1. Patchew
  2. linux
  3. View series

[PATCH net-next,v2] net: mana: Add handler for hardware servicing events

Haiyang Zhang posted 1 patch 7 months, 1 week ago
There is a newer version of this series
.../net/ethernet/microsoft/mana/gdma_main.c   | 63 +++++++++++++++++++
include/net/mana/gdma.h                       | 11 +++-
2 files changed, 72 insertions(+), 2 deletions(-)
[PATCH net-next,v2] net: mana: Add handler for hardware servicing events
Posted by Haiyang Zhang 7 months, 1 week ago 
To collaborate with hardware servicing events, upon receiving the special
EQE notification from the HW channel, remove the devices on this bus.
Then, after a waiting period based on the device specs, rescan the parent
bus to recover the devices.

Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
---
v2: 
Added dev_dbg for service type as suggested by Shradha Gupta.
Added driver cap bit.

---
 .../net/ethernet/microsoft/mana/gdma_main.c   | 63 +++++++++++++++++++
 include/net/mana/gdma.h                       | 11 +++-
 2 files changed, 72 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 4ffaf7588885..cf82c9a36c8e 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -352,11 +352,52 @@ void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit)
 }
 EXPORT_SYMBOL_NS(mana_gd_ring_cq, "NET_MANA");
 
+#define MANA_SERVICE_PERIOD 10
+
+struct mana_serv_work {
+	struct work_struct serv_work;
+	struct pci_dev *pdev;
+};
+
+static void mana_serv_func(struct work_struct *w)
+{
+	struct mana_serv_work *mns_wk = container_of(w, struct mana_serv_work, serv_work);
+	struct pci_dev *pdev = mns_wk->pdev;
+	struct pci_bus *bus, *parent;
+
+	if (!pdev)
+		goto out;
+
+	bus = pdev->bus;
+	if (!bus) {
+		dev_err(&pdev->dev, "MANA service: no bus\n");
+		goto out;
+	}
+
+	parent = bus->parent;
+	if (!parent) {
+		dev_err(&pdev->dev, "MANA service: no parent bus\n");
+		goto out;
+	}
+
+	pci_stop_and_remove_bus_device_locked(bus->self);
+
+	msleep(MANA_SERVICE_PERIOD * 1000);
+
+	pci_lock_rescan_remove();
+	pci_rescan_bus(parent);
+	pci_unlock_rescan_remove();
+
+out:
+	kfree(mns_wk);
+}
+
 static void mana_gd_process_eqe(struct gdma_queue *eq)
 {
 	u32 head = eq->head % (eq->queue_size / GDMA_EQE_SIZE);
 	struct gdma_context *gc = eq->gdma_dev->gdma_context;
 	struct gdma_eqe *eq_eqe_ptr = eq->queue_mem_ptr;
+	struct mana_serv_work *mns_wk;
 	union gdma_eqe_info eqe_info;
 	enum gdma_eqe_type type;
 	struct gdma_event event;
@@ -400,6 +441,28 @@ static void mana_gd_process_eqe(struct gdma_queue *eq)
 		eq->eq.callback(eq->eq.context, eq, &event);
 		break;
 
+	case GDMA_EQE_HWC_FPGA_RECONFIG:
+	case GDMA_EQE_HWC_SOCMANA_CRASH:
+		dev_dbg(gc->dev, "Recv MANA service type:%d\n", type);
+
+		if (gc->in_service) {
+			dev_info(gc->dev, "Already in service\n");
+			break;
+		}
+
+		mns_wk = kzalloc(sizeof(*mns_wk), GFP_ATOMIC);
+		if (!mns_wk) {
+			dev_err(gc->dev, "Fail to alloc mana_serv_work\n");
+			break;
+		}
+
+		dev_info(gc->dev, "Start MANA service type:%d\n", type);
+		gc->in_service = true;
+		mns_wk->pdev = to_pci_dev(gc->dev);
+		INIT_WORK(&mns_wk->serv_work, mana_serv_func);
+		schedule_work(&mns_wk->serv_work);
+		break;
+
 	default:
 		break;
 	}
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 228603bf03f2..d0fbc9c64cc8 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -58,8 +58,9 @@ enum gdma_eqe_type {
 	GDMA_EQE_HWC_INIT_EQ_ID_DB	= 129,
 	GDMA_EQE_HWC_INIT_DATA		= 130,
 	GDMA_EQE_HWC_INIT_DONE		= 131,
-	GDMA_EQE_HWC_SOC_RECONFIG	= 132,
+	GDMA_EQE_HWC_FPGA_RECONFIG	= 132,
 	GDMA_EQE_HWC_SOC_RECONFIG_DATA	= 133,
+	GDMA_EQE_HWC_SOCMANA_CRASH	= 135,
 	GDMA_EQE_RNIC_QP_FATAL		= 176,
 };
 
@@ -388,6 +389,8 @@ struct gdma_context {
 	u32			test_event_eq_id;
 
 	bool			is_pf;
+	bool			in_service;
+
 	phys_addr_t		bar0_pa;
 	void __iomem		*bar0_va;
 	void __iomem		*shm_base;
@@ -558,12 +561,16 @@ enum {
 /* Driver can handle holes (zeros) in the device list */
 #define GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP BIT(11)
 
+/* Driver can self reset on EQE notification */
+#define GDMA_DRV_CAP_FLAG_1_SELF_RESET_ON_EQE BIT(14)
+
 #define GDMA_DRV_CAP_FLAGS1 \
 	(GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \
 	 GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \
 	 GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG | \
 	 GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT | \
-	 GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP)
+	 GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP | \
+	 GDMA_DRV_CAP_FLAG_1_SELF_RESET_ON_EQE)
 
 #define GDMA_DRV_CAP_FLAGS2 0
 
-- 
2.34.1
Re: [PATCH net-next,v2] net: mana: Add handler for hardware servicing events
Posted by Simon Horman 7 months, 1 week ago 
On Fri, May 09, 2025 at 04:16:43PM -0700, Haiyang Zhang wrote:
> To collaborate with hardware servicing events, upon receiving the special
> EQE notification from the HW channel, remove the devices on this bus.
> Then, after a waiting period based on the device specs, rescan the parent
> bus to recover the devices.
> 
> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
> ---
> v2: 
> Added dev_dbg for service type as suggested by Shradha Gupta.
> Added driver cap bit.
> 
> ---
>  .../net/ethernet/microsoft/mana/gdma_main.c   | 63 +++++++++++++++++++
>  include/net/mana/gdma.h                       | 11 +++-
>  2 files changed, 72 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c

...

> +static void mana_serv_func(struct work_struct *w)
> +{
> +	struct mana_serv_work *mns_wk = container_of(w, struct mana_serv_work, serv_work);
> +	struct pci_dev *pdev = mns_wk->pdev;
> +	struct pci_bus *bus, *parent;

Please avoid lines wider than 80 columns in Networking code.  In this case
I would suggest separating the declaration and initialisation of mns_wk and
pdev.  Something like this (completely untested!):

	struct mana_serv_work *mns_wk;
	struct pci_bus *bus, *parent;
	struct pci_dev *pdev;

	mns_wk = container_of(w, struct mana_serv_work, serv_work);
	pdev = mns_wk->pdev;


...

> @@ -400,6 +441,28 @@ static void mana_gd_process_eqe(struct gdma_queue *eq)
>  		eq->eq.callback(eq->eq.context, eq, &event);
>  		break;
>  
> +	case GDMA_EQE_HWC_FPGA_RECONFIG:
> +	case GDMA_EQE_HWC_SOCMANA_CRASH:
> +		dev_dbg(gc->dev, "Recv MANA service type:%d\n", type);
> +
> +		if (gc->in_service) {
> +			dev_info(gc->dev, "Already in service\n");
> +			break;
> +		}
> +
> +		mns_wk = kzalloc(sizeof(*mns_wk), GFP_ATOMIC);
> +		if (!mns_wk) {
> +			dev_err(gc->dev, "Fail to alloc mana_serv_work\n");

The memory allocator will log a message on error.
So please don't also do so here.

> +			break;
> +		}
> +
> +		dev_info(gc->dev, "Start MANA service type:%d\n", type);
> +		gc->in_service = true;
> +		mns_wk->pdev = to_pci_dev(gc->dev);
> +		INIT_WORK(&mns_wk->serv_work, mana_serv_func);
> +		schedule_work(&mns_wk->serv_work);
> +		break;
> +
>  	default:
>  		break;
>  	}

...

-- 
pw-bot: changes-requested

Patchew 2.1-devel-b67e4c2

© 2016 - 2025 Red Hat, Inc.