From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 28 May 2009 18:12:24 +1000
Subject: [net] cxgb3: add GRO suppport
Message-id: E1M9aiu-0007Ri-BE@gondolin.me.apana.org.au
O-Subject: [PATCH 1/3] cxgb3: Add GRO suppport
Bugzilla: 499347
RH-Acked-by: David Miller <davem@redhat.com>
RH-Acked-by: Thomas Graf <tgraf@redhat.com>
RH-Acked-by: Mike Christie <mchristi@redhat.com>

RHEL5 bugzilla 499347

cxgb3: Add GRO suppport

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 33dd9b5..468c7f1 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -2380,7 +2380,6 @@ config CHELSIO_T1
 config CHELSIO_T3
         tristate "Chelsio Communications T3 10Gb Ethernet support"
         depends on PCI
-	select INET_LRO
 	---help---
           This driver supports Chelsio T3-based gigabit and 10Gb Ethernet
           adapters.
diff --git a/drivers/net/cxgb3/adapter.h b/drivers/net/cxgb3/adapter.h
index 277c5f9..01e497a 100644
--- a/drivers/net/cxgb3/adapter.h
+++ b/drivers/net/cxgb3/adapter.h
@@ -42,7 +42,6 @@
 #include <linux/cache.h>
 #include <linux/mutex.h>
 #include <linux/bitops.h>
-#include <linux/inet_lro.h>
 #include "t3cdev.h"
 #include <asm/io.h>
 
@@ -182,27 +181,20 @@ enum {				/* per port SGE statistics */
 	SGE_PSTAT_TX_CSUM,	/* # of TX checksum offloads */
 	SGE_PSTAT_VLANEX,	/* # of VLAN tag extractions */
 	SGE_PSTAT_VLANINS,	/* # of VLAN tag insertions */
-	SGE_PSTAT_LRO_AGGR,	/* # of page chunks added to LRO sessions */
-	SGE_PSTAT_LRO_FLUSHED,	/* # of flushed LRO sessions */
-	SGE_PSTAT_LRO_NO_DESC,	/* # of overflown LRO sessions */
 
 	SGE_PSTAT_MAX		/* must be last */
 };
 
-#define T3_MAX_LRO_SES 8
-#define T3_MAX_LRO_MAX_PKTS 64
+struct napi_gro_fraginfo;
 
 struct sge_qset {		/* an SGE queue set */
 	struct adapter *adap;
+	struct napi_struct napi;
 	struct sge_rspq rspq;
 	struct sge_fl fl[SGE_RXQ_PER_SET];
 	struct sge_txq txq[SGE_TXQ_PER_SET];
-	struct net_lro_mgr lro_mgr;
-	struct net_lro_desc lro_desc[T3_MAX_LRO_SES];
-	struct skb_frag_struct *lro_frag_tbl;
-	int lro_nfrags;
+	int nomem;
 	int lro_enabled;
-	int lro_frag_len;
 	void *lro_va;
 	struct net_device *netdev;	/* associated net device */
 	unsigned long txq_stopped;	/* which Tx queues are stopped */
diff --git a/drivers/net/cxgb3/cxgb3_main.c b/drivers/net/cxgb3/cxgb3_main.c
index d93a563..6021ef6 100644
--- a/drivers/net/cxgb3/cxgb3_main.c
+++ b/drivers/net/cxgb3/cxgb3_main.c
@@ -610,8 +610,11 @@ static int setup_sge_qsets(struct adapter *adap)
 
 		for (j = pi->first_qset; j < pi->first_qset + pi->nqsets;
 		     ++j, ++qset_idx) {
-			if (!(pi->rx_offload & T3_LRO))
-				adap->params.sge.qset[qset_idx].lro = 0;
+			adap->sge.qs[qset_idx].napi.dev = dev;
+			adap->params.sge.qset[qset_idx].lro =
+				!!(pi->rx_offload & T3_LRO);
+			adap->sge.qs[qset_idx].lro_enabled =
+				!!(pi->rx_offload & T3_LRO);
 			err = t3_sge_alloc_qset(adap, qset_idx, 1,
 				(adap->flags & USING_MSIX) ? qset_idx + 1 :
 							     irq_idx,
@@ -1522,9 +1525,9 @@ static void get_stats(struct net_device *dev, struct ethtool_stats *stats,
 	*data++ = collect_sge_port_stats(adapter, pi, SGE_PSTAT_VLANINS);
 	*data++ = collect_sge_port_stats(adapter, pi, SGE_PSTAT_TX_CSUM);
 	*data++ = collect_sge_port_stats(adapter, pi, SGE_PSTAT_RX_CSUM_GOOD);
-	*data++ = collect_sge_port_stats(adapter, pi, SGE_PSTAT_LRO_AGGR);
-	*data++ = collect_sge_port_stats(adapter, pi, SGE_PSTAT_LRO_FLUSHED);
-	*data++ = collect_sge_port_stats(adapter, pi, SGE_PSTAT_LRO_NO_DESC);
+	*data++ = 0;
+	*data++ = 0;
+	*data++ = 0;
 	*data++ = s->rx_cong_drops;
 
 	*data++ = s->num_toggled;
@@ -3131,7 +3134,7 @@ static int __devinit init_one(struct pci_dev *pdev,
 		netdev->mem_end = mmio_start + mmio_len - 1;
 		netdev->features |= NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
 		netdev->features |= NETIF_F_LLTX;
-		netdev->features |= NETIF_F_LRO;
+		netdev->features |= NETIF_F_GRO;
 		if (pci_using_dac)
 			netdev->features |= NETIF_F_HIGHDMA;
 
diff --git a/drivers/net/cxgb3/sge.c b/drivers/net/cxgb3/sge.c
index 0fb6351..f7abd2a 100644
--- a/drivers/net/cxgb3/sge.c
+++ b/drivers/net/cxgb3/sge.c
@@ -609,8 +609,8 @@ static void t3_reset_qset(struct sge_qset *q)
 	q->txq_stopped = 0;
 	q->tx_reclaim_timer.function = NULL; /* for t3_stop_sge_timers() */
 	q->rx_reclaim_timer.function = NULL;
-	kfree(q->lro_frag_tbl);
-	q->lro_nfrags = q->lro_frag_len = 0;
+	q->nomem = 0;
+	napi_free_frags(&q->napi);
 }
 
 
@@ -1977,10 +1977,8 @@ static void rx_eth(struct adapter *adap, struct sge_rspq *rq,
 		qs->port_stats[SGE_PSTAT_VLANEX]++;
 		if (likely(grp))
 			if (lro)
-				lro_vlan_hwaccel_receive_skb(&qs->lro_mgr, skb,
-							     grp,
-							     ntohs(p->vlan),
-							     p);
+				vlan_gro_receive(&qs->napi, grp,
+						 ntohs(p->vlan), skb);
 			else {
 				if (unlikely(pi->iscsi_ipv4addr &&
 				    is_arp(skb))) {
@@ -1997,7 +1995,7 @@ static void rx_eth(struct adapter *adap, struct sge_rspq *rq,
 			dev_kfree_skb_any(skb);
 	} else if (rq->polling) {
 		if (lro)
-			lro_receive_skb(&qs->lro_mgr, skb, p);
+			napi_gro_receive(&qs->napi, skb);
 		else {
 			if (unlikely(pi->iscsi_ipv4addr && is_arp(skb)))
 				cxgb3_arp_process(adap, skb);
@@ -2013,59 +2011,6 @@ static inline int is_eth_tcp(u32 rss)
 }
 
 /**
- *	lro_frame_ok - check if an ingress packet is eligible for LRO
- *	@p: the CPL header of the packet
- *
- *	Returns true if a received packet is eligible for LRO.
- *	The following conditions must be true:
- *	- packet is TCP/IP Ethernet II (checked elsewhere)
- *	- not an IP fragment
- *	- no IP options
- *	- TCP/IP checksums are correct
- *	- the packet is for this host
- */
-static inline int lro_frame_ok(const struct cpl_rx_pkt *p)
-{
-	const struct ethhdr *eh = (struct ethhdr *)(p + 1);
-	const struct iphdr *ih = (struct iphdr *)(eh + 1);
-
-	return (*((u8 *)p + 1) & 0x90) == 0x10 && p->csum == htons(0xffff) &&
-		eh->h_proto == htons(ETH_P_IP) && ih->ihl == (sizeof(*ih) >> 2);
-}
-
-static int t3_get_lro_header(void **eh,  void **iph, void **tcph,
-			     u64 *hdr_flags, void *priv)
-{
-	const struct cpl_rx_pkt *cpl = priv;
-
-	if (!lro_frame_ok(cpl))
-		return -1;
-
-	*eh = (struct ethhdr *)(cpl + 1);
-	*iph = (struct iphdr *)((struct ethhdr *)*eh + 1);
-	*tcph = (struct tcphdr *)((struct iphdr *)*iph + 1);
-
-	*hdr_flags = LRO_IPV4 | LRO_TCP;
-	return 0;
-}
-
-static int t3_get_skb_header(struct sk_buff *skb,
-			      void **iph, void **tcph, u64 *hdr_flags,
-			      void *priv)
-{
-	void *eh;
-
-	return t3_get_lro_header(&eh, iph, tcph, hdr_flags, priv);
-}
-
-static int t3_get_frag_header(struct skb_frag_struct *frag, void **eh,
-			      void **iph, void **tcph, u64 *hdr_flags,
-			      void *priv)
-{
-	return t3_get_lro_header(eh, iph, tcph, hdr_flags, priv);
-}
-
-/**
  *	lro_add_page - add a page chunk to an LRO session
  *	@adap: the adapter
  *	@qs: the associated queue set
@@ -2080,34 +2025,54 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs,
 			 struct sge_fl *fl, int len, int complete)
 {
 	struct rx_sw_desc *sd = &fl->sdesc[fl->cidx];
+	struct sk_buff *skb = NULL;
 	struct cpl_rx_pkt *cpl;
-	struct skb_frag_struct *rx_frag = qs->lro_frag_tbl;
-	int nr_frags = qs->lro_nfrags, frag_len = qs->lro_frag_len;
+	struct skb_frag_struct *rx_frag;
+	int nr_frags;
 	int offset = 0;
 
-	if (!nr_frags) {
-		offset = 2 + sizeof(struct cpl_rx_pkt);
-		qs->lro_va = cpl = sd->pg_chunk.va + 2;
+	if (!qs->nomem) {
+		skb = napi_get_frags(&qs->napi);
+		qs->nomem = !skb;
 	}
 
 	fl->credits--;
 
-	len -= offset;
 	pci_unmap_single(adap->pdev, pci_unmap_addr(sd, dma_addr),
 			 fl->buf_size, PCI_DMA_FROMDEVICE);
 
+	if (!skb) {
+		put_page(sd->pg_chunk.page);
+		if (complete)
+			qs->nomem = 0;
+		return;
+	}
+
+	rx_frag = skb_shinfo(skb)->frags;
+	nr_frags = skb_shinfo(skb)->nr_frags;
+
+	if (!nr_frags) {
+		offset = 2 + sizeof(struct cpl_rx_pkt);
+		qs->lro_va = sd->pg_chunk.va + 2;
+	}
+	len -= offset;
+
+  	prefetch(qs->lro_va);
+
 	rx_frag += nr_frags;
 	rx_frag->page = sd->pg_chunk.page;
 	rx_frag->page_offset = sd->pg_chunk.offset + offset;
 	rx_frag->size = len;
-	frag_len += len;
-	qs->lro_nfrags++;
-	qs->lro_frag_len = frag_len;
+
+ 	skb->len += len;
+ 	skb->data_len += len;
+ 	skb->truesize += len;
+ 	skb_shinfo(skb)->nr_frags++;
 
 	if (!complete)
 		return;
 
-	qs->lro_nfrags = qs->lro_frag_len = 0;
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
 	cpl = qs->lro_va;
 
 	if (unlikely(cpl->vlan_valid)) {
@@ -2116,40 +2081,11 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs,
 		struct vlan_group *grp = pi->vlan_grp;
 
 		if (likely(grp != NULL)) {
-			lro_vlan_hwaccel_receive_frags(&qs->lro_mgr,
-						       qs->lro_frag_tbl,
-						       frag_len, frag_len,
-						       grp, ntohs(cpl->vlan),
-						       cpl, 0);
+			vlan_gro_frags(&qs->napi, grp, ntohs(cpl->vlan));
 			return;
 		}
 	}
-	lro_receive_frags(&qs->lro_mgr, qs->lro_frag_tbl,
-			  frag_len, frag_len, cpl, 0);
-}
-
-/**
- *	init_lro_mgr - initialize a LRO manager object
- *	@lro_mgr: the LRO manager object
- */
-static void init_lro_mgr(struct sge_qset *qs, struct net_lro_mgr *lro_mgr)
-{
-	struct adapter *adapter = qs->adap;
-	struct net_device *dev = qs->netdev;
-	struct port_info *pi = netdev_priv(dev);
-
-	lro_mgr->dev = adapter->port[pi->port_id];
-	lro_mgr->features = LRO_F_NAPI;
-	lro_mgr->frag_align_pad = NET_IP_ALIGN;
-	lro_mgr->ip_summed = CHECKSUM_UNNECESSARY;
-	lro_mgr->ip_summed_aggr = CHECKSUM_UNNECESSARY;
-	lro_mgr->max_desc = T3_MAX_LRO_SES;
-	lro_mgr->lro_arr = qs->lro_desc;
-	lro_mgr->get_frag_header = t3_get_frag_header;
-	lro_mgr->get_skb_header = t3_get_skb_header;
-	lro_mgr->max_aggr = T3_MAX_LRO_MAX_PKTS;
-	if (lro_mgr->max_aggr > MAX_SKB_FRAGS)
-		lro_mgr->max_aggr = MAX_SKB_FRAGS;
+	napi_gro_frags(&qs->napi);
 }
 
 /**
@@ -2392,10 +2328,7 @@ next_fl:
 	}
 
 	deliver_partial_bundle(&adap->tdev, q, offload_skbs, ngathered);
-	lro_flush_all(&qs->lro_mgr);
-	qs->port_stats[SGE_PSTAT_LRO_AGGR] = qs->lro_mgr.stats.aggregated;
-	qs->port_stats[SGE_PSTAT_LRO_FLUSHED] = qs->lro_mgr.stats.flushed;
-	qs->port_stats[SGE_PSTAT_LRO_NO_DESC] = qs->lro_mgr.stats.no_desc;
+	napi_gro_flush(&qs->napi);
 
 	if (sleeping)
 		check_ring_db(adap, qs, sleeping);
@@ -2992,7 +2925,6 @@ int t3_sge_alloc_qset(struct adapter *adapter, unsigned int id, int nports,
 {
 	int i, avail, ret = -ENOMEM;
 	struct sge_qset *q = &adapter->sge.qs[id];
-	struct net_lro_mgr *lro_mgr = &q->lro_mgr;
 
 	init_qset_cntxt(q, id);
 	setup_timer(&q->tx_reclaim_timer, sge_timer_tx, (unsigned long)q);
@@ -3072,10 +3004,6 @@ int t3_sge_alloc_qset(struct adapter *adapter, unsigned int id, int nports,
 	q->fl[0].order = FL0_PG_ORDER;
 	q->fl[1].order = FL1_PG_ORDER;
 
-	q->lro_frag_tbl = kcalloc(MAX_FRAME_SIZE / FL1_PG_CHUNK_SIZE + 1,
-				  sizeof(struct skb_frag_struct),
-				  GFP_KERNEL);
-	q->lro_nfrags = q->lro_frag_len = 0;
 	spin_lock_irq(&adapter->sge.reg_lock);
 
 	/* FL threshold comparison uses < */
@@ -3134,8 +3062,6 @@ int t3_sge_alloc_qset(struct adapter *adapter, unsigned int id, int nports,
 	if (netdev->atalk_ptr == NULL)
 		netdev->atalk_ptr = q;
 
-	init_lro_mgr(q, lro_mgr);
-
 	avail = refill_fl(adapter, &q->fl[0], q->fl[0].size,
 			  GFP_KERNEL | __GFP_COMP);
 	if (!avail) {
diff --git a/drivers/scsi/cxgb3i/cxgb3i_iscsi.c b/drivers/scsi/cxgb3i/cxgb3i_iscsi.c
index b39bdfc..ac0b8ab 100644
--- a/drivers/scsi/cxgb3i/cxgb3i_iscsi.c
+++ b/drivers/scsi/cxgb3i/cxgb3i_iscsi.c
@@ -14,6 +14,7 @@
 #include <linux/inet.h>
 #include <linux/err.h>
 #include <linux/crypto.h>
+#include <net/dst.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_eh.h>