net/mlx4_core: Fix number of EQs used in ICM initialisation

In SRIOV mode, the number of EQs used when computing the total ICM size
was incorrect.

To fix this, we do the following:
1. We add a new structure to mlx4_dev, mlx4_phys_caps, to contain physical HCA
   capabilities.  The PPF uses the phys capabilities when it computes things
   like ICM size.

   The dev_caps structure will then contain the paravirtualized values, making
   bookkeeping much easier in SRIOV mode. We add a structure rather than a
   single parameter because there will be other fields in the phys_caps.

   The first field we add to the mlx4_phys_caps structure is num_phys_eqs.

2. In INIT_HCA, when running in SRIOV mode, the "log_num_eqs" parameter
   passed to the FW is the number of EQs per VF/PF; each function (PF or VF)
   has this number of EQs available.

   However, the total number of EQs which must be allowed for in the ICM is
   (1 << log_num_eqs) * (#VFs + #PFs).  Rather than compute this quantity,
   we allocate ICM space for 1024 EQs (which is the device maximum
   number of EQs, and which is the value we place in the mlx4_phys_caps structure).

   For INIT_HCA, however, we use the per-function number of EQs as described
   above.

Signed-off-by: Marcel Apfelbaum <marcela@dev.mellanox.co.il>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlx4/main.c

@@ -142,12 +142,6 @@ struct mlx4_port_config {
 	struct pci_dev *pdev;
 };
 
-static inline int mlx4_master_get_num_eqs(struct mlx4_dev *dev)
-{
-	return dev->caps.reserved_eqs +
-		MLX4_MFUNC_EQ_NUM * (dev->num_slaves + 1);
-}
-
 int mlx4_check_port_params(struct mlx4_dev *dev,
 			   enum mlx4_port_type *port_type)
 {
@@ -217,6 +211,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	}
 
 	dev->caps.num_ports	     = dev_cap->num_ports;
+	dev->phys_caps.num_phys_eqs  = MLX4_MAX_EQ_NUM;
 	for (i = 1; i <= dev->caps.num_ports; ++i) {
 		dev->caps.vl_cap[i]	    = dev_cap->max_vl[i];
 		dev->caps.ib_mtu_cap[i]	    = dev_cap->ib_mtu[i];
@@ -810,9 +805,8 @@ static int mlx4_init_cmpt_table(struct mlx4_dev *dev, u64 cmpt_base,
 	if (err)
 		goto err_srq;
 
-	num_eqs = (mlx4_is_master(dev)) ?
-		roundup_pow_of_two(mlx4_master_get_num_eqs(dev)) :
-		dev->caps.num_eqs;
+	num_eqs = (mlx4_is_master(dev)) ? dev->phys_caps.num_phys_eqs :
+		  dev->caps.num_eqs;
 	err = mlx4_init_icm_table(dev, &priv->eq_table.cmpt_table,
 				  cmpt_base +
 				  ((u64) (MLX4_CMPT_TYPE_EQ *
@@ -874,9 +868,8 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 	}
 
 
-	num_eqs = (mlx4_is_master(dev)) ?
-		roundup_pow_of_two(mlx4_master_get_num_eqs(dev)) :
-		dev->caps.num_eqs;
+	num_eqs = (mlx4_is_master(dev)) ? dev->phys_caps.num_phys_eqs :
+		   dev->caps.num_eqs;
 	err = mlx4_init_icm_table(dev, &priv->eq_table.table,
 				  init_hca->eqc_base, dev_cap->eqc_entry_sz,
 				  num_eqs, num_eqs, 0, 0);

drivers/net/ethernet/mellanox/mlx4/profile.c

@@ -126,7 +126,9 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 	profile[MLX4_RES_AUXC].num    = request->num_qp;
 	profile[MLX4_RES_SRQ].num     = request->num_srq;
 	profile[MLX4_RES_CQ].num      = request->num_cq;
-	profile[MLX4_RES_EQ].num      = min_t(unsigned, dev_cap->max_eqs, MAX_MSIX);
+	profile[MLX4_RES_EQ].num      = mlx4_is_mfunc(dev) ?
+					dev->phys_caps.num_phys_eqs :
+					min_t(unsigned, dev_cap->max_eqs, MAX_MSIX);
 	profile[MLX4_RES_DMPT].num    = request->num_mpt;
 	profile[MLX4_RES_CMPT].num    = MLX4_NUM_CMPTS;
 	profile[MLX4_RES_MTT].num     = request->num_mtt * (1 << log_mtts_per_seg);
@@ -215,9 +217,10 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 			init_hca->log_num_cqs = profile[i].log_num;
 			break;
 		case MLX4_RES_EQ:
-			dev->caps.num_eqs     = profile[i].num;
+			dev->caps.num_eqs     = roundup_pow_of_two(min_t(unsigned, dev_cap->max_eqs,
+									 MAX_MSIX));
 			init_hca->eqc_base    = profile[i].start;
-			init_hca->log_num_eqs = profile[i].log_num;
+			init_hca->log_num_eqs = ilog2(dev->caps.num_eqs);
 			break;
 		case MLX4_RES_DMPT:
 			dev->caps.num_mpts	= profile[i].num;

include/linux/mlx4/device.h

@@ -64,6 +64,7 @@ enum {
 	MLX4_MAX_NUM_PF		= 16,
 	MLX4_MAX_NUM_VF		= 64,
 	MLX4_MFUNC_MAX		= 80,
+	MLX4_MAX_EQ_NUM		= 1024,
 	MLX4_MFUNC_EQ_NUM	= 4,
 	MLX4_MFUNC_MAX_EQES     = 8,
 	MLX4_MFUNC_EQE_MASK     = (MLX4_MFUNC_MAX_EQES - 1)
@@ -239,6 +240,10 @@ static inline u64 mlx4_fw_ver(u64 major, u64 minor, u64 subminor)
 	return (major << 32) | (minor << 16) | subminor;
 }
 
+struct mlx4_phys_caps {
+	u32			num_phys_eqs;
+};
+
 struct mlx4_caps {
 	u64			fw_ver;
 	u32			function;
@@ -499,6 +504,7 @@ struct mlx4_dev {
 	unsigned long		flags;
 	unsigned long		num_slaves;
 	struct mlx4_caps	caps;
+	struct mlx4_phys_caps	phys_caps;
 	struct radix_tree_root	qp_table_tree;
 	u8			rev_id;
 	char			board_id[MLX4_BOARD_ID_LEN];