From: Cosmin Ratiu <cratiu@nvidia.com>

First, allocate more doorbells in mlx5e_create_mdev_resources:
- one doorbell remains 'global' and will be used by all non-channel
  associated SQs (e.g. ASO, HWS, PTP, ...).
- allocate additional 'num_doorbells' doorbells. This defaults to
  minimum between 8 and max number of channels.

mlx5e_channel_pick_doorbell() now spreads out channel SQs across
available doorbells.

Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/en_common.c   | 29 ++++++++++++++++++-
 .../net/ethernet/mellanox/mlx5/core/en_main.c | 11 ++++++-
 include/linux/mlx5/driver.h                   |  4 +++
 3 files changed, 42 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index e9e36358c39d..d13cebbc763a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -143,6 +143,7 @@ static int mlx5e_create_tises(struct mlx5_core_dev *mdev, u32 tisn[MLX5_MAX_PORT
 int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises)
 {
 	struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs;
+	unsigned int num_doorbells, i;
 	int err;
 
 	err = mlx5_core_alloc_pd(mdev, &res->pdn);
@@ -163,11 +164,30 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises)
 		goto err_dealloc_transport_domain;
 	}
 
+	num_doorbells = min(MLX5_DEFAULT_NUM_DOORBELLS,
+			    mlx5e_get_max_num_channels(mdev));
+	res->bfregs = kcalloc(num_doorbells, sizeof(*res->bfregs), GFP_KERNEL);
+	if (!res->bfregs) {
+		err = -ENOMEM;
+		goto err_destroy_mkey;
+	}
+
+	for (i = 0; i < num_doorbells; i++) {
+		err = mlx5_alloc_bfreg(mdev, res->bfregs + i, false, false);
+		if (err) {
+			mlx5_core_warn(mdev,
+				       "could only allocate %d/%d doorbells, err %d.\n",
+				       i, num_doorbells, err);
+			break;
+		}
+	}
+	res->num_bfregs = i;
+
 	if (create_tises) {
 		err = mlx5e_create_tises(mdev, res->tisn);
 		if (err) {
 			mlx5_core_err(mdev, "alloc tises failed, %d\n", err);
-			goto err_destroy_mkey;
+			goto err_destroy_bfregs;
 		}
 		res->tisn_valid = true;
 	}
@@ -184,6 +204,10 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises)
 
 	return 0;
 
+err_destroy_bfregs:
+	for (i = 0; i < res->num_bfregs; i++)
+		mlx5_free_bfreg(mdev, res->bfregs + i);
+	kfree(res->bfregs);
 err_destroy_mkey:
 	mlx5_core_destroy_mkey(mdev, res->mkey);
 err_dealloc_transport_domain:
@@ -201,6 +225,9 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev)
 	mdev->mlx5e_res.dek_priv = NULL;
 	if (res->tisn_valid)
 		mlx5e_destroy_tises(mdev, res->tisn);
+	for (unsigned int i = 0; i < res->num_bfregs; i++)
+		mlx5_free_bfreg(mdev, res->bfregs + i);
+	kfree(res->bfregs);
 	mlx5_core_destroy_mkey(mdev, res->mkey);
 	mlx5_core_dealloc_transport_domain(mdev, res->td.tdn);
 	mlx5_core_dealloc_pd(mdev, res->pdn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index ef7598e048b2..4dee4c6d048d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2748,7 +2748,16 @@ void mlx5e_trigger_napi_sched(struct napi_struct *napi)
 
 static void mlx5e_channel_pick_doorbell(struct mlx5e_channel *c)
 {
-	c->bfreg = &c->mdev->priv.bfreg;
+	struct mlx5e_hw_objs *hw_objs = &c->mdev->mlx5e_res.hw_objs;
+
+	/* No dedicated Ethernet doorbells, use the global one. */
+	if (hw_objs->num_bfregs == 0) {
+		c->bfreg = &c->mdev->priv.bfreg;
+		return;
+	}
+
+	/* Round-robin between doorbells. */
+	c->bfreg = hw_objs->bfregs + c->vec_ix % hw_objs->num_bfregs;
 }
 
 static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 15c434fedff7..99b34e4809ae 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -658,6 +658,8 @@ struct mlx5e_resources {
 		u32                        pdn;
 		struct mlx5_td             td;
 		u32			   mkey;
+		struct mlx5_sq_bfreg      *bfregs;
+		unsigned int               num_bfregs;
 #define MLX5_MAX_NUM_TC 8
 		u32                        tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC];
 		bool			   tisn_valid;
@@ -801,6 +803,8 @@ struct mlx5_db {
 	int			index;
 };
 
+#define MLX5_DEFAULT_NUM_DOORBELLS 8
+
 enum {
 	MLX5_COMP_EQ_SIZE = 1024,
 };
-- 
2.31.1