macvtap: simplify usage of tap_features

[~andy/linux] / drivers / net / macvtap.c

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 876c72246ae92aa30efe1291bf90a17ed042555a..448f8a505cd963843d99bcff906e0713476f709c 100644 (file)
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -68,6 +68,8 @@ static const struct proto_ops macvtap_socket_ops;
 #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \
                      NETIF_F_TSO6 | NETIF_F_UFO)
 #define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO)
+#define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG)
+
 /*
  * RCU usage:
  * The macvtap_queue and the macvlan_dev are loosely coupled, the
@@ -278,7 +280,8 @@ static int macvtap_forward(struct net_device *dev, struct sk_buff *skb)
 {
        struct macvlan_dev *vlan = netdev_priv(dev);
        struct macvtap_queue *q = macvtap_get_queue(dev, skb);
-       netdev_features_t features;
+       netdev_features_t features = TAP_FEATURES;
+
        if (!q)
                goto drop;
 
@@ -289,7 +292,7 @@ static int macvtap_forward(struct net_device *dev, struct sk_buff *skb)
        /* Apply the forward feature mask so that we perform segmentation
         * according to users wishes.
         */
-       features = netif_skb_features(skb) & vlan->tap_features;
+       features |= vlan->tap_features;
        if (netif_needs_gso(skb, features)) {
                struct sk_buff *segs = __skb_gso_segment(skb, features, false);
 
@@ -698,6 +701,28 @@ static int macvtap_skb_to_vnet_hdr(const struct sk_buff *skb,
        return 0;
 }
 
+static unsigned long iov_pages(const struct iovec *iv, int offset,
+                              unsigned long nr_segs)
+{
+       unsigned long seg, base;
+       int pages = 0, len, size;
+
+       while (nr_segs && (offset >= iv->iov_len)) {
+               offset -= iv->iov_len;
+               ++iv;
+               --nr_segs;
+       }
+
+       for (seg = 0; seg < nr_segs; seg++) {
+               base = (unsigned long)iv[seg].iov_base + offset;
+               len = iv[seg].iov_len - offset;
+               size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
+               pages += size;
+               offset = 0;
+       }
+
+       return pages;
+}
 
 /* Get packet from user space buffer */
 static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
@@ -744,31 +769,15 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
        if (unlikely(count > UIO_MAXIOV))
                goto err;
 
-       if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY))
-               zerocopy = true;
-
-       if (zerocopy) {
-               /* Userspace may produce vectors with count greater than
-                * MAX_SKB_FRAGS, so we need to linearize parts of the skb
-                * to let the rest of data to be fit in the frags.
-                */
-               if (count > MAX_SKB_FRAGS) {
-                       copylen = iov_length(iv, count - MAX_SKB_FRAGS);
-                       if (copylen < vnet_hdr_len)
-                               copylen = 0;
-                       else
-                               copylen -= vnet_hdr_len;
-               }
-               /* There are 256 bytes to be copied in skb, so there is enough
-                * room for skb expand head in case it is used.
-                * The rest buffer is mapped from userspace.
-                */
-               if (copylen < vnet_hdr.hdr_len)
-                       copylen = vnet_hdr.hdr_len;
-               if (!copylen)
-                       copylen = GOODCOPY_LEN;
+       if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) {
+               copylen = vnet_hdr.hdr_len ? vnet_hdr.hdr_len : GOODCOPY_LEN;
                linear = copylen;
-       } else {
+               if (iov_pages(iv, vnet_hdr_len + copylen, count)
+                   <= MAX_SKB_FRAGS)
+                       zerocopy = true;
+       }
+
+       if (!zerocopy) {
                copylen = len;
                linear = vnet_hdr.hdr_len;
        }
@@ -780,9 +789,15 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 
        if (zerocopy)
                err = zerocopy_sg_from_iovec(skb, iv, vnet_hdr_len, count);
-       else
+       else {
                err = skb_copy_datagram_from_iovec(skb, 0, iv, vnet_hdr_len,
                                                   len);
+               if (!err && m && m->msg_control) {
+                       struct ubuf_info *uarg = m->msg_control;
+                       uarg->callback(uarg, false);
+               }
+       }
+
        if (err)
                goto err_kfree;
 
@@ -806,10 +821,13 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
                skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
                skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
        }
-       if (vlan)
+       if (vlan) {
+               local_bh_disable();
                macvlan_start_xmit(skb, vlan->dev);
-       else
+               local_bh_enable();
+       } else {
                kfree_skb(skb);
+       }
        rcu_read_unlock();
 
        return total_len;
@@ -873,7 +891,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
                        __be16 h_vlan_proto;
                        __be16 h_vlan_TCI;
                } veth;
-               veth.h_vlan_proto = htons(ETH_P_8021Q);
+               veth.h_vlan_proto = skb->vlan_proto;
                veth.h_vlan_TCI = htons(vlan_tx_tag_get(skb));
 
                vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto);
@@ -900,8 +918,11 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
 done:
        rcu_read_lock();
        vlan = rcu_dereference(q->vlan);
-       if (vlan)
+       if (vlan) {
+               preempt_disable();
                macvlan_count_rx(vlan, copied - vnet_hdr_len, ret == 0, 0);
+               preempt_enable();
+       }
        rcu_read_unlock();
 
        return ret ? ret : copied;
@@ -1046,8 +1067,7 @@ static int set_offload(struct macvtap_queue *q, unsigned long arg)
        /* tap_features are the same as features on tun/tap and
         * reflect user expectations.
         */
-       vlan->tap_features = vlan->dev->features &
-                           (feature_mask | ~TUN_OFFLOADS);
+       vlan->tap_features = feature_mask;
        vlan->set_features = features;
        netdev_update_features(vlan->dev);
 
@@ -1107,6 +1127,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
                rtnl_lock();
                ret = macvtap_ioctl_set_queue(file, u);
                rtnl_unlock();
+               return ret;
 
        case TUNGETFEATURES:
                if (put_user(IFF_TAP | IFF_NO_PI | IFF_VNET_HDR |