Merge branch 'skb_checksum_help'

Paul Durrant says:

====================
make skb_checksum_setup generally available

Both xen-netfront and xen-netback need to be able to set up the partial
checksum offset of an skb and may also need to recalculate the pseudo-
header checksum in the process. This functionality is currently private
and duplicated between the two drivers.

Patch #1 of this series moves the implementation into the core network code
as there is nothing xen-specific about it and it is potentially useful to
any network driver.
Patch #2 removes the private implementation from netback.
Patch #3 removes the private implementation from netfront.

v2:
- Put skb_checksum_setup in skbuff.c rather than dev.c
- remove inline
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/xen-netback/netback.c

@@ -39,7 +39,6 @@
 #include <linux/udp.h>
 
 #include <net/tcp.h>
-#include <net/ip6_checksum.h>
 
 #include <xen/xen.h>
 #include <xen/events.h>
@@ -1051,257 +1050,9 @@ static int xenvif_set_skb_gso(struct xenvif *vif,
 	return 0;
 }
 
-static inline int maybe_pull_tail(struct sk_buff *skb, unsigned int len,
-				  unsigned int max)
-{
-	if (skb_headlen(skb) >= len)
-		return 0;
-
-	/* If we need to pullup then pullup to the max, so we
-	 * won't need to do it again.
-	 */
-	if (max > skb->len)
-		max = skb->len;
-
-	if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL)
-		return -ENOMEM;
-
-	if (skb_headlen(skb) < len)
-		return -EPROTO;
-
-	return 0;
-}
-
-/* This value should be large enough to cover a tagged ethernet header plus
- * maximally sized IP and TCP or UDP headers.
- */
-#define MAX_IP_HDR_LEN 128
-
-static int checksum_setup_ip(struct xenvif *vif, struct sk_buff *skb,
-			     int recalculate_partial_csum)
-{
-	unsigned int off;
-	bool fragment;
-	int err;
-
-	fragment = false;
-
-	err = maybe_pull_tail(skb,
-			      sizeof(struct iphdr),
-			      MAX_IP_HDR_LEN);
-	if (err < 0)
-		goto out;
-
-	if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF))
-		fragment = true;
-
-	off = ip_hdrlen(skb);
-
-	err = -EPROTO;
-
-	if (fragment)
-		goto out;
-
-	switch (ip_hdr(skb)->protocol) {
-	case IPPROTO_TCP:
-		err = maybe_pull_tail(skb,
-				      off + sizeof(struct tcphdr),
-				      MAX_IP_HDR_LEN);
-		if (err < 0)
-			goto out;
-
-		if (!skb_partial_csum_set(skb, off,
-					  offsetof(struct tcphdr, check))) {
-			err = -EPROTO;
-			goto out;
-		}
-
-		if (recalculate_partial_csum)
-			tcp_hdr(skb)->check =
-				~csum_tcpudp_magic(ip_hdr(skb)->saddr,
-						   ip_hdr(skb)->daddr,
-						   skb->len - off,
-						   IPPROTO_TCP, 0);
-		break;
-	case IPPROTO_UDP:
-		err = maybe_pull_tail(skb,
-				      off + sizeof(struct udphdr),
-				      MAX_IP_HDR_LEN);
-		if (err < 0)
-			goto out;
-
-		if (!skb_partial_csum_set(skb, off,
-					  offsetof(struct udphdr, check))) {
-			err = -EPROTO;
-			goto out;
-		}
-
-		if (recalculate_partial_csum)
-			udp_hdr(skb)->check =
-				~csum_tcpudp_magic(ip_hdr(skb)->saddr,
-						   ip_hdr(skb)->daddr,
-						   skb->len - off,
-						   IPPROTO_UDP, 0);
-		break;
-	default:
-		goto out;
-	}
-
-	err = 0;
-
-out:
-	return err;
-}
-
-/* This value should be large enough to cover a tagged ethernet header plus
- * an IPv6 header, all options, and a maximal TCP or UDP header.
- */
-#define MAX_IPV6_HDR_LEN 256
-
-#define OPT_HDR(type, skb, off) \
-	(type *)(skb_network_header(skb) + (off))
-
-static int checksum_setup_ipv6(struct xenvif *vif, struct sk_buff *skb,
-			       int recalculate_partial_csum)
-{
-	int err;
-	u8 nexthdr;
-	unsigned int off;
-	unsigned int len;
-	bool fragment;
-	bool done;
-
-	fragment = false;
-	done = false;
-
-	off = sizeof(struct ipv6hdr);
-
-	err = maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN);
-	if (err < 0)
-		goto out;
-
-	nexthdr = ipv6_hdr(skb)->nexthdr;
-
-	len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len);
-	while (off <= len && !done) {
-		switch (nexthdr) {
-		case IPPROTO_DSTOPTS:
-		case IPPROTO_HOPOPTS:
-		case IPPROTO_ROUTING: {
-			struct ipv6_opt_hdr *hp;
-
-			err = maybe_pull_tail(skb,
-					      off +
-					      sizeof(struct ipv6_opt_hdr),
-					      MAX_IPV6_HDR_LEN);
-			if (err < 0)
-				goto out;
-
-			hp = OPT_HDR(struct ipv6_opt_hdr, skb, off);
-			nexthdr = hp->nexthdr;
-			off += ipv6_optlen(hp);
-			break;
-		}
-		case IPPROTO_AH: {
-			struct ip_auth_hdr *hp;
-
-			err = maybe_pull_tail(skb,
-					      off +
-					      sizeof(struct ip_auth_hdr),
-					      MAX_IPV6_HDR_LEN);
-			if (err < 0)
-				goto out;
-
-			hp = OPT_HDR(struct ip_auth_hdr, skb, off);
-			nexthdr = hp->nexthdr;
-			off += ipv6_authlen(hp);
-			break;
-		}
-		case IPPROTO_FRAGMENT: {
-			struct frag_hdr *hp;
-
-			err = maybe_pull_tail(skb,
-					      off +
-					      sizeof(struct frag_hdr),
-					      MAX_IPV6_HDR_LEN);
-			if (err < 0)
-				goto out;
-
-			hp = OPT_HDR(struct frag_hdr, skb, off);
-
-			if (hp->frag_off & htons(IP6_OFFSET | IP6_MF))
-				fragment = true;
-
-			nexthdr = hp->nexthdr;
-			off += sizeof(struct frag_hdr);
-			break;
-		}
-		default:
-			done = true;
-			break;
-		}
-	}
-
-	err = -EPROTO;
-
-	if (!done || fragment)
-		goto out;
-
-	switch (nexthdr) {
-	case IPPROTO_TCP:
-		err = maybe_pull_tail(skb,
-				      off + sizeof(struct tcphdr),
-				      MAX_IPV6_HDR_LEN);
-		if (err < 0)
-			goto out;
-
-		if (!skb_partial_csum_set(skb, off,
-					  offsetof(struct tcphdr, check))) {
-			err = -EPROTO;
-			goto out;
-		}
-
-		if (recalculate_partial_csum)
-			tcp_hdr(skb)->check =
-				~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
-						 &ipv6_hdr(skb)->daddr,
-						 skb->len - off,
-						 IPPROTO_TCP, 0);
-		break;
-	case IPPROTO_UDP:
-		err = maybe_pull_tail(skb,
-				      off + sizeof(struct udphdr),
-				      MAX_IPV6_HDR_LEN);
-		if (err < 0)
-			goto out;
-
-		if (!skb_partial_csum_set(skb, off,
-					  offsetof(struct udphdr, check))) {
-			err = -EPROTO;
-			goto out;
-		}
-
-		if (recalculate_partial_csum)
-			udp_hdr(skb)->check =
-				~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
-						 &ipv6_hdr(skb)->daddr,
-						 skb->len - off,
-						 IPPROTO_UDP, 0);
-		break;
-	default:
-		goto out;
-	}
-
-	err = 0;
-
-out:
-	return err;
-}
-
 static int checksum_setup(struct xenvif *vif, struct sk_buff *skb)
 {
-	int err = -EPROTO;
+	bool recalculate_partial_csum = false;
-	int recalculate_partial_csum = 0;
 
 	/* A GSO SKB must be CHECKSUM_PARTIAL. However some buggy
 	 * peers can fail to set NETRXF_csum_blank when sending a GSO
@@ -1311,19 +1062,14 @@ static int checksum_setup(struct xenvif *vif, struct sk_buff *skb)
 	if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) {
 		vif->rx_gso_checksum_fixup++;
 		skb->ip_summed = CHECKSUM_PARTIAL;
-		recalculate_partial_csum = 1;
+		recalculate_partial_csum = true;
 	}
 
 	/* A non-CHECKSUM_PARTIAL SKB does not require setup. */
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
 		return 0;
 
-	if (skb->protocol == htons(ETH_P_IP))
+	return skb_checksum_setup(skb, recalculate_partial_csum);
-		err = checksum_setup_ip(vif, skb, recalculate_partial_csum);
-	else if (skb->protocol == htons(ETH_P_IPV6))
-		err = checksum_setup_ipv6(vif, skb, recalculate_partial_csum);
-
-	return err;
 }
 
 static bool tx_credit_exceeded(struct xenvif *vif, unsigned size)

drivers/net/xen-netfront.c

@@ -859,9 +859,7 @@ static RING_IDX xennet_fill_frags(struct netfront_info *np,
 
 static int checksum_setup(struct net_device *dev, struct sk_buff *skb)
 {
-	struct iphdr *iph;
+	bool recalculate_partial_csum = false;
-	int err = -EPROTO;
-	int recalculate_partial_csum = 0;
 
 	/*
 	 * A GSO SKB must be CHECKSUM_PARTIAL. However some buggy
@@ -873,54 +871,14 @@ static int checksum_setup(struct net_device *dev, struct sk_buff *skb)
 		struct netfront_info *np = netdev_priv(dev);
 		np->rx_gso_checksum_fixup++;
 		skb->ip_summed = CHECKSUM_PARTIAL;
-		recalculate_partial_csum = 1;
+		recalculate_partial_csum = true;
 	}
 
 	/* A non-CHECKSUM_PARTIAL SKB does not require setup. */
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
 		return 0;
 
-	if (skb->protocol != htons(ETH_P_IP))
+	return skb_checksum_setup(skb, recalculate_partial_csum);
-		goto out;
-
-	iph = (void *)skb->data;
-
-	switch (iph->protocol) {
-	case IPPROTO_TCP:
-		if (!skb_partial_csum_set(skb, 4 * iph->ihl,
-					  offsetof(struct tcphdr, check)))
-			goto out;
-
-		if (recalculate_partial_csum) {
-			struct tcphdr *tcph = tcp_hdr(skb);
-			tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
-							 skb->len - iph->ihl*4,
-							 IPPROTO_TCP, 0);
-		}
-		break;
-	case IPPROTO_UDP:
-		if (!skb_partial_csum_set(skb, 4 * iph->ihl,
-					  offsetof(struct udphdr, check)))
-			goto out;
-
-		if (recalculate_partial_csum) {
-			struct udphdr *udph = udp_hdr(skb);
-			udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
-							 skb->len - iph->ihl*4,
-							 IPPROTO_UDP, 0);
-		}
-		break;
-	default:
-		if (net_ratelimit())
-			pr_err("Attempting to checksum a non-TCP/UDP packet, dropping a protocol %d packet\n",
-			       iph->protocol);
-		goto out;
-	}
-
-	err = 0;
-
-out:
-	return err;
 }
 
 static int handle_incoming_queue(struct net_device *dev,

include/linux/skbuff.h

@@ -2893,6 +2893,8 @@ static inline void skb_checksum_none_assert(const struct sk_buff *skb)
 
 bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off);
 
+int skb_checksum_setup(struct sk_buff *skb, bool recalculate);
+
 u32 __skb_get_poff(const struct sk_buff *skb);
 
 /**

net/core/skbuff.c

@@ -65,6 +65,7 @@
 #include <net/dst.h>
 #include <net/sock.h>
 #include <net/checksum.h>
+#include <net/ip6_checksum.h>
 #include <net/xfrm.h>
 
 #include <asm/uaccess.h>
@@ -3549,6 +3550,278 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off)
 }
 EXPORT_SYMBOL_GPL(skb_partial_csum_set);
 
+static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len,
+			       unsigned int max)
+{
+	if (skb_headlen(skb) >= len)
+		return 0;
+
+	/* If we need to pullup then pullup to the max, so we
+	 * won't need to do it again.
+	 */
+	if (max > skb->len)
+		max = skb->len;
+
+	if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL)
+		return -ENOMEM;
+
+	if (skb_headlen(skb) < len)
+		return -EPROTO;
+
+	return 0;
+}
+
+/* This value should be large enough to cover a tagged ethernet header plus
+ * maximally sized IP and TCP or UDP headers.
+ */
+#define MAX_IP_HDR_LEN 128
+
+static int skb_checksum_setup_ip(struct sk_buff *skb, bool recalculate)
+{
+	unsigned int off;
+	bool fragment;
+	int err;
+
+	fragment = false;
+
+	err = skb_maybe_pull_tail(skb,
+				  sizeof(struct iphdr),
+				  MAX_IP_HDR_LEN);
+	if (err < 0)
+		goto out;
+
+	if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF))
+		fragment = true;
+
+	off = ip_hdrlen(skb);
+
+	err = -EPROTO;
+
+	if (fragment)
+		goto out;
+
+	switch (ip_hdr(skb)->protocol) {
+	case IPPROTO_TCP:
+		err = skb_maybe_pull_tail(skb,
+					  off + sizeof(struct tcphdr),
+					  MAX_IP_HDR_LEN);
+		if (err < 0)
+			goto out;
+
+		if (!skb_partial_csum_set(skb, off,
+					  offsetof(struct tcphdr, check))) {
+			err = -EPROTO;
+			goto out;
+		}
+
+		if (recalculate)
+			tcp_hdr(skb)->check =
+				~csum_tcpudp_magic(ip_hdr(skb)->saddr,
+						   ip_hdr(skb)->daddr,
+						   skb->len - off,
+						   IPPROTO_TCP, 0);
+		break;
+	case IPPROTO_UDP:
+		err = skb_maybe_pull_tail(skb,
+					  off + sizeof(struct udphdr),
+					  MAX_IP_HDR_LEN);
+		if (err < 0)
+			goto out;
+
+		if (!skb_partial_csum_set(skb, off,
+					  offsetof(struct udphdr, check))) {
+			err = -EPROTO;
+			goto out;
+		}
+
+		if (recalculate)
+			udp_hdr(skb)->check =
+				~csum_tcpudp_magic(ip_hdr(skb)->saddr,
+						   ip_hdr(skb)->daddr,
+						   skb->len - off,
+						   IPPROTO_UDP, 0);
+		break;
+	default:
+		goto out;
+	}
+
+	err = 0;
+
+out:
+	return err;
+}
+
+/* This value should be large enough to cover a tagged ethernet header plus
+ * an IPv6 header, all options, and a maximal TCP or UDP header.
+ */
+#define MAX_IPV6_HDR_LEN 256
+
+#define OPT_HDR(type, skb, off) \
+	(type *)(skb_network_header(skb) + (off))
+
+static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate)
+{
+	int err;
+	u8 nexthdr;
+	unsigned int off;
+	unsigned int len;
+	bool fragment;
+	bool done;
+
+	fragment = false;
+	done = false;
+
+	off = sizeof(struct ipv6hdr);
+
+	err = skb_maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN);
+	if (err < 0)
+		goto out;
+
+	nexthdr = ipv6_hdr(skb)->nexthdr;
+
+	len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len);
+	while (off <= len && !done) {
+		switch (nexthdr) {
+		case IPPROTO_DSTOPTS:
+		case IPPROTO_HOPOPTS:
+		case IPPROTO_ROUTING: {
+			struct ipv6_opt_hdr *hp;
+
+			err = skb_maybe_pull_tail(skb,
+						  off +
+						  sizeof(struct ipv6_opt_hdr),
+						  MAX_IPV6_HDR_LEN);
+			if (err < 0)
+				goto out;
+
+			hp = OPT_HDR(struct ipv6_opt_hdr, skb, off);
+			nexthdr = hp->nexthdr;
+			off += ipv6_optlen(hp);
+			break;
+		}
+		case IPPROTO_AH: {
+			struct ip_auth_hdr *hp;
+
+			err = skb_maybe_pull_tail(skb,
+						  off +
+						  sizeof(struct ip_auth_hdr),
+						  MAX_IPV6_HDR_LEN);
+			if (err < 0)
+				goto out;
+
+			hp = OPT_HDR(struct ip_auth_hdr, skb, off);
+			nexthdr = hp->nexthdr;
+			off += ipv6_authlen(hp);
+			break;
+		}
+		case IPPROTO_FRAGMENT: {
+			struct frag_hdr *hp;
+
+			err = skb_maybe_pull_tail(skb,
+						  off +
+						  sizeof(struct frag_hdr),
+						  MAX_IPV6_HDR_LEN);
+			if (err < 0)
+				goto out;
+
+			hp = OPT_HDR(struct frag_hdr, skb, off);
+
+			if (hp->frag_off & htons(IP6_OFFSET | IP6_MF))
+				fragment = true;
+
+			nexthdr = hp->nexthdr;
+			off += sizeof(struct frag_hdr);
+			break;
+		}
+		default:
+			done = true;
+			break;
+		}
+	}
+
+	err = -EPROTO;
+
+	if (!done || fragment)
+		goto out;
+
+	switch (nexthdr) {
+	case IPPROTO_TCP:
+		err = skb_maybe_pull_tail(skb,
+					  off + sizeof(struct tcphdr),
+					  MAX_IPV6_HDR_LEN);
+		if (err < 0)
+			goto out;
+
+		if (!skb_partial_csum_set(skb, off,
+					  offsetof(struct tcphdr, check))) {
+			err = -EPROTO;
+			goto out;
+		}
+
+		if (recalculate)
+			tcp_hdr(skb)->check =
+				~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+						 &ipv6_hdr(skb)->daddr,
+						 skb->len - off,
+						 IPPROTO_TCP, 0);
+		break;
+	case IPPROTO_UDP:
+		err = skb_maybe_pull_tail(skb,
+					  off + sizeof(struct udphdr),
+					  MAX_IPV6_HDR_LEN);
+		if (err < 0)
+			goto out;
+
+		if (!skb_partial_csum_set(skb, off,
+					  offsetof(struct udphdr, check))) {
+			err = -EPROTO;
+			goto out;
+		}
+
+		if (recalculate)
+			udp_hdr(skb)->check =
+				~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+						 &ipv6_hdr(skb)->daddr,
+						 skb->len - off,
+						 IPPROTO_UDP, 0);
+		break;
+	default:
+		goto out;
+	}
+
+	err = 0;
+
+out:
+	return err;
+}
+
+/**
+ * skb_checksum_setup - set up partial checksum offset
+ * @skb: the skb to set up
+ * @recalculate: if true the pseudo-header checksum will be recalculated
+ */
+int skb_checksum_setup(struct sk_buff *skb, bool recalculate)
+{
+	int err;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		err = skb_checksum_setup_ip(skb, recalculate);
+		break;
+
+	case htons(ETH_P_IPV6):
+		err = skb_checksum_setup_ipv6(skb, recalculate);
+		break;
+
+	default:
+		err = -EPROTO;
+		break;
+	}
+
+	return err;
+}
+EXPORT_SYMBOL(skb_checksum_setup);
+
 void __skb_warn_lro_forwarding(const struct sk_buff *skb)
 {
 	net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n",