net/mlx5: Move all IRQ logic to pci_irq.c

Finalize IRQ separation and expose irq interface.

Signed-off-by: Yuval Avnery <yuvalav@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

5 files changed, 354 insertions, 329 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 243368dc23db..cf8d2b74a2fc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -13,7 +13,7 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o
 #
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o alloc.o qp.o port.o mr.o pd.o \
-		transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
+		transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \
 		fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \
 		lib/devcom.o diag/fs_tracepoint.o diag/fw_tracer.o
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 80a436b5034a..0c72c122daef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -71,20 +71,6 @@ enum {
 
 static_assert(MLX5_EQ_POLLING_BUDGET <= MLX5_NUM_SPARE_EQE);
 
-struct mlx5_irq_info {
-	struct atomic_notifier_head nh;
-	cpumask_var_t mask;
-	char name[MLX5_MAX_IRQ_NAME];
-};
-
-struct mlx5_irq_table {
-	struct mlx5_irq_info *irq_info;
-	int nvec;
-#ifdef CONFIG_RFS_ACCEL
-	struct cpu_rmap *rmap;
-#endif
-};
-
 struct mlx5_eq_table {
 	struct list_head        comp_eqs_list;
 	struct mlx5_eq_async    pages_eq;
@@ -114,157 +100,6 @@ struct mlx5_eq_table {
 			       (1ull << MLX5_EVENT_TYPE_SRQ_LAST_WQE)	    | \
 			       (1ull << MLX5_EVENT_TYPE_SRQ_RQ_LIMIT))
 
-int mlx5_irq_table_init(struct mlx5_core_dev *dev)
-{
-	struct mlx5_irq_table *irq_table;
-
-	irq_table = kvzalloc(sizeof(*irq_table), GFP_KERNEL);
-	if (!irq_table)
-		return -ENOMEM;
-
-	dev->priv.irq_table = irq_table;
-	return 0;
-}
-
-void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev)
-{
-	kvfree(dev->priv.irq_table);
-}
-
-static int mlx5_irq_get_num_comp(struct mlx5_irq_table *table)
-{
-	return table->nvec - MLX5_EQ_VEC_COMP_BASE;
-}
-
-static struct mlx5_irq_info *mlx5_irq_get(struct mlx5_core_dev *dev, int vecidx)
-{
-	struct mlx5_irq_table *irq_table = dev->priv.irq_table;
-
-	return &irq_table->irq_info[vecidx];
-}
-
-static int mlx5_irq_attach_nb(struct mlx5_irq_table *irq_table, int vecidx,
-			      struct notifier_block *nb)
-{
-	struct mlx5_irq_info *irq_info;
-
-	irq_info = &irq_table->irq_info[vecidx];
-	return atomic_notifier_chain_register(&irq_info->nh, nb);
-}
-
-static int mlx5_irq_detach_nb(struct mlx5_irq_table *irq_table, int vecidx,
-			      struct notifier_block *nb)
-{
-	struct mlx5_irq_info *irq_info;
-
-	irq_info = &irq_table->irq_info[vecidx];
-	return atomic_notifier_chain_unregister(&irq_info->nh, nb);
-}
-
-static irqreturn_t mlx5_irq_int_handler(int irq, void *nh)
-{
-	atomic_notifier_call_chain(nh, 0, NULL);
-	return IRQ_HANDLED;
-}
-
-static void irq_set_name(char *name, int vecidx)
-{
-	switch (vecidx) {
-	case MLX5_EQ_CMD_IDX:
-		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_cmd_eq");
-		break;
-	case MLX5_EQ_ASYNC_IDX:
-		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_async_eq");
-		break;
-	case MLX5_EQ_PAGEREQ_IDX:
-		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_pages_eq");
-		break;
-	case MLX5_EQ_PFAULT_IDX:
-		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_ib_page_fault_eq");
-		break;
-	default:
-		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d",
-			 vecidx - MLX5_EQ_VEC_COMP_BASE);
-		break;
-	}
-}
-
-static int request_irqs(struct mlx5_core_dev *dev, int nvec)
-{
-	char name[MLX5_MAX_IRQ_NAME];
-	int err;
-	int i;
-
-	for (i = 0; i < nvec; i++) {
-		struct mlx5_irq_info *irq_info = mlx5_irq_get(dev, i);
-		int irqn = pci_irq_vector(dev->pdev, i);
-
-		irq_set_name(name, i);
-		ATOMIC_INIT_NOTIFIER_HEAD(&irq_info->nh);
-		snprintf(irq_info->name, MLX5_MAX_IRQ_NAME,
-			 "%s@pci:%s", name, pci_name(dev->pdev));
-		err = request_irq(irqn, mlx5_irq_int_handler, 0, irq_info->name,
-				  &irq_info->nh);
-		if (err) {
-			mlx5_core_err(dev, "Failed to request irq\n");
-			goto err_request_irq;
-		}
-	}
-	return 0;
-
-err_request_irq:
-	for (; i >= 0; i--) {
-		struct mlx5_irq_info *irq_info = mlx5_irq_get(dev, i);
-		int irqn = pci_irq_vector(dev->pdev, i);
-
-		free_irq(irqn, &irq_info->nh);
-	}
-	return  err;
-}
-
-static void irq_clear_rmap(struct mlx5_core_dev *dev)
-{
-#ifdef CONFIG_RFS_ACCEL
-	struct mlx5_irq_table *irq_table = dev->priv.irq_table;
-
-	free_irq_cpu_rmap(irq_table->rmap);
-#endif
-}
-
-static int irq_set_rmap(struct mlx5_core_dev *mdev)
-{
-	int err = 0;
-#ifdef CONFIG_RFS_ACCEL
-	struct mlx5_irq_table *irq_table = mdev->priv.irq_table;
-	int num_affinity_vec;
-	int vecidx;
-
-	num_affinity_vec = mlx5_irq_get_num_comp(irq_table);
-	irq_table->rmap = alloc_irq_cpu_rmap(num_affinity_vec);
-	if (!irq_table->rmap) {
-		err = -ENOMEM;
-		mlx5_core_err(mdev, "failed to allocate cpu_rmap. err %d", err);
-		goto err_out;
-	}
-
-	vecidx = MLX5_EQ_VEC_COMP_BASE;
-	for (; vecidx < irq_table->nvec; vecidx++) {
-		err = irq_cpu_rmap_add(irq_table->rmap,
-				       pci_irq_vector(mdev->pdev, vecidx));
-		if (err) {
-			mlx5_core_err(mdev, "irq_cpu_rmap_add failed. err %d", err);
-			goto err_irq_cpu_rmap_add;
-		}
-	}
-	return 0;
-
-err_irq_cpu_rmap_add:
-	irq_clear_rmap(mdev);
-err_out:
-#endif
-	return err;
-}
-
 static int mlx5_cmd_destroy_eq(struct mlx5_core_dev *dev, u8 eqn)
 {
 	u32 out[MLX5_ST_SZ_DW(destroy_eq_out)] = {0};
@@ -868,75 +703,6 @@ void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool arm)
 }
 EXPORT_SYMBOL(mlx5_eq_update_ci);
 
-/* Completion EQs */
-
-static int set_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
-{
-	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
-	struct mlx5_priv *priv  = &mdev->priv;
-	struct mlx5_irq_info *irq_info;
-	int irq;
-
-	irq_info = mlx5_irq_get(mdev, vecidx);
-	irq = pci_irq_vector(mdev->pdev, vecidx);
-
-	if (!zalloc_cpumask_var(&irq_info->mask, GFP_KERNEL)) {
-		mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
-		return -ENOMEM;
-	}
-
-	cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
-			irq_info->mask);
-
-	if (IS_ENABLED(CONFIG_SMP) &&
-	    irq_set_affinity_hint(irq, irq_info->mask))
-		mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq);
-
-	return 0;
-}
-
-static void clear_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
-{
-	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
-	struct mlx5_irq_info *irq_info;
-	int irq;
-
-	irq_info = mlx5_irq_get(mdev, vecidx);
-	irq = pci_irq_vector(mdev->pdev, vecidx);
-	irq_set_affinity_hint(irq, NULL);
-	free_cpumask_var(irq_info->mask);
-}
-
-static int set_comp_irq_affinity_hints(struct mlx5_core_dev *mdev)
-{
-	int nvec = mlx5_irq_get_num_comp(mdev->priv.irq_table);
-	int err;
-	int i;
-
-	for (i = 0; i < nvec; i++) {
-		err = set_comp_irq_affinity_hint(mdev, i);
-		if (err)
-			goto err_out;
-	}
-
-	return 0;
-
-err_out:
-	for (i--; i >= 0; i--)
-		clear_comp_irq_affinity_hint(mdev, i);
-
-	return err;
-}
-
-static void clear_comp_irqs_affinity_hints(struct mlx5_core_dev *mdev)
-{
-	int nvec = mlx5_irq_get_num_comp(mdev->priv.irq_table);
-	int i;
-
-	for (i = 0; i < nvec; i++)
-		clear_comp_irq_affinity_hint(mdev, i);
-}
-
 static void destroy_comp_eqs(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *table = dev->priv.eq_table;
@@ -1031,12 +797,6 @@ unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev)
 }
 EXPORT_SYMBOL(mlx5_comp_vectors_count);
 
-static struct cpumask *
-mlx5_irq_get_affinity_mask(struct mlx5_irq_table *irq_table, int vecidx)
-{
-	return irq_table->irq_info[vecidx].mask;
-}
-
 struct cpumask *
 mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector)
 {
@@ -1048,11 +808,6 @@ mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector)
 EXPORT_SYMBOL(mlx5_comp_irq_get_affinity_mask);
 
 #ifdef CONFIG_RFS_ACCEL
-static struct cpu_rmap *mlx5_irq_get_rmap(struct mlx5_irq_table *irq_table)
-{
-	return irq_table->rmap;
-}
-
 struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev)
 {
 	return mlx5_irq_get_rmap(dev->priv.eq_table->irq_table);
@@ -1082,88 +837,6 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
 	mutex_unlock(&table->lock);
 }
 
-static void unrequest_irqs(struct mlx5_core_dev *dev)
-{
-	struct mlx5_irq_table *table = dev->priv.irq_table;
-	int i;
-
-	for (i = 0; i < table->nvec; i++)
-		free_irq(pci_irq_vector(dev->pdev, i),
-			 &mlx5_irq_get(dev, i)->nh);
-}
-
-int mlx5_irq_table_create(struct mlx5_core_dev *dev)
-{
-	struct mlx5_priv *priv = &dev->priv;
-	struct mlx5_irq_table *table = priv->irq_table;
-	int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
-		      MLX5_CAP_GEN(dev, max_num_eqs) :
-		      1 << MLX5_CAP_GEN(dev, log_max_eq);
-	int nvec;
-	int err;
-
-	nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
-	       MLX5_EQ_VEC_COMP_BASE;
-	nvec = min_t(int, nvec, num_eqs);
-	if (nvec <= MLX5_EQ_VEC_COMP_BASE)
-		return -ENOMEM;
-
-	table->irq_info = kcalloc(nvec, sizeof(*table->irq_info), GFP_KERNEL);
-	if (!table->irq_info)
-		return -ENOMEM;
-
-	nvec = pci_alloc_irq_vectors(dev->pdev, MLX5_EQ_VEC_COMP_BASE + 1,
-				     nvec, PCI_IRQ_MSIX);
-	if (nvec < 0) {
-		err = nvec;
-		goto err_free_irq_info;
-	}
-
-	table->nvec = nvec;
-
-	err = irq_set_rmap(dev);
-	if (err)
-		goto err_set_rmap;
-
-	err = request_irqs(dev, nvec);
-	if (err)
-		goto err_request_irqs;
-
-	err = set_comp_irq_affinity_hints(dev);
-	if (err)
-		goto err_set_affinity;
-
-	return 0;
-
-err_set_affinity:
-	unrequest_irqs(dev);
-err_request_irqs:
-	irq_clear_rmap(dev);
-err_set_rmap:
-	pci_free_irq_vectors(dev->pdev);
-err_free_irq_info:
-	kfree(table->irq_info);
-	return err;
-}
-
-void mlx5_irq_table_destroy(struct mlx5_core_dev *dev)
-{
-	struct mlx5_irq_table *table = dev->priv.irq_table;
-	int i;
-
-	/* free_irq requires that affinity and rmap will be cleared
-	 * before calling it. This is why there is asymmetry with set_rmap
-	 * which should be called after alloc_irq but before request_irq.
-	 */
-	irq_clear_rmap(dev);
-	clear_comp_irqs_affinity_hints(dev);
-	for (i = 0; i < table->nvec; i++)
-		free_irq(pci_irq_vector(dev->pdev, i),
-			 &mlx5_irq_get(dev, i)->nh);
-	pci_free_irq_vectors(dev->pdev);
-	kfree(table->irq_info);
-}
-
 int mlx5_eq_table_create(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
index adbc228bd55d..3836c39b2900 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
@@ -7,7 +7,6 @@
 #include <linux/mlx5/eq.h>
 #include <linux/mlx5/cq.h>
 
-#define MLX5_MAX_IRQ_NAME   (32)
 #define MLX5_EQE_SIZE       (sizeof(struct mlx5_eqe))
 
 struct mlx5_eq_tasklet {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 14f1f63db3e3..e0f6783a5f6e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -157,6 +157,14 @@ int mlx5_irq_table_init(struct mlx5_core_dev *dev);
 void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev);
 int mlx5_irq_table_create(struct mlx5_core_dev *dev);
 void mlx5_irq_table_destroy(struct mlx5_core_dev *dev);
+int mlx5_irq_attach_nb(struct mlx5_irq_table *irq_table, int vecidx,
+		       struct notifier_block *nb);
+int mlx5_irq_detach_nb(struct mlx5_irq_table *irq_table, int vecidx,
+		       struct notifier_block *nb);
+struct cpumask *
+mlx5_irq_get_affinity_mask(struct mlx5_irq_table *irq_table, int vecidx);
+struct cpu_rmap *mlx5_irq_get_rmap(struct mlx5_irq_table *table);
+int mlx5_irq_get_num_comp(struct mlx5_irq_table *table);
 
 int mlx5_events_init(struct mlx5_core_dev *dev);
 void mlx5_events_cleanup(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
new file mode 100644
index 000000000000..75408639d150
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -0,0 +1,345 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include <linux/interrupt.h>
+#include <linux/notifier.h>
+#include <linux/module.h>
+#include <linux/mlx5/driver.h>
+#include "mlx5_core.h"
+#ifdef CONFIG_RFS_ACCEL
+#include <linux/cpu_rmap.h>
+#endif
+
+#define MLX5_MAX_IRQ_NAME (32)
+
+struct mlx5_irq_info {
+	struct atomic_notifier_head nh;
+	cpumask_var_t mask;
+	char name[MLX5_MAX_IRQ_NAME];
+};
+
+struct mlx5_irq_table {
+	struct mlx5_irq_info *irq_info;
+	int nvec;
+#ifdef CONFIG_RFS_ACCEL
+	struct cpu_rmap *rmap;
+#endif
+};
+
+int mlx5_irq_table_init(struct mlx5_core_dev *dev)
+{
+	struct mlx5_irq_table *irq_table;
+
+	irq_table = kvzalloc(sizeof(*irq_table), GFP_KERNEL);
+	if (!irq_table)
+		return -ENOMEM;
+
+	dev->priv.irq_table = irq_table;
+	return 0;
+}
+
+void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev)
+{
+	kvfree(dev->priv.irq_table);
+}
+
+int mlx5_irq_get_num_comp(struct mlx5_irq_table *table)
+{
+	return table->nvec - MLX5_EQ_VEC_COMP_BASE;
+}
+
+static struct mlx5_irq_info *mlx5_irq_get(struct mlx5_core_dev *dev, int vecidx)
+{
+	struct mlx5_irq_table *irq_table = dev->priv.irq_table;
+
+	return &irq_table->irq_info[vecidx];
+}
+
+int mlx5_irq_attach_nb(struct mlx5_irq_table *irq_table, int vecidx,
+		       struct notifier_block *nb)
+{
+	struct mlx5_irq_info *irq_info;
+
+	irq_info = &irq_table->irq_info[vecidx];
+	return atomic_notifier_chain_register(&irq_info->nh, nb);
+}
+
+int mlx5_irq_detach_nb(struct mlx5_irq_table *irq_table, int vecidx,
+		       struct notifier_block *nb)
+{
+	struct mlx5_irq_info *irq_info;
+
+	irq_info = &irq_table->irq_info[vecidx];
+	return atomic_notifier_chain_unregister(&irq_info->nh, nb);
+}
+
+static irqreturn_t mlx5_irq_int_handler(int irq, void *nh)
+{
+	atomic_notifier_call_chain(nh, 0, NULL);
+	return IRQ_HANDLED;
+}
+
+static void irq_set_name(char *name, int vecidx)
+{
+	switch (vecidx) {
+	case MLX5_EQ_CMD_IDX:
+		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_cmd_eq");
+		break;
+	case MLX5_EQ_ASYNC_IDX:
+		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_async_eq");
+		break;
+	case MLX5_EQ_PAGEREQ_IDX:
+		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_pages_eq");
+		break;
+	case MLX5_EQ_PFAULT_IDX:
+		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_ib_page_fault_eq");
+		break;
+	default:
+		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d",
+			 vecidx - MLX5_EQ_VEC_COMP_BASE);
+		break;
+	}
+}
+
+static int request_irqs(struct mlx5_core_dev *dev, int nvec)
+{
+	char name[MLX5_MAX_IRQ_NAME];
+	int err;
+	int i;
+
+	for (i = 0; i < nvec; i++) {
+		struct mlx5_irq_info *irq_info = mlx5_irq_get(dev, i);
+		int irqn = pci_irq_vector(dev->pdev, i);
+
+		irq_set_name(name, i);
+		ATOMIC_INIT_NOTIFIER_HEAD(&irq_info->nh);
+		snprintf(irq_info->name, MLX5_MAX_IRQ_NAME,
+			 "%s@pci:%s", name, pci_name(dev->pdev));
+		err = request_irq(irqn, mlx5_irq_int_handler, 0, irq_info->name,
+				  &irq_info->nh);
+		if (err) {
+			mlx5_core_err(dev, "Failed to request irq\n");
+			goto err_request_irq;
+		}
+	}
+	return 0;
+
+err_request_irq:
+	for (; i >= 0; i--) {
+		struct mlx5_irq_info *irq_info = mlx5_irq_get(dev, i);
+		int irqn = pci_irq_vector(dev->pdev, i);
+
+		free_irq(irqn, &irq_info->nh);
+	}
+	return  err;
+}
+
+static void irq_clear_rmap(struct mlx5_core_dev *dev)
+{
+#ifdef CONFIG_RFS_ACCEL
+	struct mlx5_irq_table *irq_table = dev->priv.irq_table;
+
+	free_irq_cpu_rmap(irq_table->rmap);
+#endif
+}
+
+static int irq_set_rmap(struct mlx5_core_dev *mdev)
+{
+	int err = 0;
+#ifdef CONFIG_RFS_ACCEL
+	struct mlx5_irq_table *irq_table = mdev->priv.irq_table;
+	int num_affinity_vec;
+	int vecidx;
+
+	num_affinity_vec = mlx5_irq_get_num_comp(irq_table);
+	irq_table->rmap = alloc_irq_cpu_rmap(num_affinity_vec);
+	if (!irq_table->rmap) {
+		err = -ENOMEM;
+		mlx5_core_err(mdev, "Failed to allocate cpu_rmap. err %d", err);
+		goto err_out;
+	}
+
+	vecidx = MLX5_EQ_VEC_COMP_BASE;
+	for (; vecidx < irq_table->nvec; vecidx++) {
+		err = irq_cpu_rmap_add(irq_table->rmap,
+				       pci_irq_vector(mdev->pdev, vecidx));
+		if (err) {
+			mlx5_core_err(mdev, "irq_cpu_rmap_add failed. err %d",
+				      err);
+			goto err_irq_cpu_rmap_add;
+		}
+	}
+	return 0;
+
+err_irq_cpu_rmap_add:
+	irq_clear_rmap(mdev);
+err_out:
+#endif
+	return err;
+}
+
+/* Completion IRQ vectors */
+
+static int set_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
+	struct mlx5_irq_info *irq_info;
+	int irq;
+
+	irq_info = mlx5_irq_get(mdev, vecidx);
+	irq = pci_irq_vector(mdev->pdev, vecidx);
+	if (!zalloc_cpumask_var(&irq_info->mask, GFP_KERNEL)) {
+		mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
+		return -ENOMEM;
+	}
+
+	cpumask_set_cpu(cpumask_local_spread(i, mdev->priv.numa_node),
+			irq_info->mask);
+
+	if (IS_ENABLED(CONFIG_SMP) &&
+	    irq_set_affinity_hint(irq, irq_info->mask))
+		mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x",
+			       irq);
+
+	return 0;
+}
+
+static void clear_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
+	struct mlx5_irq_info *irq_info;
+	int irq;
+
+	irq_info = mlx5_irq_get(mdev, vecidx);
+	irq = pci_irq_vector(mdev->pdev, vecidx);
+	irq_set_affinity_hint(irq, NULL);
+	free_cpumask_var(irq_info->mask);
+}
+
+static int set_comp_irq_affinity_hints(struct mlx5_core_dev *mdev)
+{
+	int nvec = mlx5_irq_get_num_comp(mdev->priv.irq_table);
+	int err;
+	int i;
+
+	for (i = 0; i < nvec; i++) {
+		err = set_comp_irq_affinity_hint(mdev, i);
+		if (err)
+			goto err_out;
+	}
+
+	return 0;
+
+err_out:
+	for (i--; i >= 0; i--)
+		clear_comp_irq_affinity_hint(mdev, i);
+
+	return err;
+}
+
+static void clear_comp_irqs_affinity_hints(struct mlx5_core_dev *mdev)
+{
+	int nvec = mlx5_irq_get_num_comp(mdev->priv.irq_table);
+	int i;
+
+	for (i = 0; i < nvec; i++)
+		clear_comp_irq_affinity_hint(mdev, i);
+}
+
+struct cpumask *
+mlx5_irq_get_affinity_mask(struct mlx5_irq_table *irq_table, int vecidx)
+{
+	return irq_table->irq_info[vecidx].mask;
+}
+
+#ifdef CONFIG_RFS_ACCEL
+struct cpu_rmap *mlx5_irq_get_rmap(struct mlx5_irq_table *irq_table)
+{
+	return irq_table->rmap;
+}
+#endif
+
+static void unrequest_irqs(struct mlx5_core_dev *dev)
+{
+	struct mlx5_irq_table *table = dev->priv.irq_table;
+	int i;
+
+	for (i = 0; i < table->nvec; i++)
+		free_irq(pci_irq_vector(dev->pdev, i),
+			 &mlx5_irq_get(dev, i)->nh);
+}
+
+int mlx5_irq_table_create(struct mlx5_core_dev *dev)
+{
+	struct mlx5_priv *priv = &dev->priv;
+	struct mlx5_irq_table *table = priv->irq_table;
+	int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
+		      MLX5_CAP_GEN(dev, max_num_eqs) :
+		      1 << MLX5_CAP_GEN(dev, log_max_eq);
+	int nvec;
+	int err;
+
+	nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
+	       MLX5_EQ_VEC_COMP_BASE;
+	nvec = min_t(int, nvec, num_eqs);
+	if (nvec <= MLX5_EQ_VEC_COMP_BASE)
+		return -ENOMEM;
+
+	table->irq_info = kcalloc(nvec, sizeof(*table->irq_info), GFP_KERNEL);
+	if (!table->irq_info)
+		return -ENOMEM;
+
+	nvec = pci_alloc_irq_vectors(dev->pdev, MLX5_EQ_VEC_COMP_BASE + 1,
+				     nvec, PCI_IRQ_MSIX);
+	if (nvec < 0) {
+		err = nvec;
+		goto err_free_irq_info;
+	}
+
+	table->nvec = nvec;
+
+	err = irq_set_rmap(dev);
+	if (err)
+		goto err_set_rmap;
+
+	err = request_irqs(dev, nvec);
+	if (err)
+		goto err_request_irqs;
+
+	err = set_comp_irq_affinity_hints(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to alloc affinity hint cpumask\n");
+		goto err_set_affinity;
+	}
+
+	return 0;
+
+err_set_affinity:
+	unrequest_irqs(dev);
+err_request_irqs:
+	irq_clear_rmap(dev);
+err_set_rmap:
+	pci_free_irq_vectors(dev->pdev);
+err_free_irq_info:
+	kfree(table->irq_info);
+	return err;
+}
+
+void mlx5_irq_table_destroy(struct mlx5_core_dev *dev)
+{
+	struct mlx5_irq_table *table = dev->priv.irq_table;
+	int i;
+
+	/* free_irq requires that affinity and rmap will be cleared
+	 * before calling it. This is why there is asymmetry with set_rmap
+	 * which should be called after alloc_irq but before request_irq.
+	 */
+	irq_clear_rmap(dev);
+	clear_comp_irqs_affinity_hints(dev);
+	for (i = 0; i < table->nvec; i++)
+		free_irq(pci_irq_vector(dev->pdev, i),
+			 &mlx5_irq_get(dev, i)->nh);
+	pci_free_irq_vectors(dev->pdev);
+	kfree(table->irq_info);
+}
+