Merge branch 'mlx5-next'

Saeed Mahameed says:

====================
Mellanox 100G mlx5 update 2016-11-15

This series contains four humble mlx5 features.

From Gal,
 - Add the support for PCIe statistics and expose them in ethtool

From Huy,
 - Add the support for port module events reporting and statistics
 - Add the support for driver version setting into FW (for display purposes only)

From Mohamad,
 - Extended the command interface cache flexibility

This series was generated against commit
6a02f5eb6a8a ("Merge branch 'mlxsw-i2c")

V2:
 - Changed plain "unsigned" to "unsigned int"
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

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

@@ -53,14 +53,6 @@ enum {
 	CMD_MODE_EVENTS
 };
 
-enum {
-	NUM_LONG_LISTS	  = 2,
-	NUM_MED_LISTS	  = 64,
-	LONG_LIST_SIZE	  = (2ULL * 1024 * 1024 * 1024 / PAGE_SIZE) * 8 + 16 +
-				MLX5_CMD_DATA_BLOCK_SIZE,
-	MED_LIST_SIZE	  = 16 + MLX5_CMD_DATA_BLOCK_SIZE,
-};
-
 enum {
 	MLX5_CMD_DELIVERY_STAT_OK			= 0x0,
 	MLX5_CMD_DELIVERY_STAT_SIGNAT_ERR		= 0x1,
@@ -1372,10 +1364,10 @@ static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg)
 {
 	unsigned long flags;
 
-	if (msg->cache) {
-		spin_lock_irqsave(&msg->cache->lock, flags);
-		list_add_tail(&msg->list, &msg->cache->head);
-		spin_unlock_irqrestore(&msg->cache->lock, flags);
+	if (msg->parent) {
+		spin_lock_irqsave(&msg->parent->lock, flags);
+		list_add_tail(&msg->list, &msg->parent->head);
+		spin_unlock_irqrestore(&msg->parent->lock, flags);
 	} else {
 		mlx5_free_cmd_msg(dev, msg);
 	}
@@ -1472,30 +1464,37 @@ static struct mlx5_cmd_msg *alloc_msg(struct mlx5_core_dev *dev, int in_size,
 				      gfp_t gfp)
 {
 	struct mlx5_cmd_msg *msg = ERR_PTR(-ENOMEM);
+	struct cmd_msg_cache *ch = NULL;
 	struct mlx5_cmd *cmd = &dev->cmd;
-	struct cache_ent *ent = NULL;
-
-	if (in_size > MED_LIST_SIZE && in_size <= LONG_LIST_SIZE)
-		ent = &cmd->cache.large;
-	else if (in_size > 16 && in_size <= MED_LIST_SIZE)
-		ent = &cmd->cache.med;
-
-	if (ent) {
-		spin_lock_irq(&ent->lock);
-		if (!list_empty(&ent->head)) {
-			msg = list_entry(ent->head.next, typeof(*msg), list);
-			/* For cached lists, we must explicitly state what is
-			 * the real size
-			 */
-			msg->len = in_size;
-			list_del(&msg->list);
+	int i;
+
+	if (in_size <= 16)
+		goto cache_miss;
+
+	for (i = 0; i < MLX5_NUM_COMMAND_CACHES; i++) {
+		ch = &cmd->cache[i];
+		if (in_size > ch->max_inbox_size)
+			continue;
+		spin_lock_irq(&ch->lock);
+		if (list_empty(&ch->head)) {
+			spin_unlock_irq(&ch->lock);
+			continue;
 		}
-		spin_unlock_irq(&ent->lock);
+		msg = list_entry(ch->head.next, typeof(*msg), list);
+		/* For cached lists, we must explicitly state what is
+		 * the real size
+		 */
+		msg->len = in_size;
+		list_del(&msg->list);
+		spin_unlock_irq(&ch->lock);
+		break;
 	}
 
-	if (IS_ERR(msg))
-		msg = mlx5_alloc_cmd_msg(dev, gfp, in_size, 0);
+	if (!IS_ERR(msg))
+		return msg;
 
+cache_miss:
+	msg = mlx5_alloc_cmd_msg(dev, gfp, in_size, 0);
 	return msg;
 }
 
@@ -1593,58 +1592,56 @@ EXPORT_SYMBOL(mlx5_cmd_exec_cb);
 
 static void destroy_msg_cache(struct mlx5_core_dev *dev)
 {
-	struct mlx5_cmd *cmd = &dev->cmd;
+	struct cmd_msg_cache *ch;
 	struct mlx5_cmd_msg *msg;
 	struct mlx5_cmd_msg *n;
+	int i;
 
-	list_for_each_entry_safe(msg, n, &cmd->cache.large.head, list) {
-		list_del(&msg->list);
-		mlx5_free_cmd_msg(dev, msg);
-	}
-
-	list_for_each_entry_safe(msg, n, &cmd->cache.med.head, list) {
-		list_del(&msg->list);
-		mlx5_free_cmd_msg(dev, msg);
+	for (i = 0; i < MLX5_NUM_COMMAND_CACHES; i++) {
+		ch = &dev->cmd.cache[i];
+		list_for_each_entry_safe(msg, n, &ch->head, list) {
+			list_del(&msg->list);
+			mlx5_free_cmd_msg(dev, msg);
+		}
 	}
 }
 
-static int create_msg_cache(struct mlx5_core_dev *dev)
+static unsigned cmd_cache_num_ent[MLX5_NUM_COMMAND_CACHES] = {
+	512, 32, 16, 8, 2
+};
+
+static unsigned cmd_cache_ent_size[MLX5_NUM_COMMAND_CACHES] = {
+	16 + MLX5_CMD_DATA_BLOCK_SIZE,
+	16 + MLX5_CMD_DATA_BLOCK_SIZE * 2,
+	16 + MLX5_CMD_DATA_BLOCK_SIZE * 16,
+	16 + MLX5_CMD_DATA_BLOCK_SIZE * 256,
+	16 + MLX5_CMD_DATA_BLOCK_SIZE * 512,
+};
+
+static void create_msg_cache(struct mlx5_core_dev *dev)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
+	struct cmd_msg_cache *ch;
 	struct mlx5_cmd_msg *msg;
-	int err;
 	int i;
-
-	spin_lock_init(&cmd->cache.large.lock);
-	INIT_LIST_HEAD(&cmd->cache.large.head);
-	spin_lock_init(&cmd->cache.med.lock);
-	INIT_LIST_HEAD(&cmd->cache.med.head);
-
-	for (i = 0; i < NUM_LONG_LISTS; i++) {
-		msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, LONG_LIST_SIZE, 0);
-		if (IS_ERR(msg)) {
-			err = PTR_ERR(msg);
-			goto ex_err;
-		}
-		msg->cache = &cmd->cache.large;
-		list_add_tail(&msg->list, &cmd->cache.large.head);
-	}
-
-	for (i = 0; i < NUM_MED_LISTS; i++) {
-		msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, MED_LIST_SIZE, 0);
-		if (IS_ERR(msg)) {
-			err = PTR_ERR(msg);
-			goto ex_err;
+	int k;
+
+	/* Initialize and fill the caches with initial entries */
+	for (k = 0; k < MLX5_NUM_COMMAND_CACHES; k++) {
+		ch = &cmd->cache[k];
+		spin_lock_init(&ch->lock);
+		INIT_LIST_HEAD(&ch->head);
+		ch->num_ent = cmd_cache_num_ent[k];
+		ch->max_inbox_size = cmd_cache_ent_size[k];
+		for (i = 0; i < ch->num_ent; i++) {
+			msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL | __GFP_NOWARN,
+						 ch->max_inbox_size, 0);
+			if (IS_ERR(msg))
+				break;
+			msg->parent = ch;
+			list_add_tail(&msg->list, &ch->head);
 		}
-		msg->cache = &cmd->cache.med;
-		list_add_tail(&msg->list, &cmd->cache.med.head);
 	}
-
-	return 0;
-
-ex_err:
-	destroy_msg_cache(dev);
-	return err;
 }
 
 static int alloc_cmd_page(struct mlx5_core_dev *dev, struct mlx5_cmd *cmd)
@@ -1767,11 +1764,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 
 	cmd->mode = CMD_MODE_POLLING;
 
-	err = create_msg_cache(dev);
-	if (err) {
-		dev_err(&dev->pdev->dev, "failed to create command cache\n");
-		goto err_free_page;
-	}
+	create_msg_cache(dev);
 
 	set_wqname(dev);
 	cmd->wq = create_singlethread_workqueue(cmd->wq_name);

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

@@ -171,9 +171,13 @@ static int mlx5e_get_sset_count(struct net_device *dev, int sset)
 		return NUM_SW_COUNTERS +
 		       MLX5E_NUM_Q_CNTRS(priv) +
 		       NUM_VPORT_COUNTERS + NUM_PPORT_COUNTERS +
+		       NUM_PCIE_COUNTERS +
 		       MLX5E_NUM_RQ_STATS(priv) +
 		       MLX5E_NUM_SQ_STATS(priv) +
-		       MLX5E_NUM_PFC_COUNTERS(priv);
+		       MLX5E_NUM_PFC_COUNTERS(priv) +
+		       ARRAY_SIZE(mlx5e_pme_status_desc) +
+		       ARRAY_SIZE(mlx5e_pme_error_desc);
+
 	case ETH_SS_PRIV_FLAGS:
 		return ARRAY_SIZE(mlx5e_priv_flags);
 	/* fallthrough */
@@ -213,6 +217,14 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data)
 		strcpy(data + (idx++) * ETH_GSTRING_LEN,
 		       pport_2819_stats_desc[i].format);
 
+	for (i = 0; i < NUM_PCIE_PERF_COUNTERS; i++)
+		strcpy(data + (idx++) * ETH_GSTRING_LEN,
+		       pcie_perf_stats_desc[i].format);
+
+	for (i = 0; i < NUM_PCIE_TAS_COUNTERS; i++)
+		strcpy(data + (idx++) * ETH_GSTRING_LEN,
+		       pcie_tas_stats_desc[i].format);
+
 	for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
 		for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++)
 			sprintf(data + (idx++) * ETH_GSTRING_LEN,
@@ -237,6 +249,13 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data)
 		}
 	}
 
+	/* port module event counters */
+	for (i = 0; i < ARRAY_SIZE(mlx5e_pme_status_desc); i++)
+		strcpy(data + (idx++) * ETH_GSTRING_LEN, mlx5e_pme_status_desc[i].format);
+
+	for (i = 0; i < ARRAY_SIZE(mlx5e_pme_error_desc); i++)
+		strcpy(data + (idx++) * ETH_GSTRING_LEN, mlx5e_pme_error_desc[i].format);
+
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
 		return;
 
@@ -279,6 +298,7 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
 				    struct ethtool_stats *stats, u64 *data)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_priv *mlx5_priv;
 	int i, j, tc, prio, idx = 0;
 	unsigned long pfc_combined;
 
@@ -314,6 +334,14 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
 		data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.RFC_2819_counters,
 						  pport_2819_stats_desc, i);
 
+	for (i = 0; i < NUM_PCIE_PERF_COUNTERS; i++)
+		data[idx++] = MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_perf_counters,
+						  pcie_perf_stats_desc, i);
+
+	for (i = 0; i < NUM_PCIE_TAS_COUNTERS; i++)
+		data[idx++] = MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_tas_counters,
+						  pcie_tas_stats_desc, i);
+
 	for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
 		for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++)
 			data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[prio],
@@ -335,6 +363,16 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev,
 		}
 	}
 
+	/* port module event counters */
+	mlx5_priv =  &priv->mdev->priv;
+	for (i = 0; i < ARRAY_SIZE(mlx5e_pme_status_desc); i++)
+		data[idx++] = MLX5E_READ_CTR64_CPU(mlx5_priv->pme_stats.status_counters,
+						   mlx5e_pme_status_desc, i);
+
+	for (i = 0; i < ARRAY_SIZE(mlx5e_pme_error_desc); i++)
+		data[idx++] = MLX5E_READ_CTR64_CPU(mlx5_priv->pme_stats.error_counters,
+						   mlx5e_pme_error_desc, i);
+
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
 		return;
 

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

@@ -290,12 +290,36 @@ static void mlx5e_update_q_counter(struct mlx5e_priv *priv)
 				      &qcnt->rx_out_of_buffer);
 }
 
+static void mlx5e_update_pcie_counters(struct mlx5e_priv *priv)
+{
+	struct mlx5e_pcie_stats *pcie_stats = &priv->stats.pcie;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int sz = MLX5_ST_SZ_BYTES(mpcnt_reg);
+	void *out;
+	u32 *in;
+
+	in = mlx5_vzalloc(sz);
+	if (!in)
+		return;
+
+	out = pcie_stats->pcie_perf_counters;
+	MLX5_SET(mpcnt_reg, in, grp, MLX5_PCIE_PERFORMANCE_COUNTERS_GROUP);
+	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_MPCNT, 0, 0);
+
+	out = pcie_stats->pcie_tas_counters;
+	MLX5_SET(mpcnt_reg, in, grp, MLX5_PCIE_TIMERS_AND_STATES_COUNTERS_GROUP);
+	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_MPCNT, 0, 0);
+
+	kvfree(in);
+}
+
 void mlx5e_update_stats(struct mlx5e_priv *priv)
 {
 	mlx5e_update_q_counter(priv);
 	mlx5e_update_vport_counters(priv);
 	mlx5e_update_pport_counters(priv);
 	mlx5e_update_sw_counters(priv);
+	mlx5e_update_pcie_counters(priv);
 }
 
 void mlx5e_update_stats_work(struct work_struct *work)

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

@@ -39,7 +39,7 @@
 #define MLX5E_READ_CTR32_CPU(ptr, dsc, i) \
 	(*(u32 *)((char *)ptr + dsc[i].offset))
 #define MLX5E_READ_CTR32_BE(ptr, dsc, i) \
-	be64_to_cpu(*(__be32 *)((char *)ptr + dsc[i].offset))
+	be32_to_cpu(*(__be32 *)((char *)ptr + dsc[i].offset))
 
 #define MLX5E_DECLARE_STAT(type, fld) #fld, offsetof(type, fld)
 #define MLX5E_DECLARE_RX_STAT(type, fld) "rx%d_"#fld, offsetof(type, fld)
@@ -276,6 +276,32 @@ static const struct counter_desc pport_per_prio_pfc_stats_desc[] = {
 	{ "rx_%s_pause_transition", PPORT_PER_PRIO_OFF(rx_pause_transition) },
 };
 
+#define PCIE_PERF_OFF(c) \
+	MLX5_BYTE_OFF(mpcnt_reg, counter_set.pcie_perf_cntrs_grp_data_layout.c)
+#define PCIE_PERF_GET(pcie_stats, c) \
+	MLX5_GET(mpcnt_reg, pcie_stats->pcie_perf_counters, \
+		 counter_set.pcie_perf_cntrs_grp_data_layout.c)
+#define PCIE_TAS_OFF(c) \
+	MLX5_BYTE_OFF(mpcnt_reg, counter_set.pcie_tas_cntrs_grp_data_layout.c)
+#define PCIE_TAS_GET(pcie_stats, c) \
+	MLX5_GET(mpcnt_reg, pcie_stats->pcie_tas_counters, \
+		 counter_set.pcie_tas_cntrs_grp_data_layout.c)
+
+struct mlx5e_pcie_stats {
+	__be64 pcie_perf_counters[MLX5_ST_SZ_QW(mpcnt_reg)];
+	__be64 pcie_tas_counters[MLX5_ST_SZ_QW(mpcnt_reg)];
+};
+
+static const struct counter_desc pcie_perf_stats_desc[] = {
+	{ "rx_pci_signal_integrity", PCIE_PERF_OFF(rx_errors) },
+	{ "tx_pci_signal_integrity", PCIE_PERF_OFF(tx_errors) },
+};
+
+static const struct counter_desc pcie_tas_stats_desc[] = {
+	{ "tx_pci_transport_nonfatal_msg", PCIE_TAS_OFF(non_fatal_err_msg_sent) },
+	{ "tx_pci_transport_fatal_msg", PCIE_TAS_OFF(fatal_err_msg_sent) },
+};
+
 struct mlx5e_rq_stats {
 	u64 packets;
 	u64 bytes;
@@ -360,6 +386,8 @@ static const struct counter_desc sq_stats_desc[] = {
 #define NUM_PPORT_802_3_COUNTERS	ARRAY_SIZE(pport_802_3_stats_desc)
 #define NUM_PPORT_2863_COUNTERS		ARRAY_SIZE(pport_2863_stats_desc)
 #define NUM_PPORT_2819_COUNTERS		ARRAY_SIZE(pport_2819_stats_desc)
+#define NUM_PCIE_PERF_COUNTERS		ARRAY_SIZE(pcie_perf_stats_desc)
+#define NUM_PCIE_TAS_COUNTERS		ARRAY_SIZE(pcie_tas_stats_desc)
 #define NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS \
 	ARRAY_SIZE(pport_per_prio_traffic_stats_desc)
 #define NUM_PPORT_PER_PRIO_PFC_COUNTERS \
@@ -369,6 +397,7 @@ static const struct counter_desc sq_stats_desc[] = {
 					 NUM_PPORT_2819_COUNTERS  + \
 					 NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS * \
 					 NUM_PPORT_PRIO)
+#define NUM_PCIE_COUNTERS		(NUM_PCIE_PERF_COUNTERS + NUM_PCIE_TAS_COUNTERS)
 #define NUM_RQ_STATS			ARRAY_SIZE(rq_stats_desc)
 #define NUM_SQ_STATS			ARRAY_SIZE(sq_stats_desc)
 
@@ -377,6 +406,24 @@ struct mlx5e_stats {
 	struct mlx5e_qcounter_stats qcnt;
 	struct mlx5e_vport_stats vport;
 	struct mlx5e_pport_stats pport;
+	struct mlx5e_pcie_stats pcie;
+};
+
+static const struct counter_desc mlx5e_pme_status_desc[] = {
+	{ "module_plug", 0 },
+	{ "module_unplug", 8 },
+};
+
+static const struct counter_desc mlx5e_pme_error_desc[] = {
+	{ "module_pwr_budget_exd", 0 },  /* power budget exceed */
+	{ "module_long_range", 8 },      /* long range for non MLNX cable */
+	{ "module_bus_stuck", 16 },      /* bus stuck (I2C or data shorted) */
+	{ "module_no_eeprom", 24 },      /* no eeprom/retry time out */
+	{ "module_enforce_part", 32 },   /* enforce part number list */
+	{ "module_unknown_id", 40 },     /* unknown identifier */
+	{ "module_high_temp", 48 },      /* high temperature */
+	{ "module_bad_shorted", 56 },    /* bad or shorted cable/module */
+	{ "module_unknown_status", 64 },
 };
 
 #endif /* __MLX5_EN_STATS_H__ */

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

@@ -139,6 +139,8 @@ static const char *eqe_type_str(u8 type)
 		return "MLX5_EVENT_TYPE_PORT_CHANGE";
 	case MLX5_EVENT_TYPE_GPIO_EVENT:
 		return "MLX5_EVENT_TYPE_GPIO_EVENT";
+	case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
+		return "MLX5_EVENT_TYPE_PORT_MODULE_EVENT";
 	case MLX5_EVENT_TYPE_REMOTE_CONFIG:
 		return "MLX5_EVENT_TYPE_REMOTE_CONFIG";
 	case MLX5_EVENT_TYPE_DB_BF_CONGESTION:
@@ -285,6 +287,11 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 			mlx5_eswitch_vport_event(dev->priv.eswitch, eqe);
 			break;
 #endif
+
+		case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
+			mlx5_port_module_event(dev, eqe);
+			break;
+
 		default:
 			mlx5_core_warn(dev, "Unhandled event 0x%x on EQ 0x%x\n",
 				       eqe->type, eq->eqn);
@@ -480,6 +487,11 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev)
 	    mlx5_core_is_pf(dev))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_NIC_VPORT_CHANGE);
 
+	if (MLX5_CAP_GEN(dev, port_module_event))
+		async_event_mask |= (1ull << MLX5_EVENT_TYPE_PORT_MODULE_EVENT);
+	else
+		mlx5_core_dbg(dev, "port_module_event is not set\n");
+
 	err = mlx5_create_map_eq(dev, &table->cmd_eq, MLX5_EQ_VEC_CMD,
 				 MLX5_NUM_CMD_EQE, 1ull << MLX5_EVENT_TYPE_CMD,
 				 "mlx5_cmd_eq", &dev->priv.uuari.uars[0]);

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

@@ -175,6 +175,41 @@ static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili)
 	return err;
 }
 
+static void mlx5_set_driver_version(struct mlx5_core_dev *dev)
+{
+	int driver_ver_sz = MLX5_FLD_SZ_BYTES(set_driver_version_in,
+					      driver_version);
+	u8 in[MLX5_ST_SZ_BYTES(set_driver_version_in)] = {0};
+	u8 out[MLX5_ST_SZ_BYTES(set_driver_version_out)] = {0};
+	int remaining_size = driver_ver_sz;
+	char *string;
+
+	if (!MLX5_CAP_GEN(dev, driver_version))
+		return;
+
+	string = MLX5_ADDR_OF(set_driver_version_in, in, driver_version);
+
+	strncpy(string, "Linux", remaining_size);
+
+	remaining_size = max_t(int, 0, driver_ver_sz - strlen(string));
+	strncat(string, ",", remaining_size);
+
+	remaining_size = max_t(int, 0, driver_ver_sz - strlen(string));
+	strncat(string, DRIVER_NAME, remaining_size);
+
+	remaining_size = max_t(int, 0, driver_ver_sz - strlen(string));
+	strncat(string, ",", remaining_size);
+
+	remaining_size = max_t(int, 0, driver_ver_sz - strlen(string));
+	strncat(string, DRIVER_VERSION, remaining_size);
+
+	/*Send the command*/
+	MLX5_SET(set_driver_version_in, in, opcode,
+		 MLX5_CMD_OP_SET_DRIVER_VERSION);
+
+	mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
 static int set_dma_caps(struct pci_dev *pdev)
 {
 	int err;
@@ -1015,6 +1050,8 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto err_pagealloc_stop;
 	}
 
+	mlx5_set_driver_version(dev);
+
 	mlx5_start_health_poll(dev);
 
 	err = mlx5_query_hca_caps(dev);

drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h

@@ -81,6 +81,7 @@ int mlx5_cmd_init_hca(struct mlx5_core_dev *dev);
 int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev);
 void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
 		     unsigned long param);
+void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
 void mlx5_enter_error_state(struct mlx5_core_dev *dev);
 void mlx5_disable_device(struct mlx5_core_dev *dev);
 void mlx5_recover_device(struct mlx5_core_dev *dev);

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

@@ -746,3 +746,60 @@ void mlx5_query_port_fcs(struct mlx5_core_dev *mdev, bool *supported,
 	*supported = !!(MLX5_GET(pcmr_reg, out, fcs_cap));
 	*enabled = !!(MLX5_GET(pcmr_reg, out, fcs_chk));
 }
+
+static const char *mlx5_pme_status[MLX5_MODULE_STATUS_NUM] = {
+	"Cable plugged",   /* MLX5_MODULE_STATUS_PLUGGED    = 0x1 */
+	"Cable unplugged", /* MLX5_MODULE_STATUS_UNPLUGGED  = 0x2 */
+	"Cable error",     /* MLX5_MODULE_STATUS_ERROR      = 0x3 */
+};
+
+static const char *mlx5_pme_error[MLX5_MODULE_EVENT_ERROR_NUM] = {
+	"Power budget exceeded",
+	"Long Range for non MLNX cable",
+	"Bus stuck(I2C or data shorted)",
+	"No EEPROM/retry timeout",
+	"Enforce part number list",
+	"Unknown identifier",
+	"High Temperature",
+	"Bad or shorted cable/module",
+	"Unknown status",
+};
+
+void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe)
+{
+	enum port_module_event_status_type module_status;
+	enum port_module_event_error_type error_type;
+	struct mlx5_eqe_port_module *module_event_eqe;
+	struct mlx5_priv *priv = &dev->priv;
+	u8 module_num;
+
+	module_event_eqe = &eqe->data.port_module;
+	module_num = module_event_eqe->module;
+	module_status = module_event_eqe->module_status &
+			PORT_MODULE_EVENT_MODULE_STATUS_MASK;
+	error_type = module_event_eqe->error_type &
+		     PORT_MODULE_EVENT_ERROR_TYPE_MASK;
+
+	if (module_status < MLX5_MODULE_STATUS_ERROR) {
+		priv->pme_stats.status_counters[module_status - 1]++;
+	} else if (module_status == MLX5_MODULE_STATUS_ERROR) {
+		if (error_type >= MLX5_MODULE_EVENT_ERROR_UNKNOWN)
+			/* Unknown error type */
+			error_type = MLX5_MODULE_EVENT_ERROR_UNKNOWN;
+		priv->pme_stats.error_counters[error_type]++;
+	}
+
+	if (!printk_ratelimit())
+		return;
+
+	if (module_status < MLX5_MODULE_STATUS_ERROR)
+		mlx5_core_info(dev,
+			       "Port module event: module %u, %s\n",
+			       module_num, mlx5_pme_status[module_status - 1]);
+
+	else if (module_status == MLX5_MODULE_STATUS_ERROR)
+		mlx5_core_info(dev,
+			       "Port module event[error]: module %u, %s, %s\n",
+			       module_num, mlx5_pme_status[module_status - 1],
+			       mlx5_pme_error[error_type]);
+}

include/linux/mlx5/device.h

@@ -277,6 +277,7 @@ enum mlx5_event {
 	MLX5_EVENT_TYPE_INTERNAL_ERROR	   = 0x08,
 	MLX5_EVENT_TYPE_PORT_CHANGE	   = 0x09,
 	MLX5_EVENT_TYPE_GPIO_EVENT	   = 0x15,
+	MLX5_EVENT_TYPE_PORT_MODULE_EVENT  = 0x16,
 	MLX5_EVENT_TYPE_REMOTE_CONFIG	   = 0x19,
 
 	MLX5_EVENT_TYPE_DB_BF_CONGESTION   = 0x1a,
@@ -552,6 +553,15 @@ struct mlx5_eqe_vport_change {
 	__be32		rsvd1[6];
 } __packed;
 
+struct mlx5_eqe_port_module {
+	u8        reserved_at_0[1];
+	u8        module;
+	u8        reserved_at_2[1];
+	u8        module_status;
+	u8        reserved_at_4[2];
+	u8        error_type;
+} __packed;
+
 union ev_data {
 	__be32				raw[7];
 	struct mlx5_eqe_cmd		cmd;
@@ -565,6 +575,7 @@ union ev_data {
 	struct mlx5_eqe_page_req	req_pages;
 	struct mlx5_eqe_page_fault	page_fault;
 	struct mlx5_eqe_vport_change	vport_change;
+	struct mlx5_eqe_port_module	port_module;
 } __packed;
 
 struct mlx5_eqe {
@@ -1060,6 +1071,11 @@ enum {
 	MLX5_INFINIBAND_PORT_COUNTERS_GROUP   = 0x20,
 };
 
+enum {
+	MLX5_PCIE_PERFORMANCE_COUNTERS_GROUP       = 0x0,
+	MLX5_PCIE_TIMERS_AND_STATES_COUNTERS_GROUP = 0x2,
+};
+
 static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz)
 {
 	if (pkey_sz > MLX5_MAX_LOG_PKEY_TABLE)

include/linux/mlx5/driver.h

@@ -121,6 +121,7 @@ enum {
 	MLX5_REG_HOST_ENDIANNESS = 0x7004,
 	MLX5_REG_MCIA		 = 0x9014,
 	MLX5_REG_MLCR		 = 0x902b,
+	MLX5_REG_MPCNT		 = 0x9051,
 };
 
 enum {
@@ -208,7 +209,7 @@ struct mlx5_cmd_first {
 
 struct mlx5_cmd_msg {
 	struct list_head		list;
-	struct cache_ent	       *cache;
+	struct cmd_msg_cache	       *parent;
 	u32				len;
 	struct mlx5_cmd_first		first;
 	struct mlx5_cmd_mailbox	       *next;
@@ -228,17 +229,17 @@ struct mlx5_cmd_debug {
 	u16			outlen;
 };
 
-struct cache_ent {
+struct cmd_msg_cache {
 	/* protect block chain allocations
 	 */
 	spinlock_t		lock;
 	struct list_head	head;
+	unsigned int		max_inbox_size;
+	unsigned int		num_ent;
 };
 
-struct cmd_msg_cache {
-	struct cache_ent	large;
-	struct cache_ent	med;
-
+enum {
+	MLX5_NUM_COMMAND_CACHES = 5,
 };
 
 struct mlx5_cmd_stats {
@@ -281,7 +282,7 @@ struct mlx5_cmd {
 	struct mlx5_cmd_work_ent *ent_arr[MLX5_MAX_COMMANDS];
 	struct pci_pool *pool;
 	struct mlx5_cmd_debug dbg;
-	struct cmd_msg_cache cache;
+	struct cmd_msg_cache cache[MLX5_NUM_COMMAND_CACHES];
 	int checksum_disabled;
 	struct mlx5_cmd_stats stats[MLX5_CMD_OP_MAX];
 };
@@ -498,6 +499,31 @@ struct mlx5_rl_table {
 	struct mlx5_rl_entry   *rl_entry;
 };
 
+enum port_module_event_status_type {
+	MLX5_MODULE_STATUS_PLUGGED   = 0x1,
+	MLX5_MODULE_STATUS_UNPLUGGED = 0x2,
+	MLX5_MODULE_STATUS_ERROR     = 0x3,
+	MLX5_MODULE_STATUS_NUM       = 0x3,
+};
+
+enum  port_module_event_error_type {
+	MLX5_MODULE_EVENT_ERROR_POWER_BUDGET_EXCEEDED,
+	MLX5_MODULE_EVENT_ERROR_LONG_RANGE_FOR_NON_MLNX_CABLE_MODULE,
+	MLX5_MODULE_EVENT_ERROR_BUS_STUCK,
+	MLX5_MODULE_EVENT_ERROR_NO_EEPROM_RETRY_TIMEOUT,
+	MLX5_MODULE_EVENT_ERROR_ENFORCE_PART_NUMBER_LIST,
+	MLX5_MODULE_EVENT_ERROR_UNKNOWN_IDENTIFIER,
+	MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE,
+	MLX5_MODULE_EVENT_ERROR_BAD_CABLE,
+	MLX5_MODULE_EVENT_ERROR_UNKNOWN,
+	MLX5_MODULE_EVENT_ERROR_NUM,
+};
+
+struct mlx5_port_module_event_stats {
+	u64 status_counters[MLX5_MODULE_STATUS_NUM];
+	u64 error_counters[MLX5_MODULE_EVENT_ERROR_NUM];
+};
+
 struct mlx5_priv {
 	char			name[MLX5_MAX_NAME_LEN];
 	struct mlx5_eq_table	eq_table;
@@ -559,6 +585,8 @@ struct mlx5_priv {
 	unsigned long		pci_dev_data;
 	struct mlx5_fc_stats		fc_stats;
 	struct mlx5_rl_table            rl_table;
+
+	struct mlx5_port_module_event_stats  pme_stats;
 };
 
 enum mlx5_device_state {

include/linux/mlx5/mlx5_ifc.h

@@ -83,6 +83,7 @@ enum {
 	MLX5_CMD_OP_SET_HCA_CAP                   = 0x109,
 	MLX5_CMD_OP_QUERY_ISSI                    = 0x10a,
 	MLX5_CMD_OP_SET_ISSI                      = 0x10b,
+	MLX5_CMD_OP_SET_DRIVER_VERSION            = 0x10d,
 	MLX5_CMD_OP_CREATE_MKEY                   = 0x200,
 	MLX5_CMD_OP_QUERY_MKEY                    = 0x201,
 	MLX5_CMD_OP_DESTROY_MKEY                  = 0x202,
@@ -824,7 +825,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8	   early_vf_enable[0x1];
 	u8         reserved_at_1a9[0x2];
 	u8         local_ca_ack_delay[0x5];
-	u8         reserved_at_1af[0x2];
+	u8         port_module_event[0x1];
+	u8         reserved_at_1b0[0x1];
 	u8         ports_check[0x1];
 	u8         reserved_at_1b2[0x1];
 	u8         disable_link_up[0x1];
@@ -908,7 +910,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         log_pg_sz[0x8];
 
 	u8         bf[0x1];
-	u8         reserved_at_261[0x1];
+	u8         driver_version[0x1];
 	u8         pad_tx_eth_packet[0x1];
 	u8         reserved_at_263[0x8];
 	u8         log_bf_reg_size[0x5];
@@ -1755,6 +1757,80 @@ struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits {
 	u8         reserved_at_4c0[0x300];
 };
 
+struct mlx5_ifc_pcie_perf_cntrs_grp_data_layout_bits {
+	u8         life_time_counter_high[0x20];
+
+	u8         life_time_counter_low[0x20];
+
+	u8         rx_errors[0x20];
+
+	u8         tx_errors[0x20];
+
+	u8         l0_to_recovery_eieos[0x20];
+
+	u8         l0_to_recovery_ts[0x20];
+
+	u8         l0_to_recovery_framing[0x20];
+
+	u8         l0_to_recovery_retrain[0x20];
+
+	u8         crc_error_dllp[0x20];
+
+	u8         crc_error_tlp[0x20];
+
+	u8         reserved_at_140[0x680];
+};
+
+struct mlx5_ifc_pcie_tas_cntrs_grp_data_layout_bits {
+	u8         life_time_counter_high[0x20];
+
+	u8         life_time_counter_low[0x20];
+
+	u8         time_to_boot_image_start[0x20];
+
+	u8         time_to_link_image[0x20];
+
+	u8         calibration_time[0x20];
+
+	u8         time_to_first_perst[0x20];
+
+	u8         time_to_detect_state[0x20];
+
+	u8         time_to_l0[0x20];
+
+	u8         time_to_crs_en[0x20];
+
+	u8         time_to_plastic_image_start[0x20];
+
+	u8         time_to_iron_image_start[0x20];
+
+	u8         perst_handler[0x20];
+
+	u8         times_in_l1[0x20];
+
+	u8         times_in_l23[0x20];
+
+	u8         dl_down[0x20];
+
+	u8         config_cycle1usec[0x20];
+
+	u8         config_cycle2to7usec[0x20];
+
+	u8         config_cycle_8to15usec[0x20];
+
+	u8         config_cycle_16_to_63usec[0x20];
+
+	u8         config_cycle_64usec[0x20];
+
+	u8         correctable_err_msg_sent[0x20];
+
+	u8         non_fatal_err_msg_sent[0x20];
+
+	u8         fatal_err_msg_sent[0x20];
+
+	u8         reserved_at_2e0[0x4e0];
+};
+
 struct mlx5_ifc_cmd_inter_comp_event_bits {
 	u8         command_completion_vector[0x20];
 
@@ -2919,6 +2995,12 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits {
 	u8         reserved_at_0[0x7c0];
 };
 
+union mlx5_ifc_pcie_cntrs_grp_data_layout_auto_bits {
+	struct mlx5_ifc_pcie_perf_cntrs_grp_data_layout_bits pcie_perf_cntrs_grp_data_layout;
+	struct mlx5_ifc_pcie_tas_cntrs_grp_data_layout_bits pcie_tas_cntrs_grp_data_layout;
+	u8         reserved_at_0[0x7c0];
+};
+
 union mlx5_ifc_event_auto_bits {
 	struct mlx5_ifc_comp_event_bits comp_event;
 	struct mlx5_ifc_dct_events_bits dct_events;
@@ -4004,6 +4086,25 @@ struct mlx5_ifc_query_issi_in_bits {
 	u8         reserved_at_40[0x40];
 };
 
+struct mlx5_ifc_set_driver_version_out_bits {
+	u8         status[0x8];
+	u8         reserved_0[0x18];
+
+	u8         syndrome[0x20];
+	u8         reserved_1[0x40];
+};
+
+struct mlx5_ifc_set_driver_version_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_0[0x10];
+
+	u8         reserved_1[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_2[0x40];
+	u8         driver_version[64][0x8];
+};
+
 struct mlx5_ifc_query_hca_vport_pkey_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
@@ -7219,6 +7320,18 @@ struct mlx5_ifc_ppcnt_reg_bits {
 	union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set;
 };
 
+struct mlx5_ifc_mpcnt_reg_bits {
+	u8         reserved_at_0[0x8];
+	u8         pcie_index[0x8];
+	u8         reserved_at_10[0xa];
+	u8         grp[0x6];
+
+	u8         clr[0x1];
+	u8         reserved_at_21[0x1f];
+
+	union mlx5_ifc_pcie_cntrs_grp_data_layout_auto_bits counter_set;
+};
+
 struct mlx5_ifc_ppad_reg_bits {
 	u8         reserved_at_0[0x3];
 	u8         single_mac[0x1];
@@ -7824,6 +7937,7 @@ union mlx5_ifc_ports_control_registers_document_bits {
 	struct mlx5_ifc_pmtu_reg_bits pmtu_reg;
 	struct mlx5_ifc_ppad_reg_bits ppad_reg;
 	struct mlx5_ifc_ppcnt_reg_bits ppcnt_reg;
+	struct mlx5_ifc_mpcnt_reg_bits mpcnt_reg;
 	struct mlx5_ifc_pplm_reg_bits pplm_reg;
 	struct mlx5_ifc_pplr_reg_bits pplr_reg;
 	struct mlx5_ifc_ppsc_reg_bits ppsc_reg;

include/linux/mlx5/port.h

@@ -94,6 +94,9 @@ enum mlx5e_link_mode {
 
 #define MLX5E_PROT_MASK(link_mode) (1 << link_mode)
 
+#define PORT_MODULE_EVENT_MODULE_STATUS_MASK 0xF
+#define PORT_MODULE_EVENT_ERROR_TYPE_MASK         0xF
+
 int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps);
 int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys,
 			 int ptys_size, int proto_mask, u8 local_port);