net/mlx5e: XDP, Avoid indirect call in TX flow

Use INDIRECT_CALL_2() helper to avoid the cost of the indirect call
when/if CONFIG_RETPOLINE=y.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

3 files changed, 37 insertions, 14 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index c9d308e91965..e0c1b010d41a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -34,6 +34,7 @@
 #include <net/xdp_sock_drv.h>
 #include "en/xdp.h"
 #include "en/params.h"
+#include <linux/indirect_call_wrapper.h>
 
 int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk)
 {
@@ -114,7 +115,8 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq,
 		xdpi.page.di    = *di;
 	}
 
-	return sq->xmit_xdp_frame(sq, &xdptxd, &xdpi, 0);
+	return INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe,
+			       mlx5e_xmit_xdp_frame, sq, &xdptxd, &xdpi, 0);
 }
 
 /* returns true if packet was consumed by xdp */
@@ -237,7 +239,7 @@ enum {
 	MLX5E_XDP_CHECK_START_MPWQE = 2,
 };
 
-static int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq)
+INDIRECT_CALLABLE_SCOPE int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq)
 {
 	if (unlikely(!sq->mpwqe.wqe)) {
 		const u16 stop_room = mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS);
@@ -256,10 +258,9 @@ static int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq)
 	return MLX5E_XDP_CHECK_OK;
 }
 
-static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
-				       struct mlx5e_xdp_xmit_data *xdptxd,
-				       struct mlx5e_xdp_info *xdpi,
-				       int check_result)
+INDIRECT_CALLABLE_SCOPE bool
+mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_xmit_data *xdptxd,
+			   struct mlx5e_xdp_info *xdpi, int check_result)
 {
 	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
 	struct mlx5e_xdpsq_stats *stats = sq->stats;
@@ -293,7 +294,7 @@ static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
 	return true;
 }
 
-static int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq)
+INDIRECT_CALLABLE_SCOPE int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq)
 {
 	if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) {
 		/* SQ is full, ring doorbell */
@@ -305,10 +306,9 @@ static int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq)
 	return MLX5E_XDP_CHECK_OK;
 }
 
-static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq,
-				 struct mlx5e_xdp_xmit_data *xdptxd,
-				 struct mlx5e_xdp_info *xdpi,
-				 int check_result)
+INDIRECT_CALLABLE_SCOPE bool
+mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_xmit_data *xdptxd,
+		     struct mlx5e_xdp_info *xdpi, int check_result)
 {
 	struct mlx5_wq_cyc       *wq   = &sq->wq;
 	u16                       pi   = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
@@ -506,6 +506,7 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		struct xdp_frame *xdpf = frames[i];
 		struct mlx5e_xdp_xmit_data xdptxd;
 		struct mlx5e_xdp_info xdpi;
+		bool ret;
 
 		xdptxd.data = xdpf->data;
 		xdptxd.len = xdpf->len;
@@ -522,7 +523,9 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		xdpi.frame.xdpf     = xdpf;
 		xdpi.frame.dma_addr = xdptxd.dma_addr;
 
-		if (unlikely(!sq->xmit_xdp_frame(sq, &xdptxd, &xdpi, 0))) {
+		ret = INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe,
+				      mlx5e_xmit_xdp_frame, sq, &xdptxd, &xdpi, 0);
+		if (unlikely(!ret)) {
 			dma_unmap_single(sq->pdev, xdptxd.dma_addr,
 					 xdptxd.len, DMA_TO_DEVICE);
 			xdp_return_frame_rx_napi(xdpf);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index ca48c293151b..e806c13d491f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -32,6 +32,8 @@
 #ifndef __MLX5_EN_XDP_H__
 #define __MLX5_EN_XDP_H__
 
+#include <linux/indirect_call_wrapper.h>
+
 #include "en.h"
 #include "en/txrx.h"
 
@@ -70,6 +72,17 @@ void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq);
 int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		   u32 flags);
 
+INDIRECT_CALLABLE_DECLARE(bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
+							  struct mlx5e_xdp_xmit_data *xdptxd,
+							  struct mlx5e_xdp_info *xdpi,
+							  int check_result));
+INDIRECT_CALLABLE_DECLARE(bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq,
+						    struct mlx5e_xdp_xmit_data *xdptxd,
+						    struct mlx5e_xdp_info *xdpi,
+						    int check_result));
+INDIRECT_CALLABLE_DECLARE(int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq));
+INDIRECT_CALLABLE_DECLARE(int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq));
+
 static inline void mlx5e_xdp_tx_enable(struct mlx5e_priv *priv)
 {
 	set_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
index e0b3c61af93e..0dfbc96e952a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c
@@ -6,6 +6,7 @@
 #include "en/xdp.h"
 #include "en/params.h"
 #include <net/xdp_sock_drv.h>
+#include <linux/indirect_call_wrapper.h>
 
 int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 {
@@ -75,8 +76,12 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
 	xdpi.mode = MLX5E_XDP_XMIT_MODE_XSK;
 
 	for (; budget; budget--) {
-		int check_result = sq->xmit_xdp_frame_check(sq);
+		int check_result = INDIRECT_CALL_2(sq->xmit_xdp_frame_check,
+						   mlx5e_xmit_xdp_frame_check_mpwqe,
+						   mlx5e_xmit_xdp_frame_check,
+						   sq);
 		struct xdp_desc desc;
+		bool ret;
 
 		if (unlikely(check_result < 0)) {
 			work_done = false;
@@ -98,7 +103,9 @@ bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget)
 
 		xsk_buff_raw_dma_sync_for_device(umem, xdptxd.dma_addr, xdptxd.len);
 
-		if (unlikely(!sq->xmit_xdp_frame(sq, &xdptxd, &xdpi, check_result))) {
+		ret = INDIRECT_CALL_2(sq->xmit_xdp_frame, mlx5e_xmit_xdp_frame_mpwqe,
+				      mlx5e_xmit_xdp_frame, sq, &xdptxd, &xdpi, check_result);
+		if (unlikely(!ret)) {
 			if (sq->mpwqe.wqe)
 				mlx5e_xdp_mpwqe_complete(sq);