mlxsw: spectrum: Unify delay handling between PFC and pause

When a priority is marked as lossless using DCB PFC, or when pause frames
are enabled on a port, mlxsw adds to port buffers an extra space to cover
the traffic that will arrive between the time that a pause or PFC frame is
emitted, and the time traffic actually stops. This is called the delay. The
concept is the same in PFC and pause, however the way the extra buffer
space is calculated differs.

In this patch, unify this handling. Delay is to be measured in bytes of
extra space, and will not include MTU. PFC handler sets the delay directly
from the parameter it gets through the DCB interface.

To convert pause handler, move MLXSW_SP_PAUSE_DELAY to ethtool module,
convert to bytes, and reduce it by maximum MTU, and divide by two. Then it
has the same meaning as the delay_bytes set by the PFC handler.

Keep the delay_bytes value in struct mlxsw_sp_hdroom introduced in the
previous patch. Change PFC and pause handlers to store the new delay value
there and have __mlxsw_sp_port_headroom_set() take it from there.

Instead of mlxsw_sp_pfc_delay_get() and mlxsw_sp_pg_buf_delay_get(),
introduce mlxsw_sp_hdroom_buf_delay_get() to calculate the delay provision.
Drop the unnecessary MLXSW_SP_CELL_FACTOR, and instead add an explanatory
comment describing the formula used.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 32 insertions, 37 deletions

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index ffb0e483d9cd..e436640abd4e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -616,33 +616,6 @@ static u16 mlxsw_sp_pg_buf_threshold_get(const struct mlxsw_sp *mlxsw_sp,
 	return 2 * mlxsw_sp_bytes_cells(mlxsw_sp, mtu);
 }
 
-#define MLXSW_SP_CELL_FACTOR 2	/* 2 * cell_size / (IPG + cell_size + 1) */
-
-static u16 mlxsw_sp_pfc_delay_get(const struct mlxsw_sp *mlxsw_sp, int mtu,
-				  u16 delay)
-{
-	delay = mlxsw_sp_bytes_cells(mlxsw_sp, DIV_ROUND_UP(delay,
-							    BITS_PER_BYTE));
-	return MLXSW_SP_CELL_FACTOR * delay + mlxsw_sp_bytes_cells(mlxsw_sp,
-								   mtu);
-}
-
-/* Maximum delay buffer needed in case of PAUSE frames, in bytes.
- * Assumes 100m cable and maximum MTU.
- */
-#define MLXSW_SP_PAUSE_DELAY 58752
-
-static u16 mlxsw_sp_pg_buf_delay_get(const struct mlxsw_sp *mlxsw_sp, int mtu,
-				     u16 delay, bool pfc, bool pause)
-{
-	if (pfc)
-		return mlxsw_sp_pfc_delay_get(mlxsw_sp, mtu, delay);
-	else if (pause)
-		return mlxsw_sp_bytes_cells(mlxsw_sp, MLXSW_SP_PAUSE_DELAY);
-	else
-		return 0;
-}
-
 static void mlxsw_sp_pg_buf_pack(char *pbmc_pl, int index, u16 size, u16 thres,
 				 bool lossy)
 {
@@ -653,13 +626,30 @@ static void mlxsw_sp_pg_buf_pack(char *pbmc_pl, int index, u16 size, u16 thres,
 						    thres);
 }
 
-int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
-				 u8 *prio_tc, bool pause_en,
-				 struct ieee_pfc *my_pfc)
+static u16 mlxsw_sp_hdroom_buf_delay_get(const struct mlxsw_sp *mlxsw_sp,
+					 const struct mlxsw_sp_hdroom *hdroom, int mtu)
+{
+	u16 delay_cells;
+
+	delay_cells = mlxsw_sp_bytes_cells(mlxsw_sp, hdroom->delay_bytes);
+
+	/* In the worst case scenario the delay will be made up of packets that
+	 * are all of size CELL_SIZE + 1, which means each packet will require
+	 * almost twice its true size when buffered in the switch. We therefore
+	 * multiply this value by the "cell factor", which is close to 2.
+	 *
+	 * Another MTU is added in case the transmitting host already started
+	 * transmitting a maximum length frame when the PFC packet was received.
+	 */
+	return 2 * delay_cells + mlxsw_sp_bytes_cells(mlxsw_sp, mtu);
+}
+
+int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port,
+				 struct mlxsw_sp_hdroom *hdroom,
+				 int mtu, u8 *prio_tc, bool pause_en, struct ieee_pfc *my_pfc)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	u8 pfc_en = !!my_pfc ? my_pfc->pfc_en : 0;
-	u16 delay = !!my_pfc ? my_pfc->delay : 0;
 	char pbmc_pl[MLXSW_REG_PBMC_LEN];
 	u32 taken_headroom_cells = 0;
 	u32 max_headroom_cells;
@@ -694,8 +684,7 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
 		lossy = !(pfc || pause_en);
 		thres_cells = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu);
 		thres_cells = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, thres_cells);
-		delay_cells = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay,
-							pfc, pause_en);
+		delay_cells = mlxsw_sp_hdroom_buf_delay_get(mlxsw_sp, hdroom, mtu);
 		delay_cells = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, delay_cells);
 		total_cells = thres_cells + delay_cells;
 
@@ -707,10 +696,16 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
 				     thres_cells, lossy);
 	}
 
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl);
+	if (err)
+		return err;
+
+	*mlxsw_sp_port->hdroom = *hdroom;
+	return 0;
 }
 
 int mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port,
+			       struct mlxsw_sp_hdroom *hdroom,
 			       int mtu, bool pause_en)
 {
 	u8 def_prio_tc[IEEE_8021QAZ_MAX_TCS] = {0};
@@ -721,7 +716,7 @@ int mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	prio_tc = dcb_en ? mlxsw_sp_port->dcb.ets->prio_tc : def_prio_tc;
 	my_pfc = dcb_en ? mlxsw_sp_port->dcb.pfc : NULL;
 
-	return __mlxsw_sp_port_headroom_set(mlxsw_sp_port, mtu, prio_tc,
+	return __mlxsw_sp_port_headroom_set(mlxsw_sp_port, hdroom, mtu, prio_tc,
 					    pause_en, my_pfc);
 }
 
@@ -731,7 +726,7 @@ static int mlxsw_sp_port_change_mtu(struct net_device *dev, int mtu)
 	bool pause_en = mlxsw_sp_port_is_pause_en(mlxsw_sp_port);
 	int err;
 
-	err = mlxsw_sp_port_headroom_set(mlxsw_sp_port, mtu, pause_en);
+	err = mlxsw_sp_port_headroom_set(mlxsw_sp_port, mlxsw_sp_port->hdroom, mtu, pause_en);
 	if (err)
 		return err;
 	err = mlxsw_sp_port_mtu_set(mlxsw_sp_port, mtu);
@@ -741,7 +736,7 @@ static int mlxsw_sp_port_change_mtu(struct net_device *dev, int mtu)
 	return 0;
 
 err_port_mtu_set:
-	mlxsw_sp_port_headroom_set(mlxsw_sp_port, dev->mtu, pause_en);
+	mlxsw_sp_port_headroom_set(mlxsw_sp_port, mlxsw_sp_port->hdroom, dev->mtu, pause_en);
 	return err;
 }