bnxt_en: Optimize doorbell write operations for newer chips.

Older chips require the doorbells to be written twice, but newer chips
do not.  Add a new common function bnxt_db_write() to write all
doorbells appropriately depending on the chip.  Eliminating the extra
doorbell on newer chips has a significant performance improvement
on pktgen.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -463,8 +463,7 @@ normal_tx:
 	prod = NEXT_TX(prod);
 	txr->tx_prod = prod;
 
-	writel(DB_KEY_TX | prod, txr->tx_doorbell);
-	writel(DB_KEY_TX | prod, txr->tx_doorbell);
+	bnxt_db_write(bp, txr->tx_doorbell, DB_KEY_TX | prod);
 
 tx_done:
 
@@ -1779,8 +1778,7 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 		/* Sync BD data before updating doorbell */
 		wmb();
 
-		writel(DB_KEY_TX | prod, db);
-		writel(DB_KEY_TX | prod, db);
+		bnxt_db_write(bp, db, DB_KEY_TX | prod);
 	}
 
 	cpr->cp_raw_cons = raw_cons;
@@ -1796,14 +1794,10 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 	if (event & BNXT_RX_EVENT) {
 		struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
 
-		writel(DB_KEY_RX | rxr->rx_prod, rxr->rx_doorbell);
-		writel(DB_KEY_RX | rxr->rx_prod, rxr->rx_doorbell);
-		if (event & BNXT_AGG_EVENT) {
-			writel(DB_KEY_RX | rxr->rx_agg_prod,
-			       rxr->rx_agg_doorbell);
-			writel(DB_KEY_RX | rxr->rx_agg_prod,
-			       rxr->rx_agg_doorbell);
-		}
+		bnxt_db_write(bp, rxr->rx_doorbell, DB_KEY_RX | rxr->rx_prod);
+		if (event & BNXT_AGG_EVENT)
+			bnxt_db_write(bp, rxr->rx_agg_doorbell,
+				      DB_KEY_RX | rxr->rx_agg_prod);
 	}
 	return rx_pkts;
 }
@@ -1863,13 +1857,11 @@ static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget)
 
 	cpr->cp_raw_cons = raw_cons;
 	BNXT_CP_DB(cpr->cp_doorbell, cpr->cp_raw_cons);
-	writel(DB_KEY_RX | rxr->rx_prod, rxr->rx_doorbell);
-	writel(DB_KEY_RX | rxr->rx_prod, rxr->rx_doorbell);
+	bnxt_db_write(bp, rxr->rx_doorbell, DB_KEY_RX | rxr->rx_prod);
 
-	if (event & BNXT_AGG_EVENT) {
-		writel(DB_KEY_RX | rxr->rx_agg_prod, rxr->rx_agg_doorbell);
-		writel(DB_KEY_RX | rxr->rx_agg_prod, rxr->rx_agg_doorbell);
-	}
+	if (event & BNXT_AGG_EVENT)
+		bnxt_db_write(bp, rxr->rx_agg_doorbell,
+			      DB_KEY_RX | rxr->rx_agg_prod);
 
 	if (!bnxt_has_work(bp, cpr) && rx_pkts < budget) {
 		napi_complete_done(napi, rx_pkts);
@@ -7714,6 +7706,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	bp->gro_func = bnxt_gro_func_5730x;
 	if (BNXT_CHIP_P4_PLUS(bp))
 		bp->gro_func = bnxt_gro_func_5731x;
+	else
+		bp->flags |= BNXT_FLAG_DOUBLE_DB;
 
 	rc = bnxt_hwrm_func_drv_rgtr(bp);
 	if (rc)

drivers/net/ethernet/broadcom/bnxt/bnxt.h

@@ -1022,6 +1022,7 @@ struct bnxt {
 	#define BNXT_FLAG_FW_LLDP_AGENT	0x80000
 	#define BNXT_FLAG_MULTI_HOST	0x100000
 	#define BNXT_FLAG_SHORT_CMD	0x200000
+	#define BNXT_FLAG_DOUBLE_DB	0x400000
 	#define BNXT_FLAG_CHIP_NITRO_A0	0x1000000
 
 	#define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA |		\
@@ -1254,6 +1255,14 @@ static inline u32 bnxt_tx_avail(struct bnxt *bp, struct bnxt_tx_ring_info *txr)
 		((txr->tx_prod - txr->tx_cons) & bp->tx_ring_mask);
 }
 
+/* For TX and RX ring doorbells */
+static inline void bnxt_db_write(struct bnxt *bp, void __iomem *db, u32 val)
+{
+	writel(val, db);
+	if (bp->flags & BNXT_FLAG_DOUBLE_DB)
+		writel(val, db);
+}
+
 extern const u16 bnxt_lhint_arr[];
 
 int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,

drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c

@@ -2376,8 +2376,7 @@ static int bnxt_run_loopback(struct bnxt *bp)
 	/* Sync BD data before updating doorbell */
 	wmb();
 
-	writel(DB_KEY_TX | txr->tx_prod, txr->tx_doorbell);
-	writel(DB_KEY_TX | txr->tx_prod, txr->tx_doorbell);
+	bnxt_db_write(bp, txr->tx_doorbell, DB_KEY_TX | txr->tx_prod);
 	rc = bnxt_poll_loopback(bp, pkt_size);
 
 	dma_unmap_single(&bp->pdev->dev, map, pkt_size, PCI_DMA_TODEVICE);

drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c

@@ -63,7 +63,7 @@ void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts)
 		tx_buf = &txr->tx_buf_ring[last_tx_cons];
 		rx_prod = tx_buf->rx_prod;
 	}
-	writel(DB_KEY_RX | rx_prod, rxr->rx_doorbell);
+	bnxt_db_write(bp, rxr->rx_doorbell, DB_KEY_RX | rx_prod);
 }
 
 /* returns the following: