Merge branch 'mlxsw-Offload-PRIO-qdisc'

Jiri Pirko says:

====================
mlxsw: Offload PRIO qdisc

Nogah says:

Add an offload support for PRIO qdisc for mlxsw driver.
PRIO qdisc is being offloaded by using ndo_setup_tc. It has three
commands, to set or tune the qdisc, to remove it and to get its stats.

Like RED offloading, offloading this qdisc is not enforced on the driver
and determining its offload state is done in the dump action, when the
stats are being updated.
In the driver, offloading of PRIO is supported as root qdisc only. It
supports only priorities 0-7 (the range that is used by the current static
mapping of DSCP to skb prio and by 1:1 PCP values mapping) and up to 8
bands.

Patches 1-2 offload DSCP to priority mapping in the mlxsw_sp driver.
Patch 3 adds offload support for PRIO qdisc.
Patches 4-5 Add PRIO offload support in the mlxsw_sp driver.

---
v1->v2:
- Patch 1/5:
 - Rewrite patch msg
- Patch 3/5:
 - Send all the qstats in the replace command (and not just backlog)
- Patch 5/5:
 - Align with the changes from 3/5
 - Move backlog to the generic qdisc stats struct
 - Delete extra newline
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 171 insertions, 0 deletions

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
index 971f689dd833..e11a0abfc663 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
@@ -41,9 +41,12 @@
 #include "spectrum.h"
 #include "reg.h"
 
+#define MLXSW_SP_PRIO_BAND_TO_TCLASS(band) (IEEE_8021QAZ_MAX_TCS - band - 1)
+
 enum mlxsw_sp_qdisc_type {
 	MLXSW_SP_QDISC_NO_QDISC,
 	MLXSW_SP_QDISC_RED,
+	MLXSW_SP_QDISC_PRIO,
 };
 
 struct mlxsw_sp_qdisc_ops {
@@ -63,6 +66,11 @@ struct mlxsw_sp_qdisc_ops {
 			  void *xstats_ptr);
 	void (*clean_stats)(struct mlxsw_sp_port *mlxsw_sp_port,
 			    struct mlxsw_sp_qdisc *mlxsw_sp_qdisc);
+	/* unoffload - to be used for a qdisc that stops being offloaded without
+	 * being destroyed.
+	 */
+	void (*unoffload)(struct mlxsw_sp_port *mlxsw_sp_port,
+			  struct mlxsw_sp_qdisc *mlxsw_sp_qdisc, void *params);
 };
 
 struct mlxsw_sp_qdisc {
@@ -76,6 +84,7 @@ struct mlxsw_sp_qdisc {
 		u64 tx_packets;
 		u64 drops;
 		u64 overlimits;
+		u64 backlog;
 	} stats_base;
 
 	struct mlxsw_sp_qdisc_ops *ops;
@@ -141,6 +150,9 @@ mlxsw_sp_qdisc_replace(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle,
 
 err_bad_param:
 err_config:
+	if (mlxsw_sp_qdisc->handle == handle && ops->unoffload)
+		ops->unoffload(mlxsw_sp_port, mlxsw_sp_qdisc, params);
+
 	mlxsw_sp_qdisc_destroy(mlxsw_sp_port, mlxsw_sp_qdisc);
 	return err;
 }
@@ -403,6 +415,165 @@ int mlxsw_sp_setup_tc_red(struct mlxsw_sp_port *mlxsw_sp_port,
 	}
 }
 
+static int
+mlxsw_sp_qdisc_prio_destroy(struct mlxsw_sp_port *mlxsw_sp_port,
+			    struct mlxsw_sp_qdisc *mlxsw_sp_qdisc)
+{
+	int i;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+		mlxsw_sp_port_prio_tc_set(mlxsw_sp_port, i,
+					  MLXSW_SP_PORT_DEFAULT_TCLASS);
+
+	return 0;
+}
+
+static int
+mlxsw_sp_qdisc_prio_check_params(struct mlxsw_sp_port *mlxsw_sp_port,
+				 struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
+				 void *params)
+{
+	struct tc_prio_qopt_offload_params *p = params;
+
+	if (p->bands > IEEE_8021QAZ_MAX_TCS)
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static int
+mlxsw_sp_qdisc_prio_replace(struct mlxsw_sp_port *mlxsw_sp_port,
+			    struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
+			    void *params)
+{
+	struct tc_prio_qopt_offload_params *p = params;
+	int tclass, i;
+	int err;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		tclass = MLXSW_SP_PRIO_BAND_TO_TCLASS(p->priomap[i]);
+		err = mlxsw_sp_port_prio_tc_set(mlxsw_sp_port, i, tclass);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+void
+mlxsw_sp_qdisc_prio_unoffload(struct mlxsw_sp_port *mlxsw_sp_port,
+			      struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
+			      void *params)
+{
+	struct tc_prio_qopt_offload_params *p = params;
+	u64 backlog;
+
+	backlog = mlxsw_sp_cells_bytes(mlxsw_sp_port->mlxsw_sp,
+				       mlxsw_sp_qdisc->stats_base.backlog);
+	p->qstats->backlog -= backlog;
+}
+
+static int
+mlxsw_sp_qdisc_get_prio_stats(struct mlxsw_sp_port *mlxsw_sp_port,
+			      struct mlxsw_sp_qdisc *mlxsw_sp_qdisc,
+			      struct tc_qopt_offload_stats *stats_ptr)
+{
+	u64 tx_bytes, tx_packets, drops = 0, backlog = 0;
+	struct mlxsw_sp_qdisc_stats *stats_base;
+	struct mlxsw_sp_port_xstats *xstats;
+	struct rtnl_link_stats64 *stats;
+	int i;
+
+	xstats = &mlxsw_sp_port->periodic_hw_stats.xstats;
+	stats = &mlxsw_sp_port->periodic_hw_stats.stats;
+	stats_base = &mlxsw_sp_qdisc->stats_base;
+
+	tx_bytes = stats->tx_bytes - stats_base->tx_bytes;
+	tx_packets = stats->tx_packets - stats_base->tx_packets;
+
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		drops += xstats->tail_drop[i];
+		backlog += xstats->backlog[i];
+	}
+	drops = drops - stats_base->drops;
+
+	_bstats_update(stats_ptr->bstats, tx_bytes, tx_packets);
+	stats_ptr->qstats->drops += drops;
+	stats_ptr->qstats->backlog +=
+				mlxsw_sp_cells_bytes(mlxsw_sp_port->mlxsw_sp,
+						     backlog) -
+				mlxsw_sp_cells_bytes(mlxsw_sp_port->mlxsw_sp,
+						     stats_base->backlog);
+	stats_base->backlog = backlog;
+	stats_base->drops += drops;
+	stats_base->tx_bytes += tx_bytes;
+	stats_base->tx_packets += tx_packets;
+	return 0;
+}
+
+static void
+mlxsw_sp_setup_tc_qdisc_prio_clean_stats(struct mlxsw_sp_port *mlxsw_sp_port,
+					 struct mlxsw_sp_qdisc *mlxsw_sp_qdisc)
+{
+	struct mlxsw_sp_qdisc_stats *stats_base;
+	struct mlxsw_sp_port_xstats *xstats;
+	struct rtnl_link_stats64 *stats;
+	int i;
+
+	xstats = &mlxsw_sp_port->periodic_hw_stats.xstats;
+	stats = &mlxsw_sp_port->periodic_hw_stats.stats;
+	stats_base = &mlxsw_sp_qdisc->stats_base;
+
+	stats_base->tx_packets = stats->tx_packets;
+	stats_base->tx_bytes = stats->tx_bytes;
+
+	stats_base->drops = 0;
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+		stats_base->drops += xstats->tail_drop[i];
+
+	mlxsw_sp_qdisc->stats_base.backlog = 0;
+}
+
+static struct mlxsw_sp_qdisc_ops mlxsw_sp_qdisc_ops_prio = {
+	.type = MLXSW_SP_QDISC_PRIO,
+	.check_params = mlxsw_sp_qdisc_prio_check_params,
+	.replace = mlxsw_sp_qdisc_prio_replace,
+	.unoffload = mlxsw_sp_qdisc_prio_unoffload,
+	.destroy = mlxsw_sp_qdisc_prio_destroy,
+	.get_stats = mlxsw_sp_qdisc_get_prio_stats,
+	.clean_stats = mlxsw_sp_setup_tc_qdisc_prio_clean_stats,
+};
+
+int mlxsw_sp_setup_tc_prio(struct mlxsw_sp_port *mlxsw_sp_port,
+			   struct tc_prio_qopt_offload *p)
+{
+	struct mlxsw_sp_qdisc *mlxsw_sp_qdisc;
+
+	if (p->parent != TC_H_ROOT)
+		return -EOPNOTSUPP;
+
+	mlxsw_sp_qdisc = mlxsw_sp_port->root_qdisc;
+	if (p->command == TC_PRIO_REPLACE)
+		return mlxsw_sp_qdisc_replace(mlxsw_sp_port, p->handle,
+					      mlxsw_sp_qdisc,
+					      &mlxsw_sp_qdisc_ops_prio,
+					      &p->replace_params);
+
+	if (!mlxsw_sp_qdisc_compare(mlxsw_sp_qdisc, p->handle,
+				    MLXSW_SP_QDISC_PRIO))
+		return -EOPNOTSUPP;
+
+	switch (p->command) {
+	case TC_PRIO_DESTROY:
+		return mlxsw_sp_qdisc_destroy(mlxsw_sp_port, mlxsw_sp_qdisc);
+	case TC_PRIO_STATS:
+		return mlxsw_sp_qdisc_get_stats(mlxsw_sp_port, mlxsw_sp_qdisc,
+						&p->stats);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 int mlxsw_sp_tc_qdisc_init(struct mlxsw_sp_port *mlxsw_sp_port)
 {
 	mlxsw_sp_port->root_qdisc = kzalloc(sizeof(*mlxsw_sp_port->root_qdisc),