net/mlx5: Expose crr in health buffer

Expose crr bit in struct health buffer. When set, it indicates that
the error cannot be recovered without flow involving a cold reset.
Add its value to the health buffer info log.

Signed-off-by: Shahar Shitrit <shshitrit@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Shahar Shitrit
2025-02-26 14:25:42 +02:00
committed by David S. Miller
parent 6bdce277a3
commit 63f2619972

View File

@@ -96,6 +96,11 @@ static int mlx5_health_get_rfr(u8 rfr_severity)
return rfr_severity >> MLX5_RFR_BIT_OFFSET;
}
static int mlx5_health_get_crr(u8 rfr_severity)
{
return (rfr_severity >> MLX5_CRR_BIT_OFFSET) & 0x01;
}
static bool sensor_fw_synd_rfr(struct mlx5_core_dev *dev)
{
struct mlx5_core_health *health = &dev->priv.health;
@@ -442,12 +447,15 @@ static void print_health_info(struct mlx5_core_dev *dev)
mlx5_log(dev, severity, "time %u\n", ioread32be(&h->time));
mlx5_log(dev, severity, "hw_id 0x%08x\n", ioread32be(&h->hw_id));
mlx5_log(dev, severity, "rfr %d\n", mlx5_health_get_rfr(rfr_severity));
mlx5_log(dev, severity, "crr %d\n", mlx5_health_get_crr(rfr_severity));
mlx5_log(dev, severity, "severity %d (%s)\n", severity, mlx5_loglevel_str(severity));
mlx5_log(dev, severity, "irisc_index %d\n", ioread8(&h->irisc_index));
mlx5_log(dev, severity, "synd 0x%x: %s\n", ioread8(&h->synd),
hsynd_str(ioread8(&h->synd)));
mlx5_log(dev, severity, "ext_synd 0x%04x\n", ioread16be(&h->ext_synd));
mlx5_log(dev, severity, "raw fw_ver 0x%08x\n", ioread32be(&h->fw_ver));
if (mlx5_health_get_crr(rfr_severity))
mlx5_core_warn(dev, "Cold reset is required\n");
}
static int