[NET]: Avoid allocating skb in skb_pad

First of all it is unnecessary to allocate a new skb in skb_pad since
the existing one is not shared.  More importantly, our hard_start_xmit
interface does not allow a new skb to be allocated since that breaks
requeueing.

This patch uses pskb_expand_head to expand the existing skb and linearize
it if needed.  Actually, someone should sift through every instance of
skb_pad on a non-linear skb as they do not fit the reasons why this was
originally created.

Incidentally, this fixes a minor bug when the skb is cloned (tcpdump,
TCP, etc.).  As it is skb_pad will simply write over a cloned skb.  Because
of the position of the write it is unlikely to cause problems but still
it's best if we don't do it.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/3c527.c

@@ -1031,8 +1031,7 @@ static int mc32_send_packet(struct sk_buff *skb, struct net_device *dev)
 		return 1;
 	}
 
-	skb = skb_padto(skb, ETH_ZLEN);
-	if (skb == NULL) {
+	if (skb_padto(skb, ETH_ZLEN)) {
 		netif_wake_queue(dev);
 		return 0;
 	}

drivers/net/82596.c

@@ -1070,8 +1070,7 @@ static int i596_start_xmit(struct sk_buff *skb, struct net_device *dev)
 				skb->len, (unsigned int)skb->data));
 
 	if (skb->len < ETH_ZLEN) {
-		skb = skb_padto(skb, ETH_ZLEN);
-		if (skb == NULL)
+		if (skb_padto(skb, ETH_ZLEN))
 			return 0;
 		length = ETH_ZLEN;
 	}

drivers/net/a2065.c

@@ -573,8 +573,7 @@ static int lance_start_xmit (struct sk_buff *skb, struct net_device *dev)
 	
 	if (len < ETH_ZLEN) {
 		len = ETH_ZLEN;
-		skb = skb_padto(skb, ETH_ZLEN);
-		if (skb == NULL)
+		if (skb_padto(skb, ETH_ZLEN))
 			return 0;
 	}
 

drivers/net/ariadne.c

@@ -607,8 +607,7 @@ static int ariadne_start_xmit(struct sk_buff *skb, struct net_device *dev)
     /* FIXME: is the 79C960 new enough to do its own padding right ? */
     if (skb->len < ETH_ZLEN)
     {
-    	skb = skb_padto(skb, ETH_ZLEN);
-    	if (skb == NULL)
+    	if (skb_padto(skb, ETH_ZLEN))
     	    return 0;
     	len = ETH_ZLEN;
     }

drivers/net/arm/ether1.c

@@ -700,8 +700,7 @@ ether1_sendpacket (struct sk_buff *skb, struct net_device *dev)
 	}
 
 	if (skb->len < ETH_ZLEN) {
-		skb = skb_padto(skb, ETH_ZLEN);
-		if (skb == NULL)
+		if (skb_padto(skb, ETH_ZLEN))
 			goto out;
 	}
 

drivers/net/arm/ether3.c

@@ -518,8 +518,7 @@ ether3_sendpacket(struct sk_buff *skb, struct net_device *dev)
 
 	length = (length + 1) & ~1;
 	if (length != skb->len) {
-		skb = skb_padto(skb, length);
-		if (skb == NULL)
+		if (skb_padto(skb, length))
 			goto out;
 	}
 

drivers/net/atarilance.c

@@ -804,8 +804,7 @@ static int lance_start_xmit( struct sk_buff *skb, struct net_device *dev )
 		++len;
 		
 	if (len > skb->len) {
-		skb = skb_padto(skb, len);
-		if (skb == NULL)
+		if (skb_padto(skb, len))
 			return 0;
 	}
 		

drivers/net/cassini.c

@@ -2915,8 +2915,7 @@ static int cas_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	 */
 	static int ring; 
 
-	skb = skb_padto(skb, cp->min_frame_size);
-	if (!skb)
+	if (skb_padto(skb, cp->min_frame_size))
 		return 0;
 
 	/* XXX: we need some higher-level QoS hooks to steer packets to

drivers/net/declance.c

@@ -885,8 +885,7 @@ static int lance_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	len = skblen;
 	
 	if (len < ETH_ZLEN) {
-		skb = skb_padto(skb, ETH_ZLEN);
-		if (skb == NULL)
+		if (skb_padto(skb, ETH_ZLEN))
 			return 0;
 		len = ETH_ZLEN;
 	}

drivers/net/depca.c

@@ -938,11 +938,8 @@ static int depca_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (skb->len < 1)
 		goto out;
 
-	if (skb->len < ETH_ZLEN) {
-		skb = skb_padto(skb, ETH_ZLEN);
-		if (skb == NULL)
-			goto out;
-	}
+	if (skb_padto(skb, ETH_ZLEN))
+		goto out;
 	
 	netif_stop_queue(dev);
 

drivers/net/eepro.c

@@ -1154,8 +1154,7 @@ static int eepro_send_packet(struct sk_buff *skb, struct net_device *dev)
 		printk(KERN_DEBUG  "%s: entering eepro_send_packet routine.\n", dev->name);
 
 	if (length < ETH_ZLEN) {
-		skb = skb_padto(skb, ETH_ZLEN);
-		if (skb == NULL)
+		if (skb_padto(skb, ETH_ZLEN))
 			return 0;
 		length = ETH_ZLEN;
 	}

drivers/net/eexpress.c

@@ -677,8 +677,7 @@ static int eexp_xmit(struct sk_buff *buf, struct net_device *dev)
 #endif
 
 	if (buf->len < ETH_ZLEN) {
-		buf = skb_padto(buf, ETH_ZLEN);
-		if (buf == NULL)
+		if (skb_padto(buf, ETH_ZLEN))
 			return 0;
 		length = ETH_ZLEN;
 	}

drivers/net/epic100.c

@@ -1027,11 +1027,8 @@ static int epic_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	u32 ctrl_word;
 	unsigned long flags;
 
-	if (skb->len < ETH_ZLEN) {
-		skb = skb_padto(skb, ETH_ZLEN);
-		if (skb == NULL)
-			return 0;
-	}
+	if (skb_padto(skb, ETH_ZLEN))
+		return 0;
 
 	/* Caution: the write order is important here, set the field with the
 	   "ownership" bit last. */

drivers/net/eth16i.c

@@ -1064,8 +1064,7 @@ static int eth16i_tx(struct sk_buff *skb, struct net_device *dev)
 	unsigned long flags;
 
 	if (length < ETH_ZLEN) {
-		skb = skb_padto(skb, ETH_ZLEN);
-		if (skb == NULL)
+		if (skb_padto(skb, ETH_ZLEN))
 			return 0;
 		length = ETH_ZLEN;
 	}

drivers/net/hp100.c

@@ -1487,11 +1487,8 @@ static int hp100_start_xmit_bm(struct sk_buff *skb, struct net_device *dev)
 	if (skb->len <= 0)
 		return 0;
 		
-	if (skb->len < ETH_ZLEN && lp->chip == HP100_CHIPID_SHASTA) {
-		skb = skb_padto(skb, ETH_ZLEN);
-		if (skb == NULL)
-			return 0;
-	}
+	if (lp->chip == HP100_CHIPID_SHASTA && skb_padto(skb, ETH_ZLEN))
+		return 0;
 
 	/* Get Tx ring tail pointer */
 	if (lp->txrtail->next == lp->txrhead) {

drivers/net/lance.c

@@ -968,8 +968,7 @@ static int lance_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* The old LANCE chips doesn't automatically pad buffers to min. size. */
 	if (chip_table[lp->chip_version].flags & LANCE_MUST_PAD) {
 		if (skb->len < ETH_ZLEN) {
-			skb = skb_padto(skb, ETH_ZLEN);
-			if (skb == NULL)
+			if (skb_padto(skb, ETH_ZLEN))
 				goto out;
 			lp->tx_ring[entry].length = -ETH_ZLEN;
 		}

drivers/net/lasi_82596.c

@@ -1083,8 +1083,7 @@ static int i596_start_xmit(struct sk_buff *skb, struct net_device *dev)
 				skb->len, skb->data));
 
 	if (length < ETH_ZLEN) {
-		skb = skb_padto(skb, ETH_ZLEN);
-		if (skb == NULL)
+		if (skb_padto(skb, ETH_ZLEN))
 			return 0;
 		length = ETH_ZLEN;
 	}

drivers/net/lp486e.c

@@ -877,8 +877,7 @@ static int i596_start_xmit (struct sk_buff *skb, struct net_device *dev) {
 	length = skb->len;
 	
 	if (length < ETH_ZLEN) {
-		skb = skb_padto(skb, ETH_ZLEN);
-		if (skb == NULL)
+		if (skb_padto(skb, ETH_ZLEN))
 			return 0;
 		length = ETH_ZLEN;
 	}

drivers/net/myri10ge/myri10ge.c

@@ -1939,8 +1939,7 @@ static int myri10ge_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		/* pad frames to at least ETH_ZLEN bytes */
 		if (unlikely(skb->len < ETH_ZLEN)) {
-			skb = skb_padto(skb, ETH_ZLEN);
-			if (skb == NULL) {
+			if (skb_padto(skb, ETH_ZLEN)) {
 				/* The packet is gone, so we must
 				 * return 0 */
 				mgp->stats.tx_dropped += 1;

drivers/net/pcmcia/fmvj18x_cs.c

@@ -831,8 +831,7 @@ static int fjn_start_xmit(struct sk_buff *skb, struct net_device *dev)
     
     if (length < ETH_ZLEN)
     {
-    	skb = skb_padto(skb, ETH_ZLEN);
-    	if (skb == NULL)
+    	if (skb_padto(skb, ETH_ZLEN))
     		return 0;
     	length = ETH_ZLEN;
     }

drivers/net/pcmcia/xirc2ps_cs.c

@@ -1374,8 +1374,7 @@ do_start_xmit(struct sk_buff *skb, struct net_device *dev)
      */
     if (pktlen < ETH_ZLEN)
     {
-        skb = skb_padto(skb, ETH_ZLEN);
-        if (skb == NULL)
+        if (skb_padto(skb, ETH_ZLEN))
         	return 0;
 	pktlen = ETH_ZLEN;
     }

drivers/net/r8169.c

@@ -2222,8 +2222,7 @@ static int rtl8169_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		len = skb->len;
 
 		if (unlikely(len < ETH_ZLEN)) {
-			skb = skb_padto(skb, ETH_ZLEN);
-			if (!skb)
+			if (skb_padto(skb, ETH_ZLEN))
 				goto err_update_stats;
 			len = ETH_ZLEN;
 		}

drivers/net/seeq8005.c

@@ -396,8 +396,7 @@ static int seeq8005_send_packet(struct sk_buff *skb, struct net_device *dev)
 	unsigned char *buf;
 
 	if (length < ETH_ZLEN) {
-		skb = skb_padto(skb, ETH_ZLEN);
-		if (skb == NULL)
+		if (skb_padto(skb, ETH_ZLEN))
 			return 0;
 		length = ETH_ZLEN;
 	}

drivers/net/sis190.c

@@ -1156,8 +1156,7 @@ static int sis190_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	dma_addr_t mapping;
 
 	if (unlikely(skb->len < ETH_ZLEN)) {
-		skb = skb_padto(skb, ETH_ZLEN);
-		if (!skb) {
+		if (skb_padto(skb, ETH_ZLEN)) {
 			tp->stats.tx_dropped++;
 			goto out;
 		}

drivers/net/sk98lin/skge.c

@@ -1525,7 +1525,7 @@ struct sk_buff	*pMessage)	/* pointer to send-message              */
 	** This is to resolve faulty padding by the HW with 0xaa bytes.
 	*/
 	if (BytesSend < C_LEN_ETHERNET_MINSIZE) {
-		if ((pMessage = skb_padto(pMessage, C_LEN_ETHERNET_MINSIZE)) == NULL) {
+		if (skb_padto(pMessage, C_LEN_ETHERNET_MINSIZE)) {
 			spin_unlock_irqrestore(&pTxPort->TxDesRingLock, Flags);
 			return 0;
 		}

drivers/net/skge.c

@@ -2310,8 +2310,7 @@ static int skge_xmit_frame(struct sk_buff *skb, struct net_device *dev)
 	u64 map;
 	unsigned long flags;
 
-	skb = skb_padto(skb, ETH_ZLEN);
-	if (!skb)
+	if (skb_padto(skb, ETH_ZLEN))
 		return NETDEV_TX_OK;
 
 	if (!spin_trylock_irqsave(&skge->tx_lock, flags))

drivers/net/smc9194.c

@@ -523,8 +523,7 @@ static int smc_wait_to_send_packet( struct sk_buff * skb, struct net_device * de
 	length = skb->len;
 
 	if (length < ETH_ZLEN) {
-		skb = skb_padto(skb, ETH_ZLEN);
-		if (skb == NULL) {
+		if (skb_padto(skb, ETH_ZLEN)) {
 			netif_wake_queue(dev);
 			return 0;
 		}

drivers/net/sonic.c

@@ -231,8 +231,7 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev)
 
 	length = skb->len;
 	if (length < ETH_ZLEN) {
-		skb = skb_padto(skb, ETH_ZLEN);
-		if (skb == NULL)
+		if (skb_padto(skb, ETH_ZLEN))
 			return 0;
 		length = ETH_ZLEN;
 	}

drivers/net/starfire.c

@@ -1349,8 +1349,7 @@ static int start_tx(struct sk_buff *skb, struct net_device *dev)
 
 #if defined(ZEROCOPY) && defined(HAS_BROKEN_FIRMWARE)
 	if (skb->ip_summed == CHECKSUM_HW) {
-		skb = skb_padto(skb, (skb->len + PADDING_MASK) & ~PADDING_MASK);
-		if (skb == NULL)
+		if (skb_padto(skb, (skb->len + PADDING_MASK) & ~PADDING_MASK))
 			return NETDEV_TX_OK;
 	}
 #endif /* ZEROCOPY && HAS_BROKEN_FIRMWARE */

drivers/net/via-rhine.c

@@ -1284,11 +1284,8 @@ static int rhine_start_tx(struct sk_buff *skb, struct net_device *dev)
 	/* Calculate the next Tx descriptor entry. */
 	entry = rp->cur_tx % TX_RING_SIZE;
 
-	if (skb->len < ETH_ZLEN) {
-		skb = skb_padto(skb, ETH_ZLEN);
-		if (skb == NULL)
-			return 0;
-	}
+	if (skb_padto(skb, ETH_ZLEN))
+		return 0;
 
 	rp->tx_skbuff[entry] = skb;
 

drivers/net/wireless/ray_cs.c

@@ -924,8 +924,7 @@ static int ray_dev_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
     if (length < ETH_ZLEN)
     {
-    	skb = skb_padto(skb, ETH_ZLEN);
-    	if (skb == NULL)
+    	if (skb_padto(skb, ETH_ZLEN))
     		return 0;
     	length = ETH_ZLEN;
     }

drivers/net/wireless/wavelan_cs.c

@@ -3194,11 +3194,8 @@ wavelan_packet_xmit(struct sk_buff *	skb,
 	 * and we don't have the Ethernet specific requirement of beeing
 	 * able to detect collisions, therefore in theory we don't really
 	 * need to pad. Jean II */
-	if (skb->len < ETH_ZLEN) {
-		skb = skb_padto(skb, ETH_ZLEN);
-		if (skb == NULL)
-			return 0;
-	}
+	if (skb_padto(skb, ETH_ZLEN))
+		return 0;
 
   wv_packet_write(dev, skb->data, skb->len);
 

drivers/net/yellowfin.c

@@ -862,13 +862,11 @@ static int yellowfin_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		/* Fix GX chipset errata. */
 		if (cacheline_end > 24  || cacheline_end == 0) {
 			len = skb->len + 32 - cacheline_end + 1;
-			if (len != skb->len)
-				skb = skb_padto(skb, len);
-		}
-		if (skb == NULL) {
-			yp->tx_skbuff[entry] = NULL;
-			netif_wake_queue(dev);
-			return 0;
+			if (skb_padto(skb, len)) {
+				yp->tx_skbuff[entry] = NULL;
+				netif_wake_queue(dev);
+				return 0;
+			}
 		}
 	}
 	yp->tx_skbuff[entry] = skb;

drivers/net/znet.c

@@ -544,8 +544,7 @@ static int znet_send_packet(struct sk_buff *skb, struct net_device *dev)
 		printk(KERN_DEBUG "%s: ZNet_send_packet.\n", dev->name);
 
 	if (length < ETH_ZLEN) {
-		skb = skb_padto(skb, ETH_ZLEN);
-		if (skb == NULL)
+		if (skb_padto(skb, ETH_ZLEN))
 			return 0;
 		length = ETH_ZLEN;
 	}

include/linux/skbuff.h

@@ -345,7 +345,7 @@ extern struct sk_buff *skb_realloc_headroom(struct sk_buff *skb,
 extern struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
 				       int newheadroom, int newtailroom,
 				       gfp_t priority);
-extern struct sk_buff *		skb_pad(struct sk_buff *skb, int pad);
+extern int	       skb_pad(struct sk_buff *skb, int pad);
 #define dev_kfree_skb(a)	kfree_skb(a)
 extern void	      skb_over_panic(struct sk_buff *skb, int len,
 				     void *here);
@@ -1122,16 +1122,15 @@ static inline int skb_cow(struct sk_buff *skb, unsigned int headroom)
  *
  *	Pads up a buffer to ensure the trailing bytes exist and are
  *	blanked. If the buffer already contains sufficient data it
- *	is untouched. Returns the buffer, which may be a replacement
- *	for the original, or NULL for out of memory - in which case
- *	the original buffer is still freed.
+ *	is untouched. Otherwise it is extended. Returns zero on
+ *	success. The skb is freed on error.
  */
  
-static inline struct sk_buff *skb_padto(struct sk_buff *skb, unsigned int len)
+static inline int skb_padto(struct sk_buff *skb, unsigned int len)
 {
 	unsigned int size = skb->len;
 	if (likely(size >= len))
-		return skb;
+		return 0;
 	return skb_pad(skb, len-size);
 }
 

net/core/skbuff.c

@@ -781,24 +781,40 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
  *	filled. Used by network drivers which may DMA or transfer data
  *	beyond the buffer end onto the wire.
  *
- *	May return NULL in out of memory cases.
+ *	May return error in out of memory cases. The skb is freed on error.
  */
  
-struct sk_buff *skb_pad(struct sk_buff *skb, int pad)
+int skb_pad(struct sk_buff *skb, int pad)
 {
-	struct sk_buff *nskb;
+	int err;
+	int ntail;
 	
 	/* If the skbuff is non linear tailroom is always zero.. */
-	if (skb_tailroom(skb) >= pad) {
+	if (!skb_cloned(skb) && skb_tailroom(skb) >= pad) {
 		memset(skb->data+skb->len, 0, pad);
-		return skb;
+		return 0;
 	}
-	
-	nskb = skb_copy_expand(skb, skb_headroom(skb), skb_tailroom(skb) + pad, GFP_ATOMIC);
+
+	ntail = skb->data_len + pad - (skb->end - skb->tail);
+	if (likely(skb_cloned(skb) || ntail > 0)) {
+		err = pskb_expand_head(skb, 0, ntail, GFP_ATOMIC);
+		if (unlikely(err))
+			goto free_skb;
+	}
+
+	/* FIXME: The use of this function with non-linear skb's really needs
+	 * to be audited.
+	 */
+	err = skb_linearize(skb);
+	if (unlikely(err))
+		goto free_skb;
+
+	memset(skb->data + skb->len, 0, pad);
+	return 0;
+
+free_skb:
 	kfree_skb(skb);
-	if (nskb)
-		memset(nskb->data+nskb->len, 0, pad);
-	return nskb;
+	return err;
 }	
  
 /* Trims skb to length len. It can change skb pointers.