cxgb3: manage private iSCSI IP address

The accelerated iSCSI traffic could use a private IP address unknown to the OS:
- The IP address is required in both drivers to manage ARP requests and connection set up.
- Added an control call to retrieve the ip address.
- Reply to ARP requests dedicated to the private IP address.

Signed-off-by: Divy Le Ray <divy@chelsio.com>
Signed-off-by: Karen Xie <kxie@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 121 insertions, 21 deletions

diff --git a/drivers/net/cxgb3/adapter.h b/drivers/net/cxgb3/adapter.h
index c190a69c4d71..5b346f9eaa8b 100644
--- a/drivers/net/cxgb3/adapter.h
+++ b/drivers/net/cxgb3/adapter.h
@@ -63,6 +63,7 @@ struct port_info {
         struct link_config link_config;
         struct net_device_stats netstats;
         int activity;
+        __be32 iscsi_ipv4addr;
 };
 
 enum {                          /* adapter flags */
diff --git a/drivers/net/cxgb3/cxgb3_ctl_defs.h b/drivers/net/cxgb3/cxgb3_ctl_defs.h
index 1d8d46eb3c96..55099eb3c70e 100644
--- a/drivers/net/cxgb3/cxgb3_ctl_defs.h
+++ b/drivers/net/cxgb3/cxgb3_ctl_defs.h
@@ -57,6 +57,7 @@ enum {
         RDMA_GET_MIB            = 19,
 
         GET_RX_PAGE_INFO        = 50,
+        GET_ISCSI_IPV4ADDR      = 51,
 };
 
 /*
@@ -86,6 +87,12 @@ struct iff_mac {
         u16 vlan_tag;
 };
 
+/* Structure used to request a port's iSCSI IPv4 address */
+struct iscsi_ipv4addr {
+        struct net_device *dev; /* the net_device */
+        __be32 ipv4addr;        /* the return iSCSI IPv4 address */
+};
+
 struct pci_dev;
 
 /*
diff --git a/drivers/net/cxgb3/cxgb3_offload.c b/drivers/net/cxgb3/cxgb3_offload.c
index 265aa8a15afa..1ce69b742804 100644
--- a/drivers/net/cxgb3/cxgb3_offload.c
+++ b/drivers/net/cxgb3/cxgb3_offload.c
@@ -182,7 +182,9 @@ static struct net_device *get_iff_from_mac(struct adapter *adapter,
 static int cxgb_ulp_iscsi_ctl(struct adapter *adapter, unsigned int req,
                               void *data)
 {
+        int i;
         int ret = 0;
+        unsigned int val = 0;
         struct ulp_iscsi_info *uiip = data;
 
         switch (req) {
@@ -191,32 +193,55 @@ static int cxgb_ulp_iscsi_ctl(struct adapter *adapter, unsigned int req,
                 uiip->llimit = t3_read_reg(adapter, A_ULPRX_ISCSI_LLIMIT);
                 uiip->ulimit = t3_read_reg(adapter, A_ULPRX_ISCSI_ULIMIT);
                 uiip->tagmask = t3_read_reg(adapter, A_ULPRX_ISCSI_TAGMASK);
+
+                val = t3_read_reg(adapter, A_ULPRX_ISCSI_PSZ);
+                for (i = 0; i < 4; i++, val >>= 8)
+                        uiip->pgsz_factor[i] = val & 0xFF;
+
+                val = t3_read_reg(adapter, A_TP_PARA_REG7);
+                uiip->max_txsz =
+                uiip->max_rxsz = min((val >> S_PMMAXXFERLEN0)&M_PMMAXXFERLEN0,
+                                     (val >> S_PMMAXXFERLEN1)&M_PMMAXXFERLEN1);
                 /*
                  * On tx, the iscsi pdu has to be <= tx page size and has to
                  * fit into the Tx PM FIFO.
                  */
-                uiip->max_txsz = min(adapter->params.tp.tx_pg_size,
-                                     t3_read_reg(adapter, A_PM1_TX_CFG) >> 17);
-                /* on rx, the iscsi pdu has to be < rx page size and the
-                   whole pdu + cpl headers has to fit into one sge buffer */
-                uiip->max_rxsz = min_t(unsigned int,
-                                       adapter->params.tp.rx_pg_size,
-                                       (adapter->sge.qs[0].fl[1].buf_size -
-                                        sizeof(struct cpl_rx_data) * 2 -
-                                        sizeof(struct cpl_rx_data_ddp)));
+                val = min(adapter->params.tp.tx_pg_size,
+                          t3_read_reg(adapter, A_PM1_TX_CFG) >> 17);
+                uiip->max_txsz = min(val, uiip->max_txsz);
+
+                /* set MaxRxData to 16224 */
+                val = t3_read_reg(adapter, A_TP_PARA_REG2);
+                if ((val >> S_MAXRXDATA) != 0x3f60) {
+                        val &= (M_RXCOALESCESIZE << S_RXCOALESCESIZE);
+                        val |= V_MAXRXDATA(0x3f60);
+                        printk(KERN_INFO
+                                "%s, iscsi set MaxRxData to 16224 (0x%x).\n",
+                                adapter->name, val);
+                        t3_write_reg(adapter, A_TP_PARA_REG2, val);
+                }
+
+                /*
+                 * on rx, the iscsi pdu has to be < rx page size and the
+                 * the max rx data length programmed in TP
+                 */
+                val = min(adapter->params.tp.rx_pg_size,
+                          ((t3_read_reg(adapter, A_TP_PARA_REG2)) >>
+                                S_MAXRXDATA) & M_MAXRXDATA);
+                uiip->max_rxsz = min(val, uiip->max_rxsz);
                 break;
         case ULP_ISCSI_SET_PARAMS:
                 t3_write_reg(adapter, A_ULPRX_ISCSI_TAGMASK, uiip->tagmask);
-                /* set MaxRxData and MaxCoalesceSize to 16224 */
-                t3_write_reg(adapter, A_TP_PARA_REG2, 0x3f603f60);
                 /* program the ddp page sizes */
-                {
-                        int i;
-                        unsigned int val = 0;
-                        for (i = 0; i < 4; i++)
-                                val |= (uiip->pgsz_factor[i] & 0xF) << (8 * i);
-                        if (val)
-                                t3_write_reg(adapter, A_ULPRX_ISCSI_PSZ, val);
+                for (i = 0; i < 4; i++)
+                        val |= (uiip->pgsz_factor[i] & 0xF) << (8 * i);
+                if (val && (val != t3_read_reg(adapter, A_ULPRX_ISCSI_PSZ))) {
+                        printk(KERN_INFO
+                                "%s, setting iscsi pgsz 0x%x, %u,%u,%u,%u.\n",
+                                adapter->name, val, uiip->pgsz_factor[0],
+                                uiip->pgsz_factor[1], uiip->pgsz_factor[2],
+                                uiip->pgsz_factor[3]);
+                        t3_write_reg(adapter, A_ULPRX_ISCSI_PSZ, val);
                 }
                 break;
         default:
@@ -407,6 +432,12 @@ static int cxgb_offload_ctl(struct t3cdev *tdev, unsigned int req, void *data)
                 rx_page_info->page_size = tp->rx_pg_size;
                 rx_page_info->num = tp->rx_num_pgs;
                 break;
+        case GET_ISCSI_IPV4ADDR: {
+                struct iscsi_ipv4addr *p = data;
+                struct port_info *pi = netdev_priv(p->dev);
+                p->ipv4addr = pi->iscsi_ipv4addr;
+                break;
+        }
         default:
                 return -EOPNOTSUPP;
         }
diff --git a/drivers/net/cxgb3/sge.c b/drivers/net/cxgb3/sge.c
index 63eb97473c8b..6c641a889471 100644
--- a/drivers/net/cxgb3/sge.c
+++ b/drivers/net/cxgb3/sge.c
@@ -36,6 +36,7 @@
 #include <linux/ip.h>
 #include <linux/tcp.h>
 #include <linux/dma-mapping.h>
+#include <net/arp.h>
 #include "common.h"
 #include "regs.h"
 #include "sge_defs.h"
@@ -1863,6 +1864,54 @@ static void restart_tx(struct sge_qset *qs)
 }
 
 /**
+ *      cxgb3_arp_process - process an ARP request probing a private IP address
+ *      @adapter: the adapter
+ *      @skb: the skbuff containing the ARP request
+ *
+ *      Check if the ARP request is probing the private IP address
+ *      dedicated to iSCSI, generate an ARP reply if so.
+ */
+static void cxgb3_arp_process(struct adapter *adapter, struct sk_buff *skb)
+{
+        struct net_device *dev = skb->dev;
+        struct port_info *pi;
+        struct arphdr *arp;
+        unsigned char *arp_ptr;
+        unsigned char *sha;
+        __be32 sip, tip;
+
+        if (!dev)
+                return;
+
+        skb_reset_network_header(skb);
+        arp = arp_hdr(skb);
+
+        if (arp->ar_op != htons(ARPOP_REQUEST))
+                return;
+
+        arp_ptr = (unsigned char *)(arp + 1);
+        sha = arp_ptr;
+        arp_ptr += dev->addr_len;
+        memcpy(&sip, arp_ptr, sizeof(sip));
+        arp_ptr += sizeof(sip);
+        arp_ptr += dev->addr_len;
+        memcpy(&tip, arp_ptr, sizeof(tip));
+
+        pi = netdev_priv(dev);
+        if (tip != pi->iscsi_ipv4addr)
+                return;
+
+        arp_send(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha,
+                 dev->dev_addr, sha);
+
+}
+
+static inline int is_arp(struct sk_buff *skb)
+{
+        return skb->protocol == htons(ETH_P_ARP);
+}
+
+/**
  *      rx_eth - process an ingress ethernet packet
  *      @adap: the adapter
  *      @rq: the response queue that received the packet
@@ -1885,7 +1934,7 @@ static void rx_eth(struct adapter *adap, struct sge_rspq *rq,
         pi = netdev_priv(skb->dev);
         if (pi->rx_csum_offload && p->csum_valid && p->csum == htons(0xffff) &&
             !p->fragment) {
-                rspq_to_qset(rq)->port_stats[SGE_PSTAT_RX_CSUM_GOOD]++;
+                qs->port_stats[SGE_PSTAT_RX_CSUM_GOOD]++;
                 skb->ip_summed = CHECKSUM_UNNECESSARY;
         } else
                 skb->ip_summed = CHECKSUM_NONE;
@@ -1900,16 +1949,28 @@ static void rx_eth(struct adapter *adap, struct sge_rspq *rq,
                                                              grp,
                                                              ntohs(p->vlan),
                                                              p);
-                        else
+                        else {
+                                if (unlikely(pi->iscsi_ipv4addr &&
+                                    is_arp(skb))) {
+                                        unsigned short vtag = ntohs(p->vlan) &
+                                                                VLAN_VID_MASK;
+                                        skb->dev = vlan_group_get_device(grp,
+                                                                         vtag);
+                                        cxgb3_arp_process(adap, skb);
+                                }
                                 __vlan_hwaccel_rx(skb, grp, ntohs(p->vlan),
                                                   rq->polling);
+                        }
                 else
                         dev_kfree_skb_any(skb);
         } else if (rq->polling) {
                 if (lro)
                         lro_receive_skb(&qs->lro_mgr, skb, p);
-                else
+                else {
+                        if (unlikely(pi->iscsi_ipv4addr && is_arp(skb)))
+                                cxgb3_arp_process(adap, skb);
                         netif_receive_skb(skb);
+                }
         } else
                 netif_rx(skb);
 }