i40e: optimise prefetch page refcount

refcount of rx_buffer page will be added here originally, so prefetchw
is needed, but after commit 1793668c ("i40e/i40evf: Update code to
better handle incrementing page count"), and refcount is not added
every time, so change prefetchw as prefetch.

Now it mainly services page_address(), but which accesses struct page
only when WANT_PAGE_VIRTUAL or HASHED_PAGE_VIRTUAL is defined otherwise
it returns address based on offset, so we prefetch it conditionally.

Jakub suggested to define prefetch_page_address in a common header.
Reported-by: kernel test robot <lkp@intel.com>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -1953,7 +1953,7 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring,
 	struct i40e_rx_buffer *rx_buffer;
 
 	rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean);
-	prefetchw(rx_buffer->page);
+	prefetch_page_address(rx_buffer->page);
 
 	/* we are reusing so sync this buffer for CPU use */
 	dma_sync_single_range_for_cpu(rx_ring->dev,

include/linux/prefetch.h

@@ -15,6 +15,7 @@
 #include <asm/processor.h>
 #include <asm/cache.h>
 
+struct page;
 /*
 	prefetch(x) attempts to pre-emptively get the memory pointed to
 	by address "x" into the CPU L1 cache. 
@@ -62,4 +63,11 @@ static inline void prefetch_range(void *addr, size_t len)
 #endif
 }
 
+static inline void prefetch_page_address(struct page *page)
+{
+#if defined(WANT_PAGE_VIRTUAL) || defined(HASHED_PAGE_VIRTUAL)
+	prefetch(page);
+#endif
+}
+
 #endif