sfc: Reduce RX scatter buffer size, and reduce alignment if appropriate

efx_start_datapath() asserts that we can fit 2 RX scatter buffers plus
a software structure, each appropriately aligned, into a single page.
Where L1_CACHE_BYTES == 256 and PAGE_SIZE == 4096, which is the case
on s390, this assertion fails.

The current scatter buffer size is also not a multiple of 64 or 128,
which are more common cache line sizes.  If we can make both the start
and end of a scatter buffer cache-aligned, this will reduce the need
for read-modify-write operations on inter- processor links.

Fix the alignment by reducing EFX_RX_USR_BUF_SIZE to 2048 - 256 ==
1792.  (We could use 2048 - L1_CACHE_BYTES, but EFX_RX_USR_BUF_SIZE
also affects user-level networking where a larger amount of
housekeeping data may be needed.  Although this version of the driver
does not support user-level networking, I prefer to keep scattering
behaviour consistent with the out-of-tree version.)

This still doesn't fix the s390 build because like most architectures
it has NET_IP_ALIGN == 2.  When NET_IP_ALIGN != 0 we cannot achieve
cache line alignment at either the start or end of a scatter buffer,
so there is actually no point in padding the buffers to a multiple of
the cache line size.  All we need is 4-byte alignment of the network
header, so do that.

Adjust the assertions accordingly.
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Reported-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/sfc/efx.c

@@ -643,9 +643,11 @@ static void efx_start_datapath(struct efx_nic *efx)
 		efx->rx_scatter = false;
 		efx->rx_buffer_order = 0;
 	} else if (efx->type->can_rx_scatter) {
+		BUILD_BUG_ON(EFX_RX_USR_BUF_SIZE % L1_CACHE_BYTES);
 		BUILD_BUG_ON(sizeof(struct efx_rx_page_state) +
-			     NET_IP_ALIGN + EFX_RX_USR_BUF_SIZE >
-			     PAGE_SIZE / 2);
+			     2 * ALIGN(NET_IP_ALIGN + EFX_RX_USR_BUF_SIZE,
+				       EFX_RX_BUF_ALIGNMENT) >
+			     PAGE_SIZE);
 		efx->rx_scatter = true;
 		efx->rx_dma_len = EFX_RX_USR_BUF_SIZE;
 		efx->rx_buffer_order = 0;

drivers/net/ethernet/sfc/net_driver.h

@@ -72,8 +72,20 @@
 /* Maximum possible MTU the driver supports */
 #define EFX_MAX_MTU (9 * 1024)
 
-/* Size of an RX scatter buffer.  Small enough to pack 2 into a 4K page. */
-#define EFX_RX_USR_BUF_SIZE 1824
+/* Size of an RX scatter buffer.  Small enough to pack 2 into a 4K page,
+ * and should be a multiple of the cache line size.
+ */
+#define EFX_RX_USR_BUF_SIZE	(2048 - 256)
+
+/* If possible, we should ensure cache line alignment at start and end
+ * of every buffer.  Otherwise, we just need to ensure 4-byte
+ * alignment of the network header.
+ */
+#if NET_IP_ALIGN == 0
+#define EFX_RX_BUF_ALIGNMENT	L1_CACHE_BYTES
+#else
+#define EFX_RX_BUF_ALIGNMENT	4
+#endif
 
 /* Forward declare Precision Time Protocol (PTP) support structure. */
 struct efx_ptp_data;

drivers/net/ethernet/sfc/rx.c

@@ -94,7 +94,7 @@ static inline void efx_sync_rx_buffer(struct efx_nic *efx,
 void efx_rx_config_page_split(struct efx_nic *efx)
 {
 	efx->rx_page_buf_step = ALIGN(efx->rx_dma_len + NET_IP_ALIGN,
-				      L1_CACHE_BYTES);
+				      EFX_RX_BUF_ALIGNMENT);
 	efx->rx_bufs_per_page = efx->rx_buffer_order ? 1 :
 		((PAGE_SIZE - sizeof(struct efx_rx_page_state)) /
 		 efx->rx_page_buf_step);