net: move skb->dropcount to skb->cb[]

Commit 977750076d98 ("af_packet: add interframe drop cmsg (v6)")
unionized skb->mark and skb->dropcount in order to allow recording
of the socket drop count while maintaining struct sk_buff size.

skb->dropcount was introduced since there was no available room
in skb->cb[] in packet sockets. However, its introduction led to
the inability to export skb->mark, or any other aliased field to
userspace if so desired.

Moving the dropcount metric to skb->cb[] eliminates this problem
at the expense of 4 bytes less in skb->cb[] for protocol families
using it.

Signed-off-by: Eyal Birger <eyal.birger@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d898b32dedccccbd4bda3e79ae787018fc2fbb28..bba1330757c025fc783cf10c2d6e0cfd349f2f5c 100644 (file)
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -492,7 +492,6 @@ static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1,
   *    @napi_id: id of the NAPI struct this skb came from
  *     @secmark: security marking
  *     @mark: Generic packet mark
- *     @dropcount: total number of sk_receive_queue overflows
  *     @vlan_proto: vlan encapsulation protocol
  *     @vlan_tci: vlan tag control information
  *     @inner_protocol: Protocol (encapsulation)
@@ -641,7 +640,6 @@ struct sk_buff {
 #endif
        union {
                __u32           mark;
-               __u32           dropcount;
                __u32           reserved_tailroom;
        };
 

diff --git a/include/net/sock.h b/include/net/sock.h
index 0996fe451e5f92cd4312c77317e530ccb0af80b8..38369d3580a140dd7c652b07031f91661d0a6703 100644 (file)
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2078,13 +2078,27 @@ static inline int sock_intr_errno(long timeo)
        return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR;
 }
 
+struct sock_skb_cb {
+       u32 dropcount;
+};
+
+/* Store sock_skb_cb at the end of skb->cb[] so protocol families
+ * using skb->cb[] would keep using it directly and utilize its
+ * alignement guarantee.
+ */
+#define SOCK_SKB_CB_OFFSET ((FIELD_SIZEOF(struct sk_buff, cb) - \
+                           sizeof(struct sock_skb_cb)))
+
+#define SOCK_SKB_CB(__skb) ((struct sock_skb_cb *)((__skb)->cb + \
+                           SOCK_SKB_CB_OFFSET))
+
 #define sock_skb_cb_check_size(size) \
-       BUILD_BUG_ON((size) > FIELD_SIZEOF(struct sk_buff, cb))
+       BUILD_BUG_ON((size) > SOCK_SKB_CB_OFFSET)
 
 static inline void
 sock_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb)
 {
-       skb->dropcount = atomic_read(&sk->sk_drops);
+       SOCK_SKB_CB(skb)->dropcount = atomic_read(&sk->sk_drops);
 }
 
 void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,

diff --git a/net/socket.c b/net/socket.c
index bbedbfcb42c2505fceb57fa058f262d90e1670ed..b78cf601a021c4dd4c9d91a872a2f512b92b7977 100644 (file)
--- a/net/socket.c
+++ b/net/socket.c
@@ -731,9 +731,9 @@ EXPORT_SYMBOL_GPL(__sock_recv_wifi_status);
 static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk,
                                   struct sk_buff *skb)
 {
-       if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && skb->dropcount)
+       if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && SOCK_SKB_CB(skb)->dropcount)
                put_cmsg(msg, SOL_SOCKET, SO_RXQ_OVFL,
-                       sizeof(__u32), &skb->dropcount);
+                       sizeof(__u32), &SOCK_SKB_CB(skb)->dropcount);
 }
 
 void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,