All of lore.kernel.org
 help / color / mirror / Atom feed
From: Haiyang Zhang <haiyangz@linux.microsoft.com>
To: linux-hyperv@vger.kernel.org, netdev@vger.kernel.org
Cc: haiyangz@microsoft.com, decui@microsoft.com,
	stephen@networkplumber.org, kys@microsoft.com,
	paulros@microsoft.com, olaf@aepfle.de, vkuznets@redhat.com,
	davem@davemloft.net, wei.liu@kernel.org, edumazet@google.com,
	kuba@kernel.org, pabeni@redhat.com, leon@kernel.org,
	longli@microsoft.com, ssengar@linux.microsoft.com,
	linux-rdma@vger.kernel.org, daniel@iogearbox.net,
	john.fastabend@gmail.com, bpf@vger.kernel.org, ast@kernel.org,
	hawk@kernel.org, tglx@linutronix.de,
	shradhagupta@linux.microsoft.com, andrew+netdev@lunn.ch,
	kotaranov@microsoft.com, horms@kernel.org,
	linux-kernel@vger.kernel.org
Subject: [PATCH net-next,v8] net: mana: Add handler for hardware servicing events
Date: Fri, 13 Jun 2025 10:00:34 -0700	[thread overview]
Message-ID: <1749834034-18498-1-git-send-email-haiyangz@linux.microsoft.com> (raw)

From: Haiyang Zhang <haiyangz@microsoft.com>

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>
Reviewed-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: Simon Horman <horms@kernel.org>
---
v8:
Tested rmmod as suggested by Jakub Kicinski, and found it's necessary to
add back: acquiring module refcnt.

v7:
rebased.

v6:
Not acquiring module refcnt as suggested by Paolo Abeni.

v5:
Get refcnt of the pdev struct to avoid removal before running the work
as suggested by Jakub Kicinski.

v4:
Renamed EQE type 135 to GDMA_EQE_HWC_RESET_REQUEST, since there can
be multiple cases of this reset request.

v3:
Updated for checkpatch warnings as suggested by Simon Horman.

v2:
Added dev_dbg for service type as suggested by Shradha Gupta.
Added driver cap bit.
---
 .../net/ethernet/microsoft/mana/gdma_main.c   | 75 +++++++++++++++++++
 include/net/mana/gdma.h                       | 10 ++-
 2 files changed, 83 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 3504507477c6..069b7a871b78 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -352,11 +352,59 @@ 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;
+	struct pci_bus *bus, *parent;
+	struct pci_dev *pdev;
+
+	mns_wk = container_of(w, struct mana_serv_work, serv_work);
+	pdev = mns_wk->pdev;
+
+	pci_lock_rescan_remove();
+
+	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(bus->self);
+
+	msleep(MANA_SERVICE_PERIOD * 1000);
+
+	pci_rescan_bus(parent);
+
+out:
+	pci_unlock_rescan_remove();
+
+	pci_dev_put(pdev);
+	kfree(mns_wk);
+	module_put(THIS_MODULE);
+}
+
 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;
@@ -401,6 +449,33 @@ 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:
+		dev_info(gc->dev, "Recv MANA service type:%d\n", type);
+
+		if (gc->in_service) {
+			dev_info(gc->dev, "Already in service\n");
+			break;
+		}
+
+		if (!try_module_get(THIS_MODULE)) {
+			dev_info(gc->dev, "Module is unloading\n");
+			break;
+		}
+
+		mns_wk = kzalloc(sizeof(*mns_wk), GFP_ATOMIC);
+		if (!mns_wk) {
+			module_put(THIS_MODULE);
+			break;
+		}
+
+		dev_info(gc->dev, "Start MANA service type:%d\n", type);
+		gc->in_service = true;
+		mns_wk->pdev = to_pci_dev(gc->dev);
+		pci_dev_get(mns_wk->pdev);
+		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 3ce56a816425..bfae59202669 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -58,7 +58,7 @@ 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_SOC_SERVICE	= 134,
 	GDMA_EQE_RNIC_QP_FATAL		= 176,
@@ -403,6 +403,8 @@ 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;
@@ -578,12 +580,16 @@ 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 FPGA Reconfig EQE notification */
+#define GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE BIT(17)
+
 #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_HANDLE_RECONFIG_EQE)
 
 #define GDMA_DRV_CAP_FLAGS2 0
 
-- 
2.34.1


             reply	other threads:[~2025-06-13 17:00 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-13 17:00 Haiyang Zhang [this message]
2025-06-16 22:30 ` [PATCH net-next,v8] net: mana: Add handler for hardware servicing events patchwork-bot+netdevbpf

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1749834034-18498-1-git-send-email-haiyangz@linux.microsoft.com \
    --to=haiyangz@linux.microsoft.com \
    --cc=andrew+netdev@lunn.ch \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=decui@microsoft.com \
    --cc=edumazet@google.com \
    --cc=haiyangz@microsoft.com \
    --cc=hawk@kernel.org \
    --cc=horms@kernel.org \
    --cc=john.fastabend@gmail.com \
    --cc=kotaranov@microsoft.com \
    --cc=kuba@kernel.org \
    --cc=kys@microsoft.com \
    --cc=leon@kernel.org \
    --cc=linux-hyperv@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=longli@microsoft.com \
    --cc=netdev@vger.kernel.org \
    --cc=olaf@aepfle.de \
    --cc=pabeni@redhat.com \
    --cc=paulros@microsoft.com \
    --cc=shradhagupta@linux.microsoft.com \
    --cc=ssengar@linux.microsoft.com \
    --cc=stephen@networkplumber.org \
    --cc=tglx@linutronix.de \
    --cc=vkuznets@redhat.com \
    --cc=wei.liu@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.