e1000: Use dma_wmb() instead of wmb() before doorbell writes

e1000 writes to doorbells to post transmit descriptors and fill the
receive ring. After writing descriptors to memory but before
writing to doorbells, use dma_wmb() rather than wmb(). wmb() is more
heavyweight than necessary for a device to see descriptor writes.

On x86, this avoids SFENCEs before doorbell writes in both the
Tx and Rx paths. On ARM, this converts DSB ST -> DMB OSHST.

Tested: 82576EB / x86; QEMU (qemu emulates an 8257x)

Signed-off-by: Venkatesh Srinivas <venkateshs@google.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 551de8c2fef2275b6f39a4820d5a109fb2849d04..f703fa58458ef55981dd1cb4d660f2625f65f26c 100644 (file)
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -3019,7 +3019,7 @@ static void e1000_tx_queue(struct e1000_adapter *adapter,
         * applicable for weak-ordered memory model archs,
         * such as IA-64).
         */
-       wmb();
+       dma_wmb();
 
        tx_ring->next_to_use = i;
 }
@@ -4540,7 +4540,7 @@ e1000_alloc_jumbo_rx_buffers(struct e1000_adapter *adapter,
                 * applicable for weak-ordered memory model archs,
                 * such as IA-64).
                 */
-               wmb();
+               dma_wmb();
                writel(i, adapter->hw.hw_addr + rx_ring->rdt);
        }
 }
@@ -4655,7 +4655,7 @@ static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter,
                 * applicable for weak-ordered memory model archs,
                 * such as IA-64).
                 */
-               wmb();
+               dma_wmb();
                writel(i, hw->hw_addr + rx_ring->rdt);
        }
 }