Skip to content

Commit

Permalink
net/mlx5: Rework handling of port module events
Browse files Browse the repository at this point in the history 
Add explicit HW defined error values. For simplicity, keep counters for all
statuses starting from 0, although currently status=0 is not used.

Additionally, when HW signals an unexpected cable status, it is reported
now rather than ignored. And status counter is now updated on errors.

Signed-off-by: Mikhael Goikhman <[email protected]>
Signed-off-by: Saeed Mahameed <[email protected]>
  • Loading branch information
Mikhael Goikhman authored and Saeed Mahameed committed Dec 10, 2018
1 parent 7300375 commit c2fb3db
Show file tree
Hide file tree
Showing 3 changed files with 65 additions and 45 deletions.
8 changes: 4 additions & 4 deletions drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1087,13 +1087,13 @@ static void mlx5e_grp_per_prio_update_stats(struct mlx5e_priv *priv)
}

static const struct counter_desc mlx5e_pme_status_desc[] = {
{ "module_unplug", 8 },
{ "module_unplug", sizeof(u64) * MLX5_MODULE_STATUS_UNPLUGGED },
};

static const struct counter_desc mlx5e_pme_error_desc[] = {
{ "module_bus_stuck", 16 }, /* bus stuck (I2C or data shorted) */
{ "module_high_temp", 48 }, /* high temperature */
{ "module_bad_shorted", 56 }, /* bad or shorted cable/module */
{ "module_bus_stuck", sizeof(u64) * MLX5_MODULE_EVENT_ERROR_BUS_STUCK },
{ "module_high_temp", sizeof(u64) * MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE },
{ "module_bad_shorted", sizeof(u64) * MLX5_MODULE_EVENT_ERROR_BAD_CABLE },
};

#define NUM_PME_STATUS_STATS ARRAY_SIZE(mlx5e_pme_status_desc)
Expand Down
83 changes: 52 additions & 31 deletions drivers/net/ethernet/mellanox/mlx5/core/events.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -157,23 +157,43 @@ static int temp_warn(struct notifier_block *nb, unsigned long type, void *data)
}

/* MLX5_EVENT_TYPE_PORT_MODULE_EVENT */
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_status_to_string(enum port_module_event_status_type status)
{
switch (status) {
case MLX5_MODULE_STATUS_PLUGGED:
return "Cable plugged";
case MLX5_MODULE_STATUS_UNPLUGGED:
return "Cable unplugged";
case MLX5_MODULE_STATUS_ERROR:
return "Cable error";
default:
return "Unknown status";
}
}

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",
};
static const char *mlx5_pme_error_to_string(enum port_module_event_error_type error)
{
switch (error) {
case MLX5_MODULE_EVENT_ERROR_POWER_BUDGET_EXCEEDED:
return "Power budget exceeded";
case MLX5_MODULE_EVENT_ERROR_LONG_RANGE_FOR_NON_MLNX:
return "Long Range for non MLNX cable";
case MLX5_MODULE_EVENT_ERROR_BUS_STUCK:
return "Bus stuck (I2C or data shorted)";
case MLX5_MODULE_EVENT_ERROR_NO_EEPROM_RETRY_TIMEOUT:
return "No EEPROM/retry timeout";
case MLX5_MODULE_EVENT_ERROR_ENFORCE_PART_NUMBER_LIST:
return "Enforce part number list";
case MLX5_MODULE_EVENT_ERROR_UNKNOWN_IDENTIFIER:
return "Unknown identifier";
case MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE:
return "High Temperature";
case MLX5_MODULE_EVENT_ERROR_BAD_CABLE:
return "Bad or shorted cable/module";
default:
return "Unknown error";
}
}

/* type == MLX5_EVENT_TYPE_PORT_MODULE_EVENT */
static int port_module(struct notifier_block *nb, unsigned long type, void *data)
Expand All @@ -185,6 +205,7 @@ static int port_module(struct notifier_block *nb, unsigned long type, void *data
enum port_module_event_status_type module_status;
enum port_module_event_error_type error_type;
struct mlx5_eqe_port_module *module_event_eqe;
const char *status_str, *error_str;
u8 module_num;

module_event_eqe = &eqe->data.port_module;
Expand All @@ -193,28 +214,28 @@ static int port_module(struct notifier_block *nb, unsigned long type, void *data
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) {
events->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;
events->pme_stats.error_counters[error_type]++;

if (module_status < MLX5_MODULE_STATUS_NUM)
events->pme_stats.status_counters[module_status]++;
status_str = mlx5_pme_status_to_string(module_status);

if (module_status == MLX5_MODULE_STATUS_ERROR) {
if (error_type < MLX5_MODULE_EVENT_ERROR_NUM)
events->pme_stats.error_counters[error_type]++;
error_str = mlx5_pme_error_to_string(error_type);
}

if (!printk_ratelimit())
return NOTIFY_OK;

if (module_status < MLX5_MODULE_STATUS_ERROR)
if (module_status == MLX5_MODULE_STATUS_ERROR)
mlx5_core_err(events->dev,
"Port module event[error]: module %u, %s, %s\n",
module_num, status_str, error_str);
else
mlx5_core_info(events->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(events->dev,
"Port module event[error]: module %u, %s, %s\n",
module_num, mlx5_pme_status[module_status - 1],
mlx5_pme_error[error_type]);
module_num, status_str);

return NOTIFY_OK;
}
Expand Down
19 changes: 9 additions & 10 deletions drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
View file
Original file line number Diff line number Diff line change
Expand Up @@ -51,19 +51,18 @@ 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,
MLX5_MODULE_STATUS_NUM,
};

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_POWER_BUDGET_EXCEEDED = 0x0,
MLX5_MODULE_EVENT_ERROR_LONG_RANGE_FOR_NON_MLNX = 0x1,
MLX5_MODULE_EVENT_ERROR_BUS_STUCK = 0x2,
MLX5_MODULE_EVENT_ERROR_NO_EEPROM_RETRY_TIMEOUT = 0x3,
MLX5_MODULE_EVENT_ERROR_ENFORCE_PART_NUMBER_LIST = 0x4,
MLX5_MODULE_EVENT_ERROR_UNKNOWN_IDENTIFIER = 0x5,
MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE = 0x6,
MLX5_MODULE_EVENT_ERROR_BAD_CABLE = 0x7,
MLX5_MODULE_EVENT_ERROR_NUM,
};

Expand Down

0 comments on commit c2fb3db

Please sign in to comment.