1 files changed, 69 insertions, 6 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f89e7fd59a4c..77eb60d2b496 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -169,6 +169,7 @@ struct skb_shared_hwtstamps {
  * @software:           generate software time stamp
  * @in_progress:        device driver is going to provide
  *                      hardware time stamp
+ * @prevent_sk_orphan:  make sk reference available on driver level
  * @flags:              all shared_tx flags
  *
  * These flags are attached to packets as part of the
@@ -178,7 +179,8 @@ union skb_shared_tx {
         struct {
                 __u8    hardware:1,
                         software:1,
-                        in_progress:1;
+                        in_progress:1,
+                        prevent_sk_orphan:1;
         };
         __u8 flags;
 };
@@ -202,10 +204,11 @@ struct skb_shared_info {
          */
         atomic_t        dataref;
 
-        skb_frag_t      frags[MAX_SKB_FRAGS];
         /* Intermediate layers must ensure that destructor_arg
          * remains valid until skb destructor */
         void *          destructor_arg;
+        /* must be last field, see pskb_expand_head() */
+        skb_frag_t      frags[MAX_SKB_FRAGS];
 };
 
 /* We divide dataref into two halves.  The higher 16 bits hold references
@@ -1376,6 +1379,11 @@ static inline int skb_network_offset(const struct sk_buff *skb)
         return skb_network_header(skb) - skb->data;
 }
 
+static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len)
+{
+        return pskb_may_pull(skb, skb_network_offset(skb) + len);
+}
+
 /*
  * CPUs often take a performance hit when accessing unaligned memory
  * locations. The actual performance hit varies, it can be small if the
@@ -1414,12 +1422,14 @@ static inline int skb_network_offset(const struct sk_buff *skb)
  *
  * Various parts of the networking layer expect at least 32 bytes of
  * headroom, you should not reduce this.
- * With RPS, we raised NET_SKB_PAD to 64 so that get_rps_cpus() fetches span
- * a 64 bytes aligned block to fit modern (>= 64 bytes) cache line sizes
+ *
+ * Using max(32, L1_CACHE_BYTES) makes sense (especially with RPS)
+ * to reduce average number of cache lines per packet.
+ * get_rps_cpus() for example only access one 64 bytes aligned block :
  * NET_IP_ALIGN(2) + ethernet_header(14) + IP_header(20/40) + ports(8)
  */
 #ifndef NET_SKB_PAD
-#define NET_SKB_PAD     64
+#define NET_SKB_PAD     max(32, L1_CACHE_BYTES)
 #endif
 
 extern int ___pskb_trim(struct sk_buff *skb, unsigned int len);
@@ -1931,6 +1941,36 @@ static inline ktime_t net_invalid_timestamp(void)
         return ktime_set(0, 0);
 }
 
+extern void skb_timestamping_init(void);
+
+#ifdef CONFIG_NETWORK_PHY_TIMESTAMPING
+
+extern void skb_clone_tx_timestamp(struct sk_buff *skb);
+extern bool skb_defer_rx_timestamp(struct sk_buff *skb);
+
+#else /* CONFIG_NETWORK_PHY_TIMESTAMPING */
+
+static inline void skb_clone_tx_timestamp(struct sk_buff *skb)
+{
+}
+
+static inline bool skb_defer_rx_timestamp(struct sk_buff *skb)
+{
+        return false;
+}
+
+#endif /* !CONFIG_NETWORK_PHY_TIMESTAMPING */
+
+/**
+ * skb_complete_tx_timestamp() - deliver cloned skb with tx timestamps
+ *
+ * @skb: clone of the the original outgoing packet
+ * @hwtstamps: hardware time stamps
+ *
+ */
+void skb_complete_tx_timestamp(struct sk_buff *skb,
+                               struct skb_shared_hwtstamps *hwtstamps);
+
 /**
  * skb_tstamp_tx - queue clone of skb with send time stamps
  * @orig_skb:   the original outgoing packet
@@ -1945,6 +1985,28 @@ static inline ktime_t net_invalid_timestamp(void)
 extern void skb_tstamp_tx(struct sk_buff *orig_skb,
                         struct skb_shared_hwtstamps *hwtstamps);
 
+static inline void sw_tx_timestamp(struct sk_buff *skb)
+{
+        union skb_shared_tx *shtx = skb_tx(skb);
+        if (shtx->software && !shtx->in_progress)
+                skb_tstamp_tx(skb, NULL);
+}
+
+/**
+ * skb_tx_timestamp() - Driver hook for transmit timestamping
+ *
+ * Ethernet MAC Drivers should call this function in their hard_xmit()
+ * function as soon as possible after giving the sk_buff to the MAC
+ * hardware, but before freeing the sk_buff.
+ *
+ * @skb: A socket buffer.
+ */
+static inline void skb_tx_timestamp(struct sk_buff *skb)
+{
+        skb_clone_tx_timestamp(skb);
+        sw_tx_timestamp(skb);
+}
+
 extern __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len);
 extern __sum16 __skb_checksum_complete(struct sk_buff *skb);
 
@@ -2132,7 +2194,8 @@ static inline bool skb_warn_if_lro(const struct sk_buff *skb)
         /* LRO sets gso_size but not gso_type, whereas if GSO is really
          * wanted then gso_type will be set. */
         struct skb_shared_info *shinfo = skb_shinfo(skb);
-        if (shinfo->gso_size != 0 && unlikely(shinfo->gso_type == 0)) {
+        if (skb_is_nonlinear(skb) && shinfo->gso_size != 0 &&
+            unlikely(shinfo->gso_type == 0)) {
                 __skb_warn_lro_forwarding(skb);
                 return true;
         }