From: Moshe Shemesh <mo...@mellanox.com>
Add support of dump callback for mlx5 FW fatal reporter.
The FW fatal dump use cr-dump functionality to gather cr-space data for
debug. The cr-dump uses vsc interface which is valid even if the FW
command interface is not functional, which is the case in most FW fatal
errors.
The cr-dump is stored as a memory region snapshot to ease read by
address.
Command example and output:
$ devlink health dump show pci/0000:82:00.0 reporter fw_fatal
devlink_region_name: cr-space snapshot_id: 1
$ devlink region read pci/0000:82:00.0/cr-space snapshot 1 address 983064
length 8
00000000000f0018 e1 03 00 00 fb ae a9 3f
Signed-off-by: Moshe Shemesh <mo...@mellanox.com>
Signed-off-by: Saeed Mahameed <sae...@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/health.c | 39 +++++++++++++++++++
1 file changed, 39 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c
b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index e64f0e32cd67..5271c88ef64c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -547,9 +547,48 @@ mlx5_fw_fatal_reporter_recover(struct
devlink_health_reporter *reporter,
return mlx5_health_care(dev);
}
+static int
+mlx5_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter,
+ struct devlink_fmsg *fmsg, void *priv_ctx)
+{
+ struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter);
+ char crdump_region[20];
+ u32 snapshot_id;
+ int err;
+
+ if (!mlx5_core_is_pf(dev)) {
+ mlx5_core_err(dev, "Only PF is permitted run FW fatal dump\n");
+ return -EPERM;
+ }
+
+ err = mlx5_crdump_collect(dev, crdump_region, &snapshot_id);
+ if (err)
+ return err;
+
+ if (priv_ctx) {
+ struct mlx5_fw_reporter_ctx *fw_reporter_ctx = priv_ctx;
+
+ err = mlx5_fw_reporter_ctx_pairs_put(fmsg, fw_reporter_ctx);
+ if (err)
+ return err;
+ }
+
+ err = devlink_fmsg_string_pair_put(fmsg, "devlink_region_name",
+ crdump_region);
+ if (err)
+ return err;
+
+ err = devlink_fmsg_u32_pair_put(fmsg, "snapshot_id", snapshot_id);
+ if (err)
+ return err;
+
+ return 0;
+}
+
static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = {
.name = "fw_fatal",
.recover = mlx5_fw_fatal_reporter_recover,
+ .dump = mlx5_fw_fatal_reporter_dump,
};
#define MLX5_REPORTER_FW_GRACEFUL_PERIOD 1200000
--
2.20.1
