[SRU][N:linux-bluefield][PATCH v1 3/4] net/mlx5: Expose crr in health buffer

Stav Aviram saviram at nvidia.com
Mon Oct 6 09:40:47 UTC 2025


From: Shahar Shitrit <shshitrit at nvidia.com>

BugLink: https://bugs.launchpad.net/bugs/2126876

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 at nvidia.com>
Reviewed-by: Moshe Shemesh <moshe at nvidia.com>
Signed-off-by: Tariq Toukan <tariqt at nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski at linux.intel.com>
Signed-off-by: David S. Miller <davem at davemloft.net>
(cherry picked from commit 63f26199721fdf9bf6be74c8daf3df4f6e7e80ea)
Signed-off-by: Stav Aviram <saviram at nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 2cdcafff6278..6bcd943074ed 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -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
-- 
2.38.1




More information about the kernel-team mailing list