_data.indirections_len,
                                 temp.b);
@@ -1656,7 +1770,7 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
         return -1;
     }
 
-    if (!no_rss && n->rss_data.enabled) {
+    if (!no_rss && n->rss_data.enabled && n->rss_data.enabled_software_rss) {
         int index = virtio_net_process_rss(nc, buf, size);
         if (index >= 0) {
             NetClientState *nc2 = qemu_get_subqueue(n->nic, index);
@@ -2759,13 +2873,6 @@ static int virtio_net_post_load_device(void *opaque, int version_id)
         }
     }
 
-    if (n->rss_data.enabled) {
-        trace_virtio_net_rss_enable(n->rss_data.hash_types,
-                                    n->rss_data.indirections_len,
-                                    sizeof(n->rss_data.key));
-    } else {
-        trace_virtio_net_rss_disable();
-    }
     return 0;
 }
 
@@ -2782,6 +2889,26 @@ static int virtio_net_post_load_virtio(VirtIODevice *vdev)
         virtio_net_apply_guest_offloads(n);
     }
 
+    if (n->rss_data.enabled) {
+        n->rss_data.enabled_software_rss = n->rss_data.populate_hash;
+        if (!n->rss_data.populate_hash) {
+            if (!virtio_net_attach_epbf_rss(n)) {
+                if (get_vhost_net(qemu_get_queue(n->nic)->peer)) {
+                    error_report("Can't post-load eBPF RSS for vhost");
+                } else {
+                    warn_report("Can't post-load eBPF RSS - fallback to software RSS");
+                    n->rss_data.enabled_software_rss = true;
+                }
+            }
+        }
+
+        trace_virtio_net_rss_enable(n->rss_data.hash_types,
+                                    n->rss_data.indirections_len,
+                                    sizeof(n->rss_data.key));
+    } else {
+        trace_virtio_net_rss_disable();
+    }
+
     return 0;
 }
 
@@ -3336,6 +3463,9 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp)
     n->qdev = dev;
 
     net_rx_pkt_init(&n->rx_pkt, false);
+    if (virtio_has_feature(n->host_features, VIRTIO_NET_F_RSS)) {
+        virtio_net_load_ebpf(n);
+    }
 }
 
 static void virtio_net_device_unrealize(DeviceState *dev)
@@ -3344,6 +3474,8 @@ static void virtio_net_device_unrealize(DeviceState *dev)
     VirtIONet *n = VIRTIO_NET(dev);
     int i, max_queues;
 
+    virtio_net_unload_ebpf(n);
+
     /* This will stop vhost backend if appropriate. */
     virtio_net_set_status(vdev, 0);
 
@@ -3386,6 +3518,8 @@ static void virtio_net_instance_init(Object *obj)
     device_add_bootindex_property(obj, &n->nic_conf.bootindex,
                                   "bootindex", "/ethernet-phy@0",
                                   DEVICE(n));
+
+    ebpf_rss_init(&n->ebpf_rss);
 }
 
 static int virtio_net_pre_save(void *opaque)

include/hw/virtio/virtio-net.h

@@ -21,6 +21,8 @@
 #include "qemu/option_int.h"
 #include "qom/object.h"
 
+#include "ebpf/ebpf_rss.h"
+
 #define TYPE_VIRTIO_NET "virtio-net-device"
 OBJECT_DECLARE_SIMPLE_TYPE(VirtIONet, VIRTIO_NET)
 
@@ -130,6 +132,7 @@ typedef struct VirtioNetRscChain {
 
 typedef struct VirtioNetRssData {
     bool    enabled;
+    bool    enabled_software_rss;
     bool    redirect;
     bool    populate_hash;
     uint32_t hash_types;
@@ -209,6 +212,7 @@ struct VirtIONet {
     Notifier migration_state;
     VirtioNetRssData rss_data;
     struct NetRxPkt *rx_pkt;
+    struct EBPFRSSContext ebpf_rss;
 };
 
 void virtio_net_set_netclient_name(VirtIONet *n, const char *name,

net/vhost-vdpa.c

@@ -54,6 +54,8 @@ const int vdpa_feature_bits[] = {
     VIRTIO_NET_F_MTU,
     VIRTIO_F_IOMMU_PLATFORM,
     VIRTIO_F_RING_PACKED,
+    VIRTIO_NET_F_RSS,
+    VIRTIO_NET_F_HASH_REPORT,
     VIRTIO_NET_F_GUEST_ANNOUNCE,
     VIRTIO_NET_F_STATUS,
     VHOST_INVALID_FEATURE_BIT