Merge branch 'gro-fixed-id-gso-partial'

Alexander Duyck says:

====================
GRO Fixed IPv4 ID support and GSO partial support

This patch series sets up a few different things.

First it adds support for GRO of frames with a fixed IP ID value.  This
will allow us to perform GRO for frames that go through things like an IPv6
to IPv4 header translation.

The second item we add is support for segmenting frames that are generated
this way.  Most devices only support an incrementing IP ID value, and in
the case of TCP the IP ID can be ignored in many cases since the DF bit
should be set.  So we can technically segment these frames using existing
TSO if we are willing to allow the IP ID to be mangled.  As such I have
added a matching feature for the new form of GRO/GSO called TCP IPv4 ID
mangling.  With this enabled we can assemble and disassemble a frame with
the sequence number fixed and the only ill effect will be that the IPv4 ID
will be altered which may or may not have any noticeable effect.  As such I
have defaulted the feature to disabled.

The third item this patch series adds is support for partial GSO
segmentation.  Partial GSO segmentation allows us to split a large frame
into two pieces.  The first piece will have an even multiple of MSS worth
of data and the headers before the one pointed to by csum_start will have
been updated so that they are correct for if the data payload had already
been segmented.  By doing this we can do things such as precompute the
outer header checksums for a frame to be segmented allowing us to perform
TSO on devices that don't support tunneling, or tunneling with outer header
checksums.

This patch set is based on the net-next tree, but I included "net: remove
netdevice gso_min_segs" in my tree as I assume it is likely to be applied
before this patch set will and I wanted to avoid a merge conflict.

v2: Fixed items reported by Jesse Gross
	fixed missing GSO flag in MPLS check
	adding DF check for MANGLEID
    Moved extra GSO feature checks into gso_features_check
    Rebased batches to account for "net: remove netdevice gso_min_segs"

Driver patches from the first patch set should still be compatible.  However
I do have a few changes in them so I will submit a v2 of those to Jeff
Kirsher once these patches are accepted into net-next.

Example driver patches for i40e, ixgbe, and igb:
https://patchwork.ozlabs.org/patch/608221/
https://patchwork.ozlabs.org/patch/608224/
https://patchwork.ozlabs.org/patch/608225/
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/segmentation-offloads.txt

+Segmentation Offloads in the Linux Networking Stack
+
+Introduction
+============
+
+This document describes a set of techniques in the Linux networking stack
+to take advantage of segmentation offload capabilities of various NICs.
+
+The following technologies are described:
+ * TCP Segmentation Offload - TSO
+ * UDP Fragmentation Offload - UFO
+ * IPIP, SIT, GRE, and UDP Tunnel Offloads
+ * Generic Segmentation Offload - GSO
+ * Generic Receive Offload - GRO
+ * Partial Generic Segmentation Offload - GSO_PARTIAL
+
+TCP Segmentation Offload
+========================
+
+TCP segmentation allows a device to segment a single frame into multiple
+frames with a data payload size specified in skb_shinfo()->gso_size.
+When TCP segmentation requested the bit for either SKB_GSO_TCP or
+SKB_GSO_TCP6 should be set in skb_shinfo()->gso_type and
+skb_shinfo()->gso_size should be set to a non-zero value.
+
+TCP segmentation is dependent on support for the use of partial checksum
+offload.  For this reason TSO is normally disabled if the Tx checksum
+offload for a given device is disabled.
+
+In order to support TCP segmentation offload it is necessary to populate
+the network and transport header offsets of the skbuff so that the device
+drivers will be able determine the offsets of the IP or IPv6 header and the
+TCP header.  In addition as CHECKSUM_PARTIAL is required csum_start should
+also point to the TCP header of the packet.
+
+For IPv4 segmentation we support one of two types in terms of the IP ID.
+The default behavior is to increment the IP ID with every segment.  If the
+GSO type SKB_GSO_TCP_FIXEDID is specified then we will not increment the IP
+ID and all segments will use the same IP ID.  If a device has
+NETIF_F_TSO_MANGLEID set then the IP ID can be ignored when performing TSO
+and we will either increment the IP ID for all frames, or leave it at a
+static value based on driver preference.
+
+UDP Fragmentation Offload
+=========================
+
+UDP fragmentation offload allows a device to fragment an oversized UDP
+datagram into multiple IPv4 fragments.  Many of the requirements for UDP
+fragmentation offload are the same as TSO.  However the IPv4 ID for
+fragments should not increment as a single IPv4 datagram is fragmented.
+
+IPIP, SIT, GRE, UDP Tunnel, and Remote Checksum Offloads
+========================================================
+
+In addition to the offloads described above it is possible for a frame to
+contain additional headers such as an outer tunnel.  In order to account
+for such instances an additional set of segmentation offload types were
+introduced including SKB_GSO_IPIP, SKB_GSO_SIT, SKB_GSO_GRE, and
+SKB_GSO_UDP_TUNNEL.  These extra segmentation types are used to identify
+cases where there are more than just 1 set of headers.  For example in the
+case of IPIP and SIT we should have the network and transport headers moved
+from the standard list of headers to "inner" header offsets.
+
+Currently only two levels of headers are supported.  The convention is to
+refer to the tunnel headers as the outer headers, while the encapsulated
+data is normally referred to as the inner headers.  Below is the list of
+calls to access the given headers:
+
+IPIP/SIT Tunnel:
+		Outer			Inner
+MAC		skb_mac_header
+Network		skb_network_header	skb_inner_network_header
+Transport	skb_transport_header
+
+UDP/GRE Tunnel:
+		Outer			Inner
+MAC		skb_mac_header		skb_inner_mac_header
+Network		skb_network_header	skb_inner_network_header
+Transport	skb_transport_header	skb_inner_transport_header
+
+In addition to the above tunnel types there are also SKB_GSO_GRE_CSUM and
+SKB_GSO_UDP_TUNNEL_CSUM.  These two additional tunnel types reflect the
+fact that the outer header also requests to have a non-zero checksum
+included in the outer header.
+
+Finally there is SKB_GSO_REMCSUM which indicates that a given tunnel header
+has requested a remote checksum offload.  In this case the inner headers
+will be left with a partial checksum and only the outer header checksum
+will be computed.
+
+Generic Segmentation Offload
+============================
+
+Generic segmentation offload is a pure software offload that is meant to
+deal with cases where device drivers cannot perform the offloads described
+above.  What occurs in GSO is that a given skbuff will have its data broken
+out over multiple skbuffs that have been resized to match the MSS provided
+via skb_shinfo()->gso_size.
+
+Before enabling any hardware segmentation offload a corresponding software
+offload is required in GSO.  Otherwise it becomes possible for a frame to
+be re-routed between devices and end up being unable to be transmitted.
+
+Generic Receive Offload
+=======================
+
+Generic receive offload is the complement to GSO.  Ideally any frame
+assembled by GRO should be segmented to create an identical sequence of
+frames using GSO, and any sequence of frames segmented by GSO should be
+able to be reassembled back to the original by GRO.  The only exception to
+this is IPv4 ID in the case that the DF bit is set for a given IP header.
+If the value of the IPv4 ID is not sequentially incrementing it will be
+altered so that it is when a frame assembled via GRO is segmented via GSO.
+
+Partial Generic Segmentation Offload
+====================================
+
+Partial generic segmentation offload is a hybrid between TSO and GSO.  What
+it effectively does is take advantage of certain traits of TCP and tunnels
+so that instead of having to rewrite the packet headers for each segment
+only the inner-most transport header and possibly the outer-most network
+header need to be updated.  This allows devices that do not support tunnel
+offloads or tunnel offloads with checksum to still make use of segmentation.
+
+With the partial offload what occurs is that all headers excluding the
+inner transport header are updated such that they will contain the correct
+values for if the header was simply duplicated.  The one exception to this
+is the outer IPv4 ID field.  It is up to the device drivers to guarantee
+that the IPv4 ID field is incremented in the case that a given header does
+not have the DF bit set.

include/linux/netdev_features.h

@@ -39,6 +39,7 @@ enum {
 	NETIF_F_UFO_BIT,		/* ... UDPv4 fragmentation */
 	NETIF_F_GSO_ROBUST_BIT,		/* ... ->SKB_GSO_DODGY */
 	NETIF_F_TSO_ECN_BIT,		/* ... TCP ECN support */
+	NETIF_F_TSO_MANGLEID_BIT,	/* ... IPV4 ID mangling allowed */
 	NETIF_F_TSO6_BIT,		/* ... TCPv6 segmentation */
 	NETIF_F_FSO_BIT,		/* ... FCoE segmentation */
 	NETIF_F_GSO_GRE_BIT,		/* ... GRE with TSO */
@@ -47,6 +48,10 @@ enum {
 	NETIF_F_GSO_SIT_BIT,		/* ... SIT tunnel with TSO */
 	NETIF_F_GSO_UDP_TUNNEL_BIT,	/* ... UDP TUNNEL with TSO */
 	NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT,/* ... UDP TUNNEL with TSO & CSUM */
+	NETIF_F_GSO_PARTIAL_BIT,	/* ... Only segment inner-most L4
+					 *     in hardware and all other
+					 *     headers in software.
+					 */
 	NETIF_F_GSO_TUNNEL_REMCSUM_BIT, /* ... TUNNEL with TSO & REMCSUM */
 	/**/NETIF_F_GSO_LAST =		/* last bit, see GSO_MASK */
 		NETIF_F_GSO_TUNNEL_REMCSUM_BIT,
@@ -120,6 +125,8 @@ enum {
 #define NETIF_F_GSO_SIT		__NETIF_F(GSO_SIT)
 #define NETIF_F_GSO_UDP_TUNNEL	__NETIF_F(GSO_UDP_TUNNEL)
 #define NETIF_F_GSO_UDP_TUNNEL_CSUM __NETIF_F(GSO_UDP_TUNNEL_CSUM)
+#define NETIF_F_TSO_MANGLEID	__NETIF_F(TSO_MANGLEID)
+#define NETIF_F_GSO_PARTIAL	 __NETIF_F(GSO_PARTIAL)
 #define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM)
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
 #define NETIF_F_HW_VLAN_STAG_RX	__NETIF_F(HW_VLAN_STAG_RX)
@@ -147,6 +154,7 @@ enum {
 
 /* List of features with software fallbacks. */
 #define NETIF_F_GSO_SOFTWARE	(NETIF_F_TSO | NETIF_F_TSO_ECN | \
+				 NETIF_F_TSO_MANGLEID | \
 				 NETIF_F_TSO6 | NETIF_F_UFO)
 
 /* List of IP checksum features. Note that NETIF_F_ HW_CSUM should not be

include/linux/netdevice.h

@@ -1654,6 +1654,7 @@ struct net_device {
 	netdev_features_t	vlan_features;
 	netdev_features_t	hw_enc_features;
 	netdev_features_t	mpls_features;
+	netdev_features_t	gso_partial_features;
 
 	int			ifindex;
 	int			group;
@@ -2121,7 +2122,10 @@ struct napi_gro_cb {
 	/* Used in GRE, set in fou/gue_gro_receive */
 	u8	is_fou:1;
 
-	/* 6 bit hole */
+	/* Used to determine if flush_id can be ignored */
+	u8	is_atomic:1;
+
+	/* 5 bit hole */
 
 	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
 	__wsum	csum;
@@ -3992,6 +3996,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	BUILD_BUG_ON(SKB_GSO_UDP     != (NETIF_F_UFO >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_DODGY   != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_TCPV6   != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_FCOE    != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_GRE     != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT));
@@ -4000,6 +4005,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	BUILD_BUG_ON(SKB_GSO_SIT     != (NETIF_F_GSO_SIT >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL != (NETIF_F_GSO_UDP_TUNNEL >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_PARTIAL != (NETIF_F_GSO_PARTIAL >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT));
 
 	return (features & feature) == feature;

include/linux/skbuff.h

@@ -465,23 +465,27 @@ enum {
 	/* This indicates the tcp segment has CWR set. */
 	SKB_GSO_TCP_ECN = 1 << 3,
 
-	SKB_GSO_TCPV6 = 1 << 4,
+	SKB_GSO_TCP_FIXEDID = 1 << 4,
 
-	SKB_GSO_FCOE = 1 << 5,
+	SKB_GSO_TCPV6 = 1 << 5,
 
-	SKB_GSO_GRE = 1 << 6,
+	SKB_GSO_FCOE = 1 << 6,
 
-	SKB_GSO_GRE_CSUM = 1 << 7,
+	SKB_GSO_GRE = 1 << 7,
 
-	SKB_GSO_IPIP = 1 << 8,
+	SKB_GSO_GRE_CSUM = 1 << 8,
 
-	SKB_GSO_SIT = 1 << 9,
+	SKB_GSO_IPIP = 1 << 9,
 
-	SKB_GSO_UDP_TUNNEL = 1 << 10,
+	SKB_GSO_SIT = 1 << 10,
 
-	SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11,
+	SKB_GSO_UDP_TUNNEL = 1 << 11,
 
-	SKB_GSO_TUNNEL_REMCSUM = 1 << 12,
+	SKB_GSO_UDP_TUNNEL_CSUM = 1 << 12,
+
+	SKB_GSO_PARTIAL = 1 << 13,
+
+	SKB_GSO_TUNNEL_REMCSUM = 1 << 14,
 };
 
 #if BITS_PER_LONG > 32
@@ -3589,7 +3593,10 @@ static inline struct sec_path *skb_sec_path(struct sk_buff *skb)
  * Keeps track of level of encapsulation of network headers.
  */
 struct skb_gso_cb {
+	union {
 		int	mac_offset;
+		int	data_offset;
+	};
 	int	encap_level;
 	__wsum	csum;
 	__u16	csum_start;

net/core/dev.c

@@ -2711,6 +2711,19 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 			return ERR_PTR(err);
 	}
 
+	/* Only report GSO partial support if it will enable us to
+	 * support segmentation on this frame without needing additional
+	 * work.
+	 */
+	if (features & NETIF_F_GSO_PARTIAL) {
+		netdev_features_t partial_features = NETIF_F_GSO_ROBUST;
+		struct net_device *dev = skb->dev;
+
+		partial_features |= dev->features & dev->gso_partial_features;
+		if (!skb_gso_ok(skb, features | partial_features))
+			features &= ~NETIF_F_GSO_PARTIAL;
+	}
+
 	BUILD_BUG_ON(SKB_SGO_CB_OFFSET +
 		     sizeof(*SKB_GSO_CB(skb)) > sizeof(skb->cb));
 
@@ -2825,14 +2838,45 @@ static netdev_features_t dflt_features_check(const struct sk_buff *skb,
 	return vlan_features_check(skb, features);
 }
 
+static netdev_features_t gso_features_check(const struct sk_buff *skb,
+					    struct net_device *dev,
+					    netdev_features_t features)
+{
+	u16 gso_segs = skb_shinfo(skb)->gso_segs;
+
+	if (gso_segs > dev->gso_max_segs)
+		return features & ~NETIF_F_GSO_MASK;
+
+	/* Support for GSO partial features requires software
+	 * intervention before we can actually process the packets
+	 * so we need to strip support for any partial features now
+	 * and we can pull them back in after we have partially
+	 * segmented the frame.
+	 */
+	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL))
+		features &= ~dev->gso_partial_features;
+
+	/* Make sure to clear the IPv4 ID mangling feature if the
+	 * IPv4 header has the potential to be fragmented.
+	 */
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) {
+		struct iphdr *iph = skb->encapsulation ?
+				    inner_ip_hdr(skb) : ip_hdr(skb);
+
+		if (!(iph->frag_off & htons(IP_DF)))
+			features &= ~NETIF_F_TSO_MANGLEID;
+	}
+
+	return features;
+}
+
 netdev_features_t netif_skb_features(struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
 	netdev_features_t features = dev->features;
-	u16 gso_segs = skb_shinfo(skb)->gso_segs;
 
-	if (gso_segs > dev->gso_max_segs)
-		features &= ~NETIF_F_GSO_MASK;
+	if (skb_is_gso(skb))
+		features = gso_features_check(skb, dev, features);
 
 	/* If encapsulation offload request, verify we are testing
 	 * hardware encapsulation features instead of standard
@@ -4440,6 +4484,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		NAPI_GRO_CB(skb)->free = 0;
 		NAPI_GRO_CB(skb)->encap_mark = 0;
 		NAPI_GRO_CB(skb)->is_fou = 0;
+		NAPI_GRO_CB(skb)->is_atomic = 1;
 		NAPI_GRO_CB(skb)->gro_remcsum_start = 0;
 
 		/* Setup for GRO checksum validation */
@@ -6706,6 +6751,14 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
 		}
 	}
 
+	/* GSO partial features require GSO partial be set */
+	if ((features & dev->gso_partial_features) &&
+	    !(features & NETIF_F_GSO_PARTIAL)) {
+		netdev_dbg(dev,
+			   "Dropping partially supported GSO features since no GSO partial.\n");
+		features &= ~dev->gso_partial_features;
+	}
+
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	if (dev->netdev_ops->ndo_busy_poll)
 		features |= NETIF_F_BUSY_POLL;
@@ -6976,9 +7029,11 @@ int register_netdevice(struct net_device *dev)
 	dev->features |= NETIF_F_SOFT_FEATURES;
 	dev->wanted_features = dev->features & dev->hw_features;
 
-	if (!(dev->flags & IFF_LOOPBACK)) {
+	if (!(dev->flags & IFF_LOOPBACK))
 		dev->hw_features |= NETIF_F_NOCACHE_COPY;
-	}
+
+	if (dev->hw_features & NETIF_F_TSO)
+		dev->hw_features |= NETIF_F_TSO_MANGLEID;
 
 	/* Make NETIF_F_HIGHDMA inheritable to VLAN devices.
 	 */
@@ -6986,7 +7041,7 @@ int register_netdevice(struct net_device *dev)
 
 	/* Make NETIF_F_SG inheritable to tunnel devices.
 	 */
-	dev->hw_enc_features |= NETIF_F_SG;
+	dev->hw_enc_features |= NETIF_F_SG | NETIF_F_GSO_PARTIAL;
 
 	/* Make NETIF_F_SG inheritable to MPLS.
 	 */

net/core/ethtool.c

@@ -79,12 +79,16 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_UFO_BIT] =              "tx-udp-fragmentation",
 	[NETIF_F_GSO_ROBUST_BIT] =       "tx-gso-robust",
 	[NETIF_F_TSO_ECN_BIT] =          "tx-tcp-ecn-segmentation",
+	[NETIF_F_TSO_MANGLEID_BIT] =	 "tx-tcp-mangleid-segmentation",
 	[NETIF_F_TSO6_BIT] =             "tx-tcp6-segmentation",
 	[NETIF_F_FSO_BIT] =              "tx-fcoe-segmentation",
 	[NETIF_F_GSO_GRE_BIT] =		 "tx-gre-segmentation",
+	[NETIF_F_GSO_GRE_CSUM_BIT] =	 "tx-gre-csum-segmentation",
 	[NETIF_F_GSO_IPIP_BIT] =	 "tx-ipip-segmentation",
 	[NETIF_F_GSO_SIT_BIT] =		 "tx-sit-segmentation",
 	[NETIF_F_GSO_UDP_TUNNEL_BIT] =	 "tx-udp_tnl-segmentation",
+	[NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation",
+	[NETIF_F_GSO_PARTIAL_BIT] =	 "tx-gso-partial",
 
 	[NETIF_F_FCOE_CRC_BIT] =         "tx-checksum-fcoe-crc",
 	[NETIF_F_SCTP_CRC_BIT] =        "tx-checksum-sctp",

net/core/skbuff.c

@@ -3076,8 +3076,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 	struct sk_buff *frag_skb = head_skb;
 	unsigned int offset = doffset;
 	unsigned int tnl_hlen = skb_tnl_header_len(head_skb);
+	unsigned int partial_segs = 0;
 	unsigned int headroom;
-	unsigned int len;
+	unsigned int len = head_skb->len;
 	__be16 proto;
 	bool csum;
 	int sg = !!(features & NETIF_F_SG);
@@ -3094,6 +3095,15 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 
 	csum = !!can_checksum_protocol(features, proto);
 
+	/* GSO partial only requires that we trim off any excess that
+	 * doesn't fit into an MSS sized block, so take care of that
+	 * now.
+	 */
+	if (features & NETIF_F_GSO_PARTIAL) {
+		partial_segs = len / mss;
+		mss *= partial_segs;
+	}
+
 	headroom = skb_headroom(head_skb);
 	pos = skb_headlen(head_skb);
 
@@ -3281,6 +3291,23 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 	 */
 	segs->prev = tail;
 
+	/* Update GSO info on first skb in partial sequence. */
+	if (partial_segs) {
+		int type = skb_shinfo(head_skb)->gso_type;
+
+		/* Update type to add partial and then remove dodgy if set */
+		type |= SKB_GSO_PARTIAL;
+		type &= ~SKB_GSO_DODGY;
+
+		/* Update GSO info and prepare to start updating headers on
+		 * our way back down the stack of protocols.
+		 */
+		skb_shinfo(segs)->gso_size = skb_shinfo(head_skb)->gso_size;
+		skb_shinfo(segs)->gso_segs = partial_segs;
+		skb_shinfo(segs)->gso_type = type;
+		SKB_GSO_CB(segs)->data_offset = skb_headroom(segs) + doffset;
+	}
+
 	/* Following permits correct backpressure, for protocols
 	 * using skb_set_owner_w().
 	 * Idea is to tranfert ownership from head_skb to last segment.

net/ipv4/af_inet.c

@@ -1195,12 +1195,12 @@ EXPORT_SYMBOL(inet_sk_rebuild_header);
 static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 					netdev_features_t features)
 {
+	bool udpfrag = false, fixedid = false, encap;
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	const struct net_offload *ops;
 	unsigned int offset = 0;
-	bool udpfrag, encap;
 	struct iphdr *iph;
-	int proto;
+	int proto, tot_len;
 	int nhoff;
 	int ihl;
 	int id;
@@ -1217,7 +1217,9 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_TCPV6 |
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_UDP_TUNNEL_CSUM |
+		       SKB_GSO_TCP_FIXEDID |
 		       SKB_GSO_TUNNEL_REMCSUM |
+		       SKB_GSO_PARTIAL |
 		       0)))
 		goto out;
 
@@ -1248,11 +1250,14 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 
 	segs = ERR_PTR(-EPROTONOSUPPORT);
 
-	if (skb->encapsulation &&
-	    skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP))
-		udpfrag = proto == IPPROTO_UDP && encap;
-	else
-		udpfrag = proto == IPPROTO_UDP && !skb->encapsulation;
+	if (!skb->encapsulation || encap) {
+		udpfrag = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
+		fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID);
+
+		/* fixed ID is invalid if DF bit is not set */
+		if (fixedid && !(iph->frag_off & htons(IP_DF)))
+			goto out;
+	}
 
 	ops = rcu_dereference(inet_offloads[proto]);
 	if (likely(ops && ops->callbacks.gso_segment))
@@ -1265,15 +1270,25 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 	do {
 		iph = (struct iphdr *)(skb_mac_header(skb) + nhoff);
 		if (udpfrag) {
-			iph->id = htons(id);
 			iph->frag_off = htons(offset >> 3);
 			if (skb->next)
 				iph->frag_off |= htons(IP_MF);
 			offset += skb->len - nhoff - ihl;
+			tot_len = skb->len - nhoff;
+		} else if (skb_is_gso(skb)) {
+			if (!fixedid) {
+				iph->id = htons(id);
+				id += skb_shinfo(skb)->gso_segs;
+			}
+			tot_len = skb_shinfo(skb)->gso_size +
+				  SKB_GSO_CB(skb)->data_offset +
+				  skb->head - (unsigned char *)iph;
 		} else {
+			if (!fixedid)
 				iph->id = htons(id++);
+			tot_len = skb->len - nhoff;
 		}
-		iph->tot_len = htons(skb->len - nhoff);
+		iph->tot_len = htons(tot_len);
 		ip_send_check(iph);
 		if (encap)
 			skb_reset_inner_headers(skb);
@@ -1325,6 +1340,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 
 	for (p = *head; p; p = p->next) {
 		struct iphdr *iph2;
+		u16 flush_id;
 
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
@@ -1348,16 +1364,36 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
 			(iph->tos ^ iph2->tos) |
 			((iph->frag_off ^ iph2->frag_off) & htons(IP_DF));
 
-		/* Save the IP ID check to be included later when we get to
-		 * the transport layer so only the inner most IP ID is checked.
-		 * This is because some GSO/TSO implementations do not
-		 * correctly increment the IP ID for the outer hdrs.
-		 */
-		NAPI_GRO_CB(p)->flush_id =
-			    ((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id);
 		NAPI_GRO_CB(p)->flush |= flush;
+
+		/* We need to store of the IP ID check to be included later
+		 * when we can verify that this packet does in fact belong
+		 * to a given flow.
+		 */
+		flush_id = (u16)(id - ntohs(iph2->id));
+
+		/* This bit of code makes it much easier for us to identify
+		 * the cases where we are doing atomic vs non-atomic IP ID
+		 * checks.  Specifically an atomic check can return IP ID
+		 * values 0 - 0xFFFF, while a non-atomic check can only
+		 * return 0 or 0xFFFF.
+		 */
+		if (!NAPI_GRO_CB(p)->is_atomic ||
+		    !(iph->frag_off & htons(IP_DF))) {
+			flush_id ^= NAPI_GRO_CB(p)->count;
+			flush_id = flush_id ? 0xFFFF : 0;
+		}
+
+		/* If the previous IP ID value was based on an atomic
+		 * datagram we can overwrite the value and ignore it.
+		 */
+		if (NAPI_GRO_CB(skb)->is_atomic)
+			NAPI_GRO_CB(p)->flush_id = flush_id;
+		else
+			NAPI_GRO_CB(p)->flush_id |= flush_id;
 	}
 
+	NAPI_GRO_CB(skb)->is_atomic = !!(iph->frag_off & htons(IP_DF));
 	NAPI_GRO_CB(skb)->flush |= flush;
 	skb_set_network_header(skb, off);
 	/* The above will be needed by the transport layer if there is one

net/ipv4/gre_offload.c

@@ -32,10 +32,12 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_UDP |
 				  SKB_GSO_DODGY |
 				  SKB_GSO_TCP_ECN |
+				  SKB_GSO_TCP_FIXEDID |
 				  SKB_GSO_GRE |
 				  SKB_GSO_GRE_CSUM |
 				  SKB_GSO_IPIP |
-				  SKB_GSO_SIT)))
+				  SKB_GSO_SIT |
+				  SKB_GSO_PARTIAL)))
 		goto out;
 
 	if (!skb->encapsulation)
@@ -86,7 +88,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 	skb = segs;
 	do {
 		struct gre_base_hdr *greh;
-		__be32 *pcsum;
+		__sum16 *pcsum;
 
 		/* Set up inner headers if we are offloading inner checksum */
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
@@ -106,10 +108,25 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 			continue;
 
 		greh = (struct gre_base_hdr *)skb_transport_header(skb);
-		pcsum = (__be32 *)(greh + 1);
+		pcsum = (__sum16 *)(greh + 1);
 
+		if (skb_is_gso(skb)) {
+			unsigned int partial_adj;
+
+			/* Adjust checksum to account for the fact that
+			 * the partial checksum is based on actual size
+			 * whereas headers should be based on MSS size.
+			 */
+			partial_adj = skb->len + skb_headroom(skb) -
+				      SKB_GSO_CB(skb)->data_offset -
+				      skb_shinfo(skb)->gso_size;
+			*pcsum = ~csum_fold((__force __wsum)htonl(partial_adj));
+		} else {
 			*pcsum = 0;
-		*(__sum16 *)pcsum = gso_make_checksum(skb, 0);
+		}
+
+		*(pcsum + 1) = 0;
+		*pcsum = gso_make_checksum(skb, 0);
 	} while ((skb = skb->next));
 out:
 	return segs;

net/ipv4/tcp_offload.c

@@ -89,6 +89,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 			     ~(SKB_GSO_TCPV4 |
 			       SKB_GSO_DODGY |
 			       SKB_GSO_TCP_ECN |
+			       SKB_GSO_TCP_FIXEDID |
 			       SKB_GSO_TCPV6 |
 			       SKB_GSO_GRE |
 			       SKB_GSO_GRE_CSUM |
@@ -98,7 +99,8 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 			       SKB_GSO_UDP_TUNNEL_CSUM |
 			       SKB_GSO_TUNNEL_REMCSUM |
 			       0) ||
-			     !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
+			     !(type & (SKB_GSO_TCPV4 |
+				       SKB_GSO_TCPV6))))
 			goto out;
 
 		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
@@ -107,6 +109,12 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 		goto out;
 	}
 
+	/* GSO partial only requires splitting the frame into an MSS
+	 * multiple and possibly a remainder.  So update the mss now.
+	 */
+	if (features & NETIF_F_GSO_PARTIAL)
+		mss = skb->len - (skb->len % mss);
+
 	copy_destructor = gso_skb->destructor == tcp_wfree;
 	ooo_okay = gso_skb->ooo_okay;
 	/* All segments but the first should have ooo_okay cleared */
@@ -131,7 +139,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	newcheck = ~csum_fold((__force __wsum)((__force u32)th->check +
 					       (__force u32)delta));
 
-	do {
+	while (skb->next) {
 		th->fin = th->psh = 0;
 		th->check = newcheck;
 
@@ -151,7 +159,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 
 		th->seq = htonl(seq);
 		th->cwr = 0;
-	} while (skb->next);
+	}
 
 	/* Following permits TCP Small Queues to work well with GSO :
 	 * The callback to TCP stack will be called at the time last frag
@@ -237,7 +245,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 
 found:
 	/* Include the IP ID check below from the inner most IP hdr */
-	flush = NAPI_GRO_CB(p)->flush | NAPI_GRO_CB(p)->flush_id;
+	flush = NAPI_GRO_CB(p)->flush;
 	flush |= (__force int)(flags & TCP_FLAG_CWR);
 	flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
 		  ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH));
@@ -246,6 +254,17 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 		flush |= *(u32 *)((u8 *)th + i) ^
 			 *(u32 *)((u8 *)th2 + i);
 
+	/* When we receive our second frame we can made a decision on if we
+	 * continue this flow as an atomic flow with a fixed ID or if we use
+	 * an incrementing ID.
+	 */
+	if (NAPI_GRO_CB(p)->flush_id != 1 ||
+	    NAPI_GRO_CB(p)->count != 1 ||
+	    !NAPI_GRO_CB(p)->is_atomic)
+		flush |= NAPI_GRO_CB(p)->flush_id;
+	else
+		NAPI_GRO_CB(p)->is_atomic = false;
+
 	mss = skb_shinfo(p)->gso_size;
 
 	flush |= (len - 1) >= mss;
@@ -314,6 +333,9 @@ static int tcp4_gro_complete(struct sk_buff *skb, int thoff)
 				  iph->daddr, 0);
 	skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4;
 
+	if (NAPI_GRO_CB(skb)->is_atomic)
+		skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_FIXEDID;
+
 	return tcp_gro_complete(skb);
 }
 

net/ipv4/udp_offload.c

@@ -39,8 +39,11 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	 * 16 bit length field due to the header being added outside of an
 	 * IP or IPv6 frame that was already limited to 64K - 1.
 	 */
-	partial = csum_sub(csum_unfold(uh->check),
-			   (__force __wsum)htonl(skb->len));
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL)
+		partial = (__force __wsum)uh->len;
+	else
+		partial = (__force __wsum)htonl(skb->len);
+	partial = csum_sub(csum_unfold(uh->check), partial);
 
 	/* setup inner skb. */
 	skb->encapsulation = 0;
@@ -89,7 +92,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	udp_offset = outer_hlen - tnl_hlen;
 	skb = segs;
 	do {
-		__be16 len;
+		unsigned int len;
 
 		if (remcsum)
 			skb->ip_summed = CHECKSUM_NONE;
@@ -107,14 +110,26 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 		skb_reset_mac_header(skb);
 		skb_set_network_header(skb, mac_len);
 		skb_set_transport_header(skb, udp_offset);
-		len = htons(skb->len - udp_offset);
+		len = skb->len - udp_offset;
 		uh = udp_hdr(skb);
-		uh->len = len;
+
+		/* If we are only performing partial GSO the inner header
+		 * will be using a length value equal to only one MSS sized
+		 * segment instead of the entire frame.
+		 */
+		if (skb_is_gso(skb)) {
+			uh->len = htons(skb_shinfo(skb)->gso_size +
+					SKB_GSO_CB(skb)->data_offset +
+					skb->head - (unsigned char *)uh);
+		} else {
+			uh->len = htons(len);
+		}
 
 		if (!need_csum)
 			continue;
 
-		uh->check = ~csum_fold(csum_add(partial, (__force __wsum)len));
+		uh->check = ~csum_fold(csum_add(partial,
+				       (__force __wsum)htonl(len)));
 
 		if (skb->encapsulation || !offload_csum) {
 			uh->check = gso_make_checksum(skb, ~uh->check);

net/ipv6/ip6_offload.c

@@ -63,6 +63,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	int proto;
 	struct frag_hdr *fptr;
 	unsigned int unfrag_ip6hlen;
+	unsigned int payload_len;
 	u8 *prevhdr;
 	int offset = 0;
 	bool encap, udpfrag;
@@ -73,6 +74,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_UDP |
 		       SKB_GSO_DODGY |
 		       SKB_GSO_TCP_ECN |
+		       SKB_GSO_TCP_FIXEDID |
+		       SKB_GSO_TCPV6 |
 		       SKB_GSO_GRE |
 		       SKB_GSO_GRE_CSUM |
 		       SKB_GSO_IPIP |
@@ -80,7 +83,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_UDP_TUNNEL |
 		       SKB_GSO_UDP_TUNNEL_CSUM |
 		       SKB_GSO_TUNNEL_REMCSUM |
-		       SKB_GSO_TCPV6 |
+		       SKB_GSO_PARTIAL |
 		       0)))
 		goto out;
 
@@ -117,7 +120,13 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 
 	for (skb = segs; skb; skb = skb->next) {
 		ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
-		ipv6h->payload_len = htons(skb->len - nhoff - sizeof(*ipv6h));
+		if (skb_is_gso(skb))
+			payload_len = skb_shinfo(skb)->gso_size +
+				      SKB_GSO_CB(skb)->data_offset +
+				      skb->head - (unsigned char *)(ipv6h + 1);
+		else
+			payload_len = skb->len - nhoff - sizeof(*ipv6h);
+		ipv6h->payload_len = htons(payload_len);
 		skb->network_header = (u8 *)ipv6h - skb->head;
 
 		if (udpfrag) {
@@ -239,10 +248,14 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 		NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000));
 		NAPI_GRO_CB(p)->flush |= flush;
 
-		/* Clear flush_id, there's really no concept of ID in IPv6. */
+		/* If the previous IP ID value was based on an atomic
+		 * datagram we can overwrite the value and ignore it.
+		 */
+		if (NAPI_GRO_CB(skb)->is_atomic)
 			NAPI_GRO_CB(p)->flush_id = 0;
 	}
 
+	NAPI_GRO_CB(skb)->is_atomic = true;
 	NAPI_GRO_CB(skb)->flush |= flush;
 
 	skb_gro_postpull_rcsum(skb, iph, nlen);

net/mpls/mpls_gso.c

@@ -31,6 +31,7 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_TCPV6 |
 				  SKB_GSO_UDP |
 				  SKB_GSO_DODGY |
+				  SKB_GSO_TCP_FIXEDID |
 				  SKB_GSO_TCP_ECN)))
 		goto out;