e1000e: reduce writes of RX producer ptr

Reduce number of writes to RX producer pointer.   When alloc'ing RX
buffers, only write the RX producer pointer once every
E1000_RX_BUFFER_WRITE (16) buffers created.
Signed-off-by: Tom Herbert <therbert@google.com>
Acked-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/e1000e/netdev.c

@@ -548,17 +548,7 @@ static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter,
 		rx_desc = E1000_RX_DESC(*rx_ring, i);
 		rx_desc->buffer_addr = cpu_to_le64(buffer_info->dma);
 
-		i++;
-		if (i == rx_ring->count)
-			i = 0;
-		buffer_info = &rx_ring->buffer_info[i];
-	}
-
-	if (rx_ring->next_to_use != i) {
-		rx_ring->next_to_use = i;
-		if (i-- == 0)
-			i = (rx_ring->count - 1);
-
+		if (unlikely(!(i & (E1000_RX_BUFFER_WRITE - 1)))) {
 			/*
 			 * Force memory writes to complete before letting h/w
 			 * know there are new descriptors to fetch.  (Only
@@ -568,6 +558,13 @@ static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter,
 			wmb();
 			writel(i, adapter->hw.hw_addr + rx_ring->tail);
 		}
+		i++;
+		if (i == rx_ring->count)
+			i = 0;
+		buffer_info = &rx_ring->buffer_info[i];
+	}
+
+	rx_ring->next_to_use = i;
 }
 
 /**
@@ -649,19 +646,7 @@ static void e1000_alloc_rx_buffers_ps(struct e1000_adapter *adapter,
 
 		rx_desc->read.buffer_addr[0] = cpu_to_le64(buffer_info->dma);
 
-		i++;
-		if (i == rx_ring->count)
-			i = 0;
-		buffer_info = &rx_ring->buffer_info[i];
-	}
-
-no_buffers:
-	if (rx_ring->next_to_use != i) {
-		rx_ring->next_to_use = i;
-
-		if (!(i--))
-			i = (rx_ring->count - 1);
-
+		if (unlikely(!(i & (E1000_RX_BUFFER_WRITE - 1)))) {
 			/*
 			 * Force memory writes to complete before letting h/w
 			 * know there are new descriptors to fetch.  (Only
@@ -669,13 +654,17 @@ static void e1000_alloc_rx_buffers_ps(struct e1000_adapter *adapter,
 			 * such as IA-64).
 			 */
 			wmb();
-		/*
-		 * Hardware increments by 16 bytes, but packet split
-		 * descriptors are 32 bytes...so we increment tail
-		 * twice as much.
-		 */
 			writel(i<<1, adapter->hw.hw_addr + rx_ring->tail);
 		}
+
+		i++;
+		if (i == rx_ring->count)
+			i = 0;
+		buffer_info = &rx_ring->buffer_info[i];
+	}
+
+no_buffers:
+	rx_ring->next_to_use = i;
 }
 
 /**