macvtap: read vnet_hdr_size once

[pandora-kernel.git] / drivers / net / macvtap.c

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 96b9e3c..1c3db94 100644 (file)
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -15,6 +15,7 @@
 #include <linux/cdev.h>
 #include <linux/fs.h>
 
+#include <net/ipv6.h>
 #include <net/net_namespace.h>
 #include <net/rtnetlink.h>
 #include <net/sock.h>
@@ -577,6 +578,8 @@ static int macvtap_skb_from_vnet_hdr(struct sk_buff *skb,
                        break;
                case VIRTIO_NET_HDR_GSO_UDP:
                        gso_type = SKB_GSO_UDP;
+                       if (skb->protocol == htons(ETH_P_IPV6))
+                               ipv6_proxy_select_ident(skb);
                        break;
                default:
                        return -EINVAL;
@@ -641,12 +644,38 @@ 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;
+}
+
+/* Neighbour code has some assumptions on HH_DATA_MOD alignment */
+#define MACVTAP_RESERVE HH_DATA_OFF(ETH_HLEN)
 
 /* Get packet from user space buffer */
 static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
                                const struct iovec *iv, unsigned long total_len,
                                size_t count, int noblock)
 {
+       int good_linear = SKB_MAX_HEAD(MACVTAP_RESERVE);
        struct sk_buff *skb;
        struct macvlan_dev *vlan;
        unsigned long len = total_len;
@@ -658,7 +687,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
        size_t linear;
 
        if (q->flags & IFF_VNET_HDR) {
-               vnet_hdr_len = q->vnet_hdr_sz;
+               vnet_hdr_len = ACCESS_ONCE(q->vnet_hdr_sz);
 
                err = -EINVAL;
                if (len < vnet_hdr_len)
@@ -687,45 +716,43 @@ 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;
+               if (copylen > good_linear)
+                       copylen = good_linear;
+               else if (copylen < ETH_HLEN)
+                       copylen = ETH_HLEN;
                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;
+               if (linear > good_linear)
+                       linear = good_linear;
+               else if (linear < ETH_HLEN)
+                       linear = ETH_HLEN;
        }
 
-       skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, copylen,
+       skb = macvtap_alloc_skb(&q->sk, MACVTAP_RESERVE, copylen,
                                linear, noblock, &err);
        if (!skb)
                goto err;
 
        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);
+               }
+       }
+
        if (err)
                goto err_kfree;
 
@@ -790,7 +817,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
 
        if (q->flags & IFF_VNET_HDR) {
                struct virtio_net_hdr vnet_hdr;
-               vnet_hdr_len = q->vnet_hdr_sz;
+               vnet_hdr_len = ACCESS_ONCE(q->vnet_hdr_sz);
                if ((len -= vnet_hdr_len) < 0)
                        return -EINVAL;