net/mlx5: Lag, add debugfs to query hardware lag state

Lag state has become very complicated with many modes, flags, types and
port selections methods and future work will add additional features.

Add a debugfs to query the current lag state. A new directory named "lag"
will be created under the mlx5 debugfs directory. As the driver has
debugfs per pci function the location will be: <debugfs>/mlx5/<BDF>/lag

For example:
/sys/kernel/debug/mlx5/0000:08:00.0/lag

The following files are exposed:

- state: Returns "active" or "disabled". If "active" it means hardware
         lag is active.

- members: Returns the BDFs of all the members of lag object.

- type: Returns the type of the lag currently configured. Valid only
	if hardware lag is active.
	* "roce" - Members are bare metal PFs.
	* "switchdev" - Members are in switchdev mode.
	* "multipath" - ECMP offloads.

- port_sel_mode: Returns the egress port selection method, valid
		 only if hardware lag is active.
		 * "queue_affinity" - Egress port is selected by
		   the QP/SQ affinity.
		 * "hash" - Egress port is selected by hash done on
		   each packet. Controlled by: xmit_hash_policy of the
		   bond device.
- flags: Returns flags that are specific per lag @type. Valid only if
	 hardware lag is active.
	 * "shared_fdb" - "on" or "off", if "on" single FDB is used.

- mapping: Returns the mapping which is used to select egress port.
	   Valid only if hardware lag is active.
	   If @port_sel_mode is "hash" returns the active egress ports.
	   The hash result will select only active ports.
	   if @port_sel_mode is "queue_affinity" returns the mapping
	   between the configured port affinity of the QP/SQ and actual
	   egress port. For example:
	   * 1:1 - Mapping means if the configured affinity is port 1
	           traffic will egress via port 1.
	   * 1:2 - Mapping means if the configured affinity is port 1
		   traffic will egress via port 2. This can happen
		   if port 1 is down or in active/backup mode and port 1
		   is backup.
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

drivers/net/ethernet/mellanox/mlx5/core/Makefile

@@ -14,7 +14,7 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o alloc.o port.o mr.o pd.o \
 		transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \
-		fs_counters.o fs_ft_pool.o rl.o lag/lag.o dev.o events.o wq.o lib/gid.o \
+		fs_counters.o fs_ft_pool.o rl.o lag/debugfs.o lag/lag.o dev.o events.o wq.o lib/gid.o \
 		lib/devcom.o lib/pci_vsc.o lib/dm.o lib/fs_ttc.o diag/fs_tracepoint.o \
 		diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o \
 		fw_reset.o qos.o lib/tout.o

drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c

+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include "lag.h"
+
+static char *get_str_mode_type(struct mlx5_lag *ldev)
+{
+	if (ldev->flags & MLX5_LAG_FLAG_ROCE)
+		return "roce";
+	if (ldev->flags & MLX5_LAG_FLAG_SRIOV)
+		return "switchdev";
+	if (ldev->flags & MLX5_LAG_FLAG_MULTIPATH)
+		return "multipath";
+
+	return NULL;
+}
+
+static int type_show(struct seq_file *file, void *priv)
+{
+	struct mlx5_core_dev *dev = file->private;
+	struct mlx5_lag *ldev;
+	char *mode = NULL;
+
+	ldev = dev->priv.lag;
+	mutex_lock(&ldev->lock);
+	if (__mlx5_lag_is_active(ldev))
+		mode = get_str_mode_type(ldev);
+	mutex_unlock(&ldev->lock);
+	if (!mode)
+		return -EINVAL;
+	seq_printf(file, "%s\n", mode);
+
+	return 0;
+}
+
+static int port_sel_mode_show(struct seq_file *file, void *priv)
+{
+	struct mlx5_core_dev *dev = file->private;
+	struct mlx5_lag *ldev;
+	int ret = 0;
+	char *mode;
+
+	ldev = dev->priv.lag;
+	mutex_lock(&ldev->lock);
+	if (__mlx5_lag_is_active(ldev))
+		mode = get_str_port_sel_mode(ldev->flags);
+	else
+		ret = -EINVAL;
+	mutex_unlock(&ldev->lock);
+	if (ret || !mode)
+		return ret;
+
+	seq_printf(file, "%s\n", mode);
+	return 0;
+}
+
+static int state_show(struct seq_file *file, void *priv)
+{
+	struct mlx5_core_dev *dev = file->private;
+	struct mlx5_lag *ldev;
+	bool active;
+
+	ldev = dev->priv.lag;
+	mutex_lock(&ldev->lock);
+	active = __mlx5_lag_is_active(ldev);
+	mutex_unlock(&ldev->lock);
+	seq_printf(file, "%s\n", active ? "active" : "disabled");
+	return 0;
+}
+
+static int flags_show(struct seq_file *file, void *priv)
+{
+	struct mlx5_core_dev *dev = file->private;
+	struct mlx5_lag *ldev;
+	bool shared_fdb;
+	bool lag_active;
+
+	ldev = dev->priv.lag;
+	mutex_lock(&ldev->lock);
+	lag_active = __mlx5_lag_is_active(ldev);
+	if (lag_active)
+		shared_fdb = ldev->shared_fdb;
+
+	mutex_unlock(&ldev->lock);
+	if (!lag_active)
+		return -EINVAL;
+
+	seq_printf(file, "%s:%s\n", "shared_fdb", shared_fdb ? "on" : "off");
+	return 0;
+}
+
+static int mapping_show(struct seq_file *file, void *priv)
+{
+	struct mlx5_core_dev *dev = file->private;
+	u8 ports[MLX5_MAX_PORTS] = {};
+	struct mlx5_lag *ldev;
+	bool hash = false;
+	bool lag_active;
+	int num_ports;
+	int i;
+
+	ldev = dev->priv.lag;
+	mutex_lock(&ldev->lock);
+	lag_active = __mlx5_lag_is_active(ldev);
+	if (lag_active) {
+		if (ldev->flags & MLX5_LAG_FLAG_HASH_BASED) {
+			mlx5_infer_tx_enabled(&ldev->tracker, ldev->ports, ports,
+					      &num_ports);
+			hash = true;
+		} else {
+			for (i = 0; i < ldev->ports; i++)
+				ports[i] = ldev->v2p_map[i];
+			num_ports = ldev->ports;
+		}
+	}
+	mutex_unlock(&ldev->lock);
+	if (!lag_active)
+		return -EINVAL;
+
+	for (i = 0; i < num_ports; i++) {
+		if (hash)
+			seq_printf(file, "%d\n", ports[i] + 1);
+		else
+			seq_printf(file, "%d:%d\n", i + 1, ports[i]);
+	}
+
+	return 0;
+}
+
+static int members_show(struct seq_file *file, void *priv)
+{
+	struct mlx5_core_dev *dev = file->private;
+	struct mlx5_lag *ldev;
+	int i;
+
+	ldev = dev->priv.lag;
+	mutex_lock(&ldev->lock);
+	for (i = 0; i < ldev->ports; i++) {
+		if (!ldev->pf[i].dev)
+			continue;
+		seq_printf(file, "%s\n", dev_name(ldev->pf[i].dev->device));
+	}
+	mutex_unlock(&ldev->lock);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(type);
+DEFINE_SHOW_ATTRIBUTE(port_sel_mode);
+DEFINE_SHOW_ATTRIBUTE(state);
+DEFINE_SHOW_ATTRIBUTE(flags);
+DEFINE_SHOW_ATTRIBUTE(mapping);
+DEFINE_SHOW_ATTRIBUTE(members);
+
+void mlx5_ldev_add_debugfs(struct mlx5_core_dev *dev)
+{
+	struct dentry *dbg;
+
+	dbg = debugfs_create_dir("lag", mlx5_debugfs_get_dev_root(dev));
+	dev->priv.dbg.lag_debugfs = dbg;
+
+	debugfs_create_file("type", 0444, dbg, dev, &type_fops);
+	debugfs_create_file("port_sel_mode", 0444, dbg, dev, &port_sel_mode_fops);
+	debugfs_create_file("state", 0444, dbg, dev, &state_fops);
+	debugfs_create_file("flags", 0444, dbg, dev, &flags_fops);
+	debugfs_create_file("mapping", 0444, dbg, dev, &mapping_fops);
+	debugfs_create_file("members", 0444, dbg, dev, &members_fops);
+}
+
+void mlx5_ldev_remove_debugfs(struct dentry *dbg)
+{
+	debugfs_remove_recursive(dbg);
+}

drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c

@@ -120,8 +120,8 @@ static void mlx5_infer_tx_disabled(struct lag_tracker *tracker, u8 num_ports,
 	}
 }
 
-static void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports,
-				  u8 *ports, int *num_enabled)
+void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports,
+			   u8 *ports, int *num_enabled)
 {
 	int i;
 
@@ -454,7 +454,7 @@ static int mlx5_lag_set_port_sel_mode(struct mlx5_lag *ldev,
 	return mlx5_lag_set_port_sel_mode_offloads(ldev, tracker, flags);
 }
 
-static char *get_str_port_sel_mode(u8 flags)
+char *get_str_port_sel_mode(u8 flags)
 {
 	if (flags &  MLX5_LAG_FLAG_HASH_BASED)
 		return "hash";
@@ -1106,6 +1106,10 @@ void mlx5_lag_remove_mdev(struct mlx5_core_dev *dev)
 	if (!ldev)
 		return;
 
+	/* mdev is being removed, might as well remove debugfs
+	 * as early as possible.
+	 */
+	mlx5_ldev_remove_debugfs(dev->priv.dbg.lag_debugfs);
 recheck:
 	mutex_lock(&ldev->lock);
 	if (ldev->mode_changes_in_progress) {
@@ -1137,6 +1141,7 @@ void mlx5_lag_add_mdev(struct mlx5_core_dev *dev)
 		msleep(100);
 		goto recheck;
 	}
+	mlx5_ldev_add_debugfs(dev);
 }
 
 void mlx5_lag_remove_netdev(struct mlx5_core_dev *dev,

drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h

@@ -4,6 +4,8 @@
 #ifndef __MLX5_LAG_H__
 #define __MLX5_LAG_H__
 
+#include <linux/debugfs.h>
+
 #define MLX5_LAG_MAX_HASH_BUCKETS 16
 #include "mlx5_core.h"
 #include "mp.h"
@@ -90,4 +92,11 @@ int mlx5_activate_lag(struct mlx5_lag *ldev,
 int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
 				struct net_device *ndev);
 
+char *get_str_port_sel_mode(u8 flags);
+void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports,
+			   u8 *ports, int *num_enabled);
+
+void mlx5_ldev_add_debugfs(struct mlx5_core_dev *dev);
+void mlx5_ldev_remove_debugfs(struct dentry *dbg);
+
 #endif /* __MLX5_LAG_H__ */

include/linux/mlx5/driver.h

@@ -558,6 +558,7 @@ struct mlx5_debugfs_entries {
 	struct dentry *cq_debugfs;
 	struct dentry *cmdif_debugfs;
 	struct dentry *pages_debugfs;
+	struct dentry *lag_debugfs;
 };
 
 struct mlx5_ft_pool;