{NET, IB}/mlx4: Add device managed flow steering firmware API

The driver is modified to support three operation modes.

If supported by firmware use the device managed flow steering
API, that which we call device managed steering mode. Else, if
the firmware supports the B0 steering mode use it, and finally,
if none of the above, use the A0 steering mode.

When the steering mode is device managed, the code is modified
such that L2 based rules set by the mlx4_en driver for Ethernet
unicast and multicast, and the IB stack multicast attach calls
done through the mlx4_ib driver are all routed to use the device
managed API.

When attaching rule using device managed flow steering API,
the firmware returns a 64 bit registration id, which is to be
provided during detach.

Currently the firmware is always programmed during HCA initialization
to use standard L2 hashing. Future work should be done to allow
configuring the flow-steering hash function with common, non
proprietary means.

Signed-off-by: Hadar Hen Zion <hadarh@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 43 insertions, 13 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index f8125a82c0cb..42645166bae2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -91,7 +91,9 @@ module_param_named(log_num_mgm_entry_size,
 MODULE_PARM_DESC(log_num_mgm_entry_size, "log mgm size, that defines the num"
 					 " of qp per mcg, for example:"
 					 " 10 gives 248.range: 9<="
-					 " log_num_mgm_entry_size <= 12");
+					 " log_num_mgm_entry_size <= 12."
+					 " Not in use with device managed"
+					 " flow steering");
 
 #define MLX4_VF                                        (1 << 0)
 
@@ -274,20 +276,27 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.max_gso_sz	     = dev_cap->max_gso_sz;
 	dev->caps.max_rss_tbl_sz     = dev_cap->max_rss_tbl_sz;
 
-	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER &&
-	    dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) {
-		dev->caps.steering_mode = MLX4_STEERING_MODE_B0;
+	if (dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_FS_EN) {
+		dev->caps.steering_mode = MLX4_STEERING_MODE_DEVICE_MANAGED;
+		dev->caps.num_qp_per_mgm = dev_cap->fs_max_num_qp_per_entry;
+		dev->caps.fs_log_max_ucast_qp_range_size =
+			dev_cap->fs_log_max_ucast_qp_range_size;
 	} else {
-		dev->caps.steering_mode = MLX4_STEERING_MODE_A0;
+		if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER &&
+		    dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) {
+			dev->caps.steering_mode = MLX4_STEERING_MODE_B0;
+		} else {
+			dev->caps.steering_mode = MLX4_STEERING_MODE_A0;
 
-		if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER ||
-		    dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)
-			mlx4_warn(dev, "Must have UC_STEER and MC_STEER flags "
-				       "set to use B0 steering. Falling back to A0 steering mode.\n");
+			if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER ||
+			    dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)
+				mlx4_warn(dev, "Must have UC_STEER and MC_STEER flags "
+						"set to use B0 steering. Falling back to A0 steering mode.\n");
+		}
+		dev->caps.num_qp_per_mgm = mlx4_get_qp_per_mgm(dev);
 	}
 	mlx4_dbg(dev, "Steering mode is: %s\n",
 		 mlx4_steering_mode_str(dev->caps.steering_mode));
-	dev->caps.num_qp_per_mgm = mlx4_get_qp_per_mgm(dev);
 
 	/* Sense port always allowed on supported devices for ConnectX1 and 2 */
 	if (dev->pdev->device != 0x1003)
@@ -982,9 +991,11 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 	}
 
 	/*
-	 * It's not strictly required, but for simplicity just map the
-	 * whole multicast group table now.  The table isn't very big
-	 * and it's a lot easier than trying to track ref counts.
+	 * For flow steering device managed mode it is required to use
+	 * mlx4_init_icm_table. For B0 steering mode it's not strictly
+	 * required, but for simplicity just map the whole multicast
+	 * group table now.  The table isn't very big and it's a lot
+	 * easier than trying to track ref counts.
 	 */
 	err = mlx4_init_icm_table(dev, &priv->mcg_table.table,
 				  init_hca->mc_base,
@@ -1220,7 +1231,26 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 			goto err_stop_fw;
 		}
 
+		priv->fs_hash_mode = MLX4_FS_L2_HASH;
+
+		switch (priv->fs_hash_mode) {
+		case MLX4_FS_L2_HASH:
+			init_hca.fs_hash_enable_bits = 0;
+			break;
+
+		case MLX4_FS_L2_L3_L4_HASH:
+			/* Enable flow steering with
+			 * udp unicast and tcp unicast
+			 */
+			init_hca.fs_hash_enable_bits =
+				MLX4_FS_UDP_UC_EN | MLX4_FS_TCP_UC_EN;
+			break;
+		}
+
 		profile = default_profile;
+		if (dev->caps.steering_mode ==
+		    MLX4_STEERING_MODE_DEVICE_MANAGED)
+			profile.num_mcg = MLX4_FS_NUM_MCG;
 
 		icm_size = mlx4_make_profile(dev, &profile, &dev_cap,
 					     &init_hca);