net/mlx5: Rate limit tables support

Configuring and managing HW rate limit tables.
The HW holds a table of rate limits, each rate is
associated with an index in that table.
Later a Send Queue uses this index to set the rate limit.
Multiple Send Queues can have the same rate limit, which is
represented by a single entry in this table.
Even though a rate can be shared, each queue is being rate
limited independently of others.

The SW shadow of this table holds the rate itself,
the index in the HW table and the refcount (number of queues)
working with this rate.

The exported functions are mlx5_rl_add_rate and mlx5_rl_remove_rate.
Number of different rates and their values are derived
from HW capabilities.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 31 insertions, 0 deletions

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 73a48479892d..e0a3ed758287 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1330,6 +1330,7 @@ enum mlx5_cap_type {
 	MLX5_CAP_ESWITCH,
 	MLX5_CAP_RESERVED,
 	MLX5_CAP_VECTOR_CALC,
+	MLX5_CAP_QOS,
 	/* NUM OF CAP Types */
 	MLX5_CAP_NUM
 };
@@ -1414,6 +1415,9 @@ enum mlx5_cap_type {
 	MLX5_GET(vector_calc_cap, \
 		 mdev->hca_caps_cur[MLX5_CAP_VECTOR_CALC], cap)
 
+#define MLX5_CAP_QOS(mdev, cap)\
+	MLX5_GET(qos_cap, mdev->hca_caps_cur[MLX5_CAP_QOS], cap)
+
 enum {
 	MLX5_CMD_STAT_OK			= 0x0,
 	MLX5_CMD_STAT_INT_ERR			= 0x1,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 80776d0c52dc..46260fdc5305 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -481,6 +481,21 @@ struct mlx5_fc_stats {
 
 struct mlx5_eswitch;
 
+struct mlx5_rl_entry {
+	u32                     rate;
+	u16                     index;
+	u16                     refcount;
+};
+
+struct mlx5_rl_table {
+	/* protect rate limit table */
+	struct mutex            rl_lock;
+	u16                     max_size;
+	u32                     max_rate;
+	u32                     min_rate;
+	struct mlx5_rl_entry   *rl_entry;
+};
+
 struct mlx5_priv {
 	char			name[MLX5_MAX_NAME_LEN];
 	struct mlx5_eq_table	eq_table;
@@ -544,6 +559,7 @@ struct mlx5_priv {
 	struct mlx5_flow_root_namespace *esw_ingress_root_ns;
 
 	struct mlx5_fc_stats		fc_stats;
+	struct mlx5_rl_table            rl_table;
 };
 
 enum mlx5_device_state {
@@ -861,6 +877,12 @@ int mlx5_query_odp_caps(struct mlx5_core_dev *dev,
 int mlx5_core_query_ib_ppcnt(struct mlx5_core_dev *dev,
 			     u8 port_num, void *out, size_t sz);
 
+int mlx5_init_rl_table(struct mlx5_core_dev *dev);
+void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev);
+int mlx5_rl_add_rate(struct mlx5_core_dev *dev, u32 rate, u16 *index);
+void mlx5_rl_remove_rate(struct mlx5_core_dev *dev, u32 rate);
+bool mlx5_rl_is_in_range(struct mlx5_core_dev *dev, u32 rate);
+
 static inline int fw_initializing(struct mlx5_core_dev *dev)
 {
 	return ioread32be(&dev->iseg->initializing) >> 31;
@@ -938,6 +960,11 @@ static inline int mlx5_get_gid_table_len(u16 param)
 	return 8 * (1 << param);
 }
 
+static inline bool mlx5_rl_is_supported(struct mlx5_core_dev *dev)
+{
+	return !!(dev->priv.rl_table.max_size);
+}
+
 enum {
 	MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32,
 };