Merge tag 'net-pull-request' of https://github.com/jasowang/qemu into staging

# -----BEGIN PGP SIGNATURE-----
#
# iQEzBAABCAAdFiEEIV1G9IJGaJ7HfzVi7wSWWzmNYhEFAmZewo4ACgkQ7wSWWzmN
# YhHhxgf/ZaECxru4fP8wi34XdSG/PR+BF+W5M9gZIRGrHg3vIf3/LRTpZTDccbRN
# Qpwtypr9O6/AWG9Os80rn7alsmMDxN8PDDNLa9T3wf5pJUQSyQ87Yy0MiuTNPSKD
# HKYUIfIlbFCM5WUW4huMmg98gKTgnzZMqOoRyMFZitbkR59qCm+Exws4HtXvCH68
# 3k4lgvnFccmzO9iIzaOUIPs+Yf04Kw/FrY0Q/6nypvqbF2W80Md6w02JMQuTLwdF
# Guxeg/n6g0NLvCBbkjiM2VWfTaWJYbwFSwRTAMxM/geqh7qAgGsmD0N5lPlgqRDy
# uAy2GvFyrwzcD0lYqf0/fRK0Go0HPA==
# =J70K
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 04 Jun 2024 02:30:22 AM CDT
# gpg:                using RSA key 215D46F48246689EC77F3562EF04965B398D6211
# gpg: Good signature from "Jason Wang (Jason Wang on RedHat) <jasowang@redhat.com>" [undefined]
# 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: 215D 46F4 8246 689E C77F  3562 EF04 965B 398D 6211

* tag 'net-pull-request' of https://github.com/jasowang/qemu:
  ebpf: Added traces back. Changed source set for eBPF to 'system'.
  virtio-net: drop too short packets early
  ebpf: Add a separate target for skeleton
  ebpf: Refactor tun_rss_steering_prog()
  ebpf: Return 0 when configuration fails
  ebpf: Fix RSS error handling
  virtio-net: Do not write hashes to peer buffer
  virtio-net: Always set populate_hash
  virtio-net: Unify the logic to update NIC state for RSS
  virtio-net: Disable RSS on reset
  virtio-net: Shrink header byte swapping buffer
  virtio-net: Copy header only when necessary
  virtio-net: Add only one queue pair when realizing
  virtio-net: Do not propagate ebpf-rss-fds errors
  tap: Shrink zeroed virtio-net header
  tap: Call tap_receive_iov() from tap_receive()
  net: Remove receive_raw()
  net: Move virtio-net header length assertion
  tap: Remove qemu_using_vnet_hdr()
  tap: Remove tap_probe_vnet_hdr_len()

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

1 files changed, 128 insertions, 154 deletions

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 24e5e7d347..9c7e85caea 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -360,7 +360,8 @@ static void virtio_net_vnet_endian_status(VirtIONet *n, uint8_t status)
          * can't do it, we fallback onto fixing the headers in the core
          * virtio-net code.
          */
-        n->needs_vnet_hdr_swap = virtio_net_set_vnet_endian(vdev, n->nic->ncs,
+        n->needs_vnet_hdr_swap = n->has_vnet_hdr &&
+                                 virtio_net_set_vnet_endian(vdev, n->nic->ncs,
                                                             queue_pairs, true);
     } else if (virtio_net_started(n, vdev->status)) {
         /* After using the device, we need to reset the network backend to
@@ -599,40 +600,6 @@ static void virtio_net_queue_enable(VirtIODevice *vdev, uint32_t queue_index)
     }
 }
 
-static void virtio_net_reset(VirtIODevice *vdev)
-{
-    VirtIONet *n = VIRTIO_NET(vdev);
-    int i;
-
-    /* Reset back to compatibility mode */
-    n->promisc = 1;
-    n->allmulti = 0;
-    n->alluni = 0;
-    n->nomulti = 0;
-    n->nouni = 0;
-    n->nobcast = 0;
-    /* multiqueue is disabled by default */
-    n->curr_queue_pairs = 1;
-    timer_del(n->announce_timer.tm);
-    n->announce_timer.round = 0;
-    n->status &= ~VIRTIO_NET_S_ANNOUNCE;
-
-    /* Flush any MAC and VLAN filter table state */
-    n->mac_table.in_use = 0;
-    n->mac_table.first_multi = 0;
-    n->mac_table.multi_overflow = 0;
-    n->mac_table.uni_overflow = 0;
-    memset(n->mac_table.macs, 0, MAC_TABLE_ENTRIES * ETH_ALEN);
-    memcpy(&n->mac[0], &n->nic->conf->macaddr, sizeof(n->mac));
-    qemu_format_nic_info_str(qemu_get_queue(n->nic), n->mac);
-    memset(n->vlans, 0, MAX_VLAN >> 3);
-
-    /* Flush any async TX */
-    for (i = 0;  i < n->max_queue_pairs; i++) {
-        flush_or_purge_queued_packets(qemu_get_subqueue(n->nic, i));
-    }
-}
-
 static void peer_test_vnet_hdr(VirtIONet *n)
 {
     NetClientState *nc = qemu_get_queue(n->nic);
@@ -675,11 +642,6 @@ static void virtio_net_set_mrg_rx_bufs(VirtIONet *n, int mergeable_rx_bufs,
 
     n->mergeable_rx_bufs = mergeable_rx_bufs;
 
-    /*
-     * Note: when extending the vnet header, please make sure to
-     * change the vnet header copying logic in virtio_net_flush_tx()
-     * as well.
-     */
     if (version_1) {
         n->guest_hdr_len = hash_report ?
             sizeof(struct virtio_net_hdr_v1_hash) :
@@ -689,6 +651,7 @@ 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_queue_pairs; i++) {
@@ -1270,18 +1233,6 @@ 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);
@@ -1329,24 +1280,56 @@ static void virtio_net_detach_epbf_rss(VirtIONet *n)
     virtio_net_attach_ebpf_to_backend(n->nic, -1);
 }
 
-static bool virtio_net_load_ebpf_fds(VirtIONet *n, Error **errp)
+static void virtio_net_commit_rss_config(VirtIONet *n)
+{
+    if (n->rss_data.enabled) {
+        n->rss_data.enabled_software_rss = n->rss_data.populate_hash;
+        if (n->rss_data.populate_hash) {
+            virtio_net_detach_epbf_rss(n);
+        } else if (!virtio_net_attach_epbf_rss(n)) {
+            if (get_vhost_net(qemu_get_queue(n->nic)->peer)) {
+                warn_report("Can't load eBPF RSS for vhost");
+            } else {
+                warn_report("Can't 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 {
+        virtio_net_detach_epbf_rss(n);
+        trace_virtio_net_rss_disable();
+    }
+}
+
+static void virtio_net_disable_rss(VirtIONet *n)
+{
+    if (!n->rss_data.enabled) {
+        return;
+    }
+
+    n->rss_data.enabled = false;
+    virtio_net_commit_rss_config(n);
+}
+
+static bool virtio_net_load_ebpf_fds(VirtIONet *n)
 {
     int fds[EBPF_RSS_MAX_FDS] = { [0 ... EBPF_RSS_MAX_FDS - 1] = -1};
     int ret = true;
     int i = 0;
 
-    ERRP_GUARD();
-
     if (n->nr_ebpf_rss_fds != EBPF_RSS_MAX_FDS) {
-        error_setg(errp,
-                  "Expected %d file descriptors but got %d",
-                  EBPF_RSS_MAX_FDS, n->nr_ebpf_rss_fds);
+        warn_report("Expected %d file descriptors but got %d",
+                    EBPF_RSS_MAX_FDS, n->nr_ebpf_rss_fds);
        return false;
    }
 
     for (i = 0; i < n->nr_ebpf_rss_fds; i++) {
-        fds[i] = monitor_fd_param(monitor_cur(), n->ebpf_rss_fds[i], errp);
-        if (*errp) {
+        fds[i] = monitor_fd_param(monitor_cur(), n->ebpf_rss_fds[i],
+                                  &error_warn);
+        if (fds[i] < 0) {
             ret = false;
             goto exit;
         }
@@ -1355,7 +1338,7 @@ static bool virtio_net_load_ebpf_fds(VirtIONet *n, Error **errp)
     ret = ebpf_rss_load_fds(&n->ebpf_rss, fds[0], fds[1], fds[2], fds[3]);
 
 exit:
-    if (!ret || *errp) {
+    if (!ret) {
         for (i = 0; i < n->nr_ebpf_rss_fds && fds[i] != -1; i++) {
             close(fds[i]);
         }
@@ -1364,13 +1347,12 @@ exit:
     return ret;
 }
 
-static bool virtio_net_load_ebpf(VirtIONet *n, Error **errp)
+static bool virtio_net_load_ebpf(VirtIONet *n)
 {
     bool ret = false;
 
     if (virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
-        if (!(n->ebpf_rss_fds
-                && virtio_net_load_ebpf_fds(n, errp))) {
+        if (!(n->ebpf_rss_fds && virtio_net_load_ebpf_fds(n))) {
             ret = ebpf_rss_load(&n->ebpf_rss);
         }
     }
@@ -1496,28 +1478,7 @@ 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);
+    virtio_net_commit_rss_config(n);
     return queue_pairs;
 error:
     trace_virtio_net_rss_error(err_msg, err_value);
@@ -1869,16 +1830,9 @@ static uint8_t virtio_net_get_hash_type(bool hasip4,
     return 0xff;
 }
 
-static void virtio_set_packet_hash(const uint8_t *buf, uint8_t report,
-                                   uint32_t hash)
-{
-    struct virtio_net_hdr_v1_hash *hdr = (void *)buf;
-    hdr->hash_value = hash;
-    hdr->hash_report = report;
-}
-
 static int virtio_net_process_rss(NetClientState *nc, const uint8_t *buf,
-                                  size_t size)
+                                  size_t size,
+                                  struct virtio_net_hdr_v1_hash *hdr)
 {
     VirtIONet *n = qemu_get_nic_opaque(nc);
     unsigned int index = nc->queue_index, new_index = index;
@@ -1909,7 +1863,8 @@ static int virtio_net_process_rss(NetClientState *nc, const uint8_t *buf,
                                              n->rss_data.hash_types);
     if (net_hash_type > NetPktRssIpV6UdpEx) {
         if (n->rss_data.populate_hash) {
-            virtio_set_packet_hash(buf, VIRTIO_NET_HASH_REPORT_NONE, 0);
+            hdr->hash_value = VIRTIO_NET_HASH_REPORT_NONE;
+            hdr->hash_report = 0;
         }
         return n->rss_data.redirect ? n->rss_data.default_queue : -1;
     }
@@ -1917,7 +1872,8 @@ static int virtio_net_process_rss(NetClientState *nc, const uint8_t *buf,
     hash = net_rx_pkt_calc_rss_hash(pkt, net_hash_type, n->rss_data.key);
 
     if (n->rss_data.populate_hash) {
-        virtio_set_packet_hash(buf, reports[net_hash_type], hash);
+        hdr->hash_value = hash;
+        hdr->hash_report = reports[net_hash_type];
     }
 
     if (n->rss_data.redirect) {
@@ -1937,7 +1893,7 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
     VirtQueueElement *elems[VIRTQUEUE_MAX_SIZE];
     size_t lens[VIRTQUEUE_MAX_SIZE];
     struct iovec mhdr_sg[VIRTQUEUE_MAX_SIZE];
-    struct virtio_net_hdr_mrg_rxbuf mhdr;
+    struct virtio_net_hdr_v1_hash extra_hdr;
     unsigned mhdr_cnt = 0;
     size_t offset, i, guest_offset, j;
     ssize_t err;
@@ -1947,7 +1903,7 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
     }
 
     if (!no_rss && n->rss_data.enabled && n->rss_data.enabled_software_rss) {
-        int index = virtio_net_process_rss(nc, buf, size);
+        int index = virtio_net_process_rss(nc, buf, size, &extra_hdr);
         if (index >= 0) {
             NetClientState *nc2 = qemu_get_subqueue(n->nic, index);
             return virtio_net_receive_rcu(nc2, buf, size, true);
@@ -2007,15 +1963,17 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
             if (n->mergeable_rx_bufs) {
                 mhdr_cnt = iov_copy(mhdr_sg, ARRAY_SIZE(mhdr_sg),
                                     sg, elem->in_num,
-                                    offsetof(typeof(mhdr), num_buffers),
-                                    sizeof(mhdr.num_buffers));
+                                    offsetof(typeof(extra_hdr), hdr.num_buffers),
+                                    sizeof(extra_hdr.hdr.num_buffers));
             }
 
             receive_header(n, sg, elem->in_num, buf, size);
             if (n->rss_data.populate_hash) {
-                offset = sizeof(mhdr);
+                offset = offsetof(typeof(extra_hdr), hash_value);
                 iov_from_buf(sg, elem->in_num, offset,
-                             buf + offset, n->host_hdr_len - sizeof(mhdr));
+                             (char *)&extra_hdr + offset,
+                             sizeof(extra_hdr.hash_value) +
+                             sizeof(extra_hdr.hash_report));
             }
             offset = n->host_hdr_len;
             total += n->guest_hdr_len;
@@ -2045,10 +2003,11 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf,
     }
 
     if (mhdr_cnt) {
-        virtio_stw_p(vdev, &mhdr.num_buffers, i);
+        virtio_stw_p(vdev, &extra_hdr.hdr.num_buffers, i);
         iov_from_buf(mhdr_sg, mhdr_cnt,
                      0,
-                     &mhdr.num_buffers, sizeof mhdr.num_buffers);
+                     &extra_hdr.hdr.num_buffers,
+                     sizeof extra_hdr.hdr.num_buffers);
     }
 
     for (j = 0; j < i; j++) {
@@ -2738,7 +2697,7 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q)
         ssize_t ret;
         unsigned int out_num;
         struct iovec sg[VIRTQUEUE_MAX_SIZE], sg2[VIRTQUEUE_MAX_SIZE + 1], *out_sg;
-        struct virtio_net_hdr_v1_hash vhdr;
+        struct virtio_net_hdr vhdr;
 
         elem = virtqueue_pop(q->tx_vq, sizeof(VirtQueueElement));
         if (!elem) {
@@ -2749,32 +2708,25 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q)
         out_sg = elem->out_sg;
         if (out_num < 1) {
             virtio_error(vdev, "virtio-net header not in first element");
-            virtqueue_detach_element(q->tx_vq, elem, 0);
-            g_free(elem);
-            return -EINVAL;
+            goto detach;
         }
 
-        if (n->has_vnet_hdr) {
-            if (iov_to_buf(out_sg, out_num, 0, &vhdr, n->guest_hdr_len) <
-                n->guest_hdr_len) {
+        if (n->needs_vnet_hdr_swap) {
+            if (iov_to_buf(out_sg, out_num, 0, &vhdr, sizeof(vhdr)) <
+                sizeof(vhdr)) {
                 virtio_error(vdev, "virtio-net header incorrect");
-                virtqueue_detach_element(q->tx_vq, elem, 0);
-                g_free(elem);
-                return -EINVAL;
+                goto detach;
             }
-            if (n->needs_vnet_hdr_swap) {
-                virtio_net_hdr_swap(vdev, (void *) &vhdr);
-                sg2[0].iov_base = &vhdr;
-                sg2[0].iov_len = n->guest_hdr_len;
-                out_num = iov_copy(&sg2[1], ARRAY_SIZE(sg2) - 1,
-                                   out_sg, out_num,
-                                   n->guest_hdr_len, -1);
-                if (out_num == VIRTQUEUE_MAX_SIZE) {
-                    goto drop;
-                }
-                out_num += 1;
-                out_sg = sg2;
+            virtio_net_hdr_swap(vdev, &vhdr);
+            sg2[0].iov_base = &vhdr;
+            sg2[0].iov_len = sizeof(vhdr);
+            out_num = iov_copy(&sg2[1], ARRAY_SIZE(sg2) - 1, out_sg, out_num,
+                               sizeof(vhdr), -1);
+            if (out_num == VIRTQUEUE_MAX_SIZE) {
+                goto drop;
             }
+            out_num += 1;
+            out_sg = sg2;
         }
         /*
          * If host wants to see the guest header as is, we can
@@ -2791,6 +2743,11 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q)
                              n->guest_hdr_len, -1);
             out_num = sg_num;
             out_sg = sg;
+
+            if (out_num < 1) {
+                virtio_error(vdev, "virtio-net nothing to send");
+                goto detach;
+            }
         }
 
         ret = qemu_sendv_packet_async(qemu_get_subqueue(n->nic, queue_index),
@@ -2811,6 +2768,11 @@ drop:
         }
     }
     return num_packets;
+
+detach:
+    virtqueue_detach_element(q->tx_vq, elem, 0);
+    g_free(elem);
+    return -EINVAL;
 }
 
 static void virtio_net_tx_timer(void *opaque);
@@ -3120,26 +3082,7 @@ static int virtio_net_post_load_device(void *opaque, int version_id)
         }
     }
 
-    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)) {
-                    warn_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();
-    }
+    virtio_net_commit_rss_config(n);
     return 0;
 }
 
@@ -3746,9 +3689,7 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp)
     n->net_conf.tx_queue_size = MIN(virtio_net_max_tx_queue_size(n),
                                     n->net_conf.tx_queue_size);
 
-    for (i = 0; i < n->max_queue_pairs; i++) {
-        virtio_net_add_queue(n, i);
-    }
+    virtio_net_add_queue(n, 0);
 
     n->ctrl_vq = virtio_add_queue(vdev, 64, virtio_net_handle_ctrl);
     qemu_macaddr_default_if_unset(&n->nic_conf.macaddr);
@@ -3778,9 +3719,6 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp)
 
     peer_test_vnet_hdr(n);
     if (peer_has_vnet_hdr(n)) {
-        for (i = 0; i < n->max_queue_pairs; i++) {
-            qemu_using_vnet_hdr(qemu_get_subqueue(n->nic, i)->peer, true);
-        }
         n->host_hdr_len = sizeof(struct virtio_net_hdr);
     } else {
         n->host_hdr_len = 0;
@@ -3812,7 +3750,7 @@ static void virtio_net_device_realize(DeviceState *dev, Error **errp)
     net_rx_pkt_init(&n->rx_pkt);
 
     if (virtio_has_feature(n->host_features, VIRTIO_NET_F_RSS)) {
-        virtio_net_load_ebpf(n, errp);
+        virtio_net_load_ebpf(n);
     }
 }
 
@@ -3860,6 +3798,42 @@ static void virtio_net_device_unrealize(DeviceState *dev)
     virtio_cleanup(vdev);
 }
 
+static void virtio_net_reset(VirtIODevice *vdev)
+{
+    VirtIONet *n = VIRTIO_NET(vdev);
+    int i;
+
+    /* Reset back to compatibility mode */
+    n->promisc = 1;
+    n->allmulti = 0;
+    n->alluni = 0;
+    n->nomulti = 0;
+    n->nouni = 0;
+    n->nobcast = 0;
+    /* multiqueue is disabled by default */
+    n->curr_queue_pairs = 1;
+    timer_del(n->announce_timer.tm);
+    n->announce_timer.round = 0;
+    n->status &= ~VIRTIO_NET_S_ANNOUNCE;
+
+    /* Flush any MAC and VLAN filter table state */
+    n->mac_table.in_use = 0;
+    n->mac_table.first_multi = 0;
+    n->mac_table.multi_overflow = 0;
+    n->mac_table.uni_overflow = 0;
+    memset(n->mac_table.macs, 0, MAC_TABLE_ENTRIES * ETH_ALEN);
+    memcpy(&n->mac[0], &n->nic->conf->macaddr, sizeof(n->mac));
+    qemu_format_nic_info_str(qemu_get_queue(n->nic), n->mac);
+    memset(n->vlans, 0, MAX_VLAN >> 3);
+
+    /* Flush any async TX */
+    for (i = 0;  i < n->max_queue_pairs; i++) {
+        flush_or_purge_queued_packets(qemu_get_subqueue(n->nic, i));
+    }
+
+    virtio_net_disable_rss(n);
+}
+
 static void virtio_net_instance_init(Object *obj)
 {
     VirtIONet *n = VIRTIO_NET(obj);