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

# -----BEGIN PGP SIGNATURE-----
#
# iQEzBAABCAAdFiEEIV1G9IJGaJ7HfzVi7wSWWzmNYhEFAmfO1zkACgkQ7wSWWzmN
# YhET+wf+PkaGeFTNUrOtWpl35fSMKlmOVbb1fkPfuhVBmeY2Vh1EIN3OjqnzdV0F
# wxpuk+wwmFiuV1n6RNuMHQ0nz1mhgsSlZh93N5rArC/PUr3iViaT0cb82RjwxhaI
# RODBhhy7V9WxEhT9hR8sCP2ky2mrKgcYbjiIEw+IvFZOVQa58rMr2h/cbAb/iH4l
# 7T9Wba03JBqOS6qgzSFZOMxvqnYdVjhqXN8M6W9ngRJOjPEAkTB6Evwep6anRjcM
# mCUOgkf2sgQwKve8pYAeTMkzXFctvTc/qCU4ZbN8XcoKVVxe2jllGQqdOpMskPEf
# slOuINeW5M0K5gyjsb/huqcOTfDI2A==
# =/Y0+
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 10 Mar 2025 20:12:41 HKT
# gpg:                using RSA key 215D46F48246689EC77F3562EF04965B398D6211
# gpg: Good signature from "Jason Wang (Jason Wang on RedHat) <jasowang@redhat.com>" [full]
# Primary key fingerprint: 215D 46F4 8246 689E C77F  3562 EF04 965B 398D 6211

* tag 'net-pull-request' of https://github.com/jasowang/qemu:
  tap-linux: Open ipvtap and macvtap
  Revert "hw/net/net_tx_pkt: Fix overrun in update_sctp_checksum()"
  util/iov: Do not assert offset is in iov
  net: move backend cleanup to NIC cleanup
  net: parameterize the removing client from nc list

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

6 files changed, 51 insertions, 32 deletions

diff --git a/hw/net/net_tx_pkt.c b/hw/net/net_tx_pkt.c
index 1f79b82..903238d 100644
--- a/hw/net/net_tx_pkt.c
+++ b/hw/net/net_tx_pkt.c
@@ -141,10 +141,6 @@ bool net_tx_pkt_update_sctp_checksum(struct NetTxPkt *pkt)
     uint32_t csum = 0;
     struct iovec *pl_start_frag = pkt->vec + NET_TX_PKT_PL_START_FRAG;
 
-    if (iov_size(pl_start_frag, pkt->payload_frags) < 8 + sizeof(csum)) {
-        return false;
-    }
-
     if (iov_from_buf(pl_start_frag, pkt->payload_frags, 8, &csum, sizeof(csum)) < sizeof(csum)) {
         return false;
     }
diff --git a/include/qemu/iov.h b/include/qemu/iov.h
index 44f9db5..9535673 100644
--- a/include/qemu/iov.h
+++ b/include/qemu/iov.h
@@ -31,7 +31,7 @@ size_t iov_size(const struct iovec *iov, const unsigned int iov_cnt);
  * only part of data will be copied, up to the end of the iovec.
  * Number of bytes actually copied will be returned, which is
  *  min(bytes, iov_size(iov)-offset)
- * `Offset' must point to the inside of iovec.
+ * Returns 0 when `offset' points to the outside of iovec.
  */
 size_t iov_from_buf_full(const struct iovec *iov, unsigned int iov_cnt,
                          size_t offset, const void *buf, size_t bytes);
@@ -67,11 +67,12 @@ iov_to_buf(const struct iovec *iov, const unsigned int iov_cnt,
 /**
  * Set data bytes pointed out by iovec `iov' of size `iov_cnt' elements,
  * starting at byte offset `start', to value `fillc', repeating it
- * `bytes' number of times.  `Offset' must point to the inside of iovec.
+ * `bytes' number of times.
  * If `bytes' is large enough, only last bytes portion of iovec,
  * up to the end of it, will be filled with the specified value.
  * Function return actual number of bytes processed, which is
  * min(size, iov_size(iov) - offset).
+ * Returns 0 when `offset' points to the outside of iovec.
  */
 size_t iov_memset(const struct iovec *iov, const unsigned int iov_cnt,
                   size_t offset, int fillc, size_t bytes);
diff --git a/net/net.c b/net/net.c
index a3996d5..39d6f28 100644
--- a/net/net.c
+++ b/net/net.c
@@ -381,9 +381,12 @@ NetClientState *qemu_get_peer(NetClientState *nc, int queue_index)
     return ncs->peer;
 }
 
-static void qemu_cleanup_net_client(NetClientState *nc)
+static void qemu_cleanup_net_client(NetClientState *nc,
+                                    bool remove_from_net_clients)
 {
-    QTAILQ_REMOVE(&net_clients, nc, next);
+    if (remove_from_net_clients) {
+        QTAILQ_REMOVE(&net_clients, nc, next);
+    }
 
     if (nc->info->cleanup) {
         nc->info->cleanup(nc);
@@ -425,7 +428,13 @@ void qemu_del_net_client(NetClientState *nc)
         object_unparent(OBJECT(nf));
     }
 
-    /* If there is a peer NIC, delete and cleanup client, but do not free. */
+    /*
+     * If there is a peer NIC, transfer ownership to it.  Delete the client
+     * from net_client list but do not cleanup nor free.  This way NIC can
+     * still access to members of the backend.
+     *
+     * The cleanup and free will be done when the NIC is free.
+     */
     if (nc->peer && nc->peer->info->type == NET_CLIENT_DRIVER_NIC) {
         NICState *nic = qemu_get_nic(nc->peer);
         if (nic->peer_deleted) {
@@ -435,21 +444,18 @@ void qemu_del_net_client(NetClientState *nc)
 
         for (i = 0; i < queues; i++) {
             ncs[i]->peer->link_down = true;
+            QTAILQ_REMOVE(&net_clients, ncs[i], next);
         }
 
         if (nc->peer->info->link_status_changed) {
             nc->peer->info->link_status_changed(nc->peer);
         }
 
-        for (i = 0; i < queues; i++) {
-            qemu_cleanup_net_client(ncs[i]);
-        }
-
         return;
     }
 
     for (i = 0; i < queues; i++) {
-        qemu_cleanup_net_client(ncs[i]);
+        qemu_cleanup_net_client(ncs[i], true);
         qemu_free_net_client(ncs[i]);
     }
 }
@@ -462,8 +468,12 @@ void qemu_del_nic(NICState *nic)
 
     for (i = 0; i < queues; i++) {
         NetClientState *nc = qemu_get_subqueue(nic, i);
-        /* If this is a peer NIC and peer has already been deleted, free it now. */
+        /*
+         * If this is a peer NIC and peer has already been deleted, clean it up
+         * and free it now.
+         */
         if (nic->peer_deleted) {
+            qemu_cleanup_net_client(nc->peer, false);
             qemu_free_net_client(nc->peer);
         } else if (nc->peer) {
             /* if there are RX packets pending, complete them */
@@ -474,7 +484,7 @@ void qemu_del_nic(NICState *nic)
     for (i = queues - 1; i >= 0; i--) {
         NetClientState *nc = qemu_get_subqueue(nic, i);
 
-        qemu_cleanup_net_client(nc);
+        qemu_cleanup_net_client(nc, true);
         qemu_free_net_client(nc);
     }
 
@@ -1678,6 +1688,9 @@ void net_cleanup(void)
      * of the latest NET_CLIENT_DRIVER_NIC, and operate on *p as we walk
      * the list.
      *
+     * However, the NIC may have peers that trust to be clean beyond this
+     * point.  For example, if they have been removed with device_del.
+     *
      * The 'nc' variable isn't part of the list traversal; it's purely
      * for convenience as too much '(*p)->' has a tendency to make the
      * readers' eyes bleed.
@@ -1685,6 +1698,17 @@ void net_cleanup(void)
     while (*p) {
         nc = *p;
         if (nc->info->type == NET_CLIENT_DRIVER_NIC) {
+            NICState *nic = qemu_get_nic(nc);
+
+            if (nic->peer_deleted) {
+                int queues = MAX(nic->conf->peers.queues, 1);
+
+                for (int i = 0; i < queues; i++) {
+                    nc = qemu_get_subqueue(nic, i);
+                    qemu_cleanup_net_client(nc->peer, false);
+                }
+            }
+
             /* Skip NET_CLIENT_DRIVER_NIC entries */
             p = &QTAILQ_NEXT(nc, next);
         } else {
diff --git a/net/tap-linux.c b/net/tap-linux.c
index 1226d5f..22ec2f4 100644
--- a/net/tap-linux.c
+++ b/net/tap-linux.c
@@ -45,10 +45,21 @@ int tap_open(char *ifname, int ifname_size, int *vnet_hdr,
     int len = sizeof(struct virtio_net_hdr);
     unsigned int features;
 
-    fd = RETRY_ON_EINTR(open(PATH_NET_TUN, O_RDWR));
+
+    ret = if_nametoindex(ifname);
+    if (ret) {
+        g_autofree char *file = g_strdup_printf("/dev/tap%d", ret);
+        fd = open(file, O_RDWR);
+    } else {
+        fd = -1;
+    }
+
     if (fd < 0) {
-        error_setg_errno(errp, errno, "could not open %s", PATH_NET_TUN);
-        return -1;
+        fd = RETRY_ON_EINTR(open(PATH_NET_TUN, O_RDWR));
+        if (fd < 0) {
+            error_setg_errno(errp, errno, "could not open %s", PATH_NET_TUN);
+            return -1;
+        }
     }
     memset(&ifr, 0, sizeof(ifr));
     ifr.ifr_flags = IFF_TAP | IFF_NO_PI;
diff --git a/net/vhost-vdpa.c b/net/vhost-vdpa.c
index bd01866..f7a54f4 100644
--- a/net/vhost-vdpa.c
+++ b/net/vhost-vdpa.c
@@ -224,14 +224,6 @@ static void vhost_vdpa_cleanup(NetClientState *nc)
 {
     VhostVDPAState *s = DO_UPCAST(VhostVDPAState, nc, nc);
 
-    /*
-     * If a peer NIC is attached, do not cleanup anything.
-     * Cleanup will happen as a part of qemu_cleanup() -> net_cleanup()
-     * when the guest is shutting down.
-     */
-    if (nc->peer && nc->peer->info->type == NET_CLIENT_DRIVER_NIC) {
-        return;
-    }
     munmap(s->cvq_cmd_out_buffer, vhost_vdpa_net_cvq_cmd_page_len());
     munmap(s->status, vhost_vdpa_net_cvq_cmd_page_len());
     if (s->vhost_net) {
diff --git a/util/iov.c b/util/iov.c
index 7777116..f8536f0 100644
--- a/util/iov.c
+++ b/util/iov.c
@@ -37,7 +37,6 @@ size_t iov_from_buf_full(const struct iovec *iov, unsigned int iov_cnt,
             offset -= iov[i].iov_len;
         }
     }
-    assert(offset == 0);
     return done;
 }
 
@@ -56,7 +55,6 @@ size_t iov_to_buf_full(const struct iovec *iov, const unsigned int iov_cnt,
             offset -= iov[i].iov_len;
         }
     }
-    assert(offset == 0);
     return done;
 }
 
@@ -75,7 +73,6 @@ size_t iov_memset(const struct iovec *iov, const unsigned int iov_cnt,
             offset -= iov[i].iov_len;
         }
     }
-    assert(offset == 0);
     return done;
 }
 
@@ -277,7 +274,6 @@ unsigned iov_copy(struct iovec *dst_iov, unsigned int dst_iov_cnt,
         bytes -= len;
         offset = 0;
     }
-    assert(offset == 0);
     return j;
 }
 
@@ -348,7 +344,6 @@ size_t qemu_iovec_concat_iov(QEMUIOVector *dst,
             soffset -= src_iov[i].iov_len;
         }
     }
-    assert(soffset == 0); /* offset beyond end of src */
 
     return done;
 }