Merge branch 'mlx5-new-device-events'

Saeed Mahameed says:

====================
Mellanox, mlx5 new device events

The following series is for mlx5-next tree [1], it adds the support of two
new device events, from Ilan Tayari:

1. High temperature warnings.
2. FPGA QP error event.

In case of no objection this series will be applied to mlx5-next tree
and will be sent later as a pull request to both rdma and net trees.

[1] https://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux.git/log/?h=mlx5-next

v1->v2:
  - improve commit message of the FPGA QP error event patch.
====================
Acked-by: NDoug Ledford <dledford@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

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

@@ -144,6 +144,8 @@ static const char *eqe_type_str(u8 type)
 		return "MLX5_EVENT_TYPE_GPIO_EVENT";
 	case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
 		return "MLX5_EVENT_TYPE_PORT_MODULE_EVENT";
+	case MLX5_EVENT_TYPE_TEMP_WARN_EVENT:
+		return "MLX5_EVENT_TYPE_TEMP_WARN_EVENT";
 	case MLX5_EVENT_TYPE_REMOTE_CONFIG:
 		return "MLX5_EVENT_TYPE_REMOTE_CONFIG";
 	case MLX5_EVENT_TYPE_DB_BF_CONGESTION:
@@ -162,6 +164,8 @@ static const char *eqe_type_str(u8 type)
 		return "MLX5_EVENT_TYPE_NIC_VPORT_CHANGE";
 	case MLX5_EVENT_TYPE_FPGA_ERROR:
 		return "MLX5_EVENT_TYPE_FPGA_ERROR";
+	case MLX5_EVENT_TYPE_FPGA_QP_ERROR:
+		return "MLX5_EVENT_TYPE_FPGA_QP_ERROR";
 	case MLX5_EVENT_TYPE_GENERAL_EVENT:
 		return "MLX5_EVENT_TYPE_GENERAL_EVENT";
 	default:
@@ -396,6 +400,20 @@ static void general_event_handler(struct mlx5_core_dev *dev,
 	}
 }
 
+static void mlx5_temp_warning_event(struct mlx5_core_dev *dev,
+				    struct mlx5_eqe *eqe)
+{
+	u64 value_lsb;
+	u64 value_msb;
+
+	value_lsb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_lsb);
+	value_msb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_msb);
+
+	mlx5_core_warn(dev,
+		       "High temperature on sensors with bit set %llx %llx",
+		       value_msb, value_lsb);
+}
+
 /* caller must eventually call mlx5_cq_put on the returned cq */
 static struct mlx5_core_cq *mlx5_eq_cq_get(struct mlx5_eq *eq, u32 cqn)
 {
@@ -547,9 +565,14 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
 			break;
 
 		case MLX5_EVENT_TYPE_FPGA_ERROR:
+		case MLX5_EVENT_TYPE_FPGA_QP_ERROR:
 			mlx5_fpga_event(dev, eqe->type, &eqe->data.raw);
 			break;
 
+		case MLX5_EVENT_TYPE_TEMP_WARN_EVENT:
+			mlx5_temp_warning_event(dev, eqe);
+			break;
+
 		case MLX5_EVENT_TYPE_GENERAL_EVENT:
 			general_event_handler(dev, eqe);
 			break;
@@ -822,10 +845,13 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev)
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_PPS_EVENT);
 
 	if (MLX5_CAP_GEN(dev, fpga))
-		async_event_mask |= (1ull << MLX5_EVENT_TYPE_FPGA_ERROR);
+		async_event_mask |= (1ull << MLX5_EVENT_TYPE_FPGA_ERROR) |
+				    (1ull << MLX5_EVENT_TYPE_FPGA_QP_ERROR);
 	if (MLX5_CAP_GEN_MAX(dev, dct))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_DCT_DRAINED);
 
+	if (MLX5_CAP_GEN(dev, temp_warn_event))
+		async_event_mask |= (1ull << MLX5_EVENT_TYPE_TEMP_WARN_EVENT);
 
 	err = mlx5_create_map_eq(dev, &table->cmd_eq, MLX5_EQ_VEC_CMD,
 				 MLX5_NUM_CMD_EQE, 1ull << MLX5_EVENT_TYPE_CMD,

include/linux/mlx5/device.h

@@ -314,6 +314,7 @@ enum mlx5_event {
 	MLX5_EVENT_TYPE_PORT_CHANGE	   = 0x09,
 	MLX5_EVENT_TYPE_GPIO_EVENT	   = 0x15,
 	MLX5_EVENT_TYPE_PORT_MODULE_EVENT  = 0x16,
+	MLX5_EVENT_TYPE_TEMP_WARN_EVENT    = 0x17,
 	MLX5_EVENT_TYPE_REMOTE_CONFIG	   = 0x19,
 	MLX5_EVENT_TYPE_GENERAL_EVENT	   = 0x22,
 	MLX5_EVENT_TYPE_PPS_EVENT          = 0x25,
@@ -330,6 +331,7 @@ enum mlx5_event {
 	MLX5_EVENT_TYPE_DCT_DRAINED        = 0x1c,
 
 	MLX5_EVENT_TYPE_FPGA_ERROR         = 0x20,
+	MLX5_EVENT_TYPE_FPGA_QP_ERROR      = 0x21,
 };
 
 enum {
@@ -626,6 +628,11 @@ struct mlx5_eqe_dct {
 	__be32  dctn;
 };
 
+struct mlx5_eqe_temp_warning {
+	__be64 sensor_warning_msb;
+	__be64 sensor_warning_lsb;
+} __packed;
+
 union ev_data {
 	__be32				raw[7];
 	struct mlx5_eqe_cmd		cmd;
@@ -642,6 +649,7 @@ union ev_data {
 	struct mlx5_eqe_port_module	port_module;
 	struct mlx5_eqe_pps		pps;
 	struct mlx5_eqe_dct             dct;
+	struct mlx5_eqe_temp_warning	temp_warning;
 } __packed;
 
 struct mlx5_eqe {

include/linux/mlx5/mlx5_ifc.h

@@ -60,6 +60,7 @@ enum {
 	MLX5_EVENT_TYPE_CODING_COMMAND_INTERFACE_COMPLETION        = 0xa,
 	MLX5_EVENT_TYPE_CODING_PAGE_REQUEST                        = 0xb,
 	MLX5_EVENT_TYPE_CODING_FPGA_ERROR                          = 0x20,
+	MLX5_EVENT_TYPE_CODING_FPGA_QP_ERROR                       = 0x21
 };
 
 enum {
@@ -912,7 +913,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         log_max_msg[0x5];
 	u8         reserved_at_1c8[0x4];
 	u8         max_tc[0x4];
-	u8         reserved_at_1d0[0x1];
+	u8         temp_warn_event[0x1];
 	u8         dcbx[0x1];
 	u8         general_notification_event[0x1];
 	u8         reserved_at_1d3[0x2];

include/linux/mlx5/mlx5_ifc_fpga.h

@@ -470,6 +470,22 @@ struct mlx5_ifc_ipsec_counters_bits {
 	u8         dropped_cmd[0x40];
 };
 
+enum {
+	MLX5_FPGA_QP_ERROR_EVENT_SYNDROME_RETRY_COUNTER_EXPIRED  = 0x1,
+	MLX5_FPGA_QP_ERROR_EVENT_SYNDROME_RNR_EXPIRED            = 0x2,
+};
+
+struct mlx5_ifc_fpga_qp_error_event_bits {
+	u8         reserved_at_0[0x40];
+
+	u8         reserved_at_40[0x18];
+	u8         syndrome[0x8];
+
+	u8         reserved_at_60[0x60];
+
+	u8         reserved_at_c0[0x8];
+	u8         fpga_qpn[0x18];
+};
 enum mlx5_ifc_fpga_ipsec_response_syndrome {
 	MLX5_FPGA_IPSEC_RESPONSE_SUCCESS = 0,
 	MLX5_FPGA_IPSEC_RESPONSE_ILLEGAL_REQUEST = 1,