i40e/i40evf: Pull code for grabbing and syncing rx_buffer from fetch_buffer

This patch pulls the code responsible for fetching the Rx buffer and
synchronizing DMA into a function, specifically called i40e_get_rx_buffer.

The general idea is to allow for better code reuse by pulling this out of
i40e_fetch_rx_buffer.  We dropped a couple of prefetches since the time
between the prefetch being called and the data being accessed was too small
to be useful.

Change-ID: I4885fce4b2637dbedc8e16431169d23d3d7e79b9
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 012e55354043d502822a321f0a8c971d2c832d23..f2256d8c5e35e1d11d1d8ed07575b48d23102d81 100644 (file)
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1753,10 +1753,36 @@ add_tail_frag:
        return i40e_can_reuse_rx_page(rx_buffer, page, truesize);
 }
 
+/**
+ * i40e_get_rx_buffer - Fetch Rx buffer and synchronize data for use
+ * @rx_ring: rx descriptor ring to transact packets on
+ * @size: size of buffer to add to skb
+ *
+ * This function will pull an Rx buffer from the ring and synchronize it
+ * for use by the CPU.
+ */
+static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring,
+                                                const unsigned int size)
+{
+       struct i40e_rx_buffer *rx_buffer;
+
+       rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
+       prefetchw(rx_buffer->page);
+
+       /* we are reusing so sync this buffer for CPU use */
+       dma_sync_single_range_for_cpu(rx_ring->dev,
+                                     rx_buffer->dma,
+                                     rx_buffer->page_offset,
+                                     size,
+                                     DMA_FROM_DEVICE);
+
+       return rx_buffer;
+}
+
 /**
  * i40e_fetch_rx_buffer - Allocate skb and populate it
  * @rx_ring: rx descriptor ring to transact packets on
- * @rx_desc: descriptor containing info written by hardware
+ * @rx_buffer: rx buffer to pull data from
  * @size: size of buffer to add to skb
  *
  * This function allocates an skb on the fly, and populates it with the page
@@ -1766,19 +1792,13 @@ add_tail_frag:
  */
 static inline
 struct sk_buff *i40e_fetch_rx_buffer(struct i40e_ring *rx_ring,
-                                    union i40e_rx_desc *rx_desc,
+                                    struct i40e_rx_buffer *rx_buffer,
                                     struct sk_buff *skb,
                                     unsigned int size)
 {
-       struct i40e_rx_buffer *rx_buffer;
-       struct page *page;
-
-       rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
-       page = rx_buffer->page;
-       prefetchw(page);
-
        if (likely(!skb)) {
-               void *page_addr = page_address(page) + rx_buffer->page_offset;
+               void *page_addr = page_address(rx_buffer->page) +
+                                 rx_buffer->page_offset;
 
                /* prefetch first cache line of first page */
                prefetch(page_addr);
@@ -1794,21 +1814,8 @@ struct sk_buff *i40e_fetch_rx_buffer(struct i40e_ring *rx_ring,
                        rx_ring->rx_stats.alloc_buff_failed++;
                        return NULL;
                }
-
-               /* we will be copying header into skb->data in
-                * pskb_may_pull so it is in our interest to prefetch
-                * it now to avoid a possible cache miss
-                */
-               prefetchw(skb->data);
        }
 
-       /* we are reusing so sync this buffer for CPU use */
-       dma_sync_single_range_for_cpu(rx_ring->dev,
-                                     rx_buffer->dma,
-                                     rx_buffer->page_offset,
-                                     size,
-                                     DMA_FROM_DEVICE);
-
        /* pull page into skb */
        if (i40e_add_rx_frag(rx_ring, rx_buffer, size, skb)) {
                /* hand second half of page back to the ring */
@@ -1886,6 +1893,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
        bool failure = false;
 
        while (likely(total_rx_packets < budget)) {
+               struct i40e_rx_buffer *rx_buffer;
                union i40e_rx_desc *rx_desc;
                unsigned int size;
                u16 vlan_tag;
@@ -1918,7 +1926,9 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
                 */
                dma_rmb();
 
-               skb = i40e_fetch_rx_buffer(rx_ring, rx_desc, skb, size);
+               rx_buffer = i40e_get_rx_buffer(rx_ring, size);
+
+               skb = i40e_fetch_rx_buffer(rx_ring, rx_buffer, skb, size);
                if (!skb)
                        break;
 

diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index e41eb46b02feb9fa44c152d188f811dd3acbf0f3..2320ec4d95ee39bcc944d4a5518b034e00245bc5 100644 (file)
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1112,10 +1112,36 @@ add_tail_frag:
        return i40e_can_reuse_rx_page(rx_buffer, page, truesize);
 }
 
+/**
+ * i40e_get_rx_buffer - Fetch Rx buffer and synchronize data for use
+ * @rx_ring: rx descriptor ring to transact packets on
+ * @size: size of buffer to add to skb
+ *
+ * This function will pull an Rx buffer from the ring and synchronize it
+ * for use by the CPU.
+ */
+static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring,
+                                                const unsigned int size)
+{
+       struct i40e_rx_buffer *rx_buffer;
+
+       rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
+       prefetchw(rx_buffer->page);
+
+       /* we are reusing so sync this buffer for CPU use */
+       dma_sync_single_range_for_cpu(rx_ring->dev,
+                                     rx_buffer->dma,
+                                     rx_buffer->page_offset,
+                                     size,
+                                     DMA_FROM_DEVICE);
+
+       return rx_buffer;
+}
+
 /**
  * i40evf_fetch_rx_buffer - Allocate skb and populate it
  * @rx_ring: rx descriptor ring to transact packets on
- * @rx_desc: descriptor containing info written by hardware
+ * @rx_buffer: rx buffer to pull data from
  * @size: size of buffer to add to skb
  *
  * This function allocates an skb on the fly, and populates it with the page
@@ -1125,19 +1151,13 @@ add_tail_frag:
  */
 static inline
 struct sk_buff *i40evf_fetch_rx_buffer(struct i40e_ring *rx_ring,
-                                      union i40e_rx_desc *rx_desc,
+                                      struct i40e_rx_buffer *rx_buffer,
                                       struct sk_buff *skb,
                                       unsigned int size)
 {
-       struct i40e_rx_buffer *rx_buffer;
-       struct page *page;
-
-       rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
-       page = rx_buffer->page;
-       prefetchw(page);
-
        if (likely(!skb)) {
-               void *page_addr = page_address(page) + rx_buffer->page_offset;
+               void *page_addr = page_address(rx_buffer->page) +
+                                 rx_buffer->page_offset;
 
                /* prefetch first cache line of first page */
                prefetch(page_addr);
@@ -1153,21 +1173,8 @@ struct sk_buff *i40evf_fetch_rx_buffer(struct i40e_ring *rx_ring,
                        rx_ring->rx_stats.alloc_buff_failed++;
                        return NULL;
                }
-
-               /* we will be copying header into skb->data in
-                * pskb_may_pull so it is in our interest to prefetch
-                * it now to avoid a possible cache miss
-                */
-               prefetchw(skb->data);
        }
 
-       /* we are reusing so sync this buffer for CPU use */
-       dma_sync_single_range_for_cpu(rx_ring->dev,
-                                     rx_buffer->dma,
-                                     rx_buffer->page_offset,
-                                     size,
-                                     DMA_FROM_DEVICE);
-
        /* pull page into skb */
        if (i40e_add_rx_frag(rx_ring, rx_buffer, size, skb)) {
                /* hand second half of page back to the ring */
@@ -1240,6 +1247,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
        bool failure = false;
 
        while (likely(total_rx_packets < budget)) {
+               struct i40e_rx_buffer *rx_buffer;
                union i40e_rx_desc *rx_desc;
                unsigned int size;
                u16 vlan_tag;
@@ -1272,7 +1280,9 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
                 */
                dma_rmb();
 
-               skb = i40evf_fetch_rx_buffer(rx_ring, rx_desc, skb, size);
+               rx_buffer = i40e_get_rx_buffer(rx_ring, size);
+
+               skb = i40evf_fetch_rx_buffer(rx_ring, rx_buffer, skb, size);
                if (!skb)
                        break;