diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index bf2de52..1b9d3130 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -631,8 +631,10 @@ static u32 ena_com_reg_bar_read32(struct ena_com_dev *ena_dev, u16 offset)
 	 */
 	wmb();
 
-	writel(mmio_read_reg, ena_dev->reg_bar + ENA_REGS_MMIO_REG_READ_OFF);
+	writel_relaxed(mmio_read_reg,
+		       ena_dev->reg_bar + ENA_REGS_MMIO_REG_READ_OFF);
 
+	mmiowb();
 	for (i = 0; i < timeout; i++) {
 		if (read_resp->req_id == mmio_read->seq_num)
 			break;
@@ -1826,7 +1828,9 @@ void ena_com_aenq_intr_handler(struct ena_com_dev *dev, void *data)
 
 	/* write the aenq doorbell after all AENQ descriptors were read */
 	mb();
-	writel((u32)aenq->head, dev->reg_bar + ENA_REGS_AENQ_HEAD_DB_OFF);
+	writel_relaxed((u32)aenq->head,
+		       dev->reg_bar + ENA_REGS_AENQ_HEAD_DB_OFF);
+	mmiowb();
 }
 
 int ena_com_dev_reset(struct ena_com_dev *ena_dev,
diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.h b/drivers/net/ethernet/amazon/ena/ena_eth_com.h
index 2f76572..6fdc753 100644
--- a/drivers/net/ethernet/amazon/ena/ena_eth_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.h
@@ -107,7 +107,8 @@ static inline int ena_com_sq_empty_space(struct ena_com_io_sq *io_sq)
 	return io_sq->q_depth - 1 - cnt;
 }
 
-static inline int ena_com_write_sq_doorbell(struct ena_com_io_sq *io_sq)
+static inline int ena_com_write_sq_doorbell(struct ena_com_io_sq *io_sq,
+					    bool relaxed)
 {
 	u16 tail;
 
@@ -116,7 +117,10 @@ static inline int ena_com_write_sq_doorbell(struct ena_com_io_sq *io_sq)
 	pr_debug("write submission queue doorbell for queue: %d tail: %d\n",
 		 io_sq->qid, tail);
 
-	writel(tail, io_sq->db_addr);
+	if (relaxed)
+		writel_relaxed(tail, io_sq->db_addr);
+	else
+		writel(tail, io_sq->db_addr);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 6975150..a822e70 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -556,7 +556,8 @@ static int ena_refill_rx_bufs(struct ena_ring *rx_ring, u32 num)
 		 * issue a doorbell
 		 */
 		wmb();
-		ena_com_write_sq_doorbell(rx_ring->ena_com_io_sq);
+		ena_com_write_sq_doorbell(rx_ring->ena_com_io_sq, true);
+		mmiowb();
 	}
 
 	rx_ring->next_to_use = next_to_use;
@@ -2151,7 +2152,7 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	if (netif_xmit_stopped(txq) || !skb->xmit_more) {
 		/* trigger the dma engine */
-		ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq);
+		ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq, false);
 		u64_stats_update_begin(&tx_ring->syncp);
 		tx_ring->tx_stats.doorbells++;
 		u64_stats_update_end(&tx_ring->syncp);
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..95871576 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -4153,9 +4153,10 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	wmb();
 
 	txdata->tx_db.data.prod += nbd;
-	barrier();
+	/* make sure descriptor update is observed by HW */
+	wmb();
 
-	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..da18aa2 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -2591,8 +2591,9 @@ static int bnx2x_run_loopback(struct bnx2x *bp, int loopback_mode)
 	wmb();
 
 	txdata->tx_db.data.prod += 2;
-	barrier();
-	DOORBELL(bp, txdata->cid, txdata->tx_db.raw);
+	/* make sure descriptor update is observed by the HW */
+	wmb();
+	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 fd97250..c766ae2 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_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index 76a4668..8e0a317 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -170,7 +170,9 @@ 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);
+
+	mmiowb();
 
 	/* Wait for PF to complete */
 	while ((tout >= 0) && (!*done)) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c7e5e6f..3ff5f65 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1922,7 +1922,7 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 		/* Sync BD data before updating doorbell */
 		wmb();
 
-		bnxt_db_write(bp, db, DB_KEY_TX | prod);
+		bnxt_db_write_relaxed(bp, db, DB_KEY_TX | prod);
 	}
 
 	cpr->cp_raw_cons = raw_cons;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 5e3d621..960162c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1402,6 +1402,15 @@ 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 with no ordering guarantee*/
+static inline void bnxt_db_write_relaxed(struct bnxt *bp, void __iomem *db,
+					 u32 val)
+{
+	writel_relaxed(val, db);
+	if (bp->flags & BNXT_FLAG_DOUBLE_DB)
+		writel_relaxed(val, db);
+}
+
 /* For TX and RX ring doorbells */
 static inline void bnxt_db_write(struct bnxt *bp, void __iomem *db, u32 val)
 {
diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index 9e5264d..b48f761 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -1858,8 +1858,9 @@ static void ql_update_small_bufq_prod_index(struct ql3_adapter *qdev)
 			qdev->small_buf_release_cnt -= 8;
 		}
 		wmb();
-		writel(qdev->small_buf_q_producer_index,
-			&port_regs->CommonRegs.rxSmallQProducerIndex);
+		writel_relaxed(qdev->small_buf_q_producer_index,
+			       &port_regs->CommonRegs.rxSmallQProducerIndex);
+		mmiowb();
 	}
 }
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index 46b0372..97c146e7 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -478,7 +478,7 @@ irqreturn_t qlcnic_83xx_clear_legacy_intr(struct qlcnic_adapter *adapter)
 	wmb();
 
 	/* clear the interrupt trigger control register */
-	writel(0, adapter->isr_int_vec);
+	writel_relaxed(0, adapter->isr_int_vec);
 	intr_val = readl(adapter->isr_int_vec);
 	do {
 		intr_val = readl(adapter->tgt_status_reg);
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h
index 84ac50f..3e71b65 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge.h
+++ b/drivers/net/ethernet/qlogic/qlge/qlge.h
@@ -2185,6 +2185,22 @@ static inline void ql_write_db_reg(u32 val, void __iomem *addr)
 }
 
 /*
+ * Doorbell Registers:
+ * Doorbell registers are virtual registers in the PCI memory space.
+ * The space is allocated by the chip during PCI initialization.  The
+ * device driver finds the doorbell address in BAR 3 in PCI config space.
+ * The registers are used to control outbound and inbound queues. For
+ * example, the producer index for an outbound queue.  Each queue uses
+ * 1 4k chunk of memory.  The lower half of the space is for outbound
+ * queues. The upper half is for inbound queues.
+ * Caller has to guarantee ordering.
+ */
+static inline void ql_write_db_reg_relaxed(u32 val, void __iomem *addr)
+{
+	writel_relaxed(val, addr);
+}
+
+/*
  * Shadow Registers:
  * Outbound queues have a consumer index that is maintained by the chip.
  * Inbound queues have a producer index that is maintained by the chip.
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 50038d9..8293c202 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -2700,7 +2700,8 @@ static netdev_tx_t qlge_send(struct sk_buff *skb, struct net_device *ndev)
 		tx_ring->prod_idx = 0;
 	wmb();
 
-	ql_write_db_reg(tx_ring->prod_idx, tx_ring->prod_idx_db_reg);
+	ql_write_db_reg_relaxed(tx_ring->prod_idx, tx_ring->prod_idx_db_reg);
+	mmiowb();
 	netif_printk(qdev, tx_queued, KERN_DEBUG, qdev->ndev,
 		     "tx queued, slot %d, len %d\n",
 		     tx_ring->prod_idx, skb->len);