[PATCH vhost 2/7] vdpa/mlx5: Delete direct MKEYs in parallel

[Dragos Tatulea <dtatulea@nvidia.com>]

Use the async interface to issue MTT MKEY deletion.

This makes destroy_user_mr() on average 8x times faster.
This number is also dependent on the size of the MR being
deleted.

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
---
 drivers/vdpa/mlx5/core/mr.c | 66 +++++++++++++++++++++++++++++++++++++
 1 file changed, 66 insertions(+)

diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
index 66e6a15f823f..8cedf2969991 100644
--- a/drivers/vdpa/mlx5/core/mr.c
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -55,6 +55,11 @@ struct mlx5_create_mkey_mem {
 	DECLARE_FLEX_ARRAY(__be64, mtt);
 };
 
+struct mlx5_destroy_mkey_mem {
+	u8 out[MLX5_ST_SZ_BYTES(destroy_mkey_out)];
+	u8 in[MLX5_ST_SZ_BYTES(destroy_mkey_in)];
+};
+
 static void fill_create_direct_mr(struct mlx5_vdpa_dev *mvdev,
 				  struct mlx5_vdpa_direct_mr *mr,
 				  struct mlx5_create_mkey_mem *mem)
@@ -91,6 +96,17 @@ static void create_direct_mr_end(struct mlx5_vdpa_dev *mvdev,
 	mr->mr = mlx5_idx_to_mkey(mkey_index);
 }
 
+static void fill_destroy_direct_mr(struct mlx5_vdpa_dev *mvdev,
+				   struct mlx5_vdpa_direct_mr *mr,
+				   struct mlx5_destroy_mkey_mem *mem)
+{
+	void *in = &mem->in;
+
+	MLX5_SET(destroy_mkey_in, in, uid, mvdev->res.uid);
+	MLX5_SET(destroy_mkey_in, in, opcode, MLX5_CMD_OP_DESTROY_MKEY);
+	MLX5_SET(destroy_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mr->mr));
+}
+
 static void destroy_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr)
 {
 	if (!mr->mr)
@@ -255,6 +271,55 @@ static int create_direct_keys(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *
 	return err;
 }
 
+static int destroy_direct_keys(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr)
+{
+	struct mlx5_destroy_mkey_mem *cmd_mem;
+	struct mlx5_vdpa_async_cmd *cmds;
+	struct mlx5_vdpa_direct_mr *dmr;
+	int err = 0;
+	int i = 0;
+
+	cmds = kvcalloc(mr->num_directs, sizeof(*cmds), GFP_KERNEL);
+	cmd_mem = kvcalloc(mr->num_directs, sizeof(*cmd_mem), GFP_KERNEL);
+	if (!cmds || !cmd_mem) {
+		err = -ENOMEM;
+		goto done;
+	}
+
+	list_for_each_entry(dmr, &mr->head, list) {
+		cmds[i].out = cmd_mem[i].out;
+		cmds[i].outlen = sizeof(cmd_mem[i].out);
+		cmds[i].in = cmd_mem[i].in;
+		cmds[i].inlen = sizeof(cmd_mem[i].in);
+		fill_destroy_direct_mr(mvdev, dmr, &cmd_mem[i]);
+		i++;
+	}
+
+	err = mlx5_vdpa_exec_async_cmds(mvdev, cmds, mr->num_directs);
+	if (err) {
+
+		mlx5_vdpa_err(mvdev, "error issuing MTT mkey deletion for direct mrs: %d\n", err);
+		goto done;
+	}
+
+	i = 0;
+	list_for_each_entry(dmr, &mr->head, list) {
+		struct mlx5_vdpa_async_cmd *cmd = &cmds[i++];
+
+		dmr->mr = 0;
+		if (cmd->err) {
+			err = err ? err : cmd->err;
+			mlx5_vdpa_err(mvdev, "error deleting MTT mkey [0x%llx, 0x%llx]: %d\n",
+				dmr->start, dmr->end, cmd->err);
+		}
+	}
+
+done:
+	kvfree(cmd_mem);
+	kvfree(cmds);
+	return err;
+}
+
 static int create_indirect_key(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr)
 {
 	int inlen;
@@ -563,6 +628,7 @@ static void destroy_user_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr
 	struct mlx5_vdpa_direct_mr *n;
 
 	destroy_indirect_key(mvdev, mr);
+	destroy_direct_keys(mvdev, mr);
 	list_for_each_entry_safe_reverse(dmr, n, &mr->head, list) {
 		list_del_init(&dmr->list);
 		unmap_direct_mr(mvdev, dmr);
-- 
2.45.1