[PATCH net-next] net: mana: Expose hardware diagnostic info via debugfs

[PATCH net-next] net: mana: Expose hardware diagnostic info via debugfs

[Erni Sri Satya Vennela]

Add debugfs entries to expose hardware configuration and diagnostic
information that aids in debugging driver initialization and runtime
operations without adding noise to dmesg.

Device-level entries (under /sys/kernel/debug/mana/<slot>/):
  - num_msix_usable, max_num_queues: Max resources from hardware
  - gdma_protocol_ver, pf_cap_flags1: VF version negotiation results
  - num_vports, bm_hostmode: Device configuration

  - port_handle: Hardware vPort handle
  - max_sq, max_rq: Max queues from vPort config
  - indir_table_sz: Indirection table size
  - steer_rx, steer_rss, steer_update_tab, steer_cqe_coalescing:
    Last applied steering configuration parameters

Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
---
 .../net/ethernet/microsoft/mana/gdma_main.c   | 12 +++++++
 drivers/net/ethernet/microsoft/mana/mana_en.c | 31 +++++++++++++++++++
 include/net/mana/gdma.h                       |  1 +
 include/net/mana/mana.h                       |  8 +++++
 4 files changed, 52 insertions(+)

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 0055c231acf6..2ba8d224fd26 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -152,6 +152,11 @@ static int mana_gd_query_max_resources(struct pci_dev *pdev)
 	if (gc->max_num_queues > gc->num_msix_usable - 1)
 		gc->max_num_queues = gc->num_msix_usable - 1;
 
+	debugfs_create_u32("num_msix_usable", 0400, gc->mana_pci_debugfs,
+			   &gc->num_msix_usable);
+	debugfs_create_u32("max_num_queues", 0400, gc->mana_pci_debugfs,
+			   &gc->max_num_queues);
+
 	return 0;
 }
 
@@ -1221,6 +1226,13 @@ int mana_gd_verify_vf_version(struct pci_dev *pdev)
 		return err ? err : -EPROTO;
 	}
 	gc->pf_cap_flags1 = resp.pf_cap_flags1;
+	gc->gdma_protocol_ver = resp.gdma_protocol_ver;
+
+	debugfs_create_x64("gdma_protocol_ver", 0400, gc->mana_pci_debugfs,
+			   &gc->gdma_protocol_ver);
+	debugfs_create_x64("pf_cap_flags1", 0400, gc->mana_pci_debugfs,
+			   &gc->pf_cap_flags1);
+
 	if (resp.pf_cap_flags1 & GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG) {
 		err = mana_gd_query_hwc_timeout(pdev, &hwc->hwc_timeout);
 		if (err) {
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 53f24244de75..25ce81283e92 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1265,6 +1265,9 @@ static int mana_query_vport_cfg(struct mana_port_context *apc, u32 vport_index,
 	apc->port_handle = resp.vport;
 	ether_addr_copy(apc->mac_addr, resp.mac_addr);
 
+	apc->vport_max_sq = *max_sq;
+	apc->vport_max_rq = *max_rq;
+
 	return 0;
 }
 
@@ -1411,6 +1414,11 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc,
 
 	netdev_info(ndev, "Configured steering vPort %llu entries %u\n",
 		    apc->port_handle, apc->indir_table_sz);
+
+	apc->steer_rx = rx;
+	apc->steer_rss = apc->rss_state;
+	apc->steer_update_tab = update_tab;
+	apc->steer_cqe_coalescing = req->cqe_coalescing_enable;
 out:
 	kfree(req);
 	return err;
@@ -3102,6 +3110,24 @@ static int mana_init_port(struct net_device *ndev)
 	eth_hw_addr_set(ndev, apc->mac_addr);
 	sprintf(vport, "vport%d", port_idx);
 	apc->mana_port_debugfs = debugfs_create_dir(vport, gc->mana_pci_debugfs);
+
+	debugfs_create_u64("port_handle", 0400, apc->mana_port_debugfs,
+			   &apc->port_handle);
+	debugfs_create_u32("max_sq", 0400, apc->mana_port_debugfs,
+			   &apc->vport_max_sq);
+	debugfs_create_u32("max_rq", 0400, apc->mana_port_debugfs,
+			   &apc->vport_max_rq);
+	debugfs_create_u32("indir_table_sz", 0400, apc->mana_port_debugfs,
+			   &apc->indir_table_sz);
+	debugfs_create_u32("steer_rx", 0400, apc->mana_port_debugfs,
+			   &apc->steer_rx);
+	debugfs_create_u32("steer_rss", 0400, apc->mana_port_debugfs,
+			   &apc->steer_rss);
+	debugfs_create_u32("steer_update_tab", 0400, apc->mana_port_debugfs,
+			   &apc->steer_update_tab);
+	debugfs_create_u32("steer_cqe_coalescing", 0400, apc->mana_port_debugfs,
+			   &apc->steer_cqe_coalescing);
+
 	return 0;
 
 reset_apc:
@@ -3587,6 +3613,11 @@ int mana_probe(struct gdma_dev *gd, bool resuming)
 		ac->num_ports = num_ports;
 
 		INIT_WORK(&ac->link_change_work, mana_link_state_handle);
+
+		debugfs_create_u16("num_vports", 0400, gc->mana_pci_debugfs,
+				   &ac->num_ports);
+		debugfs_create_u8("bm_hostmode", 0400, gc->mana_pci_debugfs,
+				  &ac->bm_hostmode);
 	} else {
 		if (ac->num_ports != num_ports) {
 			dev_err(dev, "The number of vPorts changed: %d->%d\n",
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 766f4fb25e26..9bbb7fb0c964 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -434,6 +434,7 @@ struct gdma_context {
 	struct gdma_dev		mana_ib;
 
 	u64 pf_cap_flags1;
+	u64 gdma_protocol_ver;
 
 	struct workqueue_struct *service_wq;
 
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index a078af283bdd..83f6de67c0cc 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -563,6 +563,14 @@ struct mana_port_context {
 
 	/* Debugfs */
 	struct dentry *mana_port_debugfs;
+
+	/* Cached vport/steering config for debugfs */
+	u32 vport_max_sq;
+	u32 vport_max_rq;
+	u32 steer_rx;
+	u32 steer_rss;
+	u32 steer_update_tab;
+	u32 steer_cqe_coalescing;
 };
 
 netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev);
-- 
2.34.1

Re: [net-next] net: mana: Expose hardware diagnostic info via debugfs

[Jakub Kicinski]

This is an AI-generated review of your patch. The human sending this
email has considered the AI review valid, or at least plausible.

For local reproduction steps see https://netdev-ai.bots.linux.dev/ai-local.html
---
net: mana: Expose hardware diagnostic info via debugfs

This commit adds debugfs entries to expose hardware configuration and
diagnostic information for the MANA driver. It creates device-level and
port-level debugfs entries to aid in debugging initialization and runtime
operations.

> diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
> index aef8612b73cb..fb513d7802cb 100644
> --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
> +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
> @@ -152,6 +152,11 @@ static int mana_gd_query_max_resources(struct pci_dev *pdev)
>  	if (gc->max_num_queues > gc->num_msix_usable - 1)
>  		gc->max_num_queues = gc->num_msix_usable - 1;
>
> +	debugfs_create_u32("num_msix_usable", 0400, gc->mana_pci_debugfs,
> +			   &gc->num_msix_usable);
> +	debugfs_create_u32("max_num_queues", 0400, gc->mana_pci_debugfs,
> +			   &gc->max_num_queues);
> +
>  	return 0;
>  }
>
> @@ -1222,6 +1227,13 @@ int mana_gd_verify_vf_version(struct pci_dev *pdev)
>  		return err ? err : -EPROTO;
>  	}
>  	gc->pf_cap_flags1 = resp.pf_cap_flags1;
> +	gc->gdma_protocol_ver = resp.gdma_protocol_ver;
> +
> +	debugfs_create_x64("gdma_protocol_ver", 0400, gc->mana_pci_debugfs,
> +			   &gc->gdma_protocol_ver);
> +	debugfs_create_x64("pf_cap_flags1", 0400, gc->mana_pci_debugfs,
> +			   &gc->pf_cap_flags1);
> +

Do these debugfs entries get recreated on every suspend/resume cycle?

Both mana_gd_query_max_resources() and mana_gd_verify_vf_version() are
called from mana_gd_setup() during device initialization. On suspend,
mana_gd_suspend() calls mana_gd_cleanup() which doesn't remove these
debugfs entries. When mana_gd_resume() calls mana_gd_setup() again, it
attempts to create the same debugfs entries a second time.

This means debugfs_start_creating() in fs/debugfs/inode.c will print an
error for each duplicate file:

    "'num_msix_usable' already exists in 'mana/<slot>/'"
    "'max_num_queues' already exists in 'mana/<slot>/'"
    "'gdma_protocol_ver' already exists in 'mana/<slot>/'"
    "'pf_cap_flags1' already exists in 'mana/<slot>/'"

This produces 4 error messages in dmesg on every suspend/resume cycle,
contradicting the commit message's goal of operating "without adding
noise to dmesg."

Should these device-level entries be removed during suspend (in
mana_gd_cleanup or mana_gd_suspend), or should their creation be moved
to mana_gd_probe where they're only created once?

[ ... ]
-- 
pw-bot: cr

Re: [net-next] net: mana: Expose hardware diagnostic info via debugfs

[Erni Sri Satya Vennela]

On Fri, Mar 06, 2026 at 07:22:28PM -0800, Jakub Kicinski wrote:
> This is an AI-generated review of your patch. The human sending this
> email has considered the AI review valid, or at least plausible.
> 
> For local reproduction steps see https://netdev-ai.bots.linux.dev/ai-local.html
> ---
> net: mana: Expose hardware diagnostic info via debugfs
> 
> This commit adds debugfs entries to expose hardware configuration and
> diagnostic information for the MANA driver. It creates device-level and
> port-level debugfs entries to aid in debugging initialization and runtime
> operations.
 
> Do these debugfs entries get recreated on every suspend/resume cycle?
No. Thankyou for pointing out Jakub.
I'll  make this change in next version.
> 
> Both mana_gd_query_max_resources() and mana_gd_verify_vf_version() are
> called from mana_gd_setup() during device initialization. On suspend,
> mana_gd_suspend() calls mana_gd_cleanup() which doesn't remove these
> debugfs entries. When mana_gd_resume() calls mana_gd_setup() again, it
> attempts to create the same debugfs entries a second time.
> 
> This means debugfs_start_creating() in fs/debugfs/inode.c will print an
> error for each duplicate file:
> 
>     "'num_msix_usable' already exists in 'mana/<slot>/'"
>     "'max_num_queues' already exists in 'mana/<slot>/'"
>     "'gdma_protocol_ver' already exists in 'mana/<slot>/'"
>     "'pf_cap_flags1' already exists in 'mana/<slot>/'"
> 
> This produces 4 error messages in dmesg on every suspend/resume cycle,
> contradicting the commit message's goal of operating "without adding
> noise to dmesg."
> 
> Should these device-level entries be removed during suspend (in
> mana_gd_cleanup or mana_gd_suspend), or should their creation be moved
> to mana_gd_probe where they're only created once?
Right. I will remove the entries during suspend and re-create them in
resume. 
> 
> [ ... ]
> -- 
> pw-bot: cr