netdev - [net-next v2 09/15] net/mlx5: Create FW devlink_health

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20190613203825.31049-10-saeedm@mellanox.com>
Date:   Thu, 13 Jun 2019 20:39:32 +0000
From:   Saeed Mahameed <saeedm@...lanox.com>
To:     "David S. Miller" <davem@...emloft.net>
CC:     "netdev@...r.kernel.org" <netdev@...r.kernel.org>,
        Jiri Pirko <jiri@...lanox.com>,
        Moshe Shemesh <moshe@...lanox.com>,
        Eran Ben Elisha <eranbe@...lanox.com>,
        Saeed Mahameed <saeedm@...lanox.com>
Subject: [net-next v2 09/15] net/mlx5: Create FW devlink_health_reporter

From: Moshe Shemesh <moshe@...lanox.com>

Create mlx5_devlink_health_reporter for FW reporter. The FW reporter
implements devlink_health_reporter diagnose callback.

The fw reporter diagnose command can be triggered any time by the user
to check current fw status.
In healthy status, it will return clear syndrome. Otherwise it will
return the syndrome and description of the error type.

Command example and output on healthy status:
$ devlink health diagnose pci/0000:82:00.0 reporter fw
Syndrome: 0

Command example and output on non healthy status:
$ devlink health diagnose pci/0000:82:00.0 reporter fw
Syndrome: 8 Description: unrecoverable hardware error

Signed-off-by: Moshe Shemesh <moshe@...lanox.com>
Signed-off-by: Eran Ben Elisha <eranbe@...lanox.com>
Signed-off-by: Saeed Mahameed <saeedm@...lanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/health.c  | 48 +++++++++++++++++++
 include/linux/mlx5/driver.h                   |  2 +
 2 files changed, 50 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index caf54bd7d538..973cc005ae60 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -388,6 +388,51 @@ static void print_health_info(struct mlx5_core_dev *dev)
 	mlx5_core_err(dev, "raw fw_ver 0x%08x\n", fw);
 }
 
+static int
+mlx5_fw_reporter_diagnose(struct devlink_health_reporter *reporter,
+			  struct devlink_fmsg *fmsg)
+{
+	struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter);
+	struct mlx5_core_health *health = &dev->priv.health;
+	struct health_buffer __iomem *h = health->health;
+	u8 synd;
+	int err;
+
+	synd = ioread8(&h->synd);
+	err = devlink_fmsg_u8_pair_put(fmsg, "Syndrome", synd);
+	if (err || !synd)
+		return err;
+	return devlink_fmsg_string_pair_put(fmsg, "Description", hsynd_str(synd));
+}
+
+static const struct devlink_health_reporter_ops mlx5_fw_reporter_ops = {
+		.name = "fw",
+		.diagnose = mlx5_fw_reporter_diagnose,
+};
+
+static void mlx5_fw_reporter_create(struct mlx5_core_dev *dev)
+{
+	struct mlx5_core_health *health = &dev->priv.health;
+	struct devlink *devlink = priv_to_devlink(dev);
+
+	health->fw_reporter =
+		devlink_health_reporter_create(devlink, &mlx5_fw_reporter_ops,
+					       0, false, dev);
+	if (IS_ERR(health->fw_reporter))
+		mlx5_core_warn(dev, "Failed to create fw reporter, err = %ld\n",
+			       PTR_ERR(health->fw_reporter));
+}
+
+static void mlx5_fw_reporter_destroy(struct mlx5_core_dev *dev)
+{
+	struct mlx5_core_health *health = &dev->priv.health;
+
+	if (IS_ERR_OR_NULL(health->fw_reporter))
+		return;
+
+	devlink_health_reporter_destroy(health->fw_reporter);
+}
+
 static unsigned long get_next_poll_jiffies(void)
 {
 	unsigned long next;
@@ -498,6 +543,7 @@ void mlx5_health_cleanup(struct mlx5_core_dev *dev)
 	struct mlx5_core_health *health = &dev->priv.health;
 
 	destroy_workqueue(health->wq);
+	mlx5_fw_reporter_destroy(dev);
 }
 
 int mlx5_health_init(struct mlx5_core_dev *dev)
@@ -519,5 +565,7 @@ int mlx5_health_init(struct mlx5_core_dev *dev)
 	spin_lock_init(&health->wq_lock);
 	INIT_WORK(&health->work, health_care);
 
+	mlx5_fw_reporter_create(dev);
+
 	return 0;
 }
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 89205b6cc7ef..8d5d065d1aa6 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -53,6 +53,7 @@
 #include <linux/mlx5/eq.h>
 #include <linux/timecounter.h>
 #include <linux/ptp_clock_kernel.h>
+#include <net/devlink.h>
 
 enum {
 	MLX5_BOARD_ID_LEN = 64,
@@ -443,6 +444,7 @@ struct mlx5_core_health {
 	unsigned long			flags;
 	struct work_struct		work;
 	struct delayed_work		recover_work;
+	struct devlink_health_reporter *fw_reporter;
 };
 
 struct mlx5_qp_table {
-- 
2.21.0