cxgb4/cxgb4vf: Add support for SGE doorbell queue timer

T6 introduced a Timer Mechanism in SGE called the
SGE Doorbell Queue Timer. With this we can now configure
TX Queues to get CIDX Updates when:

    Time(CIDX == PIDX) >= Timer

Previously we rely on TX Queue Status Page updates by hardware
for DMA completions. This will make Hardware/Firmware actually
deliver the CIDX Updates as Ingress Queue messages with
commensurate Interrupts.

So we now have a new RX Path component for processing CIDX Updates
and reclaiming TX Descriptors faster.

Original work by: Casey Leedom <[email protected]>

Signed-off-by: Vishal Kulkarni <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: vishalsdk

drivers/net/ethernet/chelsio/cxgb4/cxgb4.h

@@ -617,6 +617,7 @@ enum {                                 /* adapter flags */
 	FW_OFLD_CONN       = (1 << 9),
 	ROOT_NO_RELAXED_ORDERING = (1 << 10),
 	SHUTTING_DOWN	   = (1 << 11),
+	SGE_DBQ_TIMER      = (1 << 12),
 };
 
 enum {
@@ -756,6 +757,8 @@ struct sge_eth_txq {                /* state for an SGE Ethernet Tx queue */
 #ifdef CONFIG_CHELSIO_T4_DCB
 	u8 dcb_prio;		    /* DCB Priority bound to queue */
 #endif
+	u8 dbqt;                    /* SGE Doorbell Queue Timer in use */
+	unsigned int dbqtimerix;    /* SGE Doorbell Queue Timer Index */
 	unsigned long tso;          /* # of TSO requests */
 	unsigned long tx_cso;       /* # of Tx checksum offloads */
 	unsigned long vlan_ins;     /* # of Tx VLAN insertions */
@@ -816,6 +819,7 @@ struct sge {
 	u16 nqs_per_uld;	    /* # of Rx queues per ULD */
 	u16 timer_val[SGE_NTIMERS];
 	u8 counter_val[SGE_NCOUNTERS];
+	u16 dbqtimer_val[SGE_NDBQTIMERS];
 	u32 fl_pg_order;            /* large page allocation size */
 	u32 stat_len;               /* length of status page at ring end */
 	u32 pktshift;               /* padding between CPL & packet data */
@@ -1402,7 +1406,7 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 		     rspq_flush_handler_t flush_handler, int cong);
 int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 			 struct net_device *dev, struct netdev_queue *netdevq,
-			 unsigned int iqid);
+			 unsigned int iqid, u8 dbqt);
 int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq,
 			  struct net_device *dev, unsigned int iqid,
 			  unsigned int cmplqid);
@@ -1415,6 +1419,8 @@ irqreturn_t t4_sge_intr_msix(int irq, void *cookie);
 int t4_sge_init(struct adapter *adap);
 void t4_sge_start(struct adapter *adap);
 void t4_sge_stop(struct adapter *adap);
+int t4_sge_eth_txq_egress_update(struct adapter *adap, struct sge_eth_txq *q,
+				 int maxreclaim);
 void cxgb4_set_ethtool_ops(struct net_device *netdev);
 int cxgb4_write_rss(const struct port_info *pi, const u16 *queues);
 enum cpl_tx_tnl_lso_type cxgb_encap_offload_supported(struct sk_buff *skb);
@@ -1821,6 +1827,8 @@ int t4_ctrl_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf,
 int t4_ofld_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf,
 		    unsigned int vf, unsigned int eqid);
 int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox, int ctxt_type);
+int t4_read_sge_dbqtimers(struct adapter *adap, unsigned int ndbqtimers,
+			  u16 *dbqtimers);
 void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl);
 int t4_update_port_info(struct port_info *pi);
 int t4_get_link_params(struct port_info *pi, unsigned int *link_okp,

drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c

@@ -575,7 +575,7 @@ static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp,
 			struct sge_eth_txq *eq;
 
 			eq = container_of(txq, struct sge_eth_txq, q);
-			netif_tx_wake_queue(eq->txq);
+			t4_sge_eth_txq_egress_update(q->adap, eq, -1);
 		} else {
 			struct sge_uld_txq *oq;
 
@@ -933,10 +933,13 @@ static int setup_sge_queues(struct adapter *adap)
 			q->rspq.idx = j;
 			memset(&q->stats, 0, sizeof(q->stats));
 		}
-		for (j = 0; j < pi->nqsets; j++, t++) {
+
+		q = &s->ethrxq[pi->first_qset];
+		for (j = 0; j < pi->nqsets; j++, t++, q++) {
 			err = t4_sge_alloc_eth_txq(adap, t, dev,
 					netdev_get_tx_queue(dev, j),
-					s->fw_evtq.cntxt_id);
+					q->rspq.cntxt_id,
+					!!(adap->flags & SGE_DBQ_TIMER));
 			if (err)
 				goto freeout;
 		}
@@ -958,7 +961,7 @@ static int setup_sge_queues(struct adapter *adap)
 	if (!is_t4(adap->params.chip)) {
 		err = t4_sge_alloc_eth_txq(adap, &s->ptptxq, adap->port[0],
 					   netdev_get_tx_queue(adap->port[0], 0)
-					   , s->fw_evtq.cntxt_id);
+					   , s->fw_evtq.cntxt_id, false);
 		if (err)
 			goto freeout;
 	}
@@ -4325,6 +4328,14 @@ static int adap_init0(struct adapter *adap)
 	if (ret < 0)
 		goto bye;
 
+	/* Grab the SGE Doorbell Queue Timer values.  If successful, that
+	 * indicates that the Firmware and Hardware support this.
+	 */
+	ret = t4_read_sge_dbqtimers(adap, ARRAY_SIZE(adap->sge.dbqtimer_val),
+				    adap->sge.dbqtimer_val);
+	if (!ret)
+		adap->flags |= SGE_DBQ_TIMER;
+
 	if (is_bypass_device(adap->pdev->device))
 		adap->params.bypass = 1;