[PATCH v5 3/5] bnx2x: Eliminate duplicate barriers on weakly-ordered archs

[Sinan Kaya]

Code includes wmb() followed by writel(). writel() already has a
barrier on some architectures like arm64.

This ends up CPU observing two barriers back to back before executing
the register write.

Since code already has an explicit barrier call, changing writel() to
writel_relaxed().

Signed-off-by: Sinan Kaya <okaya at codeaurora.org>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x.h         | 12 ++++++++----
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c     |  2 +-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h     |  4 ++--
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c |  2 +-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c    |  4 ++--
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c   |  2 +-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c    |  2 +-
 7 files changed, 16 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 352beff..d847e1b 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -166,6 +166,12 @@ do {						\
 #define REG_RD8(bp, offset)		readb(REG_ADDR(bp, offset))
 #define REG_RD16(bp, offset)		readw(REG_ADDR(bp, offset))
 
+#define REG_WR_RELAXED(bp, offset, val)	\
+	writel_relaxed((u32)val, REG_ADDR(bp, offset))
+
+#define REG_WR16_RELAXED(bp, offset, val) \
+	writew_relaxed((u16)val, REG_ADDR(bp, offset))
+
 #define REG_WR(bp, offset, val)		writel((u32)val, REG_ADDR(bp, offset))
 #define REG_WR8(bp, offset, val)	writeb((u8)val, REG_ADDR(bp, offset))
 #define REG_WR16(bp, offset, val)	writew((u16)val, REG_ADDR(bp, offset))
@@ -758,10 +764,8 @@ struct bnx2x_fastpath {
 #if (BNX2X_DB_SHIFT < BNX2X_DB_MIN_SHIFT)
 #error "Min DB doorbell stride is 8"
 #endif
-#define DOORBELL(bp, cid, val) \
-	do { \
-		writel((u32)(val), bp->doorbells + (bp->db_size * (cid))); \
-	} while (0)
+#define DOORBELL_RELAXED(bp, cid, val) \
+	writel_relaxed((u32)(val), (bp)->doorbells + ((bp)->db_size * (cid)))
 
 /* TX CSUM helpers */
 #define SKB_CS_OFF(skb)		(offsetof(struct tcphdr, check) - \
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index d7c98e8..172fd79 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -4155,7 +4155,7 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	txdata->tx_db.data.prod += nbd;
 	barrier();
 
-	DOORBELL(bp, txdata->cid, txdata->tx_db.raw);
+	DOORBELL_RELAXED(bp, txdata->cid, txdata->tx_db.raw);
 
 	mmiowb();
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index a5265e1..a8ce5c5 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -522,8 +522,8 @@ static inline void bnx2x_update_rx_prod(struct bnx2x *bp,
 	wmb();
 
 	for (i = 0; i < sizeof(rx_prods)/4; i++)
-		REG_WR(bp, fp->ustorm_rx_prods_offset + i*4,
-		       ((u32 *)&rx_prods)[i]);
+		REG_WR_RELAXED(bp, fp->ustorm_rx_prods_offset + i * 4,
+			       ((u32 *)&rx_prods)[i]);
 
 	mmiowb(); /* keep prod updates ordered */
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index 1e33abd..bda5e4f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -2592,7 +2592,7 @@ static int bnx2x_run_loopback(struct bnx2x *bp, int loopback_mode)
 
 	txdata->tx_db.data.prod += 2;
 	barrier();
-	DOORBELL(bp, txdata->cid, txdata->tx_db.raw);
+	DOORBELL_RELAXED(bp, txdata->cid, txdata->tx_db.raw);
 
 	mmiowb();
 	barrier();
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 74fc9af..146c40d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -3817,8 +3817,8 @@ static void bnx2x_sp_prod_update(struct bnx2x *bp)
 	 */
 	mb();
 
-	REG_WR16(bp, BAR_XSTRORM_INTMEM + XSTORM_SPQ_PROD_OFFSET(func),
-		 bp->spq_prod_idx);
+	REG_WR16_RELAXED(bp, BAR_XSTRORM_INTMEM + XSTORM_SPQ_PROD_OFFSET(func),
+			 bp->spq_prod_idx);
 	mmiowb();
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index ffa7959..40e55d8 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -105,7 +105,7 @@ static void bnx2x_vf_igu_ack_sb(struct bnx2x *bp, struct bnx2x_virtf *vf,
 
 	DP(NETIF_MSG_HW, "write 0x%08x to IGU(via GRC) addr 0x%x\n",
 	   ctl, igu_addr_ctl);
-	REG_WR(bp, igu_addr_ctl, ctl);
+	REG_WR_RELAXED(bp, igu_addr_ctl, ctl);
 	mmiowb();
 	barrier();
 }
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index 76a4668..3b2f1bd 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -170,7 +170,7 @@ static int bnx2x_send_msg2pf(struct bnx2x *bp, u8 *done, dma_addr_t msg_mapping)
 	wmb();
 
 	/* Trigger the PF FW */
-	writeb(1, &zone_data->trigger.vf_pf_channel.addr_valid);
+	writeb_relaxed(1, &zone_data->trigger.vf_pf_channel.addr_valid);
 
 	/* Wait for PF to complete */
 	while ((tout >= 0) && (!*done)) {
-- 
2.7.4