From 48d83325b61043e3bbd24dd37b9fe433744cf330 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 19 Jun 2006 23:57:59 -0700
Subject: [NET]: Prevent multiple qdisc runs

Having two or more qdisc_run's contend against each other is bad because
it can induce packet reordering if the packets have to be requeued.  It
appears that this is an unintended consequence of relinquinshing the queue
lock while transmitting.  That in turn is needed for devices that spend a
lot of time in their transmit routine.

There are no advantages to be had as devices with queues are inherently
single-threaded (the loopback device is not but then it doesn't have a
queue).

Even if you were to add a queue to a parallel virtual device (e.g., bolt
a tbf filter in front of an ipip tunnel device), you would still want to
process the queue in sequence to ensure that the packets are ordered
correctly.

The solution here is to steal a bit from net_device to prevent this.

BTW, as qdisc_restart is no longer used by anyone as a module inside the
kernel (IIRC it used to with netif_wake_queue), I have not exported the
new __qdisc_run function.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux/netdevice.h')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e432b743dda..39919c882a2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -233,6 +233,7 @@ enum netdev_state_t
 	__LINK_STATE_RX_SCHED,
 	__LINK_STATE_LINKWATCH_PENDING,
 	__LINK_STATE_DORMANT,
+	__LINK_STATE_QDISC_RUNNING,
 };
 
 
-- 
cgit v1.2.3-70-g09d2


From 7967168cefdbc63bf332d6b1548eca7cd65ebbcc Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 22 Jun 2006 02:40:14 -0700
Subject: [NET]: Merge TSO/UFO fields in sk_buff

Having separate fields in sk_buff for TSO/UFO (tso_size/ufo_size) is not
going to scale if we add any more segmentation methods (e.g., DCCP).  So
let's merge them.

They were used to tell the protocol of a packet.  This function has been
subsumed by the new gso_type field.  This is essentially a set of netdev
feature bits (shifted by 16 bits) that are required to process a specific
skb.  As such it's easy to tell whether a given device can process a GSO
skb: you just have to and the gso_type field and the netdev's features
field.

I've made gso_type a conjunction.  The idea is that you have a base type
(e.g., SKB_GSO_TCPV4) that can be modified further to support new features.
For example, if we add a hardware TSO type that supports ECN, they would
declare NETIF_F_TSO | NETIF_F_TSO_ECN.  All TSO packets with CWR set would
have a gso_type of SKB_GSO_TCPV4 | SKB_GSO_TCPV4_ECN while all other TSO
packets would be SKB_GSO_TCPV4.  This means that only the CWR packets need
to be emulated in software.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/8139cp.c            |  2 +-
 drivers/net/bnx2.c              |  4 ++--
 drivers/net/chelsio/sge.c       |  4 ++--
 drivers/net/e1000/e1000_main.c  | 10 ++++-----
 drivers/net/forcedeth.c         |  4 ++--
 drivers/net/ixgb/ixgb_main.c    |  4 ++--
 drivers/net/loopback.c          |  4 ++--
 drivers/net/myri10ge/myri10ge.c |  4 ++--
 drivers/net/r8169.c             |  2 +-
 drivers/net/s2io.c              | 16 +++++++-------
 drivers/net/sky2.c              |  4 ++--
 drivers/net/tg3.c               |  4 ++--
 drivers/net/typhoon.c           |  2 +-
 drivers/s390/net/qeth_eddp.c    | 12 +++++------
 drivers/s390/net/qeth_main.c    |  4 ++--
 drivers/s390/net/qeth_tso.h     |  2 +-
 include/linux/netdevice.h       | 14 ++++++++++--
 include/linux/skbuff.h          | 12 ++++++++---
 include/net/tcp.h               |  4 ++--
 net/bridge/br_forward.c         |  4 ++--
 net/bridge/br_netfilter.c       |  2 +-
 net/core/skbuff.c               | 16 ++++++++------
 net/ipv4/ip_output.c            | 16 ++++++++------
 net/ipv4/tcp.c                  |  4 ++--
 net/ipv4/tcp_input.c            |  2 +-
 net/ipv4/tcp_output.c           | 47 ++++++++++++++++++++++++-----------------
 net/ipv6/ip6_output.c           |  7 +++---
 27 files changed, 120 insertions(+), 90 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/drivers/net/8139cp.c b/drivers/net/8139cp.c
index a26077a175a..0cdc830449d 100644
--- a/drivers/net/8139cp.c
+++ b/drivers/net/8139cp.c
@@ -797,7 +797,7 @@ static int cp_start_xmit (struct sk_buff *skb, struct net_device *dev)
 	entry = cp->tx_head;
 	eor = (entry == (CP_TX_RING_SIZE - 1)) ? RingEnd : 0;
 	if (dev->features & NETIF_F_TSO)
-		mss = skb_shinfo(skb)->tso_size;
+		mss = skb_shinfo(skb)->gso_size;
 
 	if (skb_shinfo(skb)->nr_frags == 0) {
 		struct cp_desc *txd = &cp->tx_ring[entry];
diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c
index 702d546567a..7635736cc79 100644
--- a/drivers/net/bnx2.c
+++ b/drivers/net/bnx2.c
@@ -1640,7 +1640,7 @@ bnx2_tx_int(struct bnx2 *bp)
 		skb = tx_buf->skb;
 #ifdef BCM_TSO 
 		/* partial BD completions possible with TSO packets */
-		if (skb_shinfo(skb)->tso_size) {
+		if (skb_shinfo(skb)->gso_size) {
 			u16 last_idx, last_ring_idx;
 
 			last_idx = sw_cons +
@@ -4428,7 +4428,7 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			(TX_BD_FLAGS_VLAN_TAG | (vlan_tx_tag_get(skb) << 16));
 	}
 #ifdef BCM_TSO 
-	if ((mss = skb_shinfo(skb)->tso_size) &&
+	if ((mss = skb_shinfo(skb)->gso_size) &&
 		(skb->len > (bp->dev->mtu + ETH_HLEN))) {
 		u32 tcp_opt_len, ip_tcp_len;
 
diff --git a/drivers/net/chelsio/sge.c b/drivers/net/chelsio/sge.c
index 4391bf4bf57..53efff6da78 100644
--- a/drivers/net/chelsio/sge.c
+++ b/drivers/net/chelsio/sge.c
@@ -1418,7 +1418,7 @@ int t1_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct cpl_tx_pkt *cpl;
 
 #ifdef NETIF_F_TSO
-	if (skb_shinfo(skb)->tso_size) {
+	if (skb_shinfo(skb)->gso_size) {
 		int eth_type;
 		struct cpl_tx_pkt_lso *hdr;
 
@@ -1433,7 +1433,7 @@ int t1_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		hdr->ip_hdr_words = skb->nh.iph->ihl;
 		hdr->tcp_hdr_words = skb->h.th->doff;
 		hdr->eth_type_mss = htons(MK_ETH_TYPE_MSS(eth_type,
-						skb_shinfo(skb)->tso_size));
+						skb_shinfo(skb)->gso_size));
 		hdr->len = htonl(skb->len - sizeof(*hdr));
 		cpl = (struct cpl_tx_pkt *)hdr;
 		sge->stats.tx_lso_pkts++;
diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c
index a373ccb308d..32b7d444b37 100644
--- a/drivers/net/e1000/e1000_main.c
+++ b/drivers/net/e1000/e1000_main.c
@@ -2394,7 +2394,7 @@ e1000_tso(struct e1000_adapter *adapter, struct e1000_tx_ring *tx_ring,
 	uint8_t ipcss, ipcso, tucss, tucso, hdr_len;
 	int err;
 
-	if (skb_shinfo(skb)->tso_size) {
+	if (skb_shinfo(skb)->gso_size) {
 		if (skb_header_cloned(skb)) {
 			err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
 			if (err)
@@ -2402,7 +2402,7 @@ e1000_tso(struct e1000_adapter *adapter, struct e1000_tx_ring *tx_ring,
 		}
 
 		hdr_len = ((skb->h.raw - skb->data) + (skb->h.th->doff << 2));
-		mss = skb_shinfo(skb)->tso_size;
+		mss = skb_shinfo(skb)->gso_size;
 		if (skb->protocol == htons(ETH_P_IP)) {
 			skb->nh.iph->tot_len = 0;
 			skb->nh.iph->check = 0;
@@ -2519,7 +2519,7 @@ e1000_tx_map(struct e1000_adapter *adapter, struct e1000_tx_ring *tx_ring,
 		 * tso gets written back prematurely before the data is fully
 		 * DMA'd to the controller */
 		if (!skb->data_len && tx_ring->last_tx_tso &&
-		    !skb_shinfo(skb)->tso_size) {
+		    !skb_shinfo(skb)->gso_size) {
 			tx_ring->last_tx_tso = 0;
 			size -= 4;
 		}
@@ -2757,7 +2757,7 @@ e1000_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 	}
 
 #ifdef NETIF_F_TSO
-	mss = skb_shinfo(skb)->tso_size;
+	mss = skb_shinfo(skb)->gso_size;
 	/* The controller does a simple calculation to
 	 * make sure there is enough room in the FIFO before
 	 * initiating the DMA for each buffer.  The calc is:
@@ -2807,7 +2807,7 @@ e1000_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 #ifdef NETIF_F_TSO
 	/* Controller Erratum workaround */
 	if (!skb->data_len && tx_ring->last_tx_tso &&
-	    !skb_shinfo(skb)->tso_size)
+	    !skb_shinfo(skb)->gso_size)
 		count++;
 #endif
 
diff --git a/drivers/net/forcedeth.c b/drivers/net/forcedeth.c
index 191383d461d..21be4fa071b 100644
--- a/drivers/net/forcedeth.c
+++ b/drivers/net/forcedeth.c
@@ -1495,8 +1495,8 @@ static int nv_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	np->tx_skbuff[nr] = skb;
 
 #ifdef NETIF_F_TSO
-	if (skb_shinfo(skb)->tso_size)
-		tx_flags_extra = NV_TX2_TSO | (skb_shinfo(skb)->tso_size << NV_TX2_TSO_SHIFT);
+	if (skb_shinfo(skb)->gso_size)
+		tx_flags_extra = NV_TX2_TSO | (skb_shinfo(skb)->gso_size << NV_TX2_TSO_SHIFT);
 	else
 #endif
 	tx_flags_extra = (skb->ip_summed == CHECKSUM_HW ? (NV_TX2_CHECKSUM_L3|NV_TX2_CHECKSUM_L4) : 0);
diff --git a/drivers/net/ixgb/ixgb_main.c b/drivers/net/ixgb/ixgb_main.c
index 57006fb8840..8bb32f94699 100644
--- a/drivers/net/ixgb/ixgb_main.c
+++ b/drivers/net/ixgb/ixgb_main.c
@@ -1173,7 +1173,7 @@ ixgb_tso(struct ixgb_adapter *adapter, struct sk_buff *skb)
 	uint16_t ipcse, tucse, mss;
 	int err;
 
-	if(likely(skb_shinfo(skb)->tso_size)) {
+	if(likely(skb_shinfo(skb)->gso_size)) {
 		if (skb_header_cloned(skb)) {
 			err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
 			if (err)
@@ -1181,7 +1181,7 @@ ixgb_tso(struct ixgb_adapter *adapter, struct sk_buff *skb)
 		}
 
 		hdr_len = ((skb->h.raw - skb->data) + (skb->h.th->doff << 2));
-		mss = skb_shinfo(skb)->tso_size;
+		mss = skb_shinfo(skb)->gso_size;
 		skb->nh.iph->tot_len = 0;
 		skb->nh.iph->check = 0;
 		skb->h.th->check = ~csum_tcpudp_magic(skb->nh.iph->saddr,
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index b79d6e8d304..43fef7de8cb 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -74,7 +74,7 @@ static void emulate_large_send_offload(struct sk_buff *skb)
 	struct iphdr *iph = skb->nh.iph;
 	struct tcphdr *th = (struct tcphdr*)(skb->nh.raw + (iph->ihl * 4));
 	unsigned int doffset = (iph->ihl + th->doff) * 4;
-	unsigned int mtu = skb_shinfo(skb)->tso_size + doffset;
+	unsigned int mtu = skb_shinfo(skb)->gso_size + doffset;
 	unsigned int offset = 0;
 	u32 seq = ntohl(th->seq);
 	u16 id  = ntohs(iph->id);
@@ -139,7 +139,7 @@ static int loopback_xmit(struct sk_buff *skb, struct net_device *dev)
 #endif
 
 #ifdef LOOPBACK_TSO
-	if (skb_shinfo(skb)->tso_size) {
+	if (skb_shinfo(skb)->gso_size) {
 		BUG_ON(skb->protocol != htons(ETH_P_IP));
 		BUG_ON(skb->nh.iph->protocol != IPPROTO_TCP);
 
diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c
index b983e1e0434..dbdf189436f 100644
--- a/drivers/net/myri10ge/myri10ge.c
+++ b/drivers/net/myri10ge/myri10ge.c
@@ -1879,7 +1879,7 @@ again:
 
 #ifdef NETIF_F_TSO
 	if (skb->len > (dev->mtu + ETH_HLEN)) {
-		mss = skb_shinfo(skb)->tso_size;
+		mss = skb_shinfo(skb)->gso_size;
 		if (mss != 0)
 			max_segments = MYRI10GE_MAX_SEND_DESC_TSO;
 	}
@@ -2112,7 +2112,7 @@ abort_linearize:
 		}
 		idx = (idx + 1) & tx->mask;
 	} while (idx != last_idx);
-	if (skb_shinfo(skb)->tso_size) {
+	if (skb_shinfo(skb)->gso_size) {
 		printk(KERN_ERR
 		       "myri10ge: %s: TSO but wanted to linearize?!?!?\n",
 		       mgp->dev->name);
diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
index 985afe0e627..12d1cb289bb 100644
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -2172,7 +2172,7 @@ static int rtl8169_xmit_frags(struct rtl8169_private *tp, struct sk_buff *skb,
 static inline u32 rtl8169_tso_csum(struct sk_buff *skb, struct net_device *dev)
 {
 	if (dev->features & NETIF_F_TSO) {
-		u32 mss = skb_shinfo(skb)->tso_size;
+		u32 mss = skb_shinfo(skb)->gso_size;
 
 		if (mss)
 			return LargeSend | ((mss & MSSMask) << MSSShift);
diff --git a/drivers/net/s2io.c b/drivers/net/s2io.c
index 11daed495b9..3defe5d4f7d 100644
--- a/drivers/net/s2io.c
+++ b/drivers/net/s2io.c
@@ -3959,8 +3959,8 @@ static int s2io_xmit(struct sk_buff *skb, struct net_device *dev)
 	txdp->Control_1 = 0;
 	txdp->Control_2 = 0;
 #ifdef NETIF_F_TSO
-	mss = skb_shinfo(skb)->tso_size;
-	if (mss) {
+	mss = skb_shinfo(skb)->gso_size;
+	if (skb_shinfo(skb)->gso_type == SKB_GSO_TCPV4) {
 		txdp->Control_1 |= TXD_TCP_LSO_EN;
 		txdp->Control_1 |= TXD_TCP_LSO_MSS(mss);
 	}
@@ -3980,10 +3980,10 @@ static int s2io_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	frg_len = skb->len - skb->data_len;
-	if (skb_shinfo(skb)->ufo_size) {
+	if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4) {
 		int ufo_size;
 
-		ufo_size = skb_shinfo(skb)->ufo_size;
+		ufo_size = skb_shinfo(skb)->gso_size;
 		ufo_size &= ~7;
 		txdp->Control_1 |= TXD_UFO_EN;
 		txdp->Control_1 |= TXD_UFO_MSS(ufo_size);
@@ -4009,7 +4009,7 @@ static int s2io_xmit(struct sk_buff *skb, struct net_device *dev)
 	txdp->Host_Control = (unsigned long) skb;
 	txdp->Control_1 |= TXD_BUFFER0_SIZE(frg_len);
 
-	if (skb_shinfo(skb)->ufo_size)
+	if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4)
 		txdp->Control_1 |= TXD_UFO_EN;
 
 	frg_cnt = skb_shinfo(skb)->nr_frags;
@@ -4024,12 +4024,12 @@ static int s2io_xmit(struct sk_buff *skb, struct net_device *dev)
 		    (sp->pdev, frag->page, frag->page_offset,
 		     frag->size, PCI_DMA_TODEVICE);
 		txdp->Control_1 = TXD_BUFFER0_SIZE(frag->size);
-		if (skb_shinfo(skb)->ufo_size)
+		if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4)
 			txdp->Control_1 |= TXD_UFO_EN;
 	}
 	txdp->Control_1 |= TXD_GATHER_CODE_LAST;
 
-	if (skb_shinfo(skb)->ufo_size)
+	if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4)
 		frg_cnt++; /* as Txd0 was used for inband header */
 
 	tx_fifo = mac_control->tx_FIFO_start[queue];
@@ -4043,7 +4043,7 @@ static int s2io_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (mss)
 		val64 |= TX_FIFO_SPECIAL_FUNC;
 #endif
-	if (skb_shinfo(skb)->ufo_size)
+	if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4)
 		val64 |= TX_FIFO_SPECIAL_FUNC;
 	writeq(val64, &tx_fifo->List_Control);
 
diff --git a/drivers/net/sky2.c b/drivers/net/sky2.c
index fba1e4d4d83..d3577871be2 100644
--- a/drivers/net/sky2.c
+++ b/drivers/net/sky2.c
@@ -1160,7 +1160,7 @@ static unsigned tx_le_req(const struct sk_buff *skb)
 	count = sizeof(dma_addr_t) / sizeof(u32);
 	count += skb_shinfo(skb)->nr_frags * count;
 
-	if (skb_shinfo(skb)->tso_size)
+	if (skb_shinfo(skb)->gso_size)
 		++count;
 
 	if (skb->ip_summed == CHECKSUM_HW)
@@ -1232,7 +1232,7 @@ static int sky2_xmit_frame(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	/* Check for TCP Segmentation Offload */
-	mss = skb_shinfo(skb)->tso_size;
+	mss = skb_shinfo(skb)->gso_size;
 	if (mss != 0) {
 		/* just drop the packet if non-linear expansion fails */
 		if (skb_header_cloned(skb) &&
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index b2ddd4522a8..e3e380f90f8 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -3780,7 +3780,7 @@ static int tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 #if TG3_TSO_SUPPORT != 0
 	mss = 0;
 	if (skb->len > (tp->dev->mtu + ETH_HLEN) &&
-	    (mss = skb_shinfo(skb)->tso_size) != 0) {
+	    (mss = skb_shinfo(skb)->gso_size) != 0) {
 		int tcp_opt_len, ip_tcp_len;
 
 		if (skb_header_cloned(skb) &&
@@ -3905,7 +3905,7 @@ static int tg3_start_xmit_dma_bug(struct sk_buff *skb, struct net_device *dev)
 #if TG3_TSO_SUPPORT != 0
 	mss = 0;
 	if (skb->len > (tp->dev->mtu + ETH_HLEN) &&
-	    (mss = skb_shinfo(skb)->tso_size) != 0) {
+	    (mss = skb_shinfo(skb)->gso_size) != 0) {
 		int tcp_opt_len, ip_tcp_len;
 
 		if (skb_header_cloned(skb) &&
diff --git a/drivers/net/typhoon.c b/drivers/net/typhoon.c
index d9258d42090..e49e8b520c2 100644
--- a/drivers/net/typhoon.c
+++ b/drivers/net/typhoon.c
@@ -340,7 +340,7 @@ enum state_values {
 #endif
 
 #if defined(NETIF_F_TSO)
-#define skb_tso_size(x)		(skb_shinfo(x)->tso_size)
+#define skb_tso_size(x)		(skb_shinfo(x)->gso_size)
 #define TSO_NUM_DESCRIPTORS	2
 #define TSO_OFFLOAD_ON		TYPHOON_OFFLOAD_TCP_SEGMENT
 #else
diff --git a/drivers/s390/net/qeth_eddp.c b/drivers/s390/net/qeth_eddp.c
index 0bab60a2030..38aad832145 100644
--- a/drivers/s390/net/qeth_eddp.c
+++ b/drivers/s390/net/qeth_eddp.c
@@ -420,7 +420,7 @@ __qeth_eddp_fill_context_tcp(struct qeth_eddp_context *ctx,
        }
 	tcph = eddp->skb->h.th;
 	while (eddp->skb_offset < eddp->skb->len) {
-		data_len = min((int)skb_shinfo(eddp->skb)->tso_size,
+		data_len = min((int)skb_shinfo(eddp->skb)->gso_size,
 			       (int)(eddp->skb->len - eddp->skb_offset));
 		/* prepare qdio hdr */
 		if (eddp->qh.hdr.l2.id == QETH_HEADER_TYPE_LAYER2){
@@ -515,20 +515,20 @@ qeth_eddp_calc_num_pages(struct qeth_eddp_context *ctx, struct sk_buff *skb,
 
 	QETH_DBF_TEXT(trace, 5, "eddpcanp");
 	/* can we put multiple skbs in one page? */
-	skbs_per_page = PAGE_SIZE / (skb_shinfo(skb)->tso_size + hdr_len);
+	skbs_per_page = PAGE_SIZE / (skb_shinfo(skb)->gso_size + hdr_len);
 	if (skbs_per_page > 1){
-		ctx->num_pages = (skb_shinfo(skb)->tso_segs + 1) /
+		ctx->num_pages = (skb_shinfo(skb)->gso_segs + 1) /
 				 skbs_per_page + 1;
 		ctx->elements_per_skb = 1;
 	} else {
 		/* no -> how many elements per skb? */
-		ctx->elements_per_skb = (skb_shinfo(skb)->tso_size + hdr_len +
+		ctx->elements_per_skb = (skb_shinfo(skb)->gso_size + hdr_len +
 				     PAGE_SIZE) >> PAGE_SHIFT;
 		ctx->num_pages = ctx->elements_per_skb *
-				 (skb_shinfo(skb)->tso_segs + 1);
+				 (skb_shinfo(skb)->gso_segs + 1);
 	}
 	ctx->num_elements = ctx->elements_per_skb *
-			    (skb_shinfo(skb)->tso_segs + 1);
+			    (skb_shinfo(skb)->gso_segs + 1);
 }
 
 static inline struct qeth_eddp_context *
diff --git a/drivers/s390/net/qeth_main.c b/drivers/s390/net/qeth_main.c
index 9e671a48cd2..56009d76832 100644
--- a/drivers/s390/net/qeth_main.c
+++ b/drivers/s390/net/qeth_main.c
@@ -4417,7 +4417,7 @@ qeth_send_packet(struct qeth_card *card, struct sk_buff *skb)
 	struct qeth_eddp_context *ctx = NULL;
 	int tx_bytes = skb->len;
 	unsigned short nr_frags = skb_shinfo(skb)->nr_frags;
-	unsigned short tso_size = skb_shinfo(skb)->tso_size;
+	unsigned short tso_size = skb_shinfo(skb)->gso_size;
 	int rc;
 
 	QETH_DBF_TEXT(trace, 6, "sendpkt");
@@ -4453,7 +4453,7 @@ qeth_send_packet(struct qeth_card *card, struct sk_buff *skb)
 	queue = card->qdio.out_qs
 		[qeth_get_priority_queue(card, skb, ipv, cast_type)];
 
-	if (skb_shinfo(skb)->tso_size)
+	if (skb_shinfo(skb)->gso_size)
 		large_send = card->options.large_send;
 
 	/*are we able to do TSO ? If so ,prepare and send it from here */
diff --git a/drivers/s390/net/qeth_tso.h b/drivers/s390/net/qeth_tso.h
index 24ef40ca956..593f298142c 100644
--- a/drivers/s390/net/qeth_tso.h
+++ b/drivers/s390/net/qeth_tso.h
@@ -51,7 +51,7 @@ qeth_tso_fill_header(struct qeth_card *card, struct sk_buff *skb)
 	hdr->ext.hdr_version = 1;
 	hdr->ext.hdr_len     = 28;
 	/*insert non-fix values */
-	hdr->ext.mss = skb_shinfo(skb)->tso_size;
+	hdr->ext.mss = skb_shinfo(skb)->gso_size;
 	hdr->ext.dg_hdr_len = (__u16)(iph->ihl*4 + tcph->doff*4);
 	hdr->ext.payload_len = (__u16)(skb->len - hdr->ext.dg_hdr_len -
 				       sizeof(struct qeth_hdr_tso));
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index cead6be467e..fa5671307b9 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -308,9 +308,12 @@ struct net_device
 #define NETIF_F_HW_VLAN_RX	256	/* Receive VLAN hw acceleration */
 #define NETIF_F_HW_VLAN_FILTER	512	/* Receive filtering on VLAN */
 #define NETIF_F_VLAN_CHALLENGED	1024	/* Device cannot handle VLAN packets */
-#define NETIF_F_TSO		2048	/* Can offload TCP/IP segmentation */
 #define NETIF_F_LLTX		4096	/* LockLess TX */
-#define NETIF_F_UFO             8192    /* Can offload UDP Large Send*/
+
+	/* Segmentation offload features */
+#define NETIF_F_GSO_SHIFT	16
+#define NETIF_F_TSO		(SKB_GSO_TCPV4 << NETIF_F_GSO_SHIFT)
+#define NETIF_F_UFO		(SKB_GSO_UDPV4 << NETIF_F_GSO_SHIFT)
 
 #define NETIF_F_GEN_CSUM	(NETIF_F_NO_CSUM | NETIF_F_HW_CSUM)
 #define NETIF_F_ALL_CSUM	(NETIF_F_IP_CSUM | NETIF_F_GEN_CSUM)
@@ -979,6 +982,13 @@ extern void dev_seq_stop(struct seq_file *seq, void *v);
 
 extern void linkwatch_run_queue(void);
 
+static inline int netif_needs_gso(struct net_device *dev, struct sk_buff *skb)
+{
+	int feature = skb_shinfo(skb)->gso_type << NETIF_F_GSO_SHIFT;
+	return skb_shinfo(skb)->gso_size &&
+	       (dev->features & feature) != feature;
+}
+
 #endif /* __KERNEL__ */
 
 #endif	/* _LINUX_DEV_H */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f8c7eb79a27..97b0d2d1a6b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -134,9 +134,10 @@ struct skb_frag_struct {
 struct skb_shared_info {
 	atomic_t	dataref;
 	unsigned short	nr_frags;
-	unsigned short	tso_size;
-	unsigned short	tso_segs;
-	unsigned short  ufo_size;
+	unsigned short	gso_size;
+	/* Warning: this field is not always filled in (UFO)! */
+	unsigned short	gso_segs;
+	unsigned short  gso_type;
 	unsigned int    ip6_frag_id;
 	struct sk_buff	*frag_list;
 	skb_frag_t	frags[MAX_SKB_FRAGS];
@@ -168,6 +169,11 @@ enum {
 	SKB_FCLONE_CLONE,
 };
 
+enum {
+	SKB_GSO_TCPV4 = 1 << 0,
+	SKB_GSO_UDPV4 = 1 << 1,
+};
+
 /** 
  *	struct sk_buff - socket buffer
  *	@next: Next buffer in list
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5f4eb5c7968..b197a9e615c 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -569,13 +569,13 @@ struct tcp_skb_cb {
  */
 static inline int tcp_skb_pcount(const struct sk_buff *skb)
 {
-	return skb_shinfo(skb)->tso_segs;
+	return skb_shinfo(skb)->gso_segs;
 }
 
 /* This is valid iff tcp_skb_pcount() > 1. */
 static inline int tcp_skb_mss(const struct sk_buff *skb)
 {
-	return skb_shinfo(skb)->tso_size;
+	return skb_shinfo(skb)->gso_size;
 }
 
 static inline void tcp_dec_pcount_approx(__u32 *count,
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 0dca027ceb8..8be9f2123e5 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -34,8 +34,8 @@ static inline unsigned packet_length(const struct sk_buff *skb)
 
 int br_dev_queue_push_xmit(struct sk_buff *skb)
 {
-	/* drop mtu oversized packets except tso */
-	if (packet_length(skb) > skb->dev->mtu && !skb_shinfo(skb)->tso_size)
+	/* drop mtu oversized packets except gso */
+	if (packet_length(skb) > skb->dev->mtu && !skb_shinfo(skb)->gso_size)
 		kfree_skb(skb);
 	else {
 #ifdef CONFIG_BRIDGE_NETFILTER
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 3e41f9d6d51..8298a5179ae 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -761,7 +761,7 @@ static int br_nf_dev_queue_xmit(struct sk_buff *skb)
 {
 	if (skb->protocol == htons(ETH_P_IP) &&
 	    skb->len > skb->dev->mtu &&
-	    !(skb_shinfo(skb)->ufo_size || skb_shinfo(skb)->tso_size))
+	    !skb_shinfo(skb)->gso_size)
 		return ip_fragment(skb, br_dev_queue_push_xmit);
 	else
 		return br_dev_queue_push_xmit(skb);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index fe63d4efbd4..368d98578c1 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -172,9 +172,9 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 	shinfo = skb_shinfo(skb);
 	atomic_set(&shinfo->dataref, 1);
 	shinfo->nr_frags  = 0;
-	shinfo->tso_size = 0;
-	shinfo->tso_segs = 0;
-	shinfo->ufo_size = 0;
+	shinfo->gso_size = 0;
+	shinfo->gso_segs = 0;
+	shinfo->gso_type = 0;
 	shinfo->ip6_frag_id = 0;
 	shinfo->frag_list = NULL;
 
@@ -238,8 +238,9 @@ struct sk_buff *alloc_skb_from_cache(kmem_cache_t *cp,
 
 	atomic_set(&(skb_shinfo(skb)->dataref), 1);
 	skb_shinfo(skb)->nr_frags  = 0;
-	skb_shinfo(skb)->tso_size = 0;
-	skb_shinfo(skb)->tso_segs = 0;
+	skb_shinfo(skb)->gso_size = 0;
+	skb_shinfo(skb)->gso_segs = 0;
+	skb_shinfo(skb)->gso_type = 0;
 	skb_shinfo(skb)->frag_list = NULL;
 out:
 	return skb;
@@ -528,8 +529,9 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 #endif
 	skb_copy_secmark(new, old);
 	atomic_set(&new->users, 1);
-	skb_shinfo(new)->tso_size = skb_shinfo(old)->tso_size;
-	skb_shinfo(new)->tso_segs = skb_shinfo(old)->tso_segs;
+	skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size;
+	skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs;
+	skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type;
 }
 
 /**
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 8538aac3d14..7624fd1d8f9 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -210,8 +210,7 @@ static inline int ip_finish_output(struct sk_buff *skb)
 		return dst_output(skb);
 	}
 #endif
-	if (skb->len > dst_mtu(skb->dst) &&
-	    !(skb_shinfo(skb)->ufo_size || skb_shinfo(skb)->tso_size))
+	if (skb->len > dst_mtu(skb->dst) && !skb_shinfo(skb)->gso_size)
 		return ip_fragment(skb, ip_finish_output2);
 	else
 		return ip_finish_output2(skb);
@@ -362,7 +361,7 @@ packet_routed:
 	}
 
 	ip_select_ident_more(iph, &rt->u.dst, sk,
-			     (skb_shinfo(skb)->tso_segs ?: 1) - 1);
+			     (skb_shinfo(skb)->gso_segs ?: 1) - 1);
 
 	/* Add an IP checksum. */
 	ip_send_check(iph);
@@ -744,7 +743,8 @@ static inline int ip_ufo_append_data(struct sock *sk,
 			       (length - transhdrlen));
 	if (!err) {
 		/* specify the length of each IP datagram fragment*/
-		skb_shinfo(skb)->ufo_size = (mtu - fragheaderlen);
+		skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
+		skb_shinfo(skb)->gso_type = SKB_GSO_UDPV4;
 		__skb_queue_tail(&sk->sk_write_queue, skb);
 
 		return 0;
@@ -1087,14 +1087,16 @@ ssize_t	ip_append_page(struct sock *sk, struct page *page,
 
 	inet->cork.length += size;
 	if ((sk->sk_protocol == IPPROTO_UDP) &&
-	    (rt->u.dst.dev->features & NETIF_F_UFO))
-		skb_shinfo(skb)->ufo_size = (mtu - fragheaderlen);
+	    (rt->u.dst.dev->features & NETIF_F_UFO)) {
+		skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
+		skb_shinfo(skb)->gso_type = SKB_GSO_UDPV4;
+	}
 
 
 	while (size > 0) {
 		int i;
 
-		if (skb_shinfo(skb)->ufo_size)
+		if (skb_shinfo(skb)->gso_size)
 			len = size;
 		else {
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 74998f25007..062dd1a0d8a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -571,7 +571,7 @@ new_segment:
 		skb->ip_summed = CHECKSUM_HW;
 		tp->write_seq += copy;
 		TCP_SKB_CB(skb)->end_seq += copy;
-		skb_shinfo(skb)->tso_segs = 0;
+		skb_shinfo(skb)->gso_segs = 0;
 
 		if (!copied)
 			TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_PSH;
@@ -818,7 +818,7 @@ new_segment:
 
 			tp->write_seq += copy;
 			TCP_SKB_CB(skb)->end_seq += copy;
-			skb_shinfo(skb)->tso_segs = 0;
+			skb_shinfo(skb)->gso_segs = 0;
 
 			from += copy;
 			copied += copy;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e08245bdda3..94fe5b1f9dc 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1073,7 +1073,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_
 				else
 					pkt_len = (end_seq -
 						   TCP_SKB_CB(skb)->seq);
-				if (tcp_fragment(sk, skb, pkt_len, skb_shinfo(skb)->tso_size))
+				if (tcp_fragment(sk, skb, pkt_len, skb_shinfo(skb)->gso_size))
 					break;
 				pcount = tcp_skb_pcount(skb);
 			}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 07bb5a2b375..bdd71db8bf9 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -515,15 +515,17 @@ static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned
 		/* Avoid the costly divide in the normal
 		 * non-TSO case.
 		 */
-		skb_shinfo(skb)->tso_segs = 1;
-		skb_shinfo(skb)->tso_size = 0;
+		skb_shinfo(skb)->gso_segs = 1;
+		skb_shinfo(skb)->gso_size = 0;
+		skb_shinfo(skb)->gso_type = 0;
 	} else {
 		unsigned int factor;
 
 		factor = skb->len + (mss_now - 1);
 		factor /= mss_now;
-		skb_shinfo(skb)->tso_segs = factor;
-		skb_shinfo(skb)->tso_size = mss_now;
+		skb_shinfo(skb)->gso_segs = factor;
+		skb_shinfo(skb)->gso_size = mss_now;
+		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
 	}
 }
 
@@ -914,7 +916,7 @@ static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int
 
 	if (!tso_segs ||
 	    (tso_segs > 1 &&
-	     skb_shinfo(skb)->tso_size != mss_now)) {
+	     tcp_skb_mss(skb) != mss_now)) {
 		tcp_set_skb_tso_segs(sk, skb, mss_now);
 		tso_segs = tcp_skb_pcount(skb);
 	}
@@ -1724,8 +1726,9 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	   tp->snd_una == (TCP_SKB_CB(skb)->end_seq - 1)) {
 		if (!pskb_trim(skb, 0)) {
 			TCP_SKB_CB(skb)->seq = TCP_SKB_CB(skb)->end_seq - 1;
-			skb_shinfo(skb)->tso_segs = 1;
-			skb_shinfo(skb)->tso_size = 0;
+			skb_shinfo(skb)->gso_segs = 1;
+			skb_shinfo(skb)->gso_size = 0;
+			skb_shinfo(skb)->gso_type = 0;
 			skb->ip_summed = CHECKSUM_NONE;
 			skb->csum = 0;
 		}
@@ -1930,8 +1933,9 @@ void tcp_send_fin(struct sock *sk)
 		skb->csum = 0;
 		TCP_SKB_CB(skb)->flags = (TCPCB_FLAG_ACK | TCPCB_FLAG_FIN);
 		TCP_SKB_CB(skb)->sacked = 0;
-		skb_shinfo(skb)->tso_segs = 1;
-		skb_shinfo(skb)->tso_size = 0;
+		skb_shinfo(skb)->gso_segs = 1;
+		skb_shinfo(skb)->gso_size = 0;
+		skb_shinfo(skb)->gso_type = 0;
 
 		/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
 		TCP_SKB_CB(skb)->seq = tp->write_seq;
@@ -1963,8 +1967,9 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
 	skb->csum = 0;
 	TCP_SKB_CB(skb)->flags = (TCPCB_FLAG_ACK | TCPCB_FLAG_RST);
 	TCP_SKB_CB(skb)->sacked = 0;
-	skb_shinfo(skb)->tso_segs = 1;
-	skb_shinfo(skb)->tso_size = 0;
+	skb_shinfo(skb)->gso_segs = 1;
+	skb_shinfo(skb)->gso_size = 0;
+	skb_shinfo(skb)->gso_type = 0;
 
 	/* Send it off. */
 	TCP_SKB_CB(skb)->seq = tcp_acceptable_seq(sk, tp);
@@ -2047,8 +2052,9 @@ struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	TCP_SKB_CB(skb)->seq = tcp_rsk(req)->snt_isn;
 	TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + 1;
 	TCP_SKB_CB(skb)->sacked = 0;
-	skb_shinfo(skb)->tso_segs = 1;
-	skb_shinfo(skb)->tso_size = 0;
+	skb_shinfo(skb)->gso_segs = 1;
+	skb_shinfo(skb)->gso_size = 0;
+	skb_shinfo(skb)->gso_type = 0;
 	th->seq = htonl(TCP_SKB_CB(skb)->seq);
 	th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1);
 	if (req->rcv_wnd == 0) { /* ignored for retransmitted syns */
@@ -2152,8 +2158,9 @@ int tcp_connect(struct sock *sk)
 	TCP_SKB_CB(buff)->flags = TCPCB_FLAG_SYN;
 	TCP_ECN_send_syn(sk, tp, buff);
 	TCP_SKB_CB(buff)->sacked = 0;
-	skb_shinfo(buff)->tso_segs = 1;
-	skb_shinfo(buff)->tso_size = 0;
+	skb_shinfo(buff)->gso_segs = 1;
+	skb_shinfo(buff)->gso_size = 0;
+	skb_shinfo(buff)->gso_type = 0;
 	buff->csum = 0;
 	TCP_SKB_CB(buff)->seq = tp->write_seq++;
 	TCP_SKB_CB(buff)->end_seq = tp->write_seq;
@@ -2257,8 +2264,9 @@ void tcp_send_ack(struct sock *sk)
 		buff->csum = 0;
 		TCP_SKB_CB(buff)->flags = TCPCB_FLAG_ACK;
 		TCP_SKB_CB(buff)->sacked = 0;
-		skb_shinfo(buff)->tso_segs = 1;
-		skb_shinfo(buff)->tso_size = 0;
+		skb_shinfo(buff)->gso_segs = 1;
+		skb_shinfo(buff)->gso_size = 0;
+		skb_shinfo(buff)->gso_type = 0;
 
 		/* Send it off, this clears delayed acks for us. */
 		TCP_SKB_CB(buff)->seq = TCP_SKB_CB(buff)->end_seq = tcp_acceptable_seq(sk, tp);
@@ -2293,8 +2301,9 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent)
 	skb->csum = 0;
 	TCP_SKB_CB(skb)->flags = TCPCB_FLAG_ACK;
 	TCP_SKB_CB(skb)->sacked = urgent;
-	skb_shinfo(skb)->tso_segs = 1;
-	skb_shinfo(skb)->tso_size = 0;
+	skb_shinfo(skb)->gso_segs = 1;
+	skb_shinfo(skb)->gso_size = 0;
+	skb_shinfo(skb)->gso_type = 0;
 
 	/* Use a previous sequence.  This should cause the other
 	 * end to send an ack.  Don't queue or clone SKB, just
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index d29620f4910..abb94de3376 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -148,7 +148,7 @@ static int ip6_output2(struct sk_buff *skb)
 
 int ip6_output(struct sk_buff *skb)
 {
-	if ((skb->len > dst_mtu(skb->dst) && !skb_shinfo(skb)->ufo_size) ||
+	if ((skb->len > dst_mtu(skb->dst) && !skb_shinfo(skb)->gso_size) ||
 				dst_allfrag(skb->dst))
 		return ip6_fragment(skb, ip6_output2);
 	else
@@ -833,8 +833,9 @@ static inline int ip6_ufo_append_data(struct sock *sk,
 		struct frag_hdr fhdr;
 
 		/* specify the length of each IP datagram fragment*/
-		skb_shinfo(skb)->ufo_size = (mtu - fragheaderlen) - 
-						sizeof(struct frag_hdr);
+		skb_shinfo(skb)->gso_size = mtu - fragheaderlen - 
+					    sizeof(struct frag_hdr);
+		skb_shinfo(skb)->gso_type = SKB_GSO_UDPV4;
 		ipv6_select_ident(skb, &fhdr);
 		skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
 		__skb_queue_tail(&sk->sk_write_queue, skb);
-- 
cgit v1.2.3-70-g09d2


From f6a78bfcb141f963187464bac838d46a81c3882a Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 22 Jun 2006 02:57:17 -0700
Subject: [NET]: Add generic segmentation offload

This patch adds the infrastructure for generic segmentation offload.
The idea is to tap into the potential savings of TSO without hardware
support by postponing the allocation of segmented skb's until just
before the entry point into the NIC driver.

The same structure can be used to support software IPv6 TSO, as well as
UFO and segmentation offload for other relevant protocols, e.g., DCCP.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |   8 ++-
 net/core/dev.c            | 127 ++++++++++++++++++++++++++++++++++++++++++++--
 net/sched/sch_generic.c   |  19 +++++--
 3 files changed, 143 insertions(+), 11 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index fa5671307b9..b4eae18390c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -405,6 +405,9 @@ struct net_device
 	struct list_head	qdisc_list;
 	unsigned long		tx_queue_len;	/* Max frames per queue allowed */
 
+	/* Partially transmitted GSO packet. */
+	struct sk_buff		*gso_skb;
+
 	/* ingress path synchronizer */
 	spinlock_t		ingress_lock;
 	struct Qdisc		*qdisc_ingress;
@@ -539,6 +542,7 @@ struct packet_type {
 					 struct net_device *,
 					 struct packet_type *,
 					 struct net_device *);
+	struct sk_buff		*(*gso_segment)(struct sk_buff *skb, int sg);
 	void			*af_packet_priv;
 	struct list_head	list;
 };
@@ -689,7 +693,8 @@ extern int		dev_change_name(struct net_device *, char *);
 extern int		dev_set_mtu(struct net_device *, int);
 extern int		dev_set_mac_address(struct net_device *,
 					    struct sockaddr *);
-extern void		dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev);
+extern int		dev_hard_start_xmit(struct sk_buff *skb,
+					    struct net_device *dev);
 
 extern void		dev_init(void);
 
@@ -963,6 +968,7 @@ extern int		netdev_max_backlog;
 extern int		weight_p;
 extern int		netdev_set_master(struct net_device *dev, struct net_device *master);
 extern int skb_checksum_help(struct sk_buff *skb, int inward);
+extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, int sg);
 #ifdef CONFIG_BUG
 extern void netdev_rx_csum_fault(struct net_device *dev);
 #else
diff --git a/net/core/dev.c b/net/core/dev.c
index 29e3888102b..d293e0f90a0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -116,6 +116,7 @@
 #include <asm/current.h>
 #include <linux/audit.h>
 #include <linux/dmaengine.h>
+#include <linux/err.h>
 
 /*
  *	The list of packet types we will receive (as opposed to discard)
@@ -1048,7 +1049,7 @@ static inline void net_timestamp(struct sk_buff *skb)
  *	taps currently in use.
  */
 
-void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
+static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct packet_type *ptype;
 
@@ -1186,6 +1187,40 @@ out:
 	return ret;
 }
 
+/**
+ *	skb_gso_segment - Perform segmentation on skb.
+ *	@skb: buffer to segment
+ *	@sg: whether scatter-gather is supported on the target.
+ *
+ *	This function segments the given skb and returns a list of segments.
+ */
+struct sk_buff *skb_gso_segment(struct sk_buff *skb, int sg)
+{
+	struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
+	struct packet_type *ptype;
+	int type = skb->protocol;
+
+	BUG_ON(skb_shinfo(skb)->frag_list);
+	BUG_ON(skb->ip_summed != CHECKSUM_HW);
+
+	skb->mac.raw = skb->data;
+	skb->mac_len = skb->nh.raw - skb->data;
+	__skb_pull(skb, skb->mac_len);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & 15], list) {
+		if (ptype->type == type && !ptype->dev && ptype->gso_segment) {
+			segs = ptype->gso_segment(skb, sg);
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return segs;
+}
+
+EXPORT_SYMBOL(skb_gso_segment);
+
 /* Take action when hardware reception checksum errors are detected. */
 #ifdef CONFIG_BUG
 void netdev_rx_csum_fault(struct net_device *dev)
@@ -1222,6 +1257,86 @@ static inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
 #define illegal_highdma(dev, skb)	(0)
 #endif
 
+struct dev_gso_cb {
+	void (*destructor)(struct sk_buff *skb);
+};
+
+#define DEV_GSO_CB(skb) ((struct dev_gso_cb *)(skb)->cb)
+
+static void dev_gso_skb_destructor(struct sk_buff *skb)
+{
+	struct dev_gso_cb *cb;
+
+	do {
+		struct sk_buff *nskb = skb->next;
+
+		skb->next = nskb->next;
+		nskb->next = NULL;
+		kfree_skb(nskb);
+	} while (skb->next);
+
+	cb = DEV_GSO_CB(skb);
+	if (cb->destructor)
+		cb->destructor(skb);
+}
+
+/**
+ *	dev_gso_segment - Perform emulated hardware segmentation on skb.
+ *	@skb: buffer to segment
+ *
+ *	This function segments the given skb and stores the list of segments
+ *	in skb->next.
+ */
+static int dev_gso_segment(struct sk_buff *skb)
+{
+	struct net_device *dev = skb->dev;
+	struct sk_buff *segs;
+
+	segs = skb_gso_segment(skb, dev->features & NETIF_F_SG &&
+				    !illegal_highdma(dev, skb));
+	if (unlikely(IS_ERR(segs)))
+		return PTR_ERR(segs);
+
+	skb->next = segs;
+	DEV_GSO_CB(skb)->destructor = skb->destructor;
+	skb->destructor = dev_gso_skb_destructor;
+
+	return 0;
+}
+
+int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	if (likely(!skb->next)) {
+		if (netdev_nit)
+			dev_queue_xmit_nit(skb, dev);
+
+		if (!netif_needs_gso(dev, skb))
+			return dev->hard_start_xmit(skb, dev);
+
+		if (unlikely(dev_gso_segment(skb)))
+			goto out_kfree_skb;
+	}
+
+	do {
+		struct sk_buff *nskb = skb->next;
+		int rc;
+
+		skb->next = nskb->next;
+		nskb->next = NULL;
+		rc = dev->hard_start_xmit(nskb, dev);
+		if (unlikely(rc)) {
+			skb->next = nskb;
+			return rc;
+		}
+	} while (skb->next);
+	
+	skb->destructor = DEV_GSO_CB(skb)->destructor;
+
+out_kfree_skb:
+	kfree_skb(skb);
+	return 0;
+}
+
 #define HARD_TX_LOCK(dev, cpu) {			\
 	if ((dev->features & NETIF_F_LLTX) == 0) {	\
 		netif_tx_lock(dev);			\
@@ -1266,6 +1381,10 @@ int dev_queue_xmit(struct sk_buff *skb)
 	struct Qdisc *q;
 	int rc = -ENOMEM;
 
+	/* GSO will handle the following emulations directly. */
+	if (netif_needs_gso(dev, skb))
+		goto gso;
+
 	if (skb_shinfo(skb)->frag_list &&
 	    !(dev->features & NETIF_F_FRAGLIST) &&
 	    __skb_linearize(skb))
@@ -1290,6 +1409,7 @@ int dev_queue_xmit(struct sk_buff *skb)
 	      	if (skb_checksum_help(skb, 0))
 	      		goto out_kfree_skb;
 
+gso:
 	spin_lock_prefetch(&dev->queue_lock);
 
 	/* Disable soft irqs for various locks below. Also 
@@ -1346,11 +1466,8 @@ int dev_queue_xmit(struct sk_buff *skb)
 			HARD_TX_LOCK(dev, cpu);
 
 			if (!netif_queue_stopped(dev)) {
-				if (netdev_nit)
-					dev_queue_xmit_nit(skb, dev);
-
 				rc = 0;
-				if (!dev->hard_start_xmit(skb, dev)) {
+				if (!dev_hard_start_xmit(skb, dev)) {
 					HARD_TX_UNLOCK(dev);
 					goto out;
 				}
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 7aad0121232..74d4a1dceee 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -96,8 +96,11 @@ static inline int qdisc_restart(struct net_device *dev)
 	struct sk_buff *skb;
 
 	/* Dequeue packet */
-	if ((skb = q->dequeue(q)) != NULL) {
+	if (((skb = dev->gso_skb)) || ((skb = q->dequeue(q)))) {
 		unsigned nolock = (dev->features & NETIF_F_LLTX);
+
+		dev->gso_skb = NULL;
+
 		/*
 		 * When the driver has LLTX set it does its own locking
 		 * in start_xmit. No need to add additional overhead by
@@ -134,10 +137,8 @@ static inline int qdisc_restart(struct net_device *dev)
 
 			if (!netif_queue_stopped(dev)) {
 				int ret;
-				if (netdev_nit)
-					dev_queue_xmit_nit(skb, dev);
 
-				ret = dev->hard_start_xmit(skb, dev);
+				ret = dev_hard_start_xmit(skb, dev);
 				if (ret == NETDEV_TX_OK) { 
 					if (!nolock) {
 						netif_tx_unlock(dev);
@@ -171,7 +172,10 @@ static inline int qdisc_restart(struct net_device *dev)
 		 */
 
 requeue:
-		q->ops->requeue(skb, q);
+		if (skb->next)
+			dev->gso_skb = skb;
+		else
+			q->ops->requeue(skb, q);
 		netif_schedule(dev);
 		return 1;
 	}
@@ -593,6 +597,11 @@ void dev_deactivate(struct net_device *dev)
 	/* Wait for outstanding qdisc_run calls. */
 	while (test_bit(__LINK_STATE_QDISC_RUNNING, &dev->state))
 		yield();
+
+	if (dev->gso_skb) {
+		kfree_skb(dev->gso_skb);
+		dev->gso_skb = NULL;
+	}
 }
 
 void dev_init_scheduler(struct net_device *dev)
-- 
cgit v1.2.3-70-g09d2


From 37c3185a02d4b85fbe134bf5204535405dd2c957 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 22 Jun 2006 03:07:29 -0700
Subject: [NET]: Added GSO toggle

This patch adds a generic segmentation offload toggle that can be turned
on/off for each net device.  For now it only supports in TCPv4.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ethtool.h   |  2 ++
 include/linux/netdevice.h |  1 +
 include/net/sock.h        |  4 ++++
 net/bridge/br_if.c        | 17 +++++++++++------
 net/core/ethtool.c        | 29 +++++++++++++++++++++++++++++
 5 files changed, 47 insertions(+), 6 deletions(-)

(limited to 'include/linux/netdevice.h')

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index cf2abeca92a..c6310aef5ab 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -411,6 +411,8 @@ struct ethtool_ops {
 #define ETHTOOL_GPERMADDR	0x00000020 /* Get permanent hardware address */
 #define ETHTOOL_GUFO		0x00000021 /* Get UFO enable (ethtool_value) */
 #define ETHTOOL_SUFO		0x00000022 /* Set UFO enable (ethtool_value) */
+#define ETHTOOL_GGSO		0x00000023 /* Get GSO enable (ethtool_value) */
+#define ETHTOOL_SGSO		0x00000024 /* Set GSO enable (ethtool_value) */
 
 /* compatibility with older code */
 #define SPARC_ETH_GSET		ETHTOOL_GSET
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b4eae18390c..bc747e5d713 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -308,6 +308,7 @@ struct net_device
 #define NETIF_F_HW_VLAN_RX	256	/* Receive VLAN hw acceleration */
 #define NETIF_F_HW_VLAN_FILTER	512	/* Receive filtering on VLAN */
 #define NETIF_F_VLAN_CHALLENGED	1024	/* Device cannot handle VLAN packets */
+#define NETIF_F_GSO		2048	/* Enable software GSO. */
 #define NETIF_F_LLTX		4096	/* LockLess TX */
 
 	/* Segmentation offload features */
diff --git a/include/net/sock.h b/include/net/sock.h
index d10dfecb6cb..a897f05de3b 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1030,9 +1030,13 @@ static inline void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 {
 	__sk_dst_set(sk, dst);
 	sk->sk_route_caps = dst->dev->features;
+	if (sk->sk_route_caps & NETIF_F_GSO)
+		sk->sk_route_caps |= NETIF_F_TSO;
 	if (sk->sk_route_caps & NETIF_F_TSO) {
 		if (sock_flag(sk, SOCK_NO_LARGESEND) || dst->header_len)
 			sk->sk_route_caps &= ~NETIF_F_TSO;
+		else 
+			sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
 	}
 }
 
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index fdec773f5b5..07956ecf545 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -376,15 +376,20 @@ void br_features_recompute(struct net_bridge *br)
 	features = br->feature_mask & ~NETIF_F_ALL_CSUM;
 
 	list_for_each_entry(p, &br->port_list, list) {
-		if (checksum & NETIF_F_NO_CSUM &&
-		    !(p->dev->features & NETIF_F_NO_CSUM))
+		unsigned long feature = p->dev->features;
+
+		if (checksum & NETIF_F_NO_CSUM && !(feature & NETIF_F_NO_CSUM))
 			checksum ^= NETIF_F_NO_CSUM | NETIF_F_HW_CSUM;
-		if (checksum & NETIF_F_HW_CSUM &&
-		    !(p->dev->features & NETIF_F_HW_CSUM))
+		if (checksum & NETIF_F_HW_CSUM && !(feature & NETIF_F_HW_CSUM))
 			checksum ^= NETIF_F_HW_CSUM | NETIF_F_IP_CSUM;
-		if (!(p->dev->features & NETIF_F_IP_CSUM))
+		if (!(feature & NETIF_F_IP_CSUM))
 			checksum = 0;
-		features &= p->dev->features;
+
+		if (feature & NETIF_F_GSO)
+			feature |= NETIF_F_TSO;
+		feature |= NETIF_F_GSO;
+
+		features &= feature;
 	}
 
 	br->dev->features = features | checksum | NETIF_F_LLTX;
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 33ce7ed6afc..27ce1683caf 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -614,6 +614,29 @@ static int ethtool_set_ufo(struct net_device *dev, char __user *useraddr)
 	return dev->ethtool_ops->set_ufo(dev, edata.data);
 }
 
+static int ethtool_get_gso(struct net_device *dev, char __user *useraddr)
+{
+	struct ethtool_value edata = { ETHTOOL_GGSO };
+
+	edata.data = dev->features & NETIF_F_GSO;
+	if (copy_to_user(useraddr, &edata, sizeof(edata)))
+		 return -EFAULT;
+	return 0;
+}
+
+static int ethtool_set_gso(struct net_device *dev, char __user *useraddr)
+{
+	struct ethtool_value edata;
+
+	if (copy_from_user(&edata, useraddr, sizeof(edata)))
+		return -EFAULT;
+	if (edata.data)
+		dev->features |= NETIF_F_GSO;
+	else
+		dev->features &= ~NETIF_F_GSO;
+	return 0;
+}
+
 static int ethtool_self_test(struct net_device *dev, char __user *useraddr)
 {
 	struct ethtool_test test;
@@ -905,6 +928,12 @@ int dev_ethtool(struct ifreq *ifr)
 	case ETHTOOL_SUFO:
 		rc = ethtool_set_ufo(dev, useraddr);
 		break;
+	case ETHTOOL_GGSO:
+		rc = ethtool_get_gso(dev, useraddr);
+		break;
+	case ETHTOOL_SGSO:
+		rc = ethtool_set_gso(dev, useraddr);
+		break;
 	default:
 		rc =  -EOPNOTSUPP;
 	}
-- 
cgit v1.2.3-70-g09d2