net/mlx5: Handle memory scheme ODP capabilities

When running over new FW that supports the new memory scheme ODP, set
the cap in the FW to signal the FW we are working in the new scheme.

In the memory scheme ODP the per_transport_service capabilities are RO
for the driver so we skip their setting.

Signed-off-by: Michael Guralnik <michaelgur@nvidia.com>
Link: https://patch.msgid.link/20240909100504.29797-9-michaelgur@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index cc2aa46cff0477fdbbe492924d38407818eae808..4ec6507d094a34ae8708887fffc9c65146826355 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -454,8 +454,8 @@ static int handle_hca_cap_atomic(struct mlx5_core_dev *dev, void *set_ctx)
 
 static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx)
 {
+       bool do_set = false, mem_page_fault = false;
        void *set_hca_cap;
-       bool do_set = false;
        int err;
 
        if (!IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING) ||
@@ -470,6 +470,17 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx)
        memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_ODP]->cur,
               MLX5_ST_SZ_BYTES(odp_cap));
 
+       /* For best performance, enable memory scheme ODP only when
+        * it has page prefetch enabled.
+        */
+       if (MLX5_CAP_ODP_MAX(dev, mem_page_fault) &&
+           MLX5_CAP_ODP_MAX(dev, memory_page_fault_scheme_cap.page_prefetch)) {
+               mem_page_fault = true;
+               do_set = true;
+               MLX5_SET(odp_cap, set_hca_cap, mem_page_fault, mem_page_fault);
+               goto set;
+       }
+
 #define ODP_CAP_SET_MAX(dev, field)                                            \
        do {                                                                   \
                u32 _res = MLX5_CAP_ODP_MAX(dev, field);                       \
@@ -494,10 +505,13 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx)
        ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.dc_odp_caps.read);
        ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.dc_odp_caps.atomic);
 
-       if (!do_set)
-               return 0;
+set:
+       if (do_set)
+               err = set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_ODP);
 
-       return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_ODP);
+       mlx5_core_dbg(dev, "Using ODP %s scheme\n",
+                     mem_page_fault ? "memory" : "transport");
+       return err;
 }
 
 static int max_uc_list_get_devlink_param(struct mlx5_core_dev *dev)

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 154095256d0d11cb82e1d174d52212685464831e..57c9b18c3adba65ed8dc5cd3adb0ac559398ca4b 100644 (file)
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1389,9 +1389,13 @@ enum mlx5_qcam_feature_groups {
 #define MLX5_CAP_ODP(mdev, cap)\
        MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap)
 
-#define MLX5_CAP_ODP_SCHEME(mdev, cap)                       \
-       MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, \
-                transport_page_fault_scheme_cap.cap)
+#define MLX5_CAP_ODP_SCHEME(mdev, cap)                                \
+       (MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur,         \
+                 mem_page_fault) ?                                   \
+                MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, \
+                         memory_page_fault_scheme_cap.cap) :         \
+                MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, \
+                         transport_page_fault_scheme_cap.cap))
 
 #define MLX5_CAP_ODP_MAX(mdev, cap)\
        MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->max, cap)