i40e: optimise prefetch page refcount

refcount of rx_buffer page will be added here originally, so prefetchw
is needed, but after commit 1793668c3b8c ("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 <[e-mail]>
Suggested-by: Jakub Kicinski <[e-mail]>
Signed-off-by: Li RongQing <[e-mail]>
Reviewed-by: Jesse Brandeburg <[e-mail]>
Tested-by: Aaron Brown <[e-mail]>
Signed-off-by: Tony Nguyen <[e-mail]>

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

···
 	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

···
 #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. 
···
 
 	for (cp = addr; cp < end; cp += PREFETCH_STRIDE)
 		prefetch(cp);
+#endif
+}
+
+static inline void prefetch_page_address(struct page *page)
+{
+#if defined(WANT_PAGE_VIRTUAL) || defined(HASHED_PAGE_VIRTUAL)
+	prefetch(page);
 #endif
 }