i40e: use generic unrolled_count() macro

i40e, as well as ice, has a custom loop unrolling macro for unrolling
Tx descriptors filling on XSk xmit.
Replace i40e defs with generic unrolled_count(), which is also more
convenient as it allows passing defines as its argument, not hardcoded
values, while the loop declaration will still be a usual for-loop.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20250206182630.3914318-3-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index e28f1905a4a0f884db27bbe6f56d7217b565ef68..9f47388eaba538f1127dc24f3dde33337be60bed 100644 (file)
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -2,6 +2,7 @@
 /* Copyright(c) 2018 Intel Corporation. */
 
 #include <linux/bpf_trace.h>
+#include <linux/unroll.h>
 #include <net/xdp_sock_drv.h>
 #include "i40e_txrx_common.h"
 #include "i40e_xsk.h"
@@ -529,7 +530,8 @@ static void i40e_xmit_pkt_batch(struct i40e_ring *xdp_ring, struct xdp_desc *des
        dma_addr_t dma;
        u32 i;
 
-       loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
+       unrolled_count(PKTS_PER_BATCH)
+       for (i = 0; i < PKTS_PER_BATCH; i++) {
                u32 cmd = I40E_TX_DESC_CMD_ICRC | xsk_is_eop_desc(&desc[i]);
 
                dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc[i].addr);

diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
index ef156fad52f26214b513d9fbebd85d1aa2337a53..dd16351a7af84919c016e60b1f3a20fab632adc3 100644 (file)
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
@@ -6,7 +6,7 @@
 
 #include <linux/types.h>
 
-/* This value should match the pragma in the loop_unrolled_for
+/* This value should match the pragma in the unrolled_count()
  * macro. Why 4? It is strictly empirical. It seems to be a good
  * compromise between the advantage of having simultaneous outstanding
  * reads to the DMA array that can hide each others latency and the
@@ -14,14 +14,6 @@
  */
 #define PKTS_PER_BATCH 4
 
-#ifdef __clang__
-#define loop_unrolled_for _Pragma("clang loop unroll_count(4)") for
-#elif __GNUC__ >= 8
-#define loop_unrolled_for _Pragma("GCC unroll 4") for
-#else
-#define loop_unrolled_for for
-#endif
-
 struct i40e_ring;
 struct i40e_vsi;
 struct net_device;