@@ -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,
@@ -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;
}
@@ -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);
Code includes barrier() 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. Create a new wrapper function with relaxed write operator. Use the new wrapper when a write is following a barrier(). Since code already has an explicit barrier call, changing writel() to writel_relaxed() and adding mmiowb() for ordering protection. Signed-off-by: Sinan Kaya <okaya@codeaurora.org> --- drivers/net/ethernet/amazon/ena/ena_com.c | 8 ++++++-- drivers/net/ethernet/amazon/ena/ena_eth_com.h | 8 ++++++-- drivers/net/ethernet/amazon/ena/ena_netdev.c | 5 +++-- 3 files changed, 15 insertions(+), 6 deletions(-)