net: hibmcge: fix rtnl deadlock issue

Currently, the hibmcge netdev acquires the rtnl_lock in
pci_error_handlers.reset_prepare() and releases it in
pci_error_handlers.reset_done().

However, in the PCI framework:
pci_reset_bus - __pci_reset_slot - pci_slot_save_and_disable_locked -
 pci_dev_save_and_disable - err_handler->reset_prepare(dev);

In pci_slot_save_and_disable_locked():
	list_for_each_entry(dev, &slot->bus->devices, bus_list) {
		if (!dev->slot || dev->slot!= slot)
			continue;
		pci_dev_save_and_disable(dev);
		if (dev->subordinate)
			pci_bus_save_and_disable_locked(dev->subordinate);
	}

This will iterate through all devices under the current bus and execute
err_handler->reset_prepare(), causing two devices of the hibmcge driver
to sequentially request the rtnl_lock, leading to a deadlock.

Since the driver now executes netif_device_detach()
before the reset process, it will not concurrently with
other netdev APIs, so there is no need to hold the rtnl_lock now.

Therefore, this patch removes the rtnl_lock during the reset process and
adjusts the position of HBG_NIC_STATE_RESETTING to ensure
that multiple resets are not executed concurrently.

Fixes: 3f5a61f6d5 ("net: hibmcge: Add reset supported in this module")
Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
Jijie Shao
2025-08-06 18:27:56 +08:00
committed by Jakub Kicinski
parent f6a2a31043
commit c875503a9b

View File

@@ -53,9 +53,11 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type)
{
int ret;
ASSERT_RTNL();
if (test_and_set_bit(HBG_NIC_STATE_RESETTING, &priv->state))
return -EBUSY;
if (netif_running(priv->netdev)) {
clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
dev_warn(&priv->pdev->dev,
"failed to reset because port is up\n");
return -EBUSY;
@@ -64,7 +66,6 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type)
netif_device_detach(priv->netdev);
priv->reset_type = type;
set_bit(HBG_NIC_STATE_RESETTING, &priv->state);
clear_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state);
ret = hbg_hw_event_notify(priv, HBG_HW_EVENT_RESET);
if (ret) {
@@ -84,29 +85,26 @@ static int hbg_reset_done(struct hbg_priv *priv, enum hbg_reset_type type)
type != priv->reset_type)
return 0;
ASSERT_RTNL();
clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
ret = hbg_rebuild(priv);
if (ret) {
priv->stats.reset_fail_cnt++;
set_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state);
clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
dev_err(&priv->pdev->dev, "failed to rebuild after reset\n");
return ret;
}
netif_device_attach(priv->netdev);
clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
dev_info(&priv->pdev->dev, "reset done\n");
return ret;
}
/* must be protected by rtnl lock */
int hbg_reset(struct hbg_priv *priv)
{
int ret;
ASSERT_RTNL();
ret = hbg_reset_prepare(priv, HBG_RESET_TYPE_FUNCTION);
if (ret)
return ret;
@@ -171,7 +169,6 @@ static void hbg_pci_err_reset_prepare(struct pci_dev *pdev)
struct net_device *netdev = pci_get_drvdata(pdev);
struct hbg_priv *priv = netdev_priv(netdev);
rtnl_lock();
hbg_reset_prepare(priv, HBG_RESET_TYPE_FLR);
}
@@ -181,7 +178,6 @@ static void hbg_pci_err_reset_done(struct pci_dev *pdev)
struct hbg_priv *priv = netdev_priv(netdev);
hbg_reset_done(priv, HBG_RESET_TYPE_FLR);
rtnl_unlock();
}
static const struct pci_error_handlers hbg_pci_err_handler = {