Merge tag 'mlx5-updates-2021-08-11' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5 updates 2021-08-11

This series provides misc updates to mlx5.
For more information please see tag log below.

Please pull and let me know if there is any problem.

mlx5-updates-2021-08-11

Misc. cleanup for mlx5.

1) Typos and use of netdev_warn()
2) smatch cleanup
3) Minor fix to inner TTC table creation
4) Dynamic capability cache allocation
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlx5/core/cmd.c

@@ -877,7 +877,7 @@ static void cb_timeout_handler(struct work_struct *work)
 	ent->ret = -ETIMEDOUT;
 	mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, timeout. Will cause a leak of a command resource\n",
 		       ent->idx, mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in));
-	mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+	mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true);
 
 out:
 	cmd_ent_put(ent); /* for the cmd_ent_get() took on schedule delayed work */
@@ -994,7 +994,7 @@ static void cmd_work_handler(struct work_struct *work)
 		MLX5_SET(mbox_out, ent->out, status, status);
 		MLX5_SET(mbox_out, ent->out, syndrome, drv_synd);
 
-		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+		mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true);
 		return;
 	}
 
@@ -1008,7 +1008,7 @@ static void cmd_work_handler(struct work_struct *work)
 		poll_timeout(ent);
 		/* make sure we read the descriptor after ownership is SW */
 		rmb();
-		mlx5_cmd_comp_handler(dev, 1UL << ent->idx, (ent->ret == -ETIMEDOUT));
+		mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, (ent->ret == -ETIMEDOUT));
 	}
 }
 
@@ -1068,7 +1068,7 @@ static void wait_func_handle_exec_timeout(struct mlx5_core_dev *dev,
 		       mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in));
 
 	ent->ret = -ETIMEDOUT;
-	mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true);
+	mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true);
 }
 
 static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)

drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c

@@ -520,7 +520,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 	e->out_dev = attr.out_dev;
 	e->route_dev_ifindex = attr.route_dev->ifindex;
 
-	/* It's importent to add the neigh to the hash table before checking
+	/* It's important to add the neigh to the hash table before checking
 	 * the neigh validity state. So if we'll get a notification, in case the
 	 * neigh changes it's validity state, we would find the relevant neigh
 	 * in the hash.

drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c

@@ -126,7 +126,7 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params,
 	/* Create a separate SQ, so that when the buff pool is disabled, we could
 	 * close this SQ safely and stop receiving CQEs. In other case, e.g., if
 	 * the XDPSQ was used instead, we might run into trouble when the buff pool
-	 * is disabled and then reenabled, but the SQ continues receiving CQEs
+	 * is disabled and then re-enabled, but the SQ continues receiving CQEs
 	 * from the old buff pool.
 	 */
 	err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, pool, &c->xsksq, true);

drivers/net/ethernet/mellanox/mlx5/core/en_common.c

@@ -33,7 +33,7 @@
 #include "en.h"
 
 /* mlx5e global resources should be placed in this file.
- * Global resources are common to all the netdevices crated on the same nic.
+ * Global resources are common to all the netdevices created on the same nic.
  */
 
 void mlx5e_mkey_set_relaxed_ordering(struct mlx5_core_dev *mdev, void *mkc)

drivers/net/ethernet/mellanox/mlx5/core/en_fs.c

@@ -1255,7 +1255,8 @@ static int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv)
 		return 0;
 
 	mlx5e_set_inner_ttc_params(priv, &ttc_params);
-	priv->fs.inner_ttc = mlx5_create_ttc_table(priv->mdev, &ttc_params);
+	priv->fs.inner_ttc = mlx5_create_inner_ttc_table(priv->mdev,
+							 &ttc_params);
 	if (IS_ERR(priv->fs.inner_ttc))
 		return PTR_ERR(priv->fs.inner_ttc);
 	return 0;

drivers/net/ethernet/mellanox/mlx5/core/en_rep.h

@@ -146,7 +146,7 @@ struct mlx5e_neigh_hash_entry {
 	 */
 	refcount_t refcnt;
 
-	/* Save the last reported time offloaded trafic pass over one of the
+	/* Save the last reported time offloaded traffic pass over one of the
 	 * neigh hash entry flows. Use it to periodically update the neigh
 	 * 'used' value and avoid neigh deleting by the kernel.
 	 */

drivers/net/ethernet/mellanox/mlx5/core/en_tc.c

@@ -97,7 +97,7 @@ struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = {
 	[MARK_TO_REG] = mark_to_reg_ct,
 	[LABELS_TO_REG] = labels_to_reg_ct,
 	[FTEID_TO_REG] = fteid_to_reg_ct,
-	/* For NIC rules we store the retore metadata directly
+	/* For NIC rules we store the restore metadata directly
 	 * into reg_b that is passed to SW since we don't
 	 * jump between steering domains.
 	 */
@@ -2448,7 +2448,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 			spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_3;
 		}
 	}
-	/* Currenlty supported only for MPLS over UDP */
+	/* Currently supported only for MPLS over UDP */
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS) &&
 	    !netif_is_bareudp(filter_dev)) {
 		NL_SET_ERR_MSG_MOD(extack,
@@ -2702,7 +2702,9 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 		if (s_mask && a_mask) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "can't set and add to the same HW field");
-			printk(KERN_WARNING "mlx5: can't set and add to the same HW field (%x)\n", f->field);
+			netdev_warn(priv->netdev,
+				    "mlx5: can't set and add to the same HW field (%x)\n",
+				    f->field);
 			return -EOPNOTSUPP;
 		}
 
@@ -2741,8 +2743,9 @@ static int offload_pedit_fields(struct mlx5e_priv *priv,
 		if (first < next_z && next_z < last) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "rewrite of few sub-fields isn't supported");
-			printk(KERN_WARNING "mlx5: rewrite of few sub-fields (mask %lx) isn't offloaded\n",
-			       mask);
+			netdev_warn(priv->netdev,
+				    "mlx5: rewrite of few sub-fields (mask %lx) isn't offloaded\n",
+				    mask);
 			return -EOPNOTSUPP;
 		}
 

drivers/net/ethernet/mellanox/mlx5/core/eswitch.c

@@ -1492,7 +1492,7 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int mode, int num_vfs)
 /**
  * mlx5_eswitch_enable - Enable eswitch
  * @esw:	Pointer to eswitch
- * @num_vfs:	Enable eswitch swich for given number of VFs.
+ * @num_vfs:	Enable eswitch switch for given number of VFs.
  *		Caller must pass num_vfs > 0 when enabling eswitch for
  *		vf vports.
  * mlx5_eswitch_enable() returns 0 on success or error code on failure.

drivers/net/ethernet/mellanox/mlx5/core/events.c

@@ -27,7 +27,7 @@ static int pcie_core(struct notifier_block *, unsigned long, void *);
 static int forward_event(struct notifier_block *, unsigned long, void *);
 
 static struct mlx5_nb events_nbs_ref[] = {
-	/* Events to be proccessed by mlx5_core */
+	/* Events to be processed by mlx5_core */
 	{.nb.notifier_call = any_notifier,  .event_type = MLX5_EVENT_TYPE_NOTIFY_ANY },
 	{.nb.notifier_call = temp_warn,     .event_type = MLX5_EVENT_TYPE_TEMP_WARN_EVENT },
 	{.nb.notifier_call = port_module,   .event_type = MLX5_EVENT_TYPE_PORT_MODULE_EVENT },

drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c

@@ -1516,7 +1516,7 @@ static int mlx5_fpga_esp_modify_xfrm(struct mlx5_accel_esp_xfrm *xfrm,
 	mutex_lock(&fpga_xfrm->lock);
 
 	if (!fpga_xfrm->sa_ctx)
-		/* Unbounded xfrm, chane only sw attrs */
+		/* Unbounded xfrm, change only sw attrs */
 		goto change_sw_xfrm_attrs;
 
 	/* copy original hw sa */

drivers/net/ethernet/mellanox/mlx5/core/fs_core.c

@@ -2343,7 +2343,7 @@ static int create_leaf_prios(struct mlx5_flow_namespace *ns, int prio,
 
 #define FLOW_TABLE_BIT_SZ 1
 #define GET_FLOW_TABLE_CAP(dev, offset) \
-	((be32_to_cpu(*((__be32 *)(dev->caps.hca_cur[MLX5_CAP_FLOW_TABLE]) +	\
+	((be32_to_cpu(*((__be32 *)(dev->caps.hca[MLX5_CAP_FLOW_TABLE]->cur) +	\
 			offset / 32)) >>					\
 	  (32 - FLOW_TABLE_BIT_SZ - (offset & 0x1f))) & FLOW_TABLE_BIT_SZ)
 static bool has_required_caps(struct mlx5_core_dev *dev, struct node_caps *caps)
@@ -2493,7 +2493,7 @@ static void set_prio_attrs_in_prio(struct fs_prio *prio, int acc_level)
 		acc_level_ns = set_prio_attrs_in_ns(ns, acc_level);
 
 		/* If this a prio with chains, and we can jump from one chain
-		 * (namepsace) to another, so we accumulate the levels
+		 * (namespace) to another, so we accumulate the levels
 		 */
 		if (prio->node.type == FS_TYPE_PRIO_CHAINS)
 			acc_level = acc_level_ns;

drivers/net/ethernet/mellanox/mlx5/core/health.c

@@ -170,7 +170,7 @@ static bool reset_fw_if_needed(struct mlx5_core_dev *dev)
 
 	/* The reset only needs to be issued by one PF. The health buffer is
 	 * shared between all functions, and will be cleared during a reset.
-	 * Check again to avoid a redundant 2nd reset. If the fatal erros was
+	 * Check again to avoid a redundant 2nd reset. If the fatal errors was
 	 * PCI related a reset won't help.
 	 */
 	fatal_error = mlx5_health_check_fatal_sensors(dev);
@@ -213,10 +213,6 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
 	mutex_lock(&dev->intf_state_mutex);
 	if (!err_detected && dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
 		goto unlock;/* a previous error is still being handled */
-	if (dev->state == MLX5_DEVICE_STATE_UNINITIALIZED) {
-		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
-		goto unlock;
-	}
 
 	enter_error_state(dev, force);
 unlock:

drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c

@@ -749,7 +749,7 @@ static int mlx5_pps_event(struct notifier_block *nb,
 		} else {
 			ptp_event.type = PTP_CLOCK_EXTTS;
 		}
-		/* TODOL clock->ptp can be NULL if ptp_clock_register failes */
+		/* TODOL clock->ptp can be NULL if ptp_clock_register fails */
 		ptp_clock_event(clock->ptp, &ptp_event);
 		break;
 	case PTP_PF_PEROUT:

drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c

@@ -40,7 +40,7 @@
 
 struct mlx5_vxlan {
 	struct mlx5_core_dev		*mdev;
-	/* max_num_ports is usuallly 4, 16 buckets is more than enough */
+	/* max_num_ports is usually 4, 16 buckets is more than enough */
 	DECLARE_HASHTABLE(htable, 4);
 	struct mutex                    sync_lock; /* sync add/del port HW operations */
 };

drivers/net/ethernet/mellanox/mlx5/core/main.c

@@ -389,11 +389,11 @@ static int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev,
 
 	switch (cap_mode) {
 	case HCA_CAP_OPMOD_GET_MAX:
-		memcpy(dev->caps.hca_max[cap_type], hca_caps,
+		memcpy(dev->caps.hca[cap_type]->max, hca_caps,
 		       MLX5_UN_SZ_BYTES(hca_cap_union));
 		break;
 	case HCA_CAP_OPMOD_GET_CUR:
-		memcpy(dev->caps.hca_cur[cap_type], hca_caps,
+		memcpy(dev->caps.hca[cap_type]->cur, hca_caps,
 		       MLX5_UN_SZ_BYTES(hca_cap_union));
 		break;
 	default:
@@ -469,7 +469,7 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx)
 		return err;
 
 	set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability);
-	memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_ODP],
+	memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_ODP]->cur,
 	       MLX5_ST_SZ_BYTES(odp_cap));
 
 #define ODP_CAP_SET_MAX(dev, field)                                            \
@@ -514,7 +514,7 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 
 	set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx,
 				   capability);
-	memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_GENERAL],
+	memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_GENERAL]->cur,
 	       MLX5_ST_SZ_BYTES(cmd_hca_cap));
 
 	mlx5_core_dbg(dev, "Current Pkey table size %d Setting new size %d\n",
@@ -596,7 +596,7 @@ static int handle_hca_cap_roce(struct mlx5_core_dev *dev, void *set_ctx)
 		return 0;
 
 	set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability);
-	memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_ROCE],
+	memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_ROCE]->cur,
 	       MLX5_ST_SZ_BYTES(roce_cap));
 	MLX5_SET(roce_cap, set_hca_cap, sw_r_roce_src_udp_port, 1);
 
@@ -748,14 +748,12 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev)
 static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
 			 const struct pci_device_id *id)
 {
-	struct mlx5_priv *priv = &dev->priv;
 	int err = 0;
 
 	mutex_init(&dev->pci_status_mutex);
 	pci_set_drvdata(dev->pdev, dev);
 
 	dev->bar_addr = pci_resource_start(pdev, 0);
-	priv->numa_node = dev_to_node(mlx5_core_dma_dev(dev));
 
 	err = mlx5_pci_enable_device(dev);
 	if (err) {
@@ -1249,11 +1247,6 @@ int mlx5_init_one(struct mlx5_core_dev *dev)
 	int err = 0;
 
 	mutex_lock(&dev->intf_state_mutex);
-	if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
-		mlx5_core_warn(dev, "interface is up, NOP\n");
-		goto out;
-	}
-	/* remove any previous indication of internal error */
 	dev->state = MLX5_DEVICE_STATE_UP;
 
 	err = mlx5_function_setup(dev, true);
@@ -1294,7 +1287,6 @@ int mlx5_init_one(struct mlx5_core_dev *dev)
 	mlx5_function_teardown(dev, true);
 err_function:
 	dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
-out:
 	mutex_unlock(&dev->intf_state_mutex);
 	return err;
 }
@@ -1381,6 +1373,60 @@ void mlx5_unload_one(struct mlx5_core_dev *dev)
 	mutex_unlock(&dev->intf_state_mutex);
 }
 
+static const int types[] = {
+	MLX5_CAP_GENERAL,
+	MLX5_CAP_GENERAL_2,
+	MLX5_CAP_ETHERNET_OFFLOADS,
+	MLX5_CAP_IPOIB_ENHANCED_OFFLOADS,
+	MLX5_CAP_ODP,
+	MLX5_CAP_ATOMIC,
+	MLX5_CAP_ROCE,
+	MLX5_CAP_IPOIB_OFFLOADS,
+	MLX5_CAP_FLOW_TABLE,
+	MLX5_CAP_ESWITCH_FLOW_TABLE,
+	MLX5_CAP_ESWITCH,
+	MLX5_CAP_VECTOR_CALC,
+	MLX5_CAP_QOS,
+	MLX5_CAP_DEBUG,
+	MLX5_CAP_DEV_MEM,
+	MLX5_CAP_DEV_EVENT,
+	MLX5_CAP_TLS,
+	MLX5_CAP_VDPA_EMULATION,
+	MLX5_CAP_IPSEC,
+};
+
+static void mlx5_hca_caps_free(struct mlx5_core_dev *dev)
+{
+	int type;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(types); i++) {
+		type = types[i];
+		kfree(dev->caps.hca[type]);
+	}
+}
+
+static int mlx5_hca_caps_alloc(struct mlx5_core_dev *dev)
+{
+	struct mlx5_hca_cap *cap;
+	int type;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(types); i++) {
+		cap = kzalloc(sizeof(*cap), GFP_KERNEL);
+		if (!cap)
+			goto err;
+		type = types[i];
+		dev->caps.hca[type] = cap;
+	}
+
+	return 0;
+
+err:
+	mlx5_hca_caps_free(dev);
+	return -ENOMEM;
+}
+
 int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 {
 	struct mlx5_priv *priv = &dev->priv;
@@ -1400,6 +1446,7 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	mutex_init(&priv->pgdir_mutex);
 	INIT_LIST_HEAD(&priv->pgdir_list);
 
+	priv->numa_node = dev_to_node(mlx5_core_dma_dev(dev));
 	priv->dbg_root = debugfs_create_dir(dev_name(dev->device),
 					    mlx5_debugfs_root);
 	INIT_LIST_HEAD(&priv->traps);
@@ -1416,8 +1463,14 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	if (err)
 		goto err_adev_init;
 
+	err = mlx5_hca_caps_alloc(dev);
+	if (err)
+		goto err_hca_caps;
+
 	return 0;
 
+err_hca_caps:
+	mlx5_adev_cleanup(dev);
 err_adev_init:
 	mlx5_pagealloc_cleanup(dev);
 err_pagealloc_init:
@@ -1436,6 +1489,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
 
+	mlx5_hca_caps_free(dev);
 	mlx5_adev_cleanup(dev);
 	mlx5_pagealloc_cleanup(dev);
 	mlx5_health_cleanup(dev);

drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c

@@ -18,7 +18,7 @@
 
 #define MLX5_SFS_PER_CTRL_IRQ 64
 #define MLX5_IRQ_CTRL_SF_MAX 8
-/* min num of vectores for SFs to be enabled */
+/* min num of vectors for SFs to be enabled */
 #define MLX5_IRQ_VEC_COMP_BASE_SF 2
 
 #define MLX5_EQ_SHARE_IRQ_MAX_COMP (8)
@@ -28,13 +28,13 @@
 #define MLX5_EQ_REFS_PER_IRQ (2)
 
 struct mlx5_irq {
-	u32 index;
 	struct atomic_notifier_head nh;
 	cpumask_var_t mask;
 	char name[MLX5_MAX_IRQ_NAME];
-	struct kref kref;
-	int irqn;
 	struct mlx5_irq_pool *pool;
+	int refcount;
+	u32 index;
+	int irqn;
 };
 
 struct mlx5_irq_pool {
@@ -138,9 +138,8 @@ int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int function_id,
 	return ret;
 }
 
-static void irq_release(struct kref *kref)
+static void irq_release(struct mlx5_irq *irq)
 {
-	struct mlx5_irq *irq = container_of(kref, struct mlx5_irq, kref);
 	struct mlx5_irq_pool *pool = irq->pool;
 
 	xa_erase(&pool->irqs, irq->index);
@@ -159,10 +158,31 @@ static void irq_put(struct mlx5_irq *irq)
 	struct mlx5_irq_pool *pool = irq->pool;
 
 	mutex_lock(&pool->lock);
-	kref_put(&irq->kref, irq_release);
+	irq->refcount--;
+	if (!irq->refcount)
+		irq_release(irq);
 	mutex_unlock(&pool->lock);
 }
 
+static int irq_get_locked(struct mlx5_irq *irq)
+{
+	lockdep_assert_held(&irq->pool->lock);
+	if (WARN_ON_ONCE(!irq->refcount))
+		return 0;
+	irq->refcount++;
+	return 1;
+}
+
+static int irq_get(struct mlx5_irq *irq)
+{
+	int err;
+
+	mutex_lock(&irq->pool->lock);
+	err = irq_get_locked(irq);
+	mutex_unlock(&irq->pool->lock);
+	return err;
+}
+
 static irqreturn_t irq_int_handler(int irq, void *nh)
 {
 	atomic_notifier_call_chain(nh, 0, NULL);
@@ -214,7 +234,7 @@ static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i)
 		err = -ENOMEM;
 		goto err_cpumask;
 	}
-	kref_init(&irq->kref);
+	irq->refcount = 1;
 	irq->index = i;
 	err = xa_err(xa_store(&pool->irqs, irq->index, irq, GFP_KERNEL));
 	if (err) {
@@ -235,18 +255,18 @@ static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i)
 
 int mlx5_irq_attach_nb(struct mlx5_irq *irq, struct notifier_block *nb)
 {
-	int err;
+	int ret;
 
-	err = kref_get_unless_zero(&irq->kref);
-	if (WARN_ON_ONCE(!err))
+	ret = irq_get(irq);
+	if (!ret)
 		/* Something very bad happens here, we are enabling EQ
 		 * on non-existing IRQ.
 		 */
 		return -ENOENT;
-	err = atomic_notifier_chain_register(&irq->nh, nb);
-	if (err)
+	ret = atomic_notifier_chain_register(&irq->nh, nb);
+	if (ret)
 		irq_put(irq);
-	return err;
+	return ret;
 }
 
 int mlx5_irq_detach_nb(struct mlx5_irq *irq, struct notifier_block *nb)
@@ -301,10 +321,9 @@ static struct mlx5_irq *irq_pool_find_least_loaded(struct mlx5_irq_pool *pool,
 	xa_for_each_range(&pool->irqs, index, iter, start, end) {
 		if (!cpumask_equal(iter->mask, affinity))
 			continue;
-		if (kref_read(&iter->kref) < pool->min_threshold)
+		if (iter->refcount < pool->min_threshold)
 			return iter;
-		if (!irq || kref_read(&iter->kref) <
-		    kref_read(&irq->kref))
+		if (!irq || iter->refcount < irq->refcount)
 			irq = iter;
 	}
 	return irq;
@@ -319,7 +338,7 @@ static struct mlx5_irq *irq_pool_request_affinity(struct mlx5_irq_pool *pool,
 	mutex_lock(&pool->lock);
 	least_loaded_irq = irq_pool_find_least_loaded(pool, affinity);
 	if (least_loaded_irq &&
-	    kref_read(&least_loaded_irq->kref) < pool->min_threshold)
+	    least_loaded_irq->refcount < pool->min_threshold)
 		goto out;
 	new_irq = irq_pool_create_irq(pool, affinity);
 	if (IS_ERR(new_irq)) {
@@ -337,11 +356,11 @@ static struct mlx5_irq *irq_pool_request_affinity(struct mlx5_irq_pool *pool,
 	least_loaded_irq = new_irq;
 	goto unlock;
 out:
-	kref_get(&least_loaded_irq->kref);
-	if (kref_read(&least_loaded_irq->kref) > pool->max_threshold)
+	irq_get_locked(least_loaded_irq);
+	if (least_loaded_irq->refcount > pool->max_threshold)
 		mlx5_core_dbg(pool->dev, "IRQ %u overloaded, pool_name: %s, %u EQs on this irq\n",
 			      least_loaded_irq->irqn, pool->name,
-			      kref_read(&least_loaded_irq->kref) / MLX5_EQ_REFS_PER_IRQ);
+			      least_loaded_irq->refcount / MLX5_EQ_REFS_PER_IRQ);
 unlock:
 	mutex_unlock(&pool->lock);
 	return least_loaded_irq;
@@ -357,7 +376,7 @@ irq_pool_request_vector(struct mlx5_irq_pool *pool, int vecidx,
 	mutex_lock(&pool->lock);
 	irq = xa_load(&pool->irqs, vecidx);
 	if (irq) {
-		kref_get(&irq->kref);
+		irq_get_locked(irq);
 		goto unlock;
 	}
 	irq = irq_request(pool, vecidx);
@@ -424,7 +443,7 @@ struct mlx5_irq *mlx5_irq_request(struct mlx5_core_dev *dev, u16 vecidx,
 		return irq;
 	mlx5_core_dbg(dev, "irq %u mapped to cpu %*pbl, %u EQs on this irq\n",
 		      irq->irqn, cpumask_pr_args(affinity),
-		      kref_read(&irq->kref) / MLX5_EQ_REFS_PER_IRQ);
+		      irq->refcount / MLX5_EQ_REFS_PER_IRQ);
 	return irq;
 }
 
@@ -456,8 +475,12 @@ static void irq_pool_free(struct mlx5_irq_pool *pool)
 	struct mlx5_irq *irq;
 	unsigned long index;
 
+	/* There are cases in which we are destrying the irq_table before
+	 * freeing all the IRQs, fast teardown for example. Hence, free the irqs
+	 * which might not have been freed.
+	 */
 	xa_for_each(&pool->irqs, index, irq)
-		irq_release(&irq->kref);
+		irq_release(irq);
 	xa_destroy(&pool->irqs);
 	kvfree(pool);
 }
@@ -479,7 +502,7 @@ static int irq_pools_init(struct mlx5_core_dev *dev, int sf_vec, int pf_vec)
 	if (!mlx5_sf_max_functions(dev))
 		return 0;
 	if (sf_vec < MLX5_IRQ_VEC_COMP_BASE_SF) {
-		mlx5_core_err(dev, "Not enough IRQs for SFs. SF may run at lower performance\n");
+		mlx5_core_dbg(dev, "Not enught IRQs for SFs. SF may run at lower performance\n");
 		return 0;
 	}
 
@@ -597,7 +620,7 @@ void mlx5_irq_table_destroy(struct mlx5_core_dev *dev)
 		return;
 
 	/* There are cases where IRQs still will be in used when we reaching
-	 * to here. Hence, making sure all the irqs are realeased.
+	 * to here. Hence, making sure all the irqs are released.
 	 */
 	irq_pools_destroy(table);
 	pci_free_irq_vectors(dev->pdev);

drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c

@@ -39,7 +39,7 @@ static ssize_t sfnum_show(struct device *dev, struct device_attribute *attr, cha
 	struct auxiliary_device *adev = container_of(dev, struct auxiliary_device, dev);
 	struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev);
 
-	return scnprintf(buf, PAGE_SIZE, "%u\n", sf_dev->sfnum);
+	return sysfs_emit(buf, "%u\n", sf_dev->sfnum);
 }
 static DEVICE_ATTR_RO(sfnum);
 

drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c

@@ -476,7 +476,7 @@ static void mlx5_sf_table_disable(struct mlx5_sf_table *table)
 		return;
 
 	/* Balances with refcount_set; drop the reference so that new user cmd cannot start
-	 * and new vhca event handler cannnot run.
+	 * and new vhca event handler cannot run.
 	 */
 	mlx5_sf_table_put(table);
 	wait_for_completion(&table->disable_complete);

include/linux/mlx5/device.h

@@ -1038,7 +1038,7 @@ enum {
 struct mlx5_mkey_seg {
 	/* This is a two bit field occupying bits 31-30.
 	 * bit 31 is always 0,
-	 * bit 30 is zero for regular MRs and 1 (e.g free) for UMRs that do not have tanslation
+	 * bit 30 is zero for regular MRs and 1 (e.g free) for UMRs that do not have translation
 	 */
 	u8		status;
 	u8		pcie_control;
@@ -1157,6 +1157,9 @@ enum mlx5_cap_mode {
 	HCA_CAP_OPMOD_GET_CUR	= 1,
 };
 
+/* Any new cap addition must update mlx5_hca_caps_alloc() to allocate
+ * capability memory.
+ */
 enum mlx5_cap_type {
 	MLX5_CAP_GENERAL = 0,
 	MLX5_CAP_ETHERNET_OFFLOADS,
@@ -1213,55 +1216,55 @@ enum mlx5_qcam_feature_groups {
 
 /* GET Dev Caps macros */
 #define MLX5_CAP_GEN(mdev, cap) \
-	MLX5_GET(cmd_hca_cap, mdev->caps.hca_cur[MLX5_CAP_GENERAL], cap)
+	MLX5_GET(cmd_hca_cap, mdev->caps.hca[MLX5_CAP_GENERAL]->cur, cap)
 
 #define MLX5_CAP_GEN_64(mdev, cap) \
-	MLX5_GET64(cmd_hca_cap, mdev->caps.hca_cur[MLX5_CAP_GENERAL], cap)
+	MLX5_GET64(cmd_hca_cap, mdev->caps.hca[MLX5_CAP_GENERAL]->cur, cap)
 
 #define MLX5_CAP_GEN_MAX(mdev, cap) \
-	MLX5_GET(cmd_hca_cap, mdev->caps.hca_max[MLX5_CAP_GENERAL], cap)
+	MLX5_GET(cmd_hca_cap, mdev->caps.hca[MLX5_CAP_GENERAL]->max, cap)
 
 #define MLX5_CAP_GEN_2(mdev, cap) \
-	MLX5_GET(cmd_hca_cap_2, mdev->caps.hca_cur[MLX5_CAP_GENERAL_2], cap)
+	MLX5_GET(cmd_hca_cap_2, mdev->caps.hca[MLX5_CAP_GENERAL_2]->cur, cap)
 
 #define MLX5_CAP_GEN_2_64(mdev, cap) \
-	MLX5_GET64(cmd_hca_cap_2, mdev->caps.hca_cur[MLX5_CAP_GENERAL_2], cap)
+	MLX5_GET64(cmd_hca_cap_2, mdev->caps.hca[MLX5_CAP_GENERAL_2]->cur, cap)
 
 #define MLX5_CAP_GEN_2_MAX(mdev, cap) \
-	MLX5_GET(cmd_hca_cap_2, mdev->caps.hca_max[MLX5_CAP_GENERAL_2], cap)
+	MLX5_GET(cmd_hca_cap_2, mdev->caps.hca[MLX5_CAP_GENERAL_2]->max, cap)
 
 #define MLX5_CAP_ETH(mdev, cap) \
 	MLX5_GET(per_protocol_networking_offload_caps,\
-		 mdev->caps.hca_cur[MLX5_CAP_ETHERNET_OFFLOADS], cap)
+		 mdev->caps.hca[MLX5_CAP_ETHERNET_OFFLOADS]->cur, cap)
 
 #define MLX5_CAP_ETH_MAX(mdev, cap) \
 	MLX5_GET(per_protocol_networking_offload_caps,\
-		 mdev->caps.hca_max[MLX5_CAP_ETHERNET_OFFLOADS], cap)
+		 mdev->caps.hca[MLX5_CAP_ETHERNET_OFFLOADS]->max, cap)
 
 #define MLX5_CAP_IPOIB_ENHANCED(mdev, cap) \
 	MLX5_GET(per_protocol_networking_offload_caps,\
-		 mdev->caps.hca_cur[MLX5_CAP_IPOIB_ENHANCED_OFFLOADS], cap)
+		 mdev->caps.hca[MLX5_CAP_IPOIB_ENHANCED_OFFLOADS]->cur, cap)
 
 #define MLX5_CAP_ROCE(mdev, cap) \
-	MLX5_GET(roce_cap, mdev->caps.hca_cur[MLX5_CAP_ROCE], cap)
+	MLX5_GET(roce_cap, mdev->caps.hca[MLX5_CAP_ROCE]->cur, cap)
 
 #define MLX5_CAP_ROCE_MAX(mdev, cap) \
-	MLX5_GET(roce_cap, mdev->caps.hca_max[MLX5_CAP_ROCE], cap)
+	MLX5_GET(roce_cap, mdev->caps.hca[MLX5_CAP_ROCE]->max, cap)
 
 #define MLX5_CAP_ATOMIC(mdev, cap) \
-	MLX5_GET(atomic_caps, mdev->caps.hca_cur[MLX5_CAP_ATOMIC], cap)
+	MLX5_GET(atomic_caps, mdev->caps.hca[MLX5_CAP_ATOMIC]->cur, cap)
 
 #define MLX5_CAP_ATOMIC_MAX(mdev, cap) \
-	MLX5_GET(atomic_caps, mdev->caps.hca_max[MLX5_CAP_ATOMIC], cap)
+	MLX5_GET(atomic_caps, mdev->caps.hca[MLX5_CAP_ATOMIC]->max, cap)
 
 #define MLX5_CAP_FLOWTABLE(mdev, cap) \
-	MLX5_GET(flow_table_nic_cap, mdev->caps.hca_cur[MLX5_CAP_FLOW_TABLE], cap)
+	MLX5_GET(flow_table_nic_cap, mdev->caps.hca[MLX5_CAP_FLOW_TABLE]->cur, cap)
 
 #define MLX5_CAP64_FLOWTABLE(mdev, cap) \
-	MLX5_GET64(flow_table_nic_cap, (mdev)->caps.hca_cur[MLX5_CAP_FLOW_TABLE], cap)
+	MLX5_GET64(flow_table_nic_cap, (mdev)->caps.hca[MLX5_CAP_FLOW_TABLE]->cur, cap)
 
 #define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \
-	MLX5_GET(flow_table_nic_cap, mdev->caps.hca_max[MLX5_CAP_FLOW_TABLE], cap)
+	MLX5_GET(flow_table_nic_cap, mdev->caps.hca[MLX5_CAP_FLOW_TABLE]->max, cap)
 
 #define MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) \
 	MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.cap)
@@ -1301,11 +1304,11 @@ enum mlx5_qcam_feature_groups {
 
 #define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \
 	MLX5_GET(flow_table_eswitch_cap, \
-		 mdev->caps.hca_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap)
+		 mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->cur, cap)
 
 #define MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, cap) \
 	MLX5_GET(flow_table_eswitch_cap, \
-		 mdev->caps.hca_max[MLX5_CAP_ESWITCH_FLOW_TABLE], cap)
+		 mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->max, cap)
 
 #define MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) \
 	MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_nic_esw_fdb.cap)
@@ -1327,31 +1330,31 @@ enum mlx5_qcam_feature_groups {
 
 #define MLX5_CAP_ESW(mdev, cap) \
 	MLX5_GET(e_switch_cap, \
-		 mdev->caps.hca_cur[MLX5_CAP_ESWITCH], cap)
+		 mdev->caps.hca[MLX5_CAP_ESWITCH]->cur, cap)
 
 #define MLX5_CAP64_ESW_FLOWTABLE(mdev, cap) \
 	MLX5_GET64(flow_table_eswitch_cap, \
-		(mdev)->caps.hca_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap)
+		(mdev)->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->cur, cap)
 
 #define MLX5_CAP_ESW_MAX(mdev, cap) \
 	MLX5_GET(e_switch_cap, \
-		 mdev->caps.hca_max[MLX5_CAP_ESWITCH], cap)
+		 mdev->caps.hca[MLX5_CAP_ESWITCH]->max, cap)
 
 #define MLX5_CAP_ODP(mdev, cap)\
-	MLX5_GET(odp_cap, mdev->caps.hca_cur[MLX5_CAP_ODP], cap)
+	MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap)
 
 #define MLX5_CAP_ODP_MAX(mdev, cap)\
-	MLX5_GET(odp_cap, mdev->caps.hca_max[MLX5_CAP_ODP], cap)
+	MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->max, cap)
 
 #define MLX5_CAP_VECTOR_CALC(mdev, cap) \
 	MLX5_GET(vector_calc_cap, \
-		 mdev->caps.hca_cur[MLX5_CAP_VECTOR_CALC], cap)
+		 mdev->caps.hca[MLX5_CAP_VECTOR_CALC]->cur, cap)
 
 #define MLX5_CAP_QOS(mdev, cap)\
-	MLX5_GET(qos_cap, mdev->caps.hca_cur[MLX5_CAP_QOS], cap)
+	MLX5_GET(qos_cap, mdev->caps.hca[MLX5_CAP_QOS]->cur, cap)
 
 #define MLX5_CAP_DEBUG(mdev, cap)\
-	MLX5_GET(debug_cap, mdev->caps.hca_cur[MLX5_CAP_DEBUG], cap)
+	MLX5_GET(debug_cap, mdev->caps.hca[MLX5_CAP_DEBUG]->cur, cap)
 
 #define MLX5_CAP_PCAM_FEATURE(mdev, fld) \
 	MLX5_GET(pcam_reg, (mdev)->caps.pcam, feature_cap_mask.enhanced_features.fld)
@@ -1387,27 +1390,27 @@ enum mlx5_qcam_feature_groups {
 	MLX5_GET64(fpga_cap, (mdev)->caps.fpga, cap)
 
 #define MLX5_CAP_DEV_MEM(mdev, cap)\
-	MLX5_GET(device_mem_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_MEM], cap)
+	MLX5_GET(device_mem_cap, mdev->caps.hca[MLX5_CAP_DEV_MEM]->cur, cap)
 
 #define MLX5_CAP64_DEV_MEM(mdev, cap)\
-	MLX5_GET64(device_mem_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_MEM], cap)
+	MLX5_GET64(device_mem_cap, mdev->caps.hca[MLX5_CAP_DEV_MEM]->cur, cap)
 
 #define MLX5_CAP_TLS(mdev, cap) \
-	MLX5_GET(tls_cap, (mdev)->caps.hca_cur[MLX5_CAP_TLS], cap)
+	MLX5_GET(tls_cap, (mdev)->caps.hca[MLX5_CAP_TLS]->cur, cap)
 
 #define MLX5_CAP_DEV_EVENT(mdev, cap)\
-	MLX5_ADDR_OF(device_event_cap, (mdev)->caps.hca_cur[MLX5_CAP_DEV_EVENT], cap)
+	MLX5_ADDR_OF(device_event_cap, (mdev)->caps.hca[MLX5_CAP_DEV_EVENT]->cur, cap)
 
 #define MLX5_CAP_DEV_VDPA_EMULATION(mdev, cap)\
 	MLX5_GET(virtio_emulation_cap, \
-		(mdev)->caps.hca_cur[MLX5_CAP_VDPA_EMULATION], cap)
+		(mdev)->caps.hca[MLX5_CAP_VDPA_EMULATION]->cur, cap)
 
 #define MLX5_CAP64_DEV_VDPA_EMULATION(mdev, cap)\
 	MLX5_GET64(virtio_emulation_cap, \
-		(mdev)->caps.hca_cur[MLX5_CAP_VDPA_EMULATION], cap)
+		(mdev)->caps.hca[MLX5_CAP_VDPA_EMULATION]->cur, cap)
 
 #define MLX5_CAP_IPSEC(mdev, cap)\
-	MLX5_GET(ipsec_cap, (mdev)->caps.hca_cur[MLX5_CAP_IPSEC], cap)
+	MLX5_GET(ipsec_cap, (mdev)->caps.hca[MLX5_CAP_IPSEC]->cur, cap)
 
 enum {
 	MLX5_CMD_STAT_OK			= 0x0,

include/linux/mlx5/driver.h

@@ -581,7 +581,7 @@ struct mlx5_priv {
 	/* end: qp staff */
 
 	/* start: alloc staff */
-	/* protect buffer alocation according to numa node */
+	/* protect buffer allocation according to numa node */
 	struct mutex            alloc_mutex;
 	int                     numa_node;
 
@@ -623,8 +623,7 @@ struct mlx5_priv {
 };
 
 enum mlx5_device_state {
-	MLX5_DEVICE_STATE_UNINITIALIZED,
-	MLX5_DEVICE_STATE_UP,
+	MLX5_DEVICE_STATE_UP = 1,
 	MLX5_DEVICE_STATE_INTERNAL_ERROR,
 };
 
@@ -730,6 +729,11 @@ struct mlx5_profile {
 	} mr_cache[MAX_MR_CACHE_ENTRIES];
 };
 
+struct mlx5_hca_cap {
+	u32 cur[MLX5_UN_SZ_DW(hca_cap_union)];
+	u32 max[MLX5_UN_SZ_DW(hca_cap_union)];
+};
+
 struct mlx5_core_dev {
 	struct device *device;
 	enum mlx5_coredev_type coredev_type;
@@ -741,8 +745,7 @@ struct mlx5_core_dev {
 	char			board_id[MLX5_BOARD_ID_LEN];
 	struct mlx5_cmd		cmd;
 	struct {
-		u32 hca_cur[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)];
-		u32 hca_max[MLX5_CAP_NUM][MLX5_UN_SZ_DW(hca_cap_union)];
+		struct mlx5_hca_cap *hca[MLX5_CAP_NUM];
 		u32 pcam[MLX5_ST_SZ_DW(pcam_reg)];
 		u32 mcam[MLX5_MCAM_REGS_NUM][MLX5_ST_SZ_DW(mcam_reg)];
 		u32 fpga[MLX5_ST_SZ_DW(fpga_cap)];
@@ -1111,7 +1114,7 @@ static inline u8 mlx5_mkey_variant(u32 mkey)
 }
 
 /* Async-atomic event notifier used by mlx5 core to forward FW
- * evetns recived from event queue to mlx5 consumers.
+ * evetns received from event queue to mlx5 consumers.
  * Optimise event queue dipatching.
  */
 int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb);