Merge branch 'mlx5-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux

Saeed Mahameed says:

====================
updates from mlx5-next 2022-09-24

Updates form mlx5-next including[1]:

1) HW definitions and support for NPPS clock settings.

2) various cleanups

3) Enable hash mode by default for all NICs

4) page tracker and advanced virtualization HW definitions for vfio

[1] https://lore.kernel.org/netdev/20220907233636.388475-1-saeed@kernel.org/

* 'mlx5-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux:
  net/mlx5: Remove from FPGA IFC file not-needed definitions
  net/mlx5: Remove unused structs
  net/mlx5: Remove unused functions
  net/mlx5: detect and enable bypass port select flow table
  net/mlx5: Lag, enable hash mode by default for all NICs
  net/mlx5: Lag, set active ports if support bypass port select flow table
  RDMA/mlx5: Don't set tx affinity when lag is in hash mode
  net/mlx5: add IFC bits for bypassing port select flow table
  net/mlx5: Add support for NPPS with real time mode
  net/mlx5: Expose NPPS related registers
  net/mlx5: Query ADV_VIRTUALIZATION capabilities
  net/mlx5: Introduce ifc bits for page tracker
  RDMA/mlx5: Move function mlx5_core_query_ib_ppcnt() to mlx5_ib
====================

Link: https://lore.kernel.org/all/20220927201906.234015-1-saeed@kernel.org/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 35 insertions, 2 deletions

diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c
index b4dc52392275..9c8a7b206dcf 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -147,6 +147,28 @@ static void pma_cnt_assign(struct ib_pma_portcounters *pma_cnt,
 			     vl_15_dropped);
 }
 
+static int query_ib_ppcnt(struct mlx5_core_dev *dev, u8 port_num, void *out,
+			  size_t sz)
+{
+	u32 *in;
+	int err;
+
+	in  = kvzalloc(sz, GFP_KERNEL);
+	if (!in) {
+		err = -ENOMEM;
+		return err;
+	}
+
+	MLX5_SET(ppcnt_reg, in, local_port, port_num);
+
+	MLX5_SET(ppcnt_reg, in, grp, MLX5_INFINIBAND_PORT_COUNTERS_GROUP);
+	err = mlx5_core_access_reg(dev, in, sz, out,
+				   sz, MLX5_REG_PPCNT, 0, 0);
+
+	kvfree(in);
+	return err;
+}
+
 static int process_pma_cmd(struct mlx5_ib_dev *dev, u32 port_num,
 			   const struct ib_mad *in_mad, struct ib_mad *out_mad)
 {
@@ -208,8 +230,7 @@ static int process_pma_cmd(struct mlx5_ib_dev *dev, u32 port_num,
 			goto done;
 		}
 
-		err = mlx5_core_query_ib_ppcnt(mdev, mdev_port_num,
-					       out_cnt, sz);
+		err = query_ib_ppcnt(mdev, mdev_port_num, out_cnt, sz);
 		if (!err)
 			pma_cnt_assign(pma_cnt, out_cnt);
 	}
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index e66bf72f1f04..62338f44a30e 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1541,6 +1541,18 @@ int mlx5_ib_test_wc(struct mlx5_ib_dev *dev);
 
 static inline bool mlx5_ib_lag_should_assign_affinity(struct mlx5_ib_dev *dev)
 {
+	/*
+	 * If the driver is in hash mode and the port_select_flow_table_bypass cap
+	 * is supported, it means that the driver no longer needs to assign the port
+	 * affinity by default. If a user wants to set the port affinity explicitly,
+	 * the user has a dedicated API to do that, so there is no need to assign
+	 * the port affinity by default.
+	 */
+	if (dev->lag_active &&
+	    mlx5_lag_mode_is_hash(dev->mdev) &&
+	    MLX5_CAP_PORT_SELECTION(dev->mdev, port_select_flow_table_bypass))
+		return 0;
+
 	return dev->lag_active ||
 		(MLX5_CAP_GEN(dev->mdev, num_lag_ports) > 1 &&
 		 MLX5_CAP_GEN(dev->mdev, lag_tx_port_affinity));